Set cookies SameSite value to Lax

Store worker statistics under worker id and not internal redis key
Fix unit tests

apiserver/apierrors/errors.conf

@@ -26,6 +26,9 @@
     23: ["invalid_domain_name", "malformed domain name"]
     24: ["not_public_object", "object is not public"]
 
+    # Auth / Login
+    75: ["invalid_access_key", "access key not found"]
+
     # Tasks
     100: ["task_error", "general task error"]
     101: ["invalid_task_id", "invalid task id"]
@@ -47,6 +50,12 @@
     130: ["task_not_found", "task not found"]
     131: ["events_not_added", "events not added"]
 
+    # Reports
+    150: ["operation_supported_on_reports_only", "passed task is not report"]
+
+    # Pipelines
+    160: ["cannot_remove_all_runs", "at least one pipeline run should be left"]
+
     # Models
     200: ["model_error", "general task error"]
     201: ["invalid_model_id", "invalid model id"]
@@ -67,12 +76,14 @@
     402: ["project_has_tasks", "project has associated tasks"]
     403: ["project_not_found", "project not found"]
     405: ["project_has_models", "project has associated models"]
+    406: ["project_has_datasets", "project has associated non-empty datasets"]
     407: ["invalid_project_name", "invalid project name"]
     408: ["cannot_update_project_location", "Cannot update project location. Use projects.move instead"]
     409: ["project_path_exceeds_max", "Project path exceed the maximum allowed depth"]
     410: ["project_source_and_destination_are_the_same", "Project has the same source and destination paths"]
     411: ["project_cannot_be_moved_under_itself", "Project can not be moved under itself in the projects hierarchy"]
     412: ["project_cannot_be_merged_into_its_child", "Project can not be merged into its own child"]
+    413: ["project_has_pipelines", "project has associated pipelines with active controllers"]
 
     # Queues
     701: ["invalid_queue_id", "invalid queue id"]
@@ -86,7 +97,7 @@
 
     # Database
     800: ["data_validation_error", "data validation error"]
-    801: ["expected_unique_data", "value combination already exists"]
+    801: ["expected_unique_data", "value combination already exists (unique field already contains this value)"]
 
     # Workers
     1001: ["invalid_worker_id", "invalid worker id"]

apiserver/apimodels/__init__.py

@@ -61,10 +61,11 @@ class ListField(fields.ListField):
             item.validate()
 
 
-# since there is no distinction between None and empty DictField
-# this value can be used as sentinel in order to distinguish
-# between not set and empty DictField
-DictFieldNotSet = {}
+class ScalarField(fields.BaseField):
+
+    """String field."""
+
+    types = (str, int, float, bool)
 
 
 class DictField(fields.BaseField):

apiserver/apimodels/auth.py

@@ -96,6 +96,11 @@ class GetCredentialsResponse(Base):
     credentials = ListField(CredentialsResponse)
 
 
+class EditCredentialsRequest(Base):
+    access_key = StringField(required=True)
+    label = StringField()
+
+
 class RevokeCredentialsRequest(Base):
     access_key = StringField(required=True)
 

apiserver/apimodels/events.py

@@ -13,6 +13,14 @@ from apiserver.config_repo import config
 from apiserver.utilities.stringenum import StringEnum
 
 
+class TaskRequest(Base):
+    task: str = StringField(required=True)
+
+
+class ModelRequest(Base):
+    model: str = StringField(required=True)
+
+
 class HistogramRequestBase(Base):
     samples: int = IntField(default=2000, validators=[Min(1), Max(6000)])
     key: ScalarKeyEnum = ActualEnumField(ScalarKeyEnum, default=ScalarKeyEnum.iter)
@@ -26,6 +34,12 @@ class MetricVariants(Base):
 class ScalarMetricsIterHistogramRequest(HistogramRequestBase):
     task: str = StringField(required=True)
     metrics: Sequence[MetricVariants] = ListField(items_types=MetricVariants)
+    model_events: bool = BoolField(default=False)
+
+
+class GetMetricsAndVariantsRequest(Base):
+    task: str = StringField(required=True)
+    model_events: bool = BoolField(default=False)
 
 
 class MultiTaskScalarMetricsIterHistogramRequest(HistogramRequestBase):
@@ -35,11 +49,13 @@ class MultiTaskScalarMetricsIterHistogramRequest(HistogramRequestBase):
             Length(
                 minimum_value=1,
                 maximum_value=config.get(
-                    "services.tasks.multi_task_histogram_limit", 10
+                    "services.tasks.multi_task_histogram_limit", 100
                 ),
             )
         ],
     )
+    metrics: Sequence[MetricVariants] = ListField(items_types=MetricVariants)
+    model_events: bool = BoolField(default=False)
 
 
 class TaskMetric(Base):
@@ -48,7 +64,13 @@ class TaskMetric(Base):
     variants: Sequence[str] = ListField(items_types=str)
 
 
-class DebugImagesRequest(Base):
+class LegacyMetricEventsRequest(TaskRequest):
+    iters: int = IntField(default=1, validators=validators.Min(1))
+    scroll_id: str = StringField()
+    model_events: bool = BoolField(default=False)
+
+
+class MetricEventsRequest(Base):
     metrics: Sequence[TaskMetric] = ListField(
         items_types=TaskMetric, validators=[Length(minimum_value=1)]
     )
@@ -56,24 +78,43 @@ class DebugImagesRequest(Base):
     navigate_earlier: bool = BoolField(default=True)
     refresh: bool = BoolField(default=False)
     scroll_id: str = StringField()
+    model_events: bool = BoolField(default=False)
 
 
-class TaskMetricVariant(Base):
+class VectorMetricsIterHistogramRequest(Base):
     task: str = StringField(required=True)
     metric: str = StringField(required=True)
     variant: str = StringField(required=True)
+    model_events: bool = BoolField(default=False)
 
 
-class GetDebugImageSampleRequest(TaskMetricVariant):
+class GetVariantSampleRequest(Base):
+    task: str = StringField(required=True)
+    metric: str = StringField(required=True)
+    variant: str = StringField(required=True)
     iteration: Optional[int] = IntField()
     refresh: bool = BoolField(default=False)
     scroll_id: Optional[str] = StringField()
+    navigate_current_metric: bool = BoolField(default=True)
+    model_events: bool = BoolField(default=False)
 
 
-class NextDebugImageSampleRequest(Base):
+class GetMetricSamplesRequest(Base):
+    task: str = StringField(required=True)
+    metric: str = StringField(required=True)
+    iteration: Optional[int] = IntField()
+    refresh: bool = BoolField(default=False)
+    scroll_id: Optional[str] = StringField()
+    navigate_current_metric: bool = BoolField(default=True)
+    model_events: bool = BoolField(default=False)
+
+
+class NextHistorySampleRequest(Base):
     task: str = StringField(required=True)
     scroll_id: Optional[str] = StringField()
     navigate_earlier: bool = BoolField(default=True)
+    next_iteration: bool = BoolField(default=False)
+    model_events: bool = BoolField(default=False)
 
 
 class LogOrderEnum(StringEnum):
@@ -92,6 +133,12 @@ class TaskEventsRequest(TaskEventsRequestBase):
     order: Optional[str] = ActualEnumField(LogOrderEnum, default=LogOrderEnum.asc)
     scroll_id: str = StringField()
     count_total: bool = BoolField(default=True)
+    model_events: bool = BoolField(default=False)
+
+
+class LegacyLogEventsRequest(TaskEventsRequestBase):
+    order: Optional[str] = ActualEnumField(LogOrderEnum, default=LogOrderEnum.desc)
+    scroll_id: str = StringField()
 
 
 class LogEventsRequest(TaskEventsRequestBase):
@@ -107,6 +154,7 @@ class ScalarMetricsIterRawRequest(TaskEventsRequestBase):
     metric: MetricVariants = EmbeddedField(MetricVariants, required=True)
     count_total: bool = BoolField(default=False)
     scroll_id: str = StringField()
+    model_events: bool = BoolField(default=False)
 
 
 class IterationEvents(Base):
@@ -119,21 +167,65 @@ class MetricEvents(Base):
     iterations: Sequence[IterationEvents] = ListField(items_types=IterationEvents)
 
 
-class DebugImageResponse(Base):
+class MetricEventsResponse(Base):
     metrics: Sequence[MetricEvents] = ListField(items_types=MetricEvents)
     scroll_id: str = StringField()
 
 
-class TaskMetricsRequest(Base):
+class MultiTasksRequestBase(Base):
     tasks: Sequence[str] = ListField(
         items_types=str, validators=[Length(minimum_value=1)]
     )
+    model_events: bool = BoolField(default=False)
+
+
+class SingleValueMetricsRequest(MultiTasksRequestBase):
+    metrics: Sequence[MetricVariants] = ListField(items_types=MetricVariants)
+
+
+class TaskMetricsRequest(MultiTasksRequestBase):
     event_type: EventType = ActualEnumField(EventType, required=True)
 
 
+class MultiTaskMetricsRequest(MultiTasksRequestBase):
+    event_type: EventType = ActualEnumField(EventType, default=EventType.all)
+
+
+class LegacyMultiTaskEventsRequest(MultiTasksRequestBase):
+    iters: int = IntField(default=1, validators=validators.Min(1))
+    scroll_id: str = StringField()
+
+
+class MultiTaskPlotsRequest(MultiTasksRequestBase):
+    iters: int = IntField(default=1)
+    scroll_id: str = StringField()
+    no_scroll: bool = BoolField(default=False)
+    last_iters_per_task_metric: bool = BoolField(default=True)
+    metrics: Sequence[MetricVariants] = ListField(items_types=MetricVariants)
+
+
 class TaskPlotsRequest(Base):
     task: str = StringField(required=True)
     iters: int = IntField(default=1)
     scroll_id: str = StringField()
     no_scroll: bool = BoolField(default=False)
     metrics: Sequence[MetricVariants] = ListField(items_types=MetricVariants)
+    model_events: bool = BoolField(default=False)
+
+
+class GetScalarMetricDataRequest(Base):
+    task: str = StringField(required=True)
+    metric: str = StringField(required=True)
+    scroll_id: str = StringField()
+    no_scroll: bool = BoolField(default=False)
+    model_events: bool = BoolField(default=False)
+
+
+class ClearScrollRequest(Base):
+    scroll_id: str = StringField()
+
+
+class ClearTaskLogRequest(Base):
+    task: str = StringField(required=True)
+    threshold_sec = IntField()
+    allow_locked = BoolField(default=False)

apiserver/apimodels/login.py

@@ -5,8 +5,9 @@ from apiserver.apimodels import DictField, callable_default
 
 
 class GetSupportedModesRequest(Base):
-    state = StringField(help_text="ASCII base64 encoded application state")
-    callback_url_prefix = StringField()
+    pass
+    # state = StringField(help_text="ASCII base64 encoded application state")
+    # callback_url_prefix = StringField()
 
 
 class BasicGuestMode(Base):

apiserver/apimodels/models.py

@@ -42,12 +42,29 @@ class ModelRequest(models.Base):
     model = fields.StringField(required=True)
 
 
+class TaskRequest(models.Base):
+    task = fields.StringField(required=True)
+
+
+class UpdateForTaskRequest(TaskRequest):
+    uri = fields.StringField()
+    iteration = fields.IntField()
+    override_model_id = fields.StringField()
+
+
+class UpdateModelRequest(ModelRequest):
+    task = fields.StringField()
+    iteration = fields.IntField()
+
+
 class DeleteModelRequest(ModelRequest):
     force = fields.BoolField(default=False)
+    delete_external_artifacts = fields.BoolField(default=True)
 
 
 class ModelsDeleteManyRequest(BatchRequest):
     force = fields.BoolField(default=False)
+    delete_external_artifacts = fields.BoolField(default=True)
 
 
 class PublishModelRequest(ModelRequest):
@@ -75,3 +92,8 @@ class DeleteMetadataRequest(DeleteMetadata):
 
 class AddOrUpdateMetadataRequest(AddOrUpdateMetadata):
     model = fields.StringField(required=True)
+
+
+class ModelsGetRequest(models.Base):
+    include_stats = fields.BoolField(default=False)
+    allow_public = fields.BoolField(default=True)

apiserver/apimodels/organization.py

@@ -1,4 +1,11 @@
+from enum import auto
+from typing import Sequence
+
 from jsonmodels import fields, models
+from jsonmodels.validators import Length
+
+from apiserver.apimodels import DictField, ActualEnumField, ScalarField
+from apiserver.utilities.stringenum import StringEnum
 
 
 class Filter(models.Base):
@@ -9,3 +16,47 @@ class Filter(models.Base):
 class TagsRequest(models.Base):
     include_system = fields.BoolField(default=False)
     filter = fields.EmbeddedField(Filter)
+
+
+class EntitiesCountRequest(models.Base):
+    projects = DictField()
+    tasks = DictField()
+    models = DictField()
+    pipelines = DictField()
+    datasets = DictField()
+    reports = DictField()
+    active_users = fields.ListField(str)
+    search_hidden = fields.BoolField(default=False)
+    allow_public = fields.BoolField(default=True)
+
+
+class EntityType(StringEnum):
+    task = auto()
+    model = auto()
+
+
+class ValueMapping(models.Base):
+    key = ScalarField(nullable=True)
+    value = ScalarField(nullable=True)
+
+
+class FieldMapping(models.Base):
+    field = fields.StringField(required=True)
+    name = fields.StringField()
+    values: Sequence[ValueMapping] = fields.ListField(items_types=[ValueMapping])
+
+
+class PrepareDownloadForGetAllRequest(models.Base):
+    entity_type = ActualEnumField(EntityType)
+    allow_public = fields.BoolField(default=True)
+    search_hidden = fields.BoolField(default=False)
+    only_fields = fields.ListField(
+        items_types=[str], validators=[Length(1)], required=True
+    )
+    field_mappings: Sequence[FieldMapping] = fields.ListField(
+        items_types=[FieldMapping], validators=[Length(1)], required=True
+    )
+
+
+class DownloadForGetAllRequest(models.Base):
+    prepare_id = fields.StringField(required=True)

apiserver/apimodels/pipelines.py

@@ -1,4 +1,5 @@
 from jsonmodels import models, fields
+from jsonmodels.validators import Length
 
 from apiserver.apimodels import ListField
 
@@ -8,12 +9,13 @@ class Arg(models.Base):
     value = fields.StringField(required=True)
 
 
+class DeleteRunsRequest(models.Base):
+    project = fields.StringField(required=True)
+    ids = ListField([str], required=True, validators=[Length(1)])
+
+
 class StartPipelineRequest(models.Base):
     task = fields.StringField(required=True)
     queue = fields.StringField(required=True)
     args = ListField(Arg)
-
-
-class StartPipelineResponse(models.Base):
-    pipeline = fields.StringField(required=True)
-    enqueued = fields.BoolField(required=True)
+    verify_watched_queue = fields.BoolField(default=False)

apiserver/apimodels/projects.py

@@ -1,8 +1,11 @@
+from enum import Enum, auto
+
 from jsonmodels import models, fields
 
 from apiserver.apimodels import ListField, ActualEnumField, DictField
 from apiserver.apimodels.organization import TagsRequest
 from apiserver.database.model import EntityVisibility
+from apiserver.utilities.stringenum import StringEnum
 
 
 class ProjectRequest(models.Base):
@@ -20,6 +23,7 @@ class MoveRequest(ProjectRequest):
 class DeleteRequest(ProjectRequest):
     force = fields.BoolField(default=False)
     delete_contents = fields.BoolField(default=False)
+    delete_external_artifacts = fields.BoolField(default=True)
 
 
 class ProjectOrNoneRequest(models.Base):
@@ -27,6 +31,11 @@ class ProjectOrNoneRequest(models.Base):
     include_subprojects = fields.BoolField(default=True)
 
 
+class GetUniqueMetricsRequest(ProjectOrNoneRequest):
+    model_metrics = fields.BoolField(default=False)
+    ids = fields.ListField(str)
+
+
 class GetParamsRequest(ProjectOrNoneRequest):
     page = fields.IntField(default=0)
     page_size = fields.IntField(default=500)
@@ -37,31 +46,58 @@ class ProjectTagsRequest(TagsRequest):
 
 
 class MultiProjectRequest(models.Base):
-    projects = fields.ListField(str)
+    projects = fields.ListField(items_types=[str, type(None)])
     include_subprojects = fields.BoolField(default=True)
 
 
 class ProjectTaskParentsRequest(MultiProjectRequest):
     tasks_state = ActualEnumField(EntityVisibility)
+    task_name = fields.StringField()
 
 
-class ProjectHyperparamValuesRequest(MultiProjectRequest):
+class EntityTypeEnum(StringEnum):
+    task = auto()
+    model = auto()
+
+
+class ProjectUserNamesRequest(MultiProjectRequest):
+    entity = ActualEnumField(EntityTypeEnum, default=EntityTypeEnum.task)
+
+
+class MultiProjectPagedRequest(MultiProjectRequest):
+    allow_public = fields.BoolField(default=True)
+    page = fields.IntField(default=0)
+    page_size = fields.IntField(default=500)
+
+
+class ProjectHyperparamValuesRequest(MultiProjectPagedRequest):
     section = fields.StringField(required=True)
     name = fields.StringField(required=True)
-    allow_public = fields.BoolField(default=True)
+    pattern = fields.StringField()
 
 
-class ProjectModelMetadataValuesRequest(MultiProjectRequest):
+class ProjectModelMetadataValuesRequest(MultiProjectPagedRequest):
     key = fields.StringField(required=True)
-    allow_public = fields.BoolField(default=True)
+
+
+class ProjectChildrenType(Enum):
+    pipeline = "pipeline"
+    report = "report"
+    dataset = "dataset"
 
 
 class ProjectsGetRequest(models.Base):
+    include_dataset_stats = fields.BoolField(default=False)
     include_stats = fields.BoolField(default=False)
     include_stats_filter = DictField()
     stats_with_children = fields.BoolField(default=True)
     stats_for_state = ActualEnumField(EntityVisibility, default=EntityVisibility.active)
-    non_public = fields.BoolField(default=False)
+    non_public = fields.BoolField(default=False)  # legacy, use allow_public instead
     active_users = fields.ListField(str)
     check_own_contents = fields.BoolField(default=False)
     shallow_search = fields.BoolField(default=False)
+    search_hidden = fields.BoolField(default=False)
+    allow_public = fields.BoolField(default=True)
+    children_type = ActualEnumField(ProjectChildrenType)
+    children_tags = fields.ListField(str)
+    children_tags_filter = DictField()

apiserver/apimodels/queues.py

@@ -26,9 +26,19 @@ class QueueRequest(Base):
     queue = StringField(required=True)
 
 
+class GetByIdRequest(QueueRequest):
+    max_task_entries = IntField()
+
+
+class GetAllRequest(Base):
+    max_task_entries = IntField()
+    search_hidden = BoolField(default=False)
+
+
 class GetNextTaskRequest(QueueRequest):
     queue = StringField(required=True)
     get_task_info = BoolField(default=False)
+    task = StringField()
 
 
 class DeleteRequest(QueueRequest):
@@ -59,6 +69,7 @@ class GetMetricsRequest(Base):
     from_date = FloatField(required=True, validators=validators.Min(0))
     to_date = FloatField(required=True, validators=validators.Min(0))
     interval = IntField(required=True, validators=validators.Min(1))
+    refresh = BoolField(default=False)
 
 
 class QueueMetrics(Base):

apiserver/apimodels/reports.py

@@ -0,0 +1,84 @@
+from typing import Sequence
+
+from jsonmodels import validators
+from jsonmodels.fields import StringField, ListField, BoolField, EmbeddedField, IntField
+from jsonmodels.models import Base
+from jsonmodels.validators import Length
+
+from apiserver.apimodels.events import MetricVariants, HistogramRequestBase
+
+
+class UpdateReportRequest(Base):
+    task = StringField(required=True)
+    name = StringField(nullable=True, validators=Length(minimum_value=3))
+    tags = ListField(items_types=[str])
+    comment = StringField()
+    report = StringField()
+    report_assets = ListField(items_types=[str])
+
+
+class CreateReportRequest(Base):
+    name = StringField(required=True, validators=Length(minimum_value=3))
+    tags = ListField(items_types=[str])
+    comment = StringField()
+    report = StringField()
+    project = StringField()
+    report_assets = ListField(items_types=[str])
+
+
+class PublishReportRequest(Base):
+    task = StringField(required=True)
+    message = StringField(default="")
+
+
+class ArchiveReportRequest(Base):
+    task = StringField(required=True)
+    message = StringField(default="")
+
+
+class ShareReportRequest(Base):
+    task = StringField(required=True)
+    share = BoolField(default=True)
+
+
+class DeleteReportRequest(Base):
+    task = StringField(required=True)
+    force = BoolField(default=False)
+
+
+class MoveReportRequest(Base):
+    task = StringField(required=True)
+    project = StringField()
+    project_name = StringField()
+
+
+class EventsRequest(Base):
+    iters = IntField(default=1, validators=validators.Min(1))
+    metrics: Sequence[MetricVariants] = ListField(items_types=MetricVariants)
+
+
+class PlotEventsRequest(EventsRequest):
+    last_iters_per_task_metric: bool = BoolField(default=True)
+
+
+class ScalarMetricsIterHistogram(HistogramRequestBase):
+    metrics: Sequence[MetricVariants] = ListField(items_types=MetricVariants)
+
+
+class SingleValueMetrics(Base):
+    pass
+
+
+class GetTasksDataRequest(Base):
+    debug_images: EventsRequest = EmbeddedField(EventsRequest)
+    plots: PlotEventsRequest = EmbeddedField(PlotEventsRequest)
+    scalar_metrics_iter_histogram: ScalarMetricsIterHistogram = EmbeddedField(
+        ScalarMetricsIterHistogram
+    )
+    single_value_metrics: SingleValueMetrics = EmbeddedField(SingleValueMetrics)
+    allow_public = BoolField(default=True)
+    model_events: bool = BoolField(default=False)
+
+
+class GetAllRequest(Base):
+    allow_public = BoolField(default=True)

apiserver/apimodels/server.py

@@ -6,6 +6,10 @@ class ReportStatsOptionRequest(Base):
     enabled = BoolField(default=None, nullable=True)
 
 
+class GetConfigRequest(Base):
+    path = StringField()
+
+
 class ReportStatsOptionResponse(Base):
     supported = BoolField(default=True)
     enabled = BoolField()

apiserver/apimodels/tasks.py

@@ -42,6 +42,7 @@ class StartedResponse(UpdateResponse):
 
 class EnqueueResponse(UpdateResponse):
     queued = IntField()
+    queue_watched = BoolField()
 
 
 class EnqueueBatchItem(UpdateBatchItem):
@@ -50,6 +51,7 @@ class EnqueueBatchItem(UpdateBatchItem):
 
 class EnqueueManyResponse(BatchResponse):
     succeeded: Sequence[EnqueueBatchItem] = ListField(EnqueueBatchItem)
+    queue_watched = BoolField()
 
 
 class DequeueResponse(UpdateResponse):
@@ -94,20 +96,36 @@ class UpdateRequest(TaskUpdateRequest):
     status_message = StringField(default="")
 
 
+class DequeueRequest(UpdateRequest):
+    remove_from_all_queues = BoolField(default=False)
+    new_status = StringField()
+
+
 class EnqueueRequest(UpdateRequest):
     queue = StringField()
+    queue_name = StringField()
+    verify_watched_queue = BoolField(default=False)
 
 
 class DeleteRequest(UpdateRequest):
     move_to_trash = BoolField(default=True)
     return_file_urls = BoolField(default=False)
     delete_output_models = BoolField(default=True)
+    delete_external_artifacts = BoolField(default=True)
 
 
 class SetRequirementsRequest(TaskRequest):
     requirements = DictField(required=True)
 
 
+class CompletedRequest(UpdateRequest):
+    publish = BoolField(default=False)
+
+
+class CompletedResponse(UpdateResponse):
+    published = IntField(default=0)
+
+
 class PublishRequest(UpdateRequest):
     publish_model = BoolField(default=True)
 
@@ -171,6 +189,7 @@ class ResetRequest(UpdateRequest):
     clear_all = BoolField(default=False)
     return_file_urls = BoolField(default=False)
     delete_output_models = BoolField(default=True)
+    delete_external_artifacts = BoolField(default=True)
 
 
 class MultiTaskRequest(models.Base):
@@ -260,9 +279,16 @@ class StopManyRequest(TaskBatchRequest):
     force = BoolField(default=False)
 
 
+class DequeueManyRequest(TaskBatchRequest):
+    remove_from_all_queues = BoolField(default=False)
+    new_status = StringField()
+
+
 class EnqueueManyRequest(TaskBatchRequest):
     queue = StringField()
+    queue_name = StringField()
     validate_tasks = BoolField(default=False)
+    verify_watched_queue = BoolField(default=False)
 
 
 class DeleteManyRequest(TaskBatchRequest):
@@ -270,6 +296,7 @@ class DeleteManyRequest(TaskBatchRequest):
     return_file_urls = BoolField(default=False)
     delete_output_models = BoolField(default=True)
     force = BoolField(default=False)
+    delete_external_artifacts = BoolField(default=True)
 
 
 class ResetManyRequest(TaskBatchRequest):
@@ -277,6 +304,7 @@ class ResetManyRequest(TaskBatchRequest):
     return_file_urls = BoolField(default=False)
     delete_output_models = BoolField(default=True)
     force = BoolField(default=False)
+    delete_external_artifacts = BoolField(default=True)
 
 
 class PublishManyRequest(TaskBatchRequest):
@@ -300,3 +328,13 @@ class DeleteModelsRequest(TaskRequest):
     models: Sequence[ModelItemKey] = ListField(
         [ModelItemKey], validators=Length(minimum_value=1)
     )
+
+
+class GetAllReq(models.Base):
+    allow_public = BoolField(default=True)
+    search_hidden = BoolField(default=False)
+
+
+class UpdateTagsRequest(BatchRequest):
+    add_tags = ListField([str])
+    remove_tags = ListField([str])

apiserver/apimodels/users.py

@@ -4,6 +4,10 @@ from jsonmodels.models import Base
 from apiserver.apimodels import DictField
 
 
+class UserRequest(Base):
+    user = StringField(required=True)
+
+
 class CreateRequest(Base):
     id = StringField(required=True)
     name = StringField(required=True)

apiserver/apimodels/workers.py

@@ -12,20 +12,21 @@ from jsonmodels.fields import (
 )
 from jsonmodels.models import Base
 
-from apiserver.apimodels import make_default, ListField, EnumField, JsonSerializableMixin
-
-DEFAULT_TIMEOUT = 10 * 60
+from apiserver.apimodels import ListField, EnumField, JsonSerializableMixin
+from apiserver.config_repo import config
 
 
 class WorkerRequest(Base):
     worker = StringField(required=True)
     tags = ListField(str)
+    system_tags = ListField(str)
 
 
 class RegisterRequest(WorkerRequest):
-    timeout = make_default(
-        IntField, DEFAULT_TIMEOUT
-    )()  # registration timeout in seconds (default is 10min)
+    timeout = IntField(
+        default=int(config.get("services.workers.default_worker_timeout_sec", 10 * 60))
+    )
+    """ registration timeout in seconds (default is 10min) """
     queues = ListField(six.string_types)  # list of queues this worker listens to
 
 
@@ -76,6 +77,7 @@ class WorkerEntry(Base, JsonSerializableMixin):
     last_activity_time = DateTimeField(required=True)
     last_report_time = DateTimeField()
     tags = ListField(str)
+    system_tags = ListField(str)
 
 
 class CurrentTaskEntry(IdNameEntry):
@@ -96,12 +98,18 @@ class WorkerResponseEntry(WorkerEntry):
 
 class GetAllRequest(Base):
     last_seen = IntField(default=3600)
+    tags = ListField(str)
+    system_tags = ListField(str)
 
 
 class GetAllResponse(Base):
     workers = ListField(WorkerResponseEntry)
 
 
+class GetCountRequest(GetAllRequest):
+    last_seen = IntField(default=0)
+
+
 class StatsBase(Base):
     worker_ids = ListField(str)
 

apiserver/bll/auth/__init__.py

@@ -64,7 +64,7 @@ class AuthBLL:
                 feature_set="basic",
             )
 
-            return GetTokenResponse(token=token.decode("ascii"))
+            return GetTokenResponse(token=token)
 
     @staticmethod
     def create_user(request: CreateUserRequest, call: APICall = None) -> str:

apiserver/bll/event/debug_sample_history.py

@@ -1,375 +0,0 @@
-import operator
-from typing import Sequence, Tuple, Optional
-
-import attr
-from boltons.iterutils import first
-from elasticsearch import Elasticsearch
-from jsonmodels.fields import StringField, ListField, IntField, BoolField
-from jsonmodels.models import Base
-from redis import StrictRedis
-
-from apiserver.apierrors import errors
-from apiserver.apimodels import JsonSerializableMixin
-from apiserver.bll.event.event_common import (
-    EventSettings,
-    EventType,
-    check_empty_data,
-    search_company_events,
-)
-from apiserver.bll.redis_cache_manager import RedisCacheManager
-from apiserver.database.errors import translate_errors_context
-from apiserver.timing_context import TimingContext
-from apiserver.utilities.dicts import nested_get
-
-
-class VariantState(Base):
-    name: str = StringField(required=True)
-    min_iteration: int = IntField()
-    max_iteration: int = IntField()
-
-
-class DebugSampleHistoryState(Base, JsonSerializableMixin):
-    id: str = StringField(required=True)
-    iteration: int = IntField()
-    variant: str = StringField()
-    task: str = StringField()
-    metric: str = StringField()
-    reached_first: bool = BoolField()
-    reached_last: bool = BoolField()
-    variant_states: Sequence[VariantState] = ListField([VariantState])
-    warning: str = StringField()
-
-
-@attr.s(auto_attribs=True)
-class DebugSampleHistoryResult(object):
-    scroll_id: str = None
-    event: dict = None
-    min_iteration: int = None
-    max_iteration: int = None
-
-
-class DebugSampleHistory:
-    EVENT_TYPE = EventType.metrics_image
-
-    def __init__(self, redis: StrictRedis, es: Elasticsearch):
-        self.es = es
-        self.cache_manager = RedisCacheManager(
-            state_class=DebugSampleHistoryState,
-            redis=redis,
-            expiration_interval=EventSettings.state_expiration_sec,
-        )
-
-    def get_next_debug_image(
-        self, company_id: str, task: str, state_id: str, navigate_earlier: bool
-    ) -> DebugSampleHistoryResult:
-        """
-        Get the debug image for next/prev variant on the current iteration
-        If does not exist then try getting image for the first/last variant from next/prev iteration
-        """
-        res = DebugSampleHistoryResult(scroll_id=state_id)
-        state = self.cache_manager.get_state(state_id)
-        if not state or state.task != task:
-            raise errors.bad_request.InvalidScrollId(scroll_id=state_id)
-
-        if check_empty_data(self.es, company_id=company_id, event_type=self.EVENT_TYPE):
-            return res
-
-        image = self._get_next_for_current_iteration(
-            company_id=company_id, navigate_earlier=navigate_earlier, state=state
-        ) or self._get_next_for_another_iteration(
-            company_id=company_id, navigate_earlier=navigate_earlier, state=state
-        )
-        if not image:
-            return res
-
-        self._fill_res_and_update_state(image=image, res=res, state=state)
-        self.cache_manager.set_state(state=state)
-        return res
-
-    def _fill_res_and_update_state(
-        self, image: dict, res: DebugSampleHistoryResult, state: DebugSampleHistoryState
-    ):
-        state.variant = image["variant"]
-        state.iteration = image["iter"]
-        res.event = image
-        var_state = first(s for s in state.variant_states if s.name == state.variant)
-        if var_state:
-            res.min_iteration = var_state.min_iteration
-            res.max_iteration = var_state.max_iteration
-
-    def _get_next_for_current_iteration(
-        self, company_id: str, navigate_earlier: bool, state: DebugSampleHistoryState
-    ) -> Optional[dict]:
-        """
-        Get the image for next (if navigated earlier is False) or previous variant sorted by name for the same iteration
-        Only variants for which the iteration falls into their valid range are considered
-        Return None if no such variant or image is found
-        """
-        cmp = operator.lt if navigate_earlier else operator.gt
-        variants = [
-            var_state
-            for var_state in state.variant_states
-            if cmp(var_state.name, state.variant)
-            and var_state.min_iteration <= state.iteration
-        ]
-        if not variants:
-            return
-
-        must_conditions = [
-            {"term": {"task": state.task}},
-            {"term": {"metric": state.metric}},
-            {"terms": {"variant": [v.name for v in variants]}},
-            {"term": {"iter": state.iteration}},
-            {"exists": {"field": "url"}},
-        ]
-        es_req = {
-            "size": 1,
-            "sort": {"variant": "desc" if navigate_earlier else "asc"},
-            "query": {"bool": {"must": must_conditions}},
-        }
-
-        with translate_errors_context(), TimingContext(
-            "es", "get_next_for_current_iteration"
-        ):
-            es_res = search_company_events(
-                self.es, company_id=company_id, event_type=self.EVENT_TYPE, body=es_req
-            )
-
-        hits = nested_get(es_res, ("hits", "hits"))
-        if not hits:
-            return
-
-        return hits[0]["_source"]
-
-    def _get_next_for_another_iteration(
-        self, company_id: str, navigate_earlier: bool, state: DebugSampleHistoryState
-    ) -> Optional[dict]:
-        """
-        Get the image for the first variant for the next iteration (if navigate_earlier is set to False)
-        or from the last variant for the previous iteration (otherwise)
-        The variants for which the image falls in invalid range are discarded
-        If no suitable image is found then None is returned
-        """
-
-        must_conditions = [
-            {"term": {"task": state.task}},
-            {"term": {"metric": state.metric}},
-            {"exists": {"field": "url"}},
-        ]
-
-        if navigate_earlier:
-            range_operator = "lt"
-            order = "desc"
-            variants = [
-                var_state
-                for var_state in state.variant_states
-                if var_state.min_iteration < state.iteration
-            ]
-        else:
-            range_operator = "gt"
-            order = "asc"
-            variants = state.variant_states
-
-        if not variants:
-            return
-
-        variants_conditions = [
-            {
-                "bool": {
-                    "must": [
-                        {"term": {"variant": v.name}},
-                        {"range": {"iter": {"gte": v.min_iteration}}},
-                    ]
-                }
-            }
-            for v in variants
-        ]
-        must_conditions.append({"bool": {"should": variants_conditions}})
-        must_conditions.append({"range": {"iter": {range_operator: state.iteration}}},)
-
-        es_req = {
-            "size": 1,
-            "sort": [{"iter": order}, {"variant": order}],
-            "query": {"bool": {"must": must_conditions}},
-        }
-        with translate_errors_context(), TimingContext(
-            "es", "get_next_for_another_iteration"
-        ):
-            es_res = search_company_events(
-                self.es, company_id=company_id, event_type=self.EVENT_TYPE, body=es_req
-            )
-
-        hits = nested_get(es_res, ("hits", "hits"))
-        if not hits:
-            return
-
-        return hits[0]["_source"]
-
-    def get_debug_image_for_variant(
-        self,
-        company_id: str,
-        task: str,
-        metric: str,
-        variant: str,
-        iteration: Optional[int] = None,
-        refresh: bool = False,
-        state_id: str = None,
-    ) -> DebugSampleHistoryResult:
-        """
-        Get the debug image for the requested iteration or the latest before it
-        If the iteration is not passed then get the latest event
-        """
-        res = DebugSampleHistoryResult()
-        if check_empty_data(self.es, company_id=company_id, event_type=self.EVENT_TYPE):
-            return res
-
-        def init_state(state_: DebugSampleHistoryState):
-            state_.task = task
-            state_.metric = metric
-            self._reset_variant_states(company_id=company_id, state=state_)
-
-        def validate_state(state_: DebugSampleHistoryState):
-            if state_.task != task or state_.metric != metric:
-                raise errors.bad_request.InvalidScrollId(
-                    "Task and metric stored in the state do not match the passed ones",
-                    scroll_id=state_.id,
-                )
-            if refresh:
-                self._reset_variant_states(company_id=company_id, state=state_)
-
-        state: DebugSampleHistoryState
-        with self.cache_manager.get_or_create_state(
-            state_id=state_id, init_state=init_state, validate_state=validate_state,
-        ) as state:
-            res.scroll_id = state.id
-
-            var_state = first(s for s in state.variant_states if s.name == variant)
-            if not var_state:
-                return res
-
-            res.min_iteration = var_state.min_iteration
-            res.max_iteration = var_state.max_iteration
-
-            must_conditions = [
-                {"term": {"task": task}},
-                {"term": {"metric": metric}},
-                {"term": {"variant": variant}},
-                {"exists": {"field": "url"}},
-            ]
-            if iteration is not None:
-                must_conditions.append(
-                    {
-                        "range": {
-                            "iter": {"lte": iteration, "gte": var_state.min_iteration}
-                        }
-                    }
-                )
-            else:
-                must_conditions.append(
-                    {"range": {"iter": {"gte": var_state.min_iteration}}}
-                )
-
-            es_req = {
-                "size": 1,
-                "sort": {"iter": "desc"},
-                "query": {"bool": {"must": must_conditions}},
-            }
-
-            with translate_errors_context(), TimingContext(
-                "es", "get_debug_image_for_variant"
-            ):
-                es_res = search_company_events(
-                    self.es,
-                    company_id=company_id,
-                    event_type=self.EVENT_TYPE,
-                    body=es_req,
-                )
-
-            hits = nested_get(es_res, ("hits", "hits"))
-            if not hits:
-                return res
-
-            self._fill_res_and_update_state(
-                image=hits[0]["_source"], res=res, state=state
-            )
-            return res
-
-    def _reset_variant_states(self, company_id: str, state: DebugSampleHistoryState):
-        variant_iterations = self._get_variant_iterations(
-            company_id=company_id, task=state.task, metric=state.metric
-        )
-        state.variant_states = [
-            VariantState(name=var_name, min_iteration=min_iter, max_iteration=max_iter)
-            for var_name, min_iter, max_iter in variant_iterations
-        ]
-
-    def _get_variant_iterations(
-        self,
-        company_id: str,
-        task: str,
-        metric: str,
-        variants: Optional[Sequence[str]] = None,
-    ) -> Sequence[Tuple[str, int, int]]:
-        """
-        Return valid min and max iterations that the task reported images
-        The min iteration is the lowest iteration that contains non-recycled image url
-        """
-        must = [
-            {"term": {"task": task}},
-            {"term": {"metric": metric}},
-            {"exists": {"field": "url"}},
-        ]
-        if variants:
-            must.append({"terms": {"variant": variants}})
-
-        es_req: dict = {
-            "size": 0,
-            "query": {"bool": {"must": must}},
-            "aggs": {
-                "variants": {
-                    # all variants that sent debug images
-                    "terms": {
-                        "field": "variant",
-                        "size": EventSettings.max_variants_count,
-                        "order": {"_key": "asc"},
-                    },
-                    "aggs": {
-                        "last_iter": {"max": {"field": "iter"}},
-                        "urls": {
-                            # group by urls and choose the minimal iteration
-                            # from all the maximal iterations per url
-                            "terms": {
-                                "field": "url",
-                                "order": {"max_iter": "asc"},
-                                "size": 1,
-                            },
-                            "aggs": {
-                                # find max iteration for each url
-                                "max_iter": {"max": {"field": "iter"}}
-                            },
-                        },
-                    },
-                }
-            },
-        }
-
-        with translate_errors_context(), TimingContext(
-            "es", "get_debug_image_iterations"
-        ):
-            es_res = search_company_events(
-                self.es, company_id=company_id, event_type=self.EVENT_TYPE, body=es_req
-            )
-
-        def get_variant_data(variant_bucket: dict) -> Tuple[str, int, int]:
-            variant = variant_bucket["key"]
-            urls = nested_get(variant_bucket, ("urls", "buckets"))
-            min_iter = int(urls[0]["max_iter"]["value"])
-            max_iter = int(variant_bucket["last_iter"]["value"])
-            return variant, min_iter, max_iter
-
-        return [
-            get_variant_data(variant_bucket)
-            for variant_bucket in nested_get(
-                es_res, ("aggregations", "variants", "buckets")
-            )
-        ]

apiserver/bll/event/event_common.py

@@ -1,10 +1,15 @@
+import base64
+import zlib
 from enum import Enum
-from typing import Union, Sequence, Mapping
+from typing import Union, Sequence, Mapping, Tuple
 
 from boltons.typeutils import classproperty
 from elasticsearch import Elasticsearch
 
 from apiserver.config_repo import config
+from apiserver.database.errors import translate_errors_context
+from apiserver.database.model.task.task import Task
+from apiserver.tools import safe_get
 
 
 class EventType(Enum):
@@ -16,10 +21,14 @@ class EventType(Enum):
     all = "*"
 
 
+SINGLE_SCALAR_ITERATION = -(2 ** 31)
 MetricVariants = Mapping[str, Sequence[str]]
+TaskCompanies = Mapping[str, Sequence[Task]]
 
 
 class EventSettings:
+    _max_es_allowed_aggregation_buckets = 10000
+
     @classproperty
     def max_workers(self):
         return config.get("services.events.events_retrieval.max_metrics_concurrency", 4)
@@ -31,22 +40,31 @@ class EventSettings:
         )
 
     @classproperty
-    def max_metrics_count(self):
-        return config.get("services.events.events_retrieval.max_metrics_count", 100)
-
-    @classproperty
-    def max_variants_count(self):
-        return config.get("services.events.events_retrieval.max_variants_count", 100)
+    def max_es_buckets(self):
+        percentage = (
+            min(
+                100,
+                config.get(
+                    "services.events.events_retrieval.dynamic_metrics_count_threshold",
+                    80,
+                ),
+            )
+            / 100
+        )
+        return int(self._max_es_allowed_aggregation_buckets * percentage)
 
 
-def get_index_name(company_id: str, event_type: str):
+def get_index_name(company_id: Union[str, Sequence[str]], event_type: str):
     event_type = event_type.lower().replace(" ", "_")
-    return f"events-{event_type}-{company_id}"
+    if isinstance(company_id, str):
+        company_id = [company_id]
+
+    return ",".join(f"events-{event_type}-{(c_id or '').lower()}" for c_id in company_id)
 
 
 def check_empty_data(es: Elasticsearch, company_id: str, event_type: EventType) -> bool:
     es_index = get_index_name(company_id, event_type.value)
-    if not es.indices.exists(es_index):
+    if not es.indices.exists(index=es_index):
         return True
     return False
 
@@ -66,9 +84,7 @@ def delete_company_events(
     es: Elasticsearch, company_id: str, event_type: EventType, body: dict, **kwargs
 ) -> dict:
     es_index = get_index_name(company_id, event_type.value)
-    return es.delete_by_query(
-        index=es_index, body=body, conflicts="proceed", **kwargs
-    )
+    return es.delete_by_query(index=es_index, body=body, conflicts="proceed", **kwargs)
 
 
 def count_company_events(
@@ -78,6 +94,44 @@ def count_company_events(
     return es.count(index=es_index, body=body, **kwargs)
 
 
+def get_max_metric_and_variant_counts(
+    es: Elasticsearch,
+    company_id: Union[str, Sequence[str]],
+    event_type: EventType,
+    query: dict,
+    **kwargs,
+) -> Tuple[int, int]:
+    dynamic = config.get(
+        "services.events.events_retrieval.dynamic_metrics_count", False
+    )
+    max_metrics_count = config.get(
+        "services.events.events_retrieval.max_metrics_count", 100
+    )
+    max_variants_count = config.get(
+        "services.events.events_retrieval.max_variants_count", 100
+    )
+    if not dynamic:
+        return max_metrics_count, max_variants_count
+
+    es_req: dict = {
+        "size": 0,
+        "query": query,
+        "aggs": {"metrics_count": {"cardinality": {"field": "metric"}}},
+    }
+    with translate_errors_context():
+        es_res = search_company_events(
+            es, company_id=company_id, event_type=event_type, body=es_req, **kwargs,
+        )
+
+    metrics_count = safe_get(
+        es_res, "aggregations/metrics_count/value", max_metrics_count
+    )
+    if not metrics_count:
+        return max_metrics_count, max_variants_count
+
+    return metrics_count, int(EventSettings.max_es_buckets / metrics_count)
+
+
 def get_metric_variants_condition(metric_variants: MetricVariants,) -> Sequence:
     conditions = [
         {
@@ -94,3 +148,19 @@ def get_metric_variants_condition(metric_variants: MetricVariants,) -> Sequence:
     ]
 
     return {"bool": {"should": conditions}}
+
+
+class PlotFields:
+    valid_plot = "valid_plot"
+    plot_len = "plot_len"
+    plot_str = "plot_str"
+    plot_data = "plot_data"
+    source_urls = "source_urls"
+
+
+def uncompress_plot(event: dict):
+    plot_data = event.pop(PlotFields.plot_data, None)
+    if plot_data and event.get(PlotFields.plot_str) is None:
+        event[PlotFields.plot_str] = zlib.decompress(
+            base64.b64decode(plot_data)
+        ).decode()

apiserver/bll/event/event_metrics.py

@@ -4,12 +4,11 @@ from collections import defaultdict
 from concurrent.futures.thread import ThreadPoolExecutor
 from functools import partial
 from operator import itemgetter
-from typing import Sequence, Tuple
+from typing import Sequence, Tuple, Mapping
 
+from boltons.iterutils import bucketize
 from elasticsearch import Elasticsearch
-from mongoengine import Q
 
-from apiserver.apierrors import errors
 from apiserver.bll.event.event_common import (
     EventType,
     EventSettings,
@@ -17,12 +16,14 @@ from apiserver.bll.event.event_common import (
     check_empty_data,
     MetricVariants,
     get_metric_variants_condition,
+    get_max_metric_and_variant_counts,
+    SINGLE_SCALAR_ITERATION,
+    TaskCompanies,
 )
 from apiserver.bll.event.scalar_key import ScalarKey, ScalarKeyEnum
+from apiserver.bll.query import Builder as QueryBuilder
 from apiserver.config_repo import config
 from apiserver.database.errors import translate_errors_context
-from apiserver.database.model.task.task import Task
-from apiserver.timing_context import TimingContext
 from apiserver.tools import safe_get
 
 log = config.logger(__file__)
@@ -108,57 +109,51 @@ class EventMetrics:
 
     def compare_scalar_metrics_average_per_iter(
         self,
-        company_id,
-        task_ids: Sequence[str],
+        companies: TaskCompanies,
         samples,
         key: ScalarKeyEnum,
-        allow_public=True,
+        metric_variants: MetricVariants = None,
     ):
         """
         Compare scalar metrics for different tasks per metric and variant
         The amount of points in each histogram should not exceed the requested samples
         """
-        task_name_by_id = {}
-        with translate_errors_context():
-            task_objs = Task.get_many(
-                company=company_id,
-                query=Q(id__in=task_ids),
-                allow_public=allow_public,
-                override_projection=("id", "name", "company", "company_origin"),
-                return_dicts=False,
-            )
-            if len(task_objs) < len(task_ids):
-                invalid = tuple(set(task_ids) - set(r.id for r in task_objs))
-                raise errors.bad_request.InvalidTaskId(company=company_id, ids=invalid)
-            task_name_by_id = {t.id: t.name for t in task_objs}
-
-        companies = {t.get_index_company() for t in task_objs}
-        if len(companies) > 1:
-            raise errors.bad_request.InvalidTaskId(
-                "only tasks from the same company are supported"
-            )
-
         event_type = EventType.metrics_scalar
-        company_id = next(iter(companies))
-        if check_empty_data(self.es, company_id=company_id, event_type=event_type):
+        companies = {
+            company_id: tasks
+            for company_id, tasks in companies.items()
+            if not check_empty_data(
+                self.es, company_id=company_id, event_type=event_type
+            )
+        }
+        if not companies:
             return {}
 
         get_scalar_average_per_iter = partial(
             self._get_scalar_average_per_iter_core,
-            company_id=company_id,
             event_type=event_type,
             samples=samples,
             key=ScalarKey.resolve(key),
+            metric_variants=metric_variants,
             run_parallel=False,
         )
+        task_ids, company_ids = zip(
+            *(
+                (t.id, t.company)
+                for t in itertools.chain.from_iterable(companies.values())
+            )
+        )
         with ThreadPoolExecutor(max_workers=EventSettings.max_workers) as pool:
             task_metrics = zip(
-                task_ids, pool.map(get_scalar_average_per_iter, task_ids)
+                task_ids, pool.map(get_scalar_average_per_iter, task_ids, company_ids)
             )
 
+        task_names = {
+            t.id: t.name for t in itertools.chain.from_iterable(companies.values())
+        }
         res = defaultdict(lambda: defaultdict(dict))
         for task_id, task_data in task_metrics:
-            task_name = task_name_by_id[task_id]
+            task_name = task_names[task_id]
             for metric_key, metric_data in task_data.items():
                 for variant_key, variant_data in metric_data.items():
                     variant_data["name"] = task_name
@@ -166,6 +161,75 @@ class EventMetrics:
 
         return res
 
+    def get_task_single_value_metrics(
+        self,
+        companies: TaskCompanies,
+        metric_variants: MetricVariants = None,
+    ) -> Mapping[str, dict]:
+        """
+        For the requested tasks return all the events delivered for the single iteration (-2**31)
+        """
+        companies = {
+            company_id: [t.id for t in tasks]
+            for company_id, tasks in companies.items()
+            if not check_empty_data(
+                self.es, company_id=company_id, event_type=EventType.metrics_scalar
+            )
+        }
+        if not companies:
+            return {}
+
+        with ThreadPoolExecutor(max_workers=EventSettings.max_workers) as pool:
+            task_events = list(
+                itertools.chain.from_iterable(
+                    pool.map(
+                        partial(
+                            self._get_task_single_value_metrics,
+                            metric_variants=metric_variants,
+                        ),
+                        companies.items(),
+                    )
+                ),
+            )
+
+        def _get_value(event: dict):
+            return {
+                field: event.get(field)
+                for field in ("metric", "variant", "value", "timestamp")
+            }
+
+        return {
+            task: [_get_value(e) for e in events]
+            for task, events in bucketize(task_events, itemgetter("task")).items()
+        }
+
+    def _get_task_single_value_metrics(
+        self, tasks: Tuple[str, Sequence[str]], metric_variants: MetricVariants = None
+    ) -> Sequence[dict]:
+        company_id, task_ids = tasks
+        must = [
+            {"terms": {"task": task_ids}},
+            {"term": {"iter": SINGLE_SCALAR_ITERATION}},
+        ]
+        if metric_variants:
+            must.append(get_metric_variants_condition(metric_variants))
+
+        es_req = {
+            "size": 10000,
+            "query": {"bool": {"must": must}},
+        }
+        with translate_errors_context():
+            es_res = search_company_events(
+                body=es_req,
+                es=self.es,
+                company_id=company_id,
+                event_type=EventType.metrics_scalar,
+            )
+            if not es_res["hits"]["total"]["value"]:
+                return []
+
+        return [hit["_source"] for hit in es_res["hits"]["hits"]]
+
     MetricInterval = Tuple[str, str, int, int]
     MetricIntervalGroup = Tuple[int, Sequence[Tuple[str, str]]]
 
@@ -219,11 +283,16 @@ class EventMetrics:
         Return the list og metric variant intervals as the following tuple:
         (metric, variant, interval, samples)
         """
-        must = [{"term": {"task": task_id}}]
+        must = self._task_conditions(task_id)
         if metric_variants:
             must.append(get_metric_variants_condition(metric_variants))
         query = {"bool": {"must": must}}
-
+        search_args = dict(es=self.es, company_id=company_id, event_type=event_type)
+        max_metrics, max_variants = get_max_metric_and_variant_counts(
+            query=query,
+            **search_args,
+        )
+        max_variants = int(max_variants // 2)
         es_req = {
             "size": 0,
             "query": query,
@@ -231,14 +300,14 @@ class EventMetrics:
                 "metrics": {
                     "terms": {
                         "field": "metric",
-                        "size": EventSettings.max_metrics_count,
+                        "size": max_metrics,
                         "order": {"_key": "asc"},
                     },
                     "aggs": {
                         "variants": {
                             "terms": {
                                 "field": "variant",
-                                "size": EventSettings.max_variants_count,
+                                "size": max_variants,
                                 "order": {"_key": "asc"},
                             },
                             "aggs": {
@@ -252,10 +321,7 @@ class EventMetrics:
             },
         }
 
-        with translate_errors_context(), TimingContext("es", "task_stats_get_interval"):
-            es_res = search_company_events(
-                self.es, company_id=company_id, event_type=event_type, body=es_req,
-            )
+        es_res = search_company_events(body=es_req, **search_args)
 
         aggs_result = es_res.get("aggregations")
         if not aggs_result:
@@ -307,33 +373,41 @@ class EventMetrics:
         """
         interval, metrics = metrics_interval
         aggregation = self._add_aggregation_average(key.get_aggregation(interval))
-        aggs = {
-            "metrics": {
-                "terms": {
-                    "field": "metric",
-                    "size": EventSettings.max_metrics_count,
-                    "order": {"_key": "asc"},
-                },
-                "aggs": {
-                    "variants": {
-                        "terms": {
-                            "field": "variant",
-                            "size": EventSettings.max_variants_count,
-                            "order": {"_key": "asc"},
-                        },
-                        "aggs": aggregation,
-                    }
-                },
-            }
-        }
-        aggs_result = self._query_aggregation_for_task_metrics(
-            company_id=company_id,
-            event_type=event_type,
-            aggs=aggs,
-            task_id=task_id,
-            metrics=metrics,
+        query = self._get_task_metrics_query(task_id=task_id, metrics=metrics)
+        search_args = dict(es=self.es, company_id=company_id, event_type=event_type)
+        max_metrics, max_variants = get_max_metric_and_variant_counts(
+            query=query,
+            **search_args,
         )
+        max_variants = int(max_variants // 2)
+        es_req = {
+            "size": 0,
+            "query": query,
+            "aggs": {
+                "metrics": {
+                    "terms": {
+                        "field": "metric",
+                        "size": max_metrics,
+                        "order": {"_key": "asc"},
+                    },
+                    "aggs": {
+                        "variants": {
+                            "terms": {
+                                "field": "variant",
+                                "size": max_variants,
+                                "order": {"_key": "asc"},
+                            },
+                            "aggs": aggregation,
+                        }
+                    },
+                }
+            },
+        }
 
+        with translate_errors_context():
+            es_res = search_company_events(body=es_req, **search_args)
+
+        aggs_result = es_res.get("aggregations")
         if not aggs_result:
             return {}
 
@@ -360,19 +434,20 @@ class EventMetrics:
             for key, value in aggregation.items()
         }
 
-    def _query_aggregation_for_task_metrics(
-        self,
-        company_id: str,
-        event_type: EventType,
-        aggs: dict,
+    @staticmethod
+    def _task_conditions(task_id: str) -> list:
+        return [
+            {"term": {"task": task_id}},
+            {"range": {"iter": {"gt": SINGLE_SCALAR_ITERATION}}},
+        ]
+
+    @classmethod
+    def _get_task_metrics_query(
+        cls,
         task_id: str,
         metrics: Sequence[Tuple[str, str]],
-    ) -> dict:
-        """
-        Return the result of elastic search query for the given aggregation filtered
-        by the given task_ids and metrics
-        """
-        must = [{"term": {"task": task_id}}]
+    ):
+        must = cls._task_conditions(task_id)
         if metrics:
             should = [
                 {
@@ -387,25 +462,98 @@ class EventMetrics:
             ]
             must.append({"bool": {"should": should}})
 
-        es_req = {
-            "size": 0,
-            "query": {"bool": {"must": must}},
-            "aggs": aggs,
-        }
+        return {"bool": {"must": must}}
 
-        with translate_errors_context(), TimingContext("es", "task_stats_scalar"):
-            es_res = search_company_events(
-                self.es, company_id=company_id, event_type=event_type, body=es_req,
+    def get_multi_task_metrics(self, companies: TaskCompanies, event_type: EventType) -> Mapping[str, list]:
+        """
+        For the requested tasks return reported metrics and variants
+        """
+        tasks_ids = {
+            company: [t.id for t in tasks]
+            for company, tasks in companies.items()
+        }
+        with ThreadPoolExecutor(EventSettings.max_workers) as pool:
+            companies_res: Sequence = list(
+                pool.map(
+                    partial(
+                        self._get_multi_task_metrics,
+                        event_type=event_type,
+                    ),
+                    tasks_ids.items(),
+                )
             )
 
-        return es_res.get("aggregations")
+        if len(companies_res) == 1:
+            return companies_res[0]
 
-    def get_tasks_metrics(
+        res = defaultdict(set)
+        for c_res in companies_res:
+            for m, vars_ in c_res.items():
+                res[m].update(vars_)
+
+        return {
+            k: list(v)
+            for k, v in res.items()
+        }
+
+    def _get_multi_task_metrics(
+        self, company_tasks: Tuple[str, Sequence[str]], event_type: EventType
+    ) -> Mapping[str, list]:
+        company_id, task_ids = company_tasks
+        if check_empty_data(self.es, company_id, event_type):
+            return {}
+
+        search_args = dict(
+            es=self.es,
+            company_id=company_id,
+            event_type=event_type,
+        )
+        query = QueryBuilder.terms("task", task_ids)
+        max_metrics, max_variants = get_max_metric_and_variant_counts(
+            query=query,
+            **search_args,
+        )
+        es_req = {
+            "size": 0,
+            "query": query,
+            "aggs": {
+                "metrics": {
+                    "terms": {
+                        "field": "metric",
+                        "size": max_metrics,
+                        "order": {"_key": "asc"},
+                    },
+                    "aggs": {
+                        "variants": {
+                            "terms": {
+                                "field": "variant",
+                                "size": max_variants,
+                                "order": {"_key": "asc"},
+                            },
+                        }
+                    }
+                }
+            },
+        }
+
+        es_res = search_company_events(
+            body=es_req,
+            **search_args,
+        )
+        aggs_result = es_res.get("aggregations")
+        if not aggs_result:
+            return {}
+
+        return {
+            mb["key"]: [vb["key"] for vb in mb["variants"]["buckets"]]
+            for mb in aggs_result["metrics"]["buckets"]
+        }
+
+    def get_task_metrics(
         self, company_id, task_ids: Sequence, event_type: EventType
     ) -> Sequence:
         """
-        For the requested tasks return all the metrics that
-        reported events of the requested types
+        For the requested tasks return reported metrics per task
         """
         if check_empty_data(self.es, company_id, event_type):
             return {}
@@ -426,22 +574,21 @@ class EventMetrics:
     ) -> Sequence:
         es_req = {
             "size": 0,
-            "query": {"bool": {"must": [{"term": {"task": task_id}}]}},
+            "query": {"bool": {"must": self._task_conditions(task_id)}},
             "aggs": {
                 "metrics": {
                     "terms": {
                         "field": "metric",
-                        "size": EventSettings.max_metrics_count,
+                        "size": EventSettings.max_es_buckets,
                         "order": {"_key": "asc"},
                     }
                 }
             },
         }
 
-        with translate_errors_context(), TimingContext("es", "_get_task_metrics"):
-            es_res = search_company_events(
-                self.es, company_id=company_id, event_type=event_type, body=es_req
-            )
+        es_res = search_company_events(
+            self.es, company_id=company_id, event_type=event_type, body=es_req
+        )
 
         return [
             metric["key"]

apiserver/bll/event/events_iterator.py

@@ -4,6 +4,7 @@ import attr
 import jsonmodels.models
 import jwt
 from elasticsearch import Elasticsearch
+from jwt.algorithms import get_default_algorithms
 
 from apiserver.bll.event.event_common import (
     check_empty_data,
@@ -16,7 +17,6 @@ from apiserver.bll.event.event_common import (
 from apiserver.bll.event.scalar_key import ScalarKeyEnum, ScalarKey
 from apiserver.config_repo import config
 from apiserver.database.errors import translate_errors_context
-from apiserver.timing_context import TimingContext
 
 
 @attr.s(auto_attribs=True)
@@ -64,21 +64,20 @@ class EventsIterator:
         self,
         event_type: EventType,
         company_id: str,
-        task_id: str,
+        task_ids: Sequence[str],
         metric_variants: MetricVariants = None,
     ) -> int:
-        query, _ = self._get_initial_query_and_must(task_id, metric_variants)
+        if check_empty_data(self.es, company_id, event_type):
+            return 0
+
+        query, _ = self._get_initial_query_and_must(task_ids, metric_variants)
         es_req = {
             "query": query,
         }
 
-        with translate_errors_context(), TimingContext("es", "count_task_events"):
+        with translate_errors_context():
             es_result = count_company_events(
-                self.es,
-                company_id=company_id,
-                event_type=event_type,
-                body=es_req,
-                routing=task_id,
+                self.es, company_id=company_id, event_type=event_type, body=es_req,
             )
 
             return es_result["count"]
@@ -101,7 +100,7 @@ class EventsIterator:
         For the last key-field value all the events are brought (even if the resulting size exceeds batch_size)
         so that events with this value will not be lost between the calls.
         """
-        query, must = self._get_initial_query_and_must(task_id, metric_variants)
+        query, must = self._get_initial_query_and_must([task_id], metric_variants)
 
         # retrieve the next batch of events
         es_req = {
@@ -113,13 +112,9 @@ class EventsIterator:
         if from_key_value:
             es_req["search_after"] = [from_key_value]
 
-        with translate_errors_context(), TimingContext("es", "get_task_events"):
+        with translate_errors_context():
             es_result = search_company_events(
-                self.es,
-                company_id=company_id,
-                event_type=event_type,
-                body=es_req,
-                routing=task_id,
+                self.es, company_id=company_id, event_type=event_type, body=es_req,
             )
             hits = es_result["hits"]["hits"]
             hits_total = es_result["hits"]["total"]["value"]
@@ -139,11 +134,7 @@ class EventsIterator:
                 },
             }
             es_result = search_company_events(
-                self.es,
-                company_id=company_id,
-                event_type=event_type,
-                body=es_req,
-                routing=task_id,
+                self.es, company_id=company_id, event_type=event_type, body=es_req,
             )
             last_second_hits = es_result["hits"]["hits"]
             if not last_second_hits or len(last_second_hits) < 2:
@@ -167,14 +158,14 @@ class EventsIterator:
 
     @staticmethod
     def _get_initial_query_and_must(
-        task_id: str, metric_variants: MetricVariants = None
+        task_ids: Sequence[str], metric_variants: MetricVariants = None
     ) -> Tuple[dict, list]:
         if not metric_variants:
-            must = [{"term": {"task": task_id}}]
-            query = {"term": {"task": task_id}}
+            query = {"terms": {"task": task_ids}}
+            must = [query]
         else:
             must = [
-                {"term": {"task": task_id}},
+                {"terms": {"task": task_ids}},
                 get_metric_variants_condition(metric_variants),
             ]
             query = {"bool": {"must": must}}
@@ -188,7 +179,7 @@ class Scroll(jsonmodels.models.Base):
             key=config.get(
                 "services.events.events_retrieval.scroll_id_key", "1234567890"
             ),
-        ).decode()
+        )
 
     @classmethod
     def from_scroll_id(cls, scroll_id: str):
@@ -199,6 +190,7 @@ class Scroll(jsonmodels.models.Base):
                     key=config.get(
                         "services.events.events_retrieval.scroll_id_key", "1234567890"
                     ),
+                    algorithms=get_default_algorithms(),
                 )
             )
         except jwt.PyJWTError:

apiserver/bll/event/history_debug_image_iterator.py

@@ -0,0 +1,455 @@
+import operator
+from operator import attrgetter
+from typing import Sequence, Tuple, Optional, Mapping
+
+import attr
+from boltons.iterutils import first, bucketize
+from elasticsearch import Elasticsearch
+from jsonmodels.fields import StringField, IntField, BoolField, ListField
+from jsonmodels.models import Base
+from redis.client import StrictRedis
+
+from apiserver.utilities.dicts import nested_get
+from .event_common import (
+    EventType,
+    EventSettings,
+    check_empty_data,
+    search_company_events,
+    get_max_metric_and_variant_counts,
+)
+from apiserver.apimodels import JsonSerializableMixin
+from apiserver.bll.redis_cache_manager import RedisCacheManager
+from apiserver.apierrors import errors
+
+
+class VariantState(Base):
+    name: str = StringField(required=True)
+    metric: str = StringField(default=None)
+    min_iteration: int = IntField()
+    max_iteration: int = IntField()
+
+
+class DebugImageSampleState(Base, JsonSerializableMixin):
+    id: str = StringField(required=True)
+    iteration: int = IntField()
+    variant: str = StringField()
+    task: str = StringField()
+    metric: str = StringField()
+    variant_states: Sequence[VariantState] = ListField([VariantState])
+    warning: str = StringField()
+    navigate_current_metric = BoolField(default=True)
+
+
+@attr.s(auto_attribs=True)
+class VariantSampleResult(object):
+    scroll_id: str = None
+    event: dict = None
+    min_iteration: int = None
+    max_iteration: int = None
+
+
+class HistoryDebugImageIterator:
+    event_type = EventType.metrics_image
+
+    def __init__(self, redis: StrictRedis, es: Elasticsearch):
+        self.es = es
+        self.cache_manager = RedisCacheManager(
+            state_class=DebugImageSampleState,
+            redis=redis,
+            expiration_interval=EventSettings.state_expiration_sec,
+        )
+
+    def get_next_sample(
+        self,
+        company_id: str,
+        task: str,
+        state_id: str,
+        navigate_earlier: bool,
+        next_iteration: bool,
+    ) -> VariantSampleResult:
+        """
+        Get the sample for next/prev variant on the current iteration
+        If does not exist then try getting sample for the first/last variant from next/prev iteration
+        """
+        res = VariantSampleResult(scroll_id=state_id)
+        state = self.cache_manager.get_state(state_id)
+        if not state or state.task != task:
+            raise errors.bad_request.InvalidScrollId(scroll_id=state_id)
+
+        if check_empty_data(self.es, company_id=company_id, event_type=self.event_type):
+            return res
+
+        if next_iteration:
+            event = self._get_next_for_another_iteration(
+                company_id=company_id, navigate_earlier=navigate_earlier, state=state
+            )
+        else:
+            # noinspection PyArgumentList
+            event = first(
+                f(company_id=company_id, navigate_earlier=navigate_earlier, state=state)
+                for f in (
+                    self._get_next_for_current_iteration,
+                    self._get_next_for_another_iteration,
+                )
+            )
+        if not event:
+            return res
+
+        self._fill_res_and_update_state(event=event, res=res, state=state)
+        self.cache_manager.set_state(state=state)
+        return res
+
+    @staticmethod
+    def _fill_res_and_update_state(
+        event: dict, res: VariantSampleResult, state: DebugImageSampleState
+    ):
+        state.variant = event["variant"]
+        state.metric = event["metric"]
+        state.iteration = event["iter"]
+        res.event = event
+        var_state = first(
+            vs
+            for vs in state.variant_states
+            if vs.name == state.variant and vs.metric == state.metric
+        )
+        if var_state:
+            res.min_iteration = var_state.min_iteration
+            res.max_iteration = var_state.max_iteration
+
+    @staticmethod
+    def _get_metric_conditions(variants: Sequence[VariantState]) -> dict:
+        metrics = bucketize(variants, key=attrgetter("metric"))
+
+        def _get_variants_conditions(metric_variants: Sequence[VariantState]) -> dict:
+            variants_conditions = [
+                {
+                    "bool": {
+                        "must": [
+                            {"term": {"variant": v.name}},
+                            {"range": {"iter": {"gte": v.min_iteration}}},
+                        ]
+                    }
+                }
+                for v in metric_variants
+            ]
+            return {"bool": {"should": variants_conditions}}
+
+        metrics_conditions = [
+            {
+                "bool": {
+                    "must": [
+                        {"term": {"metric": metric}},
+                        _get_variants_conditions(metric_variants),
+                    ]
+                }
+            }
+            for metric, metric_variants in metrics.items()
+        ]
+        return {"bool": {"should": metrics_conditions}}
+
+    def _get_next_for_current_iteration(
+        self, company_id: str, navigate_earlier: bool, state: DebugImageSampleState
+    ) -> Optional[dict]:
+        """
+        Get the sample for next (if navigate_earlier is False) or previous variant sorted by name for the same iteration
+        Only variants for which the iteration falls into their valid range are considered
+        Return None if no such variant or sample is found
+        """
+        if state.navigate_current_metric:
+            variants = [
+                var_state
+                for var_state in state.variant_states
+                if var_state.metric == state.metric
+            ]
+        else:
+            variants = state.variant_states
+
+        cmp = operator.lt if navigate_earlier else operator.gt
+        variants = [
+            var_state
+            for var_state in variants
+            if cmp((var_state.metric, var_state.name), (state.metric, state.variant))
+            and var_state.min_iteration <= state.iteration
+        ]
+        if not variants:
+            return
+
+        must_conditions = [
+            {"term": {"task": state.task}},
+            {"term": {"iter": state.iteration}},
+            self._get_metric_conditions(variants),
+            {"exists": {"field": "url"}},
+        ]
+        order = "desc" if navigate_earlier else "asc"
+        es_req = {
+            "size": 1,
+            "sort": [{"metric": order}, {"variant": order}],
+            "query": {"bool": {"must": must_conditions}},
+        }
+
+        es_res = search_company_events(
+            self.es,
+            company_id=company_id,
+            event_type=self.event_type,
+            body=es_req,
+        )
+
+        hits = nested_get(es_res, ("hits", "hits"))
+        if not hits:
+            return
+
+        return hits[0]["_source"]
+
+    def _get_next_for_another_iteration(
+        self, company_id: str, navigate_earlier: bool, state: DebugImageSampleState
+    ) -> Optional[dict]:
+        """
+        Get the sample for the first variant for the next iteration (if navigate_earlier is set to False)
+        or from the last variant for the previous iteration (otherwise)
+        The variants for which the sample falls in invalid range are discarded
+        If no suitable sample is found then None is returned
+        """
+        if state.navigate_current_metric:
+            variants = [
+                var_state
+                for var_state in state.variant_states
+                if var_state.metric == state.metric
+            ]
+        else:
+            variants = state.variant_states
+
+        if navigate_earlier:
+            range_operator = "lt"
+            order = "desc"
+            variants = [
+                var_state
+                for var_state in variants
+                if var_state.min_iteration < state.iteration
+            ]
+        else:
+            range_operator = "gt"
+            order = "asc"
+            variants = variants
+
+        if not variants:
+            return
+
+        must_conditions = [
+            {"term": {"task": state.task}},
+            self._get_metric_conditions(variants),
+            {"range": {"iter": {range_operator: state.iteration}}},
+            {"exists": {"field": "url"}},
+        ]
+        es_req = {
+            "size": 1,
+            "sort": [{"iter": order}, {"metric": order}, {"variant": order}],
+            "query": {"bool": {"must": must_conditions}},
+        }
+        es_res = search_company_events(
+            self.es,
+            company_id=company_id,
+            event_type=self.event_type,
+            body=es_req,
+        )
+
+        hits = nested_get(es_res, ("hits", "hits"))
+        if not hits:
+            return
+
+        return hits[0]["_source"]
+
+    def get_sample_for_variant(
+        self,
+        company_id: str,
+        task: str,
+        metric: str,
+        variant: str,
+        iteration: Optional[int] = None,
+        refresh: bool = False,
+        state_id: str = None,
+        navigate_current_metric: bool = True,
+    ) -> VariantSampleResult:
+        """
+        Get the sample for the requested iteration or the latest before it
+        If the iteration is not passed then get the latest event
+        """
+        res = VariantSampleResult()
+        if check_empty_data(self.es, company_id=company_id, event_type=self.event_type):
+            return res
+
+        def init_state(state_: DebugImageSampleState):
+            state_.task = task
+            state_.metric = metric
+            state_.navigate_current_metric = navigate_current_metric
+            self._reset_variant_states(company_id=company_id, state=state_)
+
+        def validate_state(state_: DebugImageSampleState):
+            if (
+                state_.task != task
+                or state_.navigate_current_metric != navigate_current_metric
+                or (state_.navigate_current_metric and state_.metric != metric)
+            ):
+                raise errors.bad_request.InvalidScrollId(
+                    "Task and metric stored in the state do not match the passed ones",
+                    scroll_id=state_.id,
+                )
+            # fix old variant states:
+            for vs in state_.variant_states:
+                if vs.metric is None:
+                    vs.metric = metric
+            if refresh:
+                self._reset_variant_states(company_id=company_id, state=state_)
+
+        state: DebugImageSampleState
+        with self.cache_manager.get_or_create_state(
+            state_id=state_id, init_state=init_state, validate_state=validate_state,
+        ) as state:
+            res.scroll_id = state.id
+
+            var_state = first(
+                vs
+                for vs in state.variant_states
+                if vs.name == variant and vs.metric == metric
+            )
+            if not var_state:
+                return res
+
+            res.min_iteration = var_state.min_iteration
+            res.max_iteration = var_state.max_iteration
+
+            must_conditions = [
+                {"term": {"task": task}},
+                {"term": {"metric": metric}},
+                {"term": {"variant": variant}},
+                {"exists": {"field": "url"}},
+            ]
+            if iteration is not None:
+                must_conditions.append(
+                    {
+                        "range": {
+                            "iter": {"lte": iteration, "gte": var_state.min_iteration}
+                        }
+                    }
+                )
+            else:
+                must_conditions.append(
+                    {"range": {"iter": {"gte": var_state.min_iteration}}}
+                )
+
+            es_req = {
+                "size": 1,
+                "sort": {"iter": "desc"},
+                "query": {"bool": {"must": must_conditions}},
+            }
+
+            es_res = search_company_events(
+                self.es,
+                company_id=company_id,
+                event_type=self.event_type,
+                body=es_req,
+            )
+
+            hits = nested_get(es_res, ("hits", "hits"))
+            if not hits:
+                return res
+
+            self._fill_res_and_update_state(
+                event=hits[0]["_source"], res=res, state=state
+            )
+            return res
+
+    def _reset_variant_states(self, company_id: str, state: DebugImageSampleState):
+        metrics = self._get_metric_variant_iterations(
+            company_id=company_id,
+            task=state.task,
+            metric=state.metric if state.navigate_current_metric else None,
+        )
+        state.variant_states = [
+            VariantState(
+                metric=metric,
+                name=var_name,
+                min_iteration=min_iter,
+                max_iteration=max_iter,
+            )
+            for metric, variants in metrics.items()
+            for var_name, min_iter, max_iter in variants
+        ]
+
+    def _get_metric_variant_iterations(
+        self, company_id: str, task: str, metric: str,
+    ) -> Mapping[str, Sequence[Tuple[str, int, int]]]:
+        """
+        Return valid min and max iterations that the task reported events of the required type
+        """
+        must = [
+            {"term": {"task": task}},
+            {"exists": {"field": "url"}},
+        ]
+        if metric is not None:
+            must.append({"term": {"metric": metric}})
+        query = {"bool": {"must": must}}
+
+        search_args = dict(
+            es=self.es, company_id=company_id, event_type=self.event_type,
+        )
+        max_metrics, max_variants = get_max_metric_and_variant_counts(
+            query=query, **search_args
+        )
+        max_variants = int(max_variants // 2)
+        es_req: dict = {
+            "size": 0,
+            "query": query,
+            "aggs": {
+                "metrics": {
+                    "terms": {
+                        "field": "metric",
+                        "size": max_metrics,
+                        "order": {"_key": "asc"},
+                    },
+                    "aggs": {
+                        "variants": {
+                            "terms": {
+                                "field": "variant",
+                                "size": max_variants,
+                                "order": {"_key": "asc"},
+                            },
+                            "aggs": {
+                                "last_iter": {"max": {"field": "iter"}},
+                                "urls": {
+                                    # group by urls and choose the minimal iteration
+                                    # from all the maximal iterations per url
+                                    "terms": {
+                                        "field": "url",
+                                        "order": {"max_iter": "asc"},
+                                        "size": 1,
+                                    },
+                                    "aggs": {
+                                        # find max iteration for each url
+                                        "max_iter": {"max": {"field": "iter"}}
+                                    },
+                                },
+                            },
+                        }
+                    },
+                }
+            },
+        }
+
+        es_res = search_company_events(body=es_req, **search_args)
+
+        def get_variant_data(variant_bucket: dict) -> Tuple[str, int, int]:
+            variant = variant_bucket["key"]
+            urls = nested_get(variant_bucket, ("urls", "buckets"))
+            min_iter = int(urls[0]["max_iter"]["value"])
+            max_iter = int(variant_bucket["last_iter"]["value"])
+            return variant, min_iter, max_iter
+
+        return {
+            metric_bucket["key"]: [
+                get_variant_data(variant_bucket)
+                for variant_bucket in nested_get(metric_bucket, ("variants", "buckets"))
+            ]
+            for metric_bucket in nested_get(
+                es_res, ("aggregations", "metrics", "buckets")
+            )
+        }

apiserver/bll/event/history_plots_iterator.py

@@ -0,0 +1,316 @@
+from typing import Sequence, Tuple, Optional, Mapping
+
+import attr
+from boltons.iterutils import first
+from elasticsearch import Elasticsearch
+from jsonmodels.fields import StringField, IntField, ListField, BoolField
+from jsonmodels.models import Base
+from redis.client import StrictRedis
+
+from .event_common import (
+    EventType,
+    uncompress_plot,
+    EventSettings,
+    check_empty_data,
+    search_company_events,
+)
+from apiserver.apimodels import JsonSerializableMixin
+from apiserver.utilities.dicts import nested_get
+from apiserver.bll.redis_cache_manager import RedisCacheManager
+from apiserver.apierrors import errors
+
+
+class MetricState(Base):
+    name: str = StringField(default=None)
+    min_iteration: int = IntField()
+    max_iteration: int = IntField()
+
+
+class PlotsSampleState(Base, JsonSerializableMixin):
+    id: str = StringField(required=True)
+    iteration: int = IntField()
+    task: str = StringField()
+    metric: str = StringField()
+    metric_states: Sequence[MetricState] = ListField([MetricState])
+    warning: str = StringField()
+    navigate_current_metric = BoolField(default=True)
+
+
+@attr.s(auto_attribs=True)
+class MetricSamplesResult(object):
+    scroll_id: str = None
+    events: list = []
+    min_iteration: int = None
+    max_iteration: int = None
+
+
+class HistoryPlotsIterator:
+    event_type = EventType.metrics_plot
+
+    def __init__(self, redis: StrictRedis, es: Elasticsearch):
+        self.es = es
+        self.cache_manager = RedisCacheManager(
+            state_class=PlotsSampleState,
+            redis=redis,
+            expiration_interval=EventSettings.state_expiration_sec,
+        )
+
+    def get_next_sample(
+        self,
+        company_id: str,
+        task: str,
+        state_id: str,
+        navigate_earlier: bool,
+        next_iteration: bool,
+    ) -> MetricSamplesResult:
+        """
+        Get the samples for next/prev metric on the current iteration
+        If does not exist then try getting sample for the first/last metric from next/prev iteration
+        """
+        res = MetricSamplesResult(scroll_id=state_id)
+        state = self.cache_manager.get_state(state_id)
+        if not state or state.task != task:
+            raise errors.bad_request.InvalidScrollId(scroll_id=state_id)
+
+        if check_empty_data(self.es, company_id=company_id, event_type=self.event_type):
+            return res
+
+        if navigate_earlier:
+            range_operator = "lt"
+            order = "desc"
+        else:
+            range_operator = "gt"
+            order = "asc"
+
+        must_conditions = [
+            {"term": {"task": state.task}},
+        ]
+        if state.navigate_current_metric:
+            must_conditions.append({"term": {"metric": state.metric}})
+
+        next_iteration_condition = {
+            "range": {"iter": {range_operator: state.iteration}}
+        }
+        if next_iteration or state.navigate_current_metric:
+            must_conditions.append(next_iteration_condition)
+        else:
+            next_metric_condition = {
+                "bool": {
+                    "must": [
+                        {"term": {"iter": state.iteration}},
+                        {"range": {"metric": {range_operator: state.metric}}},
+                    ]
+                }
+            }
+            must_conditions.append(
+                {"bool": {"should": [next_metric_condition, next_iteration_condition]}}
+            )
+
+        events = self._get_metric_events_for_condition(
+            company_id=company_id,
+            task=state.task,
+            order=order,
+            must_conditions=must_conditions,
+        )
+
+        if not events:
+            return res
+
+        self._fill_res_and_update_state(events=events, res=res, state=state)
+        self.cache_manager.set_state(state=state)
+        return res
+
+    def get_samples_for_metric(
+        self,
+        company_id: str,
+        task: str,
+        metric: str,
+        iteration: Optional[int] = None,
+        refresh: bool = False,
+        state_id: str = None,
+        navigate_current_metric: bool = True,
+    ) -> MetricSamplesResult:
+        """
+        Get the sample for the requested iteration or the latest before it
+        If the iteration is not passed then get the latest event
+        """
+        res = MetricSamplesResult()
+        if check_empty_data(self.es, company_id=company_id, event_type=self.event_type):
+            return res
+
+        def init_state(state_: PlotsSampleState):
+            state_.task = task
+            state_.metric = metric
+            state_.navigate_current_metric = navigate_current_metric
+            self._reset_metric_states(company_id=company_id, state=state_)
+
+        def validate_state(state_: PlotsSampleState):
+            if (
+                state_.task != task
+                or state_.navigate_current_metric != navigate_current_metric
+                or (state_.navigate_current_metric and state_.metric != metric)
+            ):
+                raise errors.bad_request.InvalidScrollId(
+                    "Task and metric stored in the state do not match the passed ones",
+                    scroll_id=state_.id,
+                )
+            if refresh:
+                self._reset_metric_states(company_id=company_id, state=state_)
+
+        state: PlotsSampleState
+        with self.cache_manager.get_or_create_state(
+            state_id=state_id, init_state=init_state, validate_state=validate_state,
+        ) as state:
+            res.scroll_id = state.id
+
+            metric_state = first(ms for ms in state.metric_states if ms.name == metric)
+            if not metric_state:
+                return res
+
+            res.min_iteration = metric_state.min_iteration
+            res.max_iteration = metric_state.max_iteration
+
+            must_conditions = [
+                {"term": {"task": task}},
+                {"term": {"metric": metric}},
+            ]
+            if iteration is not None:
+                must_conditions.append({"range": {"iter": {"lte": iteration}}})
+
+            events = self._get_metric_events_for_condition(
+                company_id=company_id,
+                task=state.task,
+                order="desc",
+                must_conditions=must_conditions,
+            )
+            if not events:
+                return res
+
+            self._fill_res_and_update_state(events=events, res=res, state=state)
+            return res
+
+    def _reset_metric_states(self, company_id: str, state: PlotsSampleState):
+        metrics = self._get_metric_iterations(
+            company_id=company_id,
+            task=state.task,
+            metric=state.metric if state.navigate_current_metric else None,
+        )
+        state.metric_states = [
+            MetricState(name=metric, min_iteration=min_iter, max_iteration=max_iter)
+            for metric, (min_iter, max_iter) in metrics.items()
+        ]
+
+    def _get_metric_iterations(
+        self, company_id: str, task: str, metric: str,
+    ) -> Mapping[str, Tuple[int, int]]:
+        """
+        Return valid min and max iterations that the task reported events of the required type
+        """
+        must = [
+            {"term": {"task": task}},
+        ]
+        if metric is not None:
+            must.append({"term": {"metric": metric}})
+        query = {"bool": {"must": must}}
+
+        es_req: dict = {
+            "size": 0,
+            "query": query,
+            "aggs": {
+                "metrics": {
+                    "terms": {
+                        "field": "metric",
+                        "size": 5000,
+                        "order": {"_key": "asc"},
+                    },
+                    "aggs": {
+                        "last_iter": {"max": {"field": "iter"}},
+                        "first_iter": {"min": {"field": "iter"}},
+                    },
+                }
+            },
+        }
+
+        es_res = search_company_events(
+            body=es_req,
+            es=self.es,
+            company_id=company_id,
+            event_type=self.event_type,
+        )
+
+        return {
+            metric_bucket["key"]: (
+                int(metric_bucket["first_iter"]["value"]),
+                int(metric_bucket["last_iter"]["value"]),
+            )
+            for metric_bucket in nested_get(
+                es_res, ("aggregations", "metrics", "buckets")
+            )
+        }
+
+    @staticmethod
+    def _fill_res_and_update_state(
+        events: Sequence[dict], res: MetricSamplesResult, state: PlotsSampleState
+    ):
+        for event in events:
+            uncompress_plot(event)
+        state.metric = events[0]["metric"]
+        state.iteration = events[0]["iter"]
+        res.events = events
+        metric_state = first(
+            ms for ms in state.metric_states if ms.name == state.metric
+        )
+        if metric_state:
+            res.min_iteration = metric_state.min_iteration
+            res.max_iteration = metric_state.max_iteration
+
+    def _get_metric_events_for_condition(
+        self, company_id: str, task: str, order: str, must_conditions: Sequence
+    ) -> Sequence:
+        es_req = {
+            "size": 0,
+            "query": {"bool": {"must": must_conditions}},
+            "aggs": {
+                "iters": {
+                    "terms": {"field": "iter", "size": 1, "order": {"_key": order}},
+                    "aggs": {
+                        "metrics": {
+                            "terms": {
+                                "field": "metric",
+                                "size": 1,
+                                "order": {"_key": order},
+                            },
+                            "aggs": {
+                                "events": {
+                                    "top_hits": {
+                                        "sort": {"variant": {"order": "asc"}},
+                                        "size": 100,
+                                    }
+                                }
+                            },
+                        },
+                    },
+                }
+            },
+        }
+        es_res = search_company_events(
+            self.es,
+            company_id=company_id,
+            event_type=self.event_type,
+            body=es_req,
+        )
+
+        aggs_result = es_res.get("aggregations")
+        if not aggs_result:
+            return []
+
+        for level in ("iters", "metrics"):
+            level_data = aggs_result[level]["buckets"]
+            if not level_data:
+                return []
+            aggs_result = level_data[0]
+
+        return [
+            hit["_source"]
+            for hit in nested_get(aggs_result, ("events", "hits", "hits"))
+        ]

apiserver/bll/event/metric_debug_images_iterator.py

@@ -0,0 +1,53 @@
+from typing import Sequence, Tuple, Callable
+
+from elasticsearch import Elasticsearch
+from redis.client import StrictRedis
+
+from apiserver.utilities.dicts import nested_get
+from .event_common import EventType
+from .metric_events_iterator import MetricEventsIterator, VariantState
+
+
+class MetricDebugImagesIterator(MetricEventsIterator):
+    def __init__(self, redis: StrictRedis, es: Elasticsearch):
+        super().__init__(redis, es, EventType.metrics_image)
+
+    def _get_extra_conditions(self) -> Sequence[dict]:
+        return [{"exists": {"field": "url"}}]
+
+    def _get_variant_state_aggs(self) -> Tuple[dict, Callable[[dict, VariantState], None]]:
+        aggs = {
+            "urls": {
+                "terms": {
+                    "field": "url",
+                    "order": {"max_iter": "desc"},
+                    "size": 1,  # we need only one url from the most recent iteration
+                },
+                "aggs": {
+                    "max_iter": {"max": {"field": "iter"}},
+                    "iters": {
+                        "top_hits": {
+                            "sort": {"iter": {"order": "desc"}},
+                            "size": 2,  # need two last iterations so that we can take
+                            # the second one as invalid
+                            "_source": "iter",
+                        }
+                    },
+                },
+            }
+        }
+
+        def fill_variant_state_data(variant_bucket: dict,  state: VariantState):
+            """If the image urls get recycled then fill the last_invalid_iteration field"""
+            top_iter_url = nested_get(variant_bucket, ("urls", "buckets"))[0]
+            iters = nested_get(top_iter_url, ("iters", "hits", "hits"))
+            if len(iters) > 1:
+                state.last_invalid_iteration = nested_get(iters[1], ("_source", "iter"))
+
+        return aggs, fill_variant_state_data
+
+    def _process_event(self, event: dict) -> dict:
+        return event
+
+    def _get_same_variant_events_order(self) -> dict:
+        return {"url": {"order": "desc"}}

apiserver/bll/event/metric_events_iterator.py

@@ -1,8 +1,9 @@
+import abc
 from concurrent.futures.thread import ThreadPoolExecutor
 from datetime import datetime
 from functools import partial
 from operator import itemgetter
-from typing import Sequence, Tuple, Optional, Mapping
+from typing import Sequence, Tuple, Optional, Mapping, Callable
 
 import attr
 import dpath
@@ -19,12 +20,13 @@ from apiserver.bll.event.event_common import (
     search_company_events,
     EventType,
     get_metric_variants_condition,
+    get_max_metric_and_variant_counts,
 )
 from apiserver.bll.redis_cache_manager import RedisCacheManager
+from apiserver.config_repo import config
 from apiserver.database.errors import translate_errors_context
 from apiserver.database.model.task.metrics import MetricEventStats
 from apiserver.database.model.task.task import Task
-from apiserver.timing_context import TimingContext
 
 
 class VariantState(Base):
@@ -49,65 +51,78 @@ class TaskScrollState(Base):
         self.last_min_iter = self.last_max_iter = None
 
 
-class DebugImageEventsScrollState(Base, JsonSerializableMixin):
+class MetricEventsScrollState(Base, JsonSerializableMixin):
     id: str = StringField(required=True)
     tasks: Sequence[TaskScrollState] = ListField([TaskScrollState])
     warning: str = StringField()
 
 
 @attr.s(auto_attribs=True)
-class DebugImagesResult(object):
+class MetricEventsResult(object):
     metric_events: Sequence[tuple] = []
     next_scroll_id: str = None
 
 
-class DebugImagesIterator:
-    EVENT_TYPE = EventType.metrics_image
-
-    def __init__(self, redis: StrictRedis, es: Elasticsearch):
+class MetricEventsIterator:
+    def __init__(self, redis: StrictRedis, es: Elasticsearch, event_type: EventType):
         self.es = es
+        self.event_type = event_type
         self.cache_manager = RedisCacheManager(
-            state_class=DebugImageEventsScrollState,
+            state_class=MetricEventsScrollState,
             redis=redis,
             expiration_interval=EventSettings.state_expiration_sec,
         )
 
     def get_task_events(
         self,
-        company_id: str,
+        companies: Mapping[str, str],
         task_metrics: Mapping[str, dict],
         iter_count: int,
         navigate_earlier: bool = True,
         refresh: bool = False,
         state_id: str = None,
-    ) -> DebugImagesResult:
-        if check_empty_data(self.es, company_id, self.EVENT_TYPE):
-            return DebugImagesResult()
+    ) -> MetricEventsResult:
+        companies = {
+            task_id: company_id
+            for task_id, company_id in companies.items()
+            if not check_empty_data(
+                self.es, company_id=company_id, event_type=self.event_type
+            )
+        }
+        if not companies:
+            return MetricEventsResult()
 
-        def init_state(state_: DebugImageEventsScrollState):
-            state_.tasks = self._init_task_states(company_id, task_metrics)
+        def init_state(state_: MetricEventsScrollState):
+            state_.tasks = self._init_task_states(companies, task_metrics)
 
-        def validate_state(state_: DebugImageEventsScrollState):
+        def validate_state(state_: MetricEventsScrollState):
             """
             Validate that the metrics stored in the state are the same
             as requested in the current call.
             Refresh the state if requested
             """
             if refresh:
-                self._reinit_outdated_task_states(company_id, state_, task_metrics)
+                self._reinit_outdated_task_states(companies, state_, task_metrics)
 
         with self.cache_manager.get_or_create_state(
             state_id=state_id, init_state=init_state, validate_state=validate_state
         ) as state:
-            res = DebugImagesResult(next_scroll_id=state.id)
+            res = MetricEventsResult(next_scroll_id=state.id)
+            specific_variants_requested = any(
+                variants
+                for t, metrics in task_metrics.items()
+                if metrics
+                for m, variants in metrics.items()
+            )
             with ThreadPoolExecutor(EventSettings.max_workers) as pool:
                 res.metric_events = list(
                     pool.map(
                         partial(
                             self._get_task_metric_events,
-                            company_id=company_id,
+                            companies=companies,
                             iter_count=iter_count,
                             navigate_earlier=navigate_earlier,
+                            specific_variants_requested=specific_variants_requested,
                         ),
                         state.tasks,
                     )
@@ -117,22 +132,20 @@ class DebugImagesIterator:
 
     def _reinit_outdated_task_states(
         self,
-        company_id,
-        state: DebugImageEventsScrollState,
+        companies: Mapping[str, str],
+        state: MetricEventsScrollState,
         task_metrics: Mapping[str, dict],
     ):
         """
-        Determine the metrics for which new debug image events were added
+        Determine the metrics for which new event_type events were added
         since their states were initialized and re-init these states
         """
-        tasks = Task.objects(id__in=list(task_metrics), company=company_id).only(
-            "id", "metric_stats"
-        )
+        tasks = Task.objects(id__in=list(task_metrics)).only("id", "metric_stats")
 
         def get_last_update_times_for_task_metrics(
             task: Task,
         ) -> Mapping[str, datetime]:
-            """For metrics that reported debug image events get mapping of the metric name to the last update times"""
+            """For metrics that reported event_type events get mapping of the metric name to the last update times"""
             metric_stats: Mapping[str, MetricEventStats] = task.metric_stats
             if not metric_stats:
                 return {}
@@ -140,10 +153,10 @@ class DebugImagesIterator:
             requested_metrics = task_metrics[task.id]
             return {
                 stats.metric: stats.event_stats_by_type[
-                    self.EVENT_TYPE.value
+                    self.event_type.value
                 ].last_update
                 for stats in metric_stats.values()
-                if self.EVENT_TYPE.value in stats.event_stats_by_type
+                if self.event_type.value in stats.event_stats_by_type
                 and (not requested_metrics or stats.metric in requested_metrics)
             }
 
@@ -167,7 +180,7 @@ class DebugImagesIterator:
             if metrics_to_recalc:
                 task_metrics_to_recalc[task] = metrics_to_recalc
 
-        updated_task_states = self._init_task_states(company_id, task_metrics_to_recalc)
+        updated_task_states = self._init_task_states(companies, task_metrics_to_recalc)
 
         def merge_with_updated_task_states(
             old_state: TaskScrollState, updates: Sequence[TaskScrollState]
@@ -197,14 +210,14 @@ class DebugImagesIterator:
         ]
 
     def _init_task_states(
-        self, company_id: str, task_metrics: Mapping[str, dict]
+        self, companies: Mapping[str, str], task_metrics: Mapping[str, dict]
     ) -> Sequence[TaskScrollState]:
         """
         Returned initialized metric scroll stated for the requested task metrics
         """
         with ThreadPoolExecutor(EventSettings.max_workers) as pool:
             task_metric_states = pool.map(
-                partial(self._init_metric_states_for_task, company_id=company_id),
+                partial(self._init_metric_states_for_task, companies=companies),
                 task_metrics.items(),
             )
 
@@ -213,18 +226,38 @@ class DebugImagesIterator:
             for task, metric_states in zip(task_metrics, task_metric_states)
         ]
 
+    @abc.abstractmethod
+    def _get_extra_conditions(self) -> Sequence[dict]:
+        pass
+
+    @abc.abstractmethod
+    def _get_variant_state_aggs(
+        self,
+    ) -> Tuple[dict, Callable[[dict, VariantState], None]]:
+        pass
+
     def _init_metric_states_for_task(
-        self, task_metrics: Tuple[str, dict], company_id: str
+        self, task_metrics: Tuple[str, dict], companies: Mapping[str, str]
     ) -> Sequence[MetricState]:
         """
         Return metric scroll states for the task filled with the variant states
-        for the variants that reported any debug images
+        for the variants that reported any event_type events
         """
         task, metrics = task_metrics
-        must = [{"term": {"task": task}}, {"exists": {"field": "url"}}]
+        company_id = companies[task]
+        must = [{"term": {"task": task}}, *self._get_extra_conditions()]
         if metrics:
             must.append(get_metric_variants_condition(metrics))
         query = {"bool": {"must": must}}
+
+        search_args = dict(
+            es=self.es, company_id=company_id, event_type=self.event_type
+        )
+        max_metrics, max_variants = get_max_metric_and_variant_counts(
+            query=query, **search_args
+        )
+        max_variants = int(max_variants // 2)
+        variant_state_aggs, fill_variant_state_data = self._get_variant_state_aggs()
         es_req: dict = {
             "size": 0,
             "query": query,
@@ -232,7 +265,7 @@ class DebugImagesIterator:
                 "metrics": {
                     "terms": {
                         "field": "metric",
-                        "size": EventSettings.max_metrics_count,
+                        "size": max_metrics,
                         "order": {"_key": "asc"},
                     },
                     "aggs": {
@@ -240,52 +273,33 @@ class DebugImagesIterator:
                         "variants": {
                             "terms": {
                                 "field": "variant",
-                                "size": EventSettings.max_variants_count,
+                                "size": max_variants,
                                 "order": {"_key": "asc"},
                             },
-                            "aggs": {
-                                "urls": {
-                                    "terms": {
-                                        "field": "url",
-                                        "order": {"max_iter": "desc"},
-                                        "size": 1,  # we need only one url from the most recent iteration
-                                    },
-                                    "aggs": {
-                                        "max_iter": {"max": {"field": "iter"}},
-                                        "iters": {
-                                            "top_hits": {
-                                                "sort": {"iter": {"order": "desc"}},
-                                                "size": 2,  # need two last iterations so that we can take
-                                                # the second one as invalid
-                                                "_source": "iter",
-                                            }
-                                        },
-                                    },
-                                }
-                            },
+                            **(
+                                {"aggs": variant_state_aggs}
+                                if variant_state_aggs
+                                else {}
+                            ),
                         },
                     },
                 }
             },
         }
 
-        with translate_errors_context(), TimingContext("es", "_init_metric_states"):
-            es_res = search_company_events(
-                self.es, company_id=company_id, event_type=self.EVENT_TYPE, body=es_req,
-            )
+        with translate_errors_context():
+            es_res = search_company_events(body=es_req, **search_args)
         if "aggregations" not in es_res:
             return []
 
         def init_variant_state(variant: dict):
             """
             Return new variant state for the passed variant bucket
-            If the image urls get recycled then fill the last_invalid_iteration field
             """
             state = VariantState(variant=variant["key"])
-            top_iter_url = dpath.get(variant, "urls/buckets")[0]
-            iters = dpath.get(top_iter_url, "iters/hits/hits")
-            if len(iters) > 1:
-                state.last_invalid_iteration = dpath.get(iters[1], "_source/iter")
+            if fill_variant_state_data:
+                fill_variant_state_data(variant, state)
+
             return state
 
         return [
@@ -300,12 +314,21 @@ class DebugImagesIterator:
             for metric in dpath.get(es_res, "aggregations/metrics/buckets")
         ]
 
+    @abc.abstractmethod
+    def _process_event(self, event: dict) -> dict:
+        pass
+
+    @abc.abstractmethod
+    def _get_same_variant_events_order(self) -> dict:
+        pass
+
     def _get_task_metric_events(
         self,
         task_state: TaskScrollState,
-        company_id: str,
+        companies: Mapping[str, str],
         iter_count: int,
         navigate_earlier: bool,
+        specific_variants_requested: bool,
     ) -> Tuple:
         """
         Return task metric events grouped by iterations
@@ -321,7 +344,7 @@ class DebugImagesIterator:
         must_conditions = [
             {"term": {"task": task_state.task}},
             {"terms": {"metric": [m.metric for m in task_state.metrics]}},
-            {"exists": {"field": "url"}},
+            *self._get_extra_conditions(),
         ]
 
         range_condition = None
@@ -332,6 +355,8 @@ class DebugImagesIterator:
         if range_condition:
             must_conditions.append({"range": {"iter": range_condition}})
 
+        metrics_count = len(task_state.metrics)
+        max_variants = int(EventSettings.max_es_buckets / (metrics_count * iter_count))
         es_req = {
             "size": 0,
             "query": {"bool": {"must": must_conditions}},
@@ -346,20 +371,20 @@ class DebugImagesIterator:
                         "metrics": {
                             "terms": {
                                 "field": "metric",
-                                "size": EventSettings.max_metrics_count,
+                                "size": metrics_count,
                                 "order": {"_key": "asc"},
                             },
                             "aggs": {
                                 "variants": {
                                     "terms": {
                                         "field": "variant",
-                                        "size": EventSettings.max_variants_count,
+                                        "size": max_variants,
                                         "order": {"_key": "asc"},
                                     },
                                     "aggs": {
                                         "events": {
                                             "top_hits": {
-                                                "sort": {"url": {"order": "desc"}}
+                                                "sort": self._get_same_variant_events_order()
                                             }
                                         }
                                     },
@@ -370,9 +395,12 @@ class DebugImagesIterator:
                 }
             },
         }
-        with translate_errors_context(), TimingContext("es", "get_debug_image_events"):
+        with translate_errors_context():
             es_res = search_company_events(
-                self.es, company_id=company_id, event_type=self.EVENT_TYPE, body=es_req,
+                self.es,
+                company_id=companies[task_state.task],
+                event_type=self.event_type,
+                body=es_req,
             )
         if "aggregations" not in es_res:
             return task_state.task, []
@@ -382,18 +410,26 @@ class DebugImagesIterator:
             for m in task_state.metrics
             for v in m.variants
         }
+        allow_uninitialized = (
+            False
+            if specific_variants_requested
+            else config.get(
+                "services.events.events_retrieval.debug_images.allow_uninitialized_variants",
+                False,
+            )
+        )
 
         def is_valid_event(event: dict) -> bool:
             key = event.get("metric"), event.get("variant")
             if key not in invalid_iterations:
-                return False
+                return allow_uninitialized
 
             max_invalid = invalid_iterations[key]
             return max_invalid is None or event.get("iter") > max_invalid
 
         def get_iteration_events(it_: dict) -> Sequence:
             return [
-                ev["_source"]
+                self._process_event(ev["_source"])
                 for m in dpath.get(it_, "metrics/buckets")
                 for v in dpath.get(m, "variants/buckets")
                 for ev in dpath.get(v, "events/hits/hits")

apiserver/bll/event/metric_plots_iterator.py

@@ -0,0 +1,25 @@
+from typing import Sequence
+
+from elasticsearch import Elasticsearch
+from redis.client import StrictRedis
+
+from .event_common import EventType, uncompress_plot
+from .metric_events_iterator import MetricEventsIterator
+
+
+class MetricPlotsIterator(MetricEventsIterator):
+    def __init__(self, redis: StrictRedis, es: Elasticsearch):
+        super().__init__(redis, es, EventType.metrics_plot)
+
+    def _get_extra_conditions(self) -> Sequence[dict]:
+        return []
+
+    def _get_variant_state_aggs(self):
+        return None, None
+
+    def _process_event(self, event: dict) -> dict:
+        uncompress_plot(event)
+        return event
+
+    def _get_same_variant_events_order(self) -> dict:
+        return {"timestamp": {"order": "desc"}}

apiserver/bll/model/__init__.py

@@ -1,16 +1,22 @@
 from datetime import datetime
-from typing import Callable, Tuple
+from typing import Callable, Tuple, Sequence, Dict, Optional
+
+from mongoengine import Q
 
 from apiserver.apierrors import errors
 from apiserver.apimodels.models import ModelTaskPublishResponse
-from apiserver.bll.task.utils import deleted_prefix
+from apiserver.bll.task.utils import deleted_prefix, get_last_metric_updates
+from apiserver.config_repo import config
 from apiserver.database.model import EntityVisibility
 from apiserver.database.model.model import Model
 from apiserver.database.model.task.task import Task, TaskStatus
+from apiserver.service_repo.auth import Identity
 from .metadata import Metadata
 
 
 class ModelBLL:
+    event_bll = None
+
     @classmethod
     def get_company_model_by_id(
         cls, company_id: str, model_id: str, only_fields=None
@@ -24,18 +30,43 @@ class ModelBLL:
             raise errors.bad_request.InvalidModelId(**query)
         return model
 
+    @staticmethod
+    def assert_exists(
+        company_id, model_ids, only=None, allow_public=False, return_models=True,
+    ) -> Optional[Sequence[Model]]:
+        model_ids = [model_ids] if isinstance(model_ids, str) else model_ids
+        ids = set(model_ids)
+        query = Q(id__in=ids)
+
+        q = Model.get_many(
+            company=company_id,
+            query=query,
+            allow_public=allow_public,
+            return_dicts=False,
+        )
+        if only:
+            q = q.only(*only)
+
+        if q.count() != len(ids):
+            raise errors.bad_request.InvalidModelId(ids=model_ids)
+
+        if return_models:
+            return list(q)
+
     @classmethod
     def publish_model(
         cls,
         model_id: str,
         company_id: str,
+        identity: Identity,
         force_publish_task: bool = False,
-        publish_task_func: Callable[[str, str, bool], dict] = None,
+        publish_task_func: Callable[[str, str, Identity, bool], dict] = None,
     ) -> Tuple[int, ModelTaskPublishResponse]:
         model = cls.get_company_model_by_id(company_id=company_id, model_id=model_id)
         if model.ready:
             raise errors.bad_request.ModelIsReady(company=company_id, model=model_id)
 
+        user_id = identity.user
         published_task = None
         if model.task and publish_task_func:
             task = (
@@ -45,18 +76,25 @@ class ModelBLL:
             )
             if task and task.status != TaskStatus.published:
                 task_publish_res = publish_task_func(
-                    model.task, company_id, force_publish_task
+                    model.task, company_id, identity, force_publish_task
                 )
                 published_task = ModelTaskPublishResponse(
                     id=model.task, data=task_publish_res
                 )
 
-        updated = model.update(upsert=False, ready=True, last_update=datetime.utcnow())
+        now = datetime.utcnow()
+        updated = model.update(
+            upsert=False,
+            ready=True,
+            last_update=now,
+            last_change=now,
+            last_changed_by=user_id,
+        )
         return updated, published_task
 
     @classmethod
     def delete_model(
-        cls, model_id: str, company_id: str, force: bool
+        cls, model_id: str, company_id: str, user_id: str, force: bool, delete_external_artifacts: bool = True,
     ) -> Tuple[int, Model]:
         model = cls.get_company_model_by_id(
             company_id=company_id,
@@ -82,49 +120,149 @@ class ModelBLL:
 
         if model.task:
             task = Task.objects(id=model.task).first()
-            if task and task.status == TaskStatus.published:
-                if not force:
-                    raise errors.bad_request.ModelCreatingTaskExists(
-                        "and published, use force=True to delete", task=model.task
-                    )
-                if task.models.output and model_id in task.models.output:
-                    now = datetime.utcnow()
+            if task:
+                now = datetime.utcnow()
+                if task.status == TaskStatus.published:
+                    if not force:
+                        raise errors.bad_request.ModelCreatingTaskExists(
+                            "and published, use force=True to delete", task=model.task
+                        )
                     Task._get_collection().update_one(
                         filter={"_id": model.task, "models.output.model": model_id},
                         update={
                             "$set": {
                                 "models.output.$[elem].model": deleted_model_id,
                                 "output.error": f"model deleted on {now.isoformat()}",
+                                "last_change": now,
+                                "last_changed_by": user_id,
                             },
-                            "last_change": now,
                         },
                         array_filters=[{"elem.model": model_id}],
                         upsert=False,
                     )
+                else:
+                    task.update(
+                        pull__models__output__model=model_id,
+                        set__last_change=now,
+                        set__last_changed_by=user_id,
+                    )
 
+        delete_external_artifacts = delete_external_artifacts and config.get(
+            "services.async_urls_delete.enabled", True
+        )
+        if delete_external_artifacts:
+            from apiserver.bll.task.task_cleanup import (
+                collect_debug_image_urls,
+                collect_plot_image_urls,
+                _schedule_for_delete,
+            )
+            urls = set()
+            urls.update(collect_debug_image_urls(company_id, model_id))
+            urls.update(collect_plot_image_urls(company_id, model_id))
+            if model.uri:
+                urls.add(model.uri)
+            if urls:
+                _schedule_for_delete(
+                    task_id=model_id,
+                    company=company_id,
+                    user=user_id,
+                    urls=urls,
+                    can_delete_folders=False,
+                )
+
+        if not cls.event_bll:
+            from apiserver.bll.event import EventBLL
+            cls.event_bll = EventBLL()
+
+        cls.event_bll.delete_task_events(company_id, model_id, allow_locked=True, model=True)
         del_count = Model.objects(id=model_id, company=company_id).delete()
         return del_count, model
 
     @classmethod
-    def archive_model(cls, model_id: str, company_id: str):
+    def archive_model(cls, model_id: str, company_id: str, user_id: str):
         cls.get_company_model_by_id(
             company_id=company_id, model_id=model_id, only_fields=("id",)
         )
+        now = datetime.utcnow()
         archived = Model.objects(company=company_id, id=model_id).update(
             add_to_set__system_tags=EntityVisibility.archived.value,
-            last_update=datetime.utcnow(),
+            last_change=now,
+            last_changed_by=user_id,
         )
 
         return archived
 
     @classmethod
-    def unarchive_model(cls, model_id: str, company_id: str):
+    def unarchive_model(cls, model_id: str, company_id: str, user_id: str):
         cls.get_company_model_by_id(
             company_id=company_id, model_id=model_id, only_fields=("id",)
         )
+        now = datetime.utcnow()
         unarchived = Model.objects(company=company_id, id=model_id).update(
             pull__system_tags=EntityVisibility.archived.value,
-            last_update=datetime.utcnow(),
+            last_change=now,
+            last_changed_by=user_id,
         )
 
         return unarchived
+
+    @classmethod
+    def get_model_stats(
+        cls, company: str, model_ids: Sequence[str],
+    ) -> Dict[str, dict]:
+        if not model_ids:
+            return {}
+
+        result = Model.aggregate(
+            [
+                {
+                    "$match": {
+                        "company": {"$in": [None, "", company]},
+                        "_id": {"$in": model_ids},
+                    }
+                },
+                {
+                    "$addFields": {
+                        "labels_count": {"$size": {"$objectToArray": "$labels"}}
+                    }
+                },
+                {"$project": {"labels_count": 1}},
+            ]
+        )
+        return {r.pop("_id"): r for r in result}
+
+    @staticmethod
+    def update_statistics(
+        company_id: str,
+        user_id: str,
+        model_id: str,
+        last_update: datetime = None,
+        last_iteration_max: int = None,
+        last_scalar_events: Dict[str, Dict[str, dict]] = None,
+    ):
+        last_update = last_update or datetime.utcnow()
+        updates = {
+            "last_update": datetime.utcnow(),
+            "last_change": last_update,
+            "last_changed_by": user_id,
+        }
+        if last_iteration_max is not None:
+            updates.update(max__last_iteration=last_iteration_max)
+
+        raw_updates = {}
+        if last_scalar_events is not None:
+            raw_updates = {}
+            if last_scalar_events is not None:
+                get_last_metric_updates(
+                    task_id=model_id,
+                    last_scalar_events=last_scalar_events,
+                    raw_updates=raw_updates,
+                    extra_updates=updates,
+                    model_events=True,
+                )
+
+        ret = Model.objects(id=model_id).update_one(**updates)
+        if ret and raw_updates:
+            Model.objects(id=model_id).update_one(__raw__=[{"$set": raw_updates}])
+
+        return ret

apiserver/bll/model/metadata.py

@@ -5,13 +5,11 @@ from mongoengine import Document
 from apiserver.apierrors import errors
 from apiserver.apimodels.metadata import MetadataItem
 from apiserver.database.model.base import GetMixin
-from apiserver.service_repo import APICall
 from apiserver.utilities.parameter_key_escaper import (
     ParameterKeyEscaper,
     mongoengine_safe,
 )
 from apiserver.config_repo import config
-from apiserver.timing_context import TimingContext
 
 log = config.logger(__file__)
 
@@ -42,27 +40,25 @@ class Metadata:
         replace_metadata: bool,
         **more_updates,
     ) -> int:
-        with TimingContext("mongo", "edit_metadata"):
-            update_cmds = dict()
-            metadata = cls.metadata_from_api(items)
-            if replace_metadata:
-                update_cmds["set__metadata"] = metadata
-            else:
-                for key, value in metadata.items():
-                    update_cmds[f"set__metadata__{mongoengine_safe(key)}"] = value
+        update_cmds = dict()
+        metadata = cls.metadata_from_api(items)
+        if replace_metadata:
+            update_cmds["set__metadata"] = metadata
+        else:
+            for key, value in metadata.items():
+                update_cmds[f"set__metadata__{mongoengine_safe(key)}"] = value
 
-            return obj.update(**update_cmds, **more_updates)
+        return obj.update(**update_cmds, **more_updates)
 
     @classmethod
     def delete_metadata(cls, obj: Document, keys: Sequence[str], **more_updates) -> int:
-        with TimingContext("mongo", "delete_metadata"):
-            return obj.update(
-                **{
-                    f"unset__metadata__{ParameterKeyEscaper.escape(key)}": 1
-                    for key in set(keys)
-                },
-                **more_updates,
-            )
+        return obj.update(
+            **{
+                f"unset__metadata__{ParameterKeyEscaper.escape(key)}": 1
+                for key in set(keys)
+            },
+            **more_updates,
+        )
 
     @staticmethod
     def _process_path(path: str):
@@ -90,13 +86,13 @@ class Metadata:
         return paths
 
     @classmethod
-    def escape_query_parameters(cls, call: APICall) -> dict:
-        if not call.data:
-            return call.data
+    def escape_query_parameters(cls, call_data: dict) -> dict:
+        if not call_data:
+            return call_data
 
-        keys = list(call.data)
+        keys = list(call_data)
         call_data = {
-            safe_key: call.data[key]
+            safe_key: call_data[key]
             for key, safe_key in zip(keys, Metadata.escape_paths(keys))
         }
 

apiserver/bll/organization/__init__.py

@@ -1,8 +1,11 @@
 from collections import defaultdict
 from enum import Enum
-from typing import Sequence, Dict
+from typing import Sequence, Dict, Type
 
+from apiserver.apierrors import errors
+from apiserver.bll.util import update_project_time
 from apiserver.config_repo import config
+from apiserver.database.model.model import AttributedDocument
 from apiserver.database.model.model import Model
 from apiserver.database.model.task.task import Task
 from apiserver.redis_manager import redman
@@ -22,6 +25,51 @@ class OrgBLL:
         self._task_tags = _TagsCache(Task, self.redis)
         self._model_tags = _TagsCache(Model, self.redis)
 
+    def edit_entity_tags(
+        self,
+        company_id,
+        entity_cls: Type[AttributedDocument],
+        entity_ids: Sequence[str],
+        add_tags: Sequence[str],
+        remove_tags: Sequence[str],
+    ) -> int:
+        if entity_cls not in (Task, Model):
+            raise errors.bad_request.ValidationError(
+                "Tags editing can be called on tasks or models only"
+            )
+        if not entity_ids:
+            raise errors.bad_request.ValidationError(
+                "No entity ids provided for editing tags"
+            )
+        if not (add_tags or remove_tags):
+            raise errors.bad_request.ValidationError(
+                "Either add tags or remove tags should be provided"
+            )
+
+        updated = 0
+        if add_tags:
+            updated += entity_cls.objects(company=company_id, id__in=entity_ids).update(
+                add_to_set__tags=add_tags
+            )
+        if remove_tags:
+            updated += entity_cls.objects(company=company_id, id__in=entity_ids).update(
+                pull_all__tags=remove_tags
+            )
+        if not updated:
+            return 0
+
+        projects = entity_cls.objects(company=company_id, id__in=entity_ids).distinct(
+            "project"
+        )
+        update_project_time(project_ids=projects)
+        self.update_tags(
+            company_id,
+            entity=Tags.Task if entity_cls is Task else Tags.Model,
+            projects=projects,
+            tags=add_tags or remove_tags
+        )
+        return updated
+
     def get_tags(
         self,
         company_id: str,
@@ -50,10 +98,10 @@ class OrgBLL:
         return ret
 
     def update_tags(
-        self, company_id: str, entity: Tags, project: str, tags=None, system_tags=None,
+        self, company_id: str, entity: Tags, projects: Sequence[str], tags=None, system_tags=None,
     ):
         tags_cache = self._get_tags_cache_for_entity(entity)
-        tags_cache.update_tags(company_id, project, tags, system_tags)
+        tags_cache.update_tags(company_id, projects, tags, system_tags)
 
     def reset_tags(self, company_id: str, entity: Tags, projects: Sequence[str]):
         tags_cache = self._get_tags_cache_for_entity(entity)

apiserver/bll/organization/tags_cache.py

@@ -6,6 +6,7 @@ from redis import Redis
 
 from apiserver.config_repo import config
 from apiserver.bll.project import project_ids_with_children
+from apiserver.database.model import EntityVisibility
 from apiserver.database.model.base import GetMixin
 from apiserver.database.model.model import Model
 from apiserver.database.model.task.task import Task
@@ -42,6 +43,8 @@ class _TagsCache:
                     query &= GetMixin.get_list_field_query(name, vals)
         if project:
             query &= Q(project__in=project_ids_with_children([project]))
+        else:
+            query &= Q(system_tags__nin=[EntityVisibility.hidden.value])
 
         return self.db_cls.objects(query).distinct(field)
 
@@ -104,7 +107,7 @@ class _TagsCache:
 
         return ret
 
-    def update_tags(self, company_id: str, project: str, tags=None, system_tags=None):
+    def update_tags(self, company_id: str, projects: Sequence[str], tags=None, system_tags=None):
         """
         Updates tags. If reset is set then both tags and system_tags
         are recalculated. Otherwise only those that are not 'None'
@@ -120,7 +123,7 @@ class _TagsCache:
         if not fields:
             return
 
-        self._delete_redis_keys(company_id, projects=[project], fields=fields)
+        self._delete_redis_keys(company_id, projects=projects, fields=fields)
 
     def reset_tags(self, company_id: str, projects: Sequence[str]):
         self._delete_redis_keys(

apiserver/bll/project/project_cleanup.py

@@ -1,6 +1,9 @@
+from collections import defaultdict
+from datetime import datetime
 from typing import Tuple, Set, Sequence
 
 import attr
+from mongoengine import Q
 
 from apiserver.apierrors import errors
 from apiserver.bll.event import EventBLL
@@ -8,13 +11,21 @@ from apiserver.bll.task.task_cleanup import (
     collect_debug_image_urls,
     collect_plot_image_urls,
     TaskUrls,
+    _schedule_for_delete,
 )
 from apiserver.config_repo import config
 from apiserver.database.model import EntityVisibility
 from apiserver.database.model.model import Model
 from apiserver.database.model.project import Project
-from apiserver.database.model.task.task import Task, ArtifactModes
-from apiserver.timing_context import TimingContext
+from apiserver.database.model.task.task import Task, ArtifactModes, TaskType, TaskStatus
+from .project_bll import (
+    ProjectBLL,
+    pipeline_tag,
+    pipelines_project_name,
+    dataset_tag,
+    datasets_project_name,
+    reports_tag,
+)
 from .sub_projects import _ids_with_children
 
 log = config.logger(__file__)
@@ -30,62 +41,166 @@ class DeleteProjectResult:
     urls: TaskUrls = None
 
 
+def _get_child_project_ids(
+    project_id: str,
+) -> Tuple[Sequence[str], Sequence[str], Sequence[str]]:
+    project_ids = _ids_with_children([project_id])
+    pipeline_ids = list(
+        Project.objects(
+            id__in=project_ids,
+            system_tags__in=[pipeline_tag],
+            basename__ne=pipelines_project_name,
+        ).scalar("id")
+    )
+    dataset_ids = list(
+        Project.objects(
+            id__in=project_ids,
+            system_tags__in=[dataset_tag],
+            basename__ne=datasets_project_name,
+        ).scalar("id")
+    )
+    return project_ids, pipeline_ids, dataset_ids
+
+
 def validate_project_delete(company: str, project_id: str):
     project = Project.get_for_writing(
-        company=company, id=project_id, _only=("id", "path")
+        company=company, id=project_id, _only=("id", "path", "system_tags")
     )
     if not project:
         raise errors.bad_request.InvalidProjectId(id=project_id)
 
-    project_ids = _ids_with_children([project_id])
+    project_ids, pipeline_ids, dataset_ids = _get_child_project_ids(project_id)
     ret = {}
-    for cls in (Task, Model):
-        ret[f"{cls.__name__.lower()}s"] = cls.objects(
-            project__in=project_ids,
-        ).count()
-    for cls in (Task, Model):
-        ret[f"non_archived_{cls.__name__.lower()}s"] = cls.objects(
-            project__in=project_ids,
+    if pipeline_ids:
+        pipelines_with_active_controllers = Task.objects(
+            project__in=pipeline_ids,
+            type=TaskType.controller,
             system_tags__nin=[EntityVisibility.archived.value],
+        ).distinct("project")
+        ret["pipelines"] = len(pipelines_with_active_controllers)
+    else:
+        ret["pipelines"] = 0
+    if dataset_ids:
+        datasets_with_data = Task.objects(
+            project__in=dataset_ids,
+            system_tags__nin=[EntityVisibility.archived.value],
+        ).distinct("project")
+        ret["datasets"] = len(datasets_with_data)
+    else:
+        ret["datasets"] = 0
+
+    project_ids = list(set(project_ids) - set(pipeline_ids) - set(dataset_ids))
+    if project_ids:
+        in_project_query = Q(project__in=project_ids)
+        for cls in (Task, Model):
+            query = (
+                in_project_query & Q(system_tags__nin=[reports_tag])
+                if cls is Task
+                else in_project_query
+            )
+            ret[f"{cls.__name__.lower()}s"] = cls.objects(query).count()
+            ret[f"non_archived_{cls.__name__.lower()}s"] = cls.objects(
+                query & Q(system_tags__nin=[EntityVisibility.archived.value])
+            ).count()
+        ret["reports"] = Task.objects(
+            in_project_query & Q(system_tags__in=[reports_tag])
         ).count()
+        ret["non_archived_reports"] = Task.objects(
+            in_project_query
+            & Q(
+                system_tags__in=[reports_tag],
+                system_tags__nin=[EntityVisibility.archived.value],
+            )
+        ).count()
+    else:
+        for cls in (Task, Model):
+            ret[f"{cls.__name__.lower()}s"] = 0
+            ret[f"non_archived_{cls.__name__.lower()}s"] = 0
+        ret["reports"] = 0
+        ret["non_archived_reports"] = 0
 
     return ret
 
 
 def delete_project(
-    company: str, project_id: str, force: bool, delete_contents: bool
+    company: str,
+    user: str,
+    project_id: str,
+    force: bool,
+    delete_contents: bool,
+    delete_external_artifacts: bool,
 ) -> Tuple[DeleteProjectResult, Set[str]]:
     project = Project.get_for_writing(
-        company=company, id=project_id, _only=("id", "path")
+        company=company, id=project_id, _only=("id", "path", "system_tags")
     )
     if not project:
         raise errors.bad_request.InvalidProjectId(id=project_id)
 
-    project_ids = _ids_with_children([project_id])
+    delete_external_artifacts = delete_external_artifacts and config.get(
+        "services.async_urls_delete.enabled", True
+    )
+    project_ids, pipeline_ids, dataset_ids = _get_child_project_ids(project_id)
     if not force:
-        for cls, error in (
-            (Task, errors.bad_request.ProjectHasTasks),
-            (Model, errors.bad_request.ProjectHasModels),
-        ):
-            non_archived = cls.objects(
-                project__in=project_ids,
+        if pipeline_ids:
+            active_controllers = Task.objects(
+                project__in=pipeline_ids,
+                type=TaskType.controller,
                 system_tags__nin=[EntityVisibility.archived.value],
             ).only("id")
-            if non_archived:
-                raise error("use force=true to delete", id=project_id)
+            if active_controllers:
+                raise errors.bad_request.ProjectHasPipelines(
+                    "please archive all the controllers or use force=true",
+                    id=project_id,
+                )
+        if dataset_ids:
+            datasets_with_data = Task.objects(
+                project__in=dataset_ids,
+                system_tags__nin=[EntityVisibility.archived.value],
+            ).only("id")
+            if datasets_with_data:
+                raise errors.bad_request.ProjectHasDatasets(
+                    "please delete all the dataset versions or use force=true",
+                    id=project_id,
+                )
+
+        regular_projects = list(set(project_ids) - set(pipeline_ids) - set(dataset_ids))
+        if regular_projects:
+            for cls, error in (
+                (Task, errors.bad_request.ProjectHasTasks),
+                (Model, errors.bad_request.ProjectHasModels),
+            ):
+                non_archived = cls.objects(
+                    project__in=regular_projects,
+                    system_tags__nin=[EntityVisibility.archived.value],
+                ).only("id")
+                if non_archived:
+                    raise error("use force=true", id=project_id)
 
     if not delete_contents:
-        with TimingContext("mongo", "update_children"):
-            for cls in (Model, Task):
-                updated_count = cls.objects(project__in=project_ids).update(
-                    project=None
-                )
-        res = DeleteProjectResult(disassociated_tasks=updated_count)
+        disassociated = defaultdict(int)
+        for cls in ProjectBLL.child_classes:
+            disassociated[cls] = cls.objects(project__in=project_ids).update(
+                project=None
+            )
+        res = DeleteProjectResult(disassociated_tasks=disassociated[Task])
     else:
-        deleted_models, model_urls = _delete_models(projects=project_ids)
-        deleted_tasks, event_urls, artifact_urls = _delete_tasks(
-            company=company, projects=project_ids
+        deleted_models, model_event_urls, model_urls = _delete_models(
+            company=company, user=user, projects=project_ids
         )
+        deleted_tasks, task_event_urls, artifact_urls = _delete_tasks(
+            company=company, user=user, projects=project_ids
+        )
+        event_urls = task_event_urls | model_event_urls
+        if delete_external_artifacts:
+            scheduled = _schedule_for_delete(
+                task_id=project_id,
+                company=company,
+                user=user,
+                urls=event_urls | model_urls | artifact_urls,
+                can_delete_folders=True,
+            )
+            for urls in (event_urls, model_urls, artifact_urls):
+                urls.difference_update(scheduled)
         res = DeleteProjectResult(
             deleted_tasks=deleted_tasks,
             deleted_models=deleted_models,
@@ -102,7 +217,9 @@ def delete_project(
     return res, affected
 
 
-def _delete_tasks(company: str, projects: Sequence[str]) -> Tuple[int, Set, Set]:
+def _delete_tasks(
+    company: str, user: str, projects: Sequence[str]
+) -> Tuple[int, Set, Set]:
     """
     Delete only the task themselves and their non published version.
     Child models under the same project are deleted separately.
@@ -113,15 +230,24 @@ def _delete_tasks(company: str, projects: Sequence[str]) -> Tuple[int, Set, Set]
     if not tasks:
         return 0, set(), set()
 
-    task_ids = {t.id for t in tasks}
-    with TimingContext("mongo", "delete_tasks_update_children"):
-        Task.objects(parent__in=task_ids, project__nin=projects).update(parent=None)
-        Model.objects(task__in=task_ids, project__nin=projects).update(task=None)
+    task_ids = list({t.id for t in tasks})
+    now = datetime.utcnow()
+    Task.objects(parent__in=task_ids, project__nin=projects).update(
+        parent=None,
+        last_change=now,
+        last_changed_by=user,
+    )
+    Model.objects(task__in=task_ids, project__nin=projects).update(
+        task=None,
+        last_change=now,
+        last_changed_by=user,
+    )
 
-    event_urls, artifact_urls = set(), set()
+    event_urls = collect_debug_image_urls(company, task_ids) | collect_plot_image_urls(
+        company, task_ids
+    )
+    artifact_urls = set()
     for task in tasks:
-        event_urls.update(collect_debug_image_urls(company, task.id))
-        event_urls.update(collect_plot_image_urls(company, task.id))
         if task.execution and task.execution.artifacts:
             artifact_urls.update(
                 {
@@ -131,46 +257,71 @@ def _delete_tasks(company: str, projects: Sequence[str]) -> Tuple[int, Set, Set]
                 }
             )
 
-    event_bll.delete_multi_task_events(company, list(task_ids))
+    event_bll.delete_multi_task_events(company, task_ids)
     deleted = tasks.delete()
     return deleted, event_urls, artifact_urls
 
 
-def _delete_models(projects: Sequence[str]) -> Tuple[int, Set[str]]:
+def _delete_models(
+    company: str, user: str, projects: Sequence[str]
+) -> Tuple[int, Set[str], Set[str]]:
     """
     Delete project models and update the tasks from other projects
     that reference them to reference None.
     """
-    with TimingContext("mongo", "delete_models"):
-        models = Model.objects(project__in=projects).only("task", "id", "uri")
-        if not models:
-            return 0, set()
+    models = Model.objects(project__in=projects).only("task", "id", "uri")
+    if not models:
+        return 0, set(), set()
 
-        model_ids = list({m.id for m in models})
+    model_ids = list({m.id for m in models})
+    deleted = "__DELETED__"
+    Task._get_collection().update_many(
+        filter={
+            "project": {"$nin": projects},
+            "models.input.model": {"$in": model_ids},
+        },
+        update={"$set": {"models.input.$[elem].model": deleted}},
+        array_filters=[{"elem.model": {"$in": model_ids}}],
+        upsert=False,
+    )
 
+    model_tasks = list({m.task for m in models if m.task})
+    if model_tasks:
+        now = datetime.utcnow()
+        # update published tasks
         Task._get_collection().update_many(
             filter={
+                "_id": {"$in": model_tasks},
                 "project": {"$nin": projects},
-                "models.input.model": {"$in": model_ids},
+                "models.output.model": {"$in": model_ids},
+                "status": TaskStatus.published,
+            },
+            update={
+                "$set": {
+                    "models.output.$[elem].model": deleted,
+                    "last_change": now,
+                    "last_changed_by": user,
+                }
             },
-            update={"$set": {"models.input.$[elem].model": None}},
             array_filters=[{"elem.model": {"$in": model_ids}}],
             upsert=False,
         )
+        # update unpublished tasks
+        Task.objects(
+            id__in=model_tasks,
+            project__nin=projects,
+            status__ne=TaskStatus.published,
+        ).update(
+            pull__models__output__model__in=model_ids,
+            set__last_change=now,
+            set__last_changed_by=user,
+        )
 
-        model_tasks = list({m.task for m in models if m.task})
-        if model_tasks:
-            Task._get_collection().update_many(
-                filter={
-                    "_id": {"$in": model_tasks},
-                    "project": {"$nin": projects},
-                    "models.output.model": {"$in": model_ids},
-                },
-                update={"$set": {"models.output.$[elem].model": None}},
-                array_filters=[{"elem.model": {"$in": model_ids}}],
-                upsert=False,
-            )
+    event_urls = collect_debug_image_urls(company, model_ids) | collect_plot_image_urls(
+        company, model_ids
+    )
+    model_urls = {m.uri for m in models if m.uri}
 
-        urls = {m.uri for m in models if m.uri}
-        deleted = models.delete()
-        return deleted, urls
+    event_bll.delete_multi_task_events(company, model_ids, model=True)
+    deleted = models.delete()
+    return deleted, event_urls, model_urls

apiserver/bll/project/project_queries.py

@@ -140,7 +140,12 @@ class ProjectQueries:
         name: str,
         include_subprojects: bool,
         allow_public: bool = True,
+        pattern: str = None,
+        page: int = 0,
+        page_size: int = 500,
     ) -> ParamValues:
+        page = max(0, page)
+        page_size = max(1, page_size)
         company_constraint = self._get_company_constraint(company_id, allow_public)
         project_constraint = self._get_project_constraint(
             project_ids, include_subprojects
@@ -160,7 +165,20 @@ class ProjectQueries:
         if not last_updated_task:
             return 0, []
 
-        redis_key = f"hyperparam_values_{company_id}_{'_'.join(project_ids)}_{section}_{name}_{allow_public}"
+        redis_key = "_".join(
+            str(part)
+            for part in (
+                "hyperparam_values",
+                company_id,
+                "_".join(project_ids),
+                section,
+                name,
+                allow_public,
+                pattern,
+                page,
+                page_size,
+            )
+        )
         last_update = last_updated_task.last_update or datetime.utcnow()
         cached_res = self._get_cached_param_values(
             key=redis_key,
@@ -172,19 +190,27 @@ class ProjectQueries:
         if cached_res:
             return cached_res
 
-        max_values = config.get("services.tasks.hyperparam_values.max_count", 100)
-        pipeline = [
-            {
-                "$match": {
-                    **company_constraint,
-                    **project_constraint,
-                    key_path: {"$exists": True},
+        match_condition = {
+            **company_constraint,
+            **project_constraint,
+            key_path: {"$exists": True},
+        }
+        if pattern:
+            match_condition["$expr"] = {
+                "$regexMatch": {
+                    "input": f"${key_path}.value",
+                    "regex": pattern,
+                    "options": "i",
                 }
-            },
+            }
+
+        pipeline = [
+            {"$match": match_condition},
             {"$project": {"value": f"${key_path}.value"}},
             {"$group": {"_id": "$value"}},
             {"$sort": {"_id": 1}},
-            {"$limit": max_values},
+            {"$skip": page * page_size},
+            {"$limit": page_size},
             {
                 "$group": {
                     "_id": 1,
@@ -209,13 +235,19 @@ class ProjectQueries:
 
     @classmethod
     def get_unique_metric_variants(
-        cls, company_id, project_ids: Sequence[str], include_subprojects: bool
+        cls,
+        company_id,
+        project_ids: Sequence[str],
+        include_subprojects: bool,
+        ids: Sequence[str],
+        model_metrics: bool = False,
     ):
         pipeline = [
             {
                 "$match": {
                     **cls._get_company_constraint(company_id),
                     **cls._get_project_constraint(project_ids, include_subprojects),
+                    **({"_id": {"$in": ids}} if ids else {}),
                 }
             },
             {"$project": {"metrics": {"$objectToArray": "$last_metrics"}}},
@@ -246,7 +278,8 @@ class ProjectQueries:
             {"$sort": OrderedDict({"_id.metric": 1, "_id.variant": 1})},
         ]
 
-        result = Task.aggregate(pipeline)
+        entity_cls = Model if model_metrics else Task
+        result = entity_cls.aggregate(pipeline)
         return [r["metrics"][0] for r in result]
 
     @classmethod
@@ -306,7 +339,11 @@ class ProjectQueries:
         key: str,
         include_subprojects: bool,
         allow_public: bool = True,
+        page: int = 0,
+        page_size: int = 500,
     ) -> ParamValues:
+        page = max(0, page)
+        page_size = max(1, page_size)
         company_constraint = self._get_company_constraint(company_id, allow_public)
         project_constraint = self._get_project_constraint(
             project_ids, include_subprojects
@@ -326,7 +363,7 @@ class ProjectQueries:
         if not last_updated_model:
             return 0, []
 
-        redis_key = f"modelmetadata_values_{company_id}_{'_'.join(project_ids)}_{key}_{allow_public}"
+        redis_key = f"modelmetadata_values_{company_id}_{'_'.join(project_ids)}_{key}_{allow_public}_{page}_{page_size}"
         last_update = last_updated_model.last_update or datetime.utcnow()
         cached_res = self._get_cached_param_values(
             key=redis_key, last_update=last_update
@@ -334,7 +371,6 @@ class ProjectQueries:
         if cached_res:
             return cached_res
 
-        max_values = config.get("services.models.metadata_values.max_count", 100)
         pipeline = [
             {
                 "$match": {
@@ -346,7 +382,8 @@ class ProjectQueries:
             {"$project": {"value": f"${key_path}.value"}},
             {"$group": {"_id": "$value"}},
             {"$sort": {"_id": 1}},
-            {"$limit": max_values},
+            {"$skip": page * page_size},
+            {"$limit": page_size},
             {
                 "$group": {
                     "_id": 1,

apiserver/bll/project/sub_projects.py

@@ -4,6 +4,7 @@ from typing import Tuple, Optional, Sequence, Mapping
 
 from apiserver import database
 from apiserver.apierrors import errors
+from apiserver.database.model import EntityVisibility
 from apiserver.database.model.project import Project
 
 name_separator = "/"
@@ -13,14 +14,16 @@ def _get_project_depth(project_name: str) -> int:
     return len(list(filter(None, project_name.split(name_separator))))
 
 
-def _validate_project_name(project_name: str) -> Tuple[str, str]:
+def _validate_project_name(project_name: str, raise_if_empty=True) -> Tuple[str, str]:
     """
     Remove redundant '/' characters. Ensure that the project name is not empty
     Return the cleaned up project name and location
     """
-    name_parts = list(filter(None, project_name.split(name_separator)))
+    name_parts = [p.strip() for p in project_name.split(name_separator) if p]
     if not name_parts:
-        raise errors.bad_request.InvalidProjectName(name=project_name)
+        if raise_if_empty:
+            raise errors.bad_request.InvalidProjectName(name=project_name)
+        return "", ""
 
     return name_separator.join(name_parts), name_separator.join(name_parts[:-1])
 
@@ -33,7 +36,7 @@ def _ensure_project(
     If needed auto-create the project and all the missing projects in the path to it
     Return the project
     """
-    name = name.strip(name_separator)
+    name, location = _validate_project_name(name, raise_if_empty=False)
     if not name:
         return None
 
@@ -42,7 +45,6 @@ def _ensure_project(
         return project
 
     now = datetime.utcnow()
-    name, location = _validate_project_name(name)
     project = Project(
         id=database.utils.id(),
         user=user,
@@ -50,6 +52,7 @@ def _ensure_project(
         created=now,
         last_update=now,
         name=name,
+        basename=name.split("/")[-1],
         **(creation_params or dict(description="")),
     )
     parent = _ensure_project(company, user, location, creation_params=creation_params)
@@ -99,13 +102,25 @@ def _get_writable_project_from_name(
     return qs.first()
 
 
+ProjectsChildren = Mapping[str, Sequence[Project]]
+
+
 def _get_sub_projects(
-    project_ids: Sequence[str], _only: Sequence[str] = ("id", "path")
-) -> Mapping[str, Sequence[Project]]:
+    project_ids: Sequence[str],
+    _only: Sequence[str] = ("id", "path"),
+    search_hidden=True,
+    allowed_ids: Sequence[str] = None,
+) -> ProjectsChildren:
     """
     Return the list of child projects of all the levels for the parent project ids
     """
-    qs = Project.objects(path__in=project_ids)
+    query = dict(path__in=project_ids)
+    if not search_hidden:
+        query["system_tags__nin"] = [EntityVisibility.hidden.value]
+    if allowed_ids:
+        query["id__in"] = allowed_ids
+
+    qs = Project.objects(**query)
     if _only:
         _only = set(_only) | {"path"}
         qs = qs.only(*_only)
@@ -129,8 +144,8 @@ def _ids_with_children(project_ids: Sequence[str]) -> Sequence[str]:
     """
     Return project ids with the ids of all the subprojects
     """
-    subprojects = Project.objects(path__in=project_ids).only("id")
-    return list({*project_ids, *(child.id for child in subprojects)})
+    children_ids = Project.objects(path__in=project_ids).scalar("id")
+    return list({*project_ids, *children_ids})
 
 
 def _update_subproject_names(
@@ -145,13 +160,17 @@ def _update_subproject_names(
     Optionally update the paths
     """
     updated = 0
+    now = datetime.utcnow()
     for child in children:
         child_suffix = name_separator.join(
-            child.name.split(name_separator)[len(old_name.split(name_separator)) :]
+            child.name.split(name_separator)[len(old_name.split(name_separator)):]
         )
-        updates = {"name": name_separator.join((project.name, child_suffix))}
+        updates = {
+            "name": name_separator.join((project.name, child_suffix)),
+            "last_update": now,
+        }
         if update_path:
-            updates["path"] = project.path + child.path[len(old_path) :]
+            updates["path"] = project.path + child.path[len(old_path):]
         updated += child.update(upsert=False, **updates)
 
     return updated
@@ -166,6 +185,7 @@ def _reposition_project_with_children(
     project.name = name_separator.join(
         filter(None, (new_location, project.name.split(name_separator)[-1]))
     )
+    project.last_update = datetime.utcnow()
     _save_under_parent(project, parent=parent)
 
     moved = 1 + _update_subproject_names(

apiserver/bll/queue/queue_bll.py

@@ -1,10 +1,12 @@
 from collections import defaultdict
 from datetime import datetime
-from typing import Callable, Sequence, Optional, Tuple
+from typing import Sequence, Optional, Tuple, Union
 
 from elasticsearch import Elasticsearch
+from mongoengine import Q
 
 from apiserver import database
+from apiserver.database.model.task.task import Task, TaskStatus
 from apiserver.es_factory import es_factory
 from apiserver.apierrors import errors
 from apiserver.bll.queue.queue_metrics import QueueMetrics
@@ -14,6 +16,8 @@ from apiserver.database.errors import translate_errors_context
 from apiserver.database.model.queue import Queue, Entry
 
 log = config.logger(__file__)
+MOVE_FIRST = "first"
+MOVE_LAST = "last"
 
 
 class QueueBLL(object):
@@ -50,8 +54,25 @@ class QueueBLL(object):
             queue.save()
             return queue
 
+    def get_by_name(
+        self, company_id: str, queue_name: str, only: Optional[Sequence[str]] = None,
+    ) -> Queue:
+        qs = Queue.objects(name=queue_name, company=company_id)
+        if only:
+            qs = qs.only(*only)
+
+        return qs.first()
+
+    @staticmethod
+    def _get_task_entries_projection(max_task_entries: int) -> dict:
+        return dict(slice__entries=max_task_entries)
+
     def get_by_id(
-        self, company_id: str, queue_id: str, only: Optional[Sequence[str]] = None
+        self,
+        company_id: str,
+        queue_id: str,
+        only: Optional[Sequence[str]] = None,
+        max_task_entries: int = None,
     ) -> Queue:
         """
         Get queue by id
@@ -62,6 +83,8 @@ class QueueBLL(object):
             qs = Queue.objects(**query)
             if only:
                 qs = qs.only(*only)
+            if max_task_entries:
+                qs = qs.fields(**self._get_task_entries_projection(max_task_entries))
             queue = qs.first()
             if not queue:
                 raise errors.bad_request.InvalidQueueId(**query)
@@ -112,7 +135,7 @@ class QueueBLL(object):
             self.get_by_id(company_id=company_id, queue_id=queue_id, only=("id",))
             return Queue.safe_update(company_id, queue_id, update_fields)
 
-    def delete(self, company_id: str, queue_id: str, force: bool) -> None:
+    def delete(self, company_id: str, user_id: str, queue_id: str, force: bool) -> None:
         """
         Delete the queue
         :raise errors.bad_request.InvalidQueueId: if the queue is not found
@@ -120,16 +143,50 @@ class QueueBLL(object):
         """
         with translate_errors_context():
             queue = self.get_by_id(company_id=company_id, queue_id=queue_id)
-            if queue.entries and not force:
-                raise errors.bad_request.QueueNotEmpty(
-                    "use force=true to delete", id=queue_id
-                )
+            if queue.entries:
+                if not force:
+                    raise errors.bad_request.QueueNotEmpty(
+                        "use force=true to delete", id=queue_id
+                    )
+                from apiserver.bll.task import ChangeStatusRequest
+
+                for item in queue.entries:
+                    try:
+                        task = Task.get(
+                            company=company_id,
+                            id=item.task,
+                            _only=[
+                                "id",
+                                "company",
+                                "status",
+                                "enqueue_status",
+                                "project",
+                            ],
+                        )
+                        if not task:
+                            continue
+
+                        ChangeStatusRequest(
+                            task=task,
+                            new_status=task.enqueue_status or TaskStatus.created,
+                            status_reason="Queue was deleted",
+                            status_message="",
+                            user_id=user_id,
+                            force=True,
+                        ).execute(enqueue_status=None)
+                    except Exception as ex:
+                        log.exception(
+                            f"Failed dequeuing task {item.task} from queue: {queue_id}"
+                        )
+
             queue.delete()
 
     def get_all(
         self,
         company_id: str,
         query_dict: dict,
+        query: Q = None,
+        max_task_entries: int = None,
         ret_params: dict = None,
     ) -> Sequence[dict]:
         """Get all the queues according to the query"""
@@ -138,13 +195,26 @@ class QueueBLL(object):
                 company=company_id,
                 parameters=query_dict,
                 query_dict=query_dict,
+                query=query,
+                projection_fields=self._get_task_entries_projection(max_task_entries)
+                if max_task_entries
+                else None,
                 ret_params=ret_params,
             )
 
+    def check_for_workers(self, company_id: str, queue_id: str) -> bool:
+        for worker in self.worker_bll.get_all(company_id):
+            if queue_id in worker.queues:
+                return True
+
+        return False
+
     def get_queue_infos(
         self,
         company_id: str,
         query_dict: dict,
+        query: Q = None,
+        max_task_entries: int = None,
         ret_params: dict = None,
     ) -> Sequence[dict]:
         """
@@ -155,7 +225,11 @@ class QueueBLL(object):
             res = Queue.get_many_with_join(
                 company=company_id,
                 query_dict=query_dict,
+                query=query,
                 override_projection=projection,
+                projection_fields=self._get_task_entries_projection(max_task_entries)
+                if max_task_entries
+                else None,
                 ret_params=ret_params,
             )
 
@@ -169,6 +243,7 @@ class QueueBLL(object):
                     {
                         "name": w.id,
                         "ip": w.ip,
+                        "key": w.key,
                         "task": w.task.to_struct() if w.task else None,
                     }
                     for w in queue_workers.get(item["id"], [])
@@ -203,16 +278,22 @@ class QueueBLL(object):
 
             return res
 
-    def get_next_task(self, company_id: str, queue_id: str) -> Optional[Entry]:
+    def get_next_task(
+        self, company_id: str, queue_id: str, task_id: str = None
+    ) -> Optional[Entry]:
         """
         Atomically pop and return the first task from the queue (or None)
         :raise errors.bad_request.InvalidQueueId: if the queue does not exist
         """
         with translate_errors_context():
             query = dict(id=queue_id, company=company_id)
-            queue = Queue.objects(**query).modify(pop__entries=-1, upsert=False)
+            queue = Queue.objects(
+                **query, **({"entries__0__task": task_id} if task_id else {})
+            ).modify(pop__entries=-1, upsert=False)
             if not queue:
-                raise errors.bad_request.InvalidQueueId(**query)
+                if not task_id or not Queue.objects(**query).first():
+                    raise errors.bad_request.InvalidQueueId(**query)
+                return
 
             self.metrics.log_queue_metrics_to_es(company_id, queues=[queue])
 
@@ -248,43 +329,147 @@ class QueueBLL(object):
             return len(entries_to_remove) if res else 0
 
     def reposition_task(
-        self,
-        company_id: str,
-        queue_id: str,
-        task_id: str,
-        pos_func: Callable[[int], int],
+        self, company_id: str, queue_id: str, task_id: str, move_count: Union[int, str],
     ) -> int:
         """
         Moves the task in the queue to the position calculated by pos_func
         Returns the updated task position in the queue
         """
-        with translate_errors_context():
-            queue = self.get_queue_with_task(
+
+        def get_queue_and_task_position():
+            q = self.get_queue_with_task(
                 company_id=company_id, queue_id=queue_id, task_id=task_id
             )
+            return q, next(i for i, e in enumerate(q.entries) if e.task == task_id)
 
-            position = next(i for i, e in enumerate(queue.entries) if e.task == task_id)
-            new_position = pos_func(position)
+        with translate_errors_context():
+            queue, position = get_queue_and_task_position()
+            if move_count == MOVE_FIRST:
+                new_position = 0
+            elif move_count == MOVE_LAST:
+                new_position = len(queue.entries) - 1
+            else:
+                new_position = position + move_count
+            if new_position == position:
+                return new_position
 
-            if new_position != position:
-                entry = queue.entries[position]
-                query = dict(id=queue_id, company=company_id)
-                updated = Queue.objects(entries__task=task_id, **query).update_one(
-                    pull__entries=entry, last_update=datetime.utcnow()
-                )
-                if not updated:
-                    raise errors.bad_request.RemovedDuringReposition(
-                        task=task_id, **query
-                    )
-                inst = {"$push": {"entries": {"$each": [entry.to_proper_dict()]}}}
-                if new_position >= 0:
-                    inst["$push"]["entries"]["$position"] = new_position
-                res = Queue.objects(entries__task__ne=task_id, **query).update_one(
-                    __raw__=inst
-                )
-                if not res:
-                    raise errors.bad_request.FailedAddingDuringReposition(
-                        task=task_id, **query
-                    )
+            without_entry = {
+                "$filter": {
+                    "input": "$entries",
+                    "as": "entry",
+                    "cond": {"$ne": ["$$entry.task", task_id]},
+                }
+            }
+            task_entry = {
+                "$filter": {
+                    "input": "$entries",
+                    "as": "entry",
+                    "cond": {"$eq": ["$$entry.task", task_id]},
+                }
+            }
+            if move_count == MOVE_FIRST:
+                operations = [
+                    {
+                        "$set": {
+                            "entries": {"$concatArrays": [task_entry, without_entry]}
+                        }
+                    }
+                ]
+            elif move_count == MOVE_LAST:
+                operations = [
+                    {
+                        "$set": {
+                            "entries": {"$concatArrays": [without_entry, task_entry]}
+                        }
+                    }
+                ]
+            else:
+                operations = [
+                    {
+                        "$set": {
+                            "new_pos": {
+                                "$add": [
+                                    {"$indexOfArray": ["$entries.task", task_id]},
+                                    move_count,
+                                ]
+                            },
+                            "without_entry": without_entry,
+                            "task_entry": task_entry,
+                        }
+                    },
+                    {
+                        "$set": {
+                            "entries": {
+                                "$switch": {
+                                    "branches": [
+                                        {
+                                            "case": {"$lte": ["$new_pos", 0]},
+                                            "then": {
+                                                "$concatArrays": [
+                                                    "$task_entry",
+                                                    "$without_entry",
+                                                ]
+                                            },
+                                        },
+                                        {
+                                            "case": {
+                                                "$gte": [
+                                                    "$new_pos",
+                                                    {"$size": "$without_entry"},
+                                                ]
+                                            },
+                                            "then": {
+                                                "$concatArrays": [
+                                                    "$without_entry",
+                                                    "$task_entry",
+                                                ]
+                                            },
+                                        },
+                                    ],
+                                    "default": {
+                                        "$concatArrays": [
+                                            {"$slice": ["$without_entry", "$new_pos"]},
+                                            "$task_entry",
+                                            {
+                                                "$slice": [
+                                                    "$without_entry",
+                                                    "$new_pos",
+                                                    {"$size": "$without_entry"},
+                                                ]
+                                            },
+                                        ]
+                                    },
+                                }
+                            }
+                        }
+                    },
+                    {"$unset": ["new_pos", "without_entry", "task_entry"]},
+                ]
 
-            return new_position
+            updated = Queue.objects(
+                id=queue_id, company=company_id, entries__task=task_id
+            ).update_one(__raw__=operations)
+
+            if not updated:
+                raise errors.bad_request.FailedAddingDuringReposition(task=task_id)
+
+            return get_queue_and_task_position()[1]
+
+    def count_entries(self, company: str, queue_id: str) -> Optional[int]:
+        res = next(
+            Queue.aggregate(
+                [
+                    {
+                        "$match": {
+                            "company": {"$in": [None, "", company]},
+                            "_id": queue_id,
+                        }
+                    },
+                    {"$project": {"count": {"$size": "$entries"}}},
+                ]
+            ),
+            None,
+        )
+        if res is None:
+            raise errors.bad_request.InvalidQueueId(queue_id=queue_id)
+        return int(res.get("count"))

apiserver/bll/queue/queue_metrics.py

@@ -1,8 +1,10 @@
+import json
 from collections import defaultdict
 from datetime import datetime
+from time import sleep
 from typing import Sequence
 
-import elasticsearch.helpers
+from boltons.typeutils import classproperty
 from elasticsearch import Elasticsearch
 
 from apiserver.es_factory import es_factory
@@ -11,25 +13,30 @@ from apiserver.bll.query import Builder as QueryBuilder
 from apiserver.config_repo import config
 from apiserver.database.errors import translate_errors_context
 from apiserver.database.model.queue import Queue, Entry
-from apiserver.timing_context import TimingContext
+from apiserver.redis_manager import redman
+from apiserver.utilities.threads_manager import ThreadsManager
 
 log = config.logger(__file__)
+_conf = config.get("services.queues")
+_queue_metrics_key_pattern = "queue_metrics_{queue}"
+redis = redman.connection("apiserver")
+
+
+class EsKeys:
+    WAITING_TIME_FIELD = "average_waiting_time"
+    QUEUE_LENGTH_FIELD = "queue_length"
+    TIMESTAMP_FIELD = "timestamp"
+    QUEUE_FIELD = "queue"
 
 
 class QueueMetrics:
-    class EsKeys:
-        WAITING_TIME_FIELD = "average_waiting_time"
-        QUEUE_LENGTH_FIELD = "queue_length"
-        TIMESTAMP_FIELD = "timestamp"
-        QUEUE_FIELD = "queue"
-
     def __init__(self, es: Elasticsearch):
         self.es = es
 
     @staticmethod
     def _queue_metrics_prefix_for_company(company_id: str) -> str:
         """Returns the es index prefix for the company"""
-        return f"queue_metrics_{company_id}_"
+        return f"queue_metrics_{company_id.lower()}_"
 
     @staticmethod
     def _get_es_index_suffix():
@@ -49,7 +56,7 @@ class QueueMetrics:
         total_waiting_in_secs = sum((now - e.added).total_seconds() for e in entries)
         return total_waiting_in_secs / len(entries)
 
-    def log_queue_metrics_to_es(self, company_id: str, queues: Sequence[Queue]) -> bool:
+    def log_queue_metrics_to_es(self, company_id: str, queues: Sequence[Queue]) -> int:
         """
         Calculate and write queue statistics (avg waiting time and queue length) to Elastic
         :return: True if the write to es was successful, false otherwise
@@ -63,23 +70,22 @@ class QueueMetrics:
 
         def make_doc(queue: Queue) -> dict:
             entries = [e for e in queue.entries if e.added]
-            return dict(
-                _index=es_index,
-                _source={
-                    self.EsKeys.TIMESTAMP_FIELD: timestamp,
-                    self.EsKeys.QUEUE_FIELD: queue.id,
-                    self.EsKeys.WAITING_TIME_FIELD: self._calc_avg_waiting_time(
-                        entries
-                    ),
-                    self.EsKeys.QUEUE_LENGTH_FIELD: len(entries),
-                },
-            )
+            return {
+                EsKeys.TIMESTAMP_FIELD: timestamp,
+                EsKeys.QUEUE_FIELD: queue.id,
+                EsKeys.WAITING_TIME_FIELD: self._calc_avg_waiting_time(entries),
+                EsKeys.QUEUE_LENGTH_FIELD: len(entries),
+            }
 
-        actions = list(map(make_doc, queues))
+        logged = 0
+        for q in queues:
+            queue_doc = make_doc(q)
+            self.es.index(index=es_index, document=queue_doc)
+            redis_key = _queue_metrics_key_pattern.format(queue=q.id)
+            redis.set(redis_key, json.dumps(queue_doc))
+            logged += 1
 
-        es_res = elasticsearch.helpers.bulk(self.es, actions)
-        added, errors = es_res[:2]
-        return (added == len(actions)) and not errors
+        return logged
 
     def _log_current_metrics(self, company_id: str, queue_ids=Sequence[str]):
         query = dict(company=company_id)
@@ -90,8 +96,7 @@ class QueueMetrics:
 
     def _search_company_metrics(self, company_id: str, es_req: dict) -> dict:
         return self.es.search(
-            index=f"{self._queue_metrics_prefix_for_company(company_id)}*",
-            body=es_req,
+            index=f"{self._queue_metrics_prefix_for_company(company_id)}*", body=es_req,
         )
 
     @classmethod
@@ -105,13 +110,13 @@ class QueueMetrics:
         return {
             "dates": {
                 "date_histogram": {
-                    "field": cls.EsKeys.TIMESTAMP_FIELD,
+                    "field": EsKeys.TIMESTAMP_FIELD,
                     "fixed_interval": f"{interval}s",
                     "min_doc_count": 1,
                 },
                 "aggs": {
                     "queues": {
-                        "terms": {"field": cls.EsKeys.QUEUE_FIELD},
+                        "terms": {"field": EsKeys.QUEUE_FIELD},
                         "aggs": cls._get_top_waiting_agg(),
                     }
                 },
@@ -128,13 +133,13 @@ class QueueMetrics:
             "top_avg_waiting": {
                 "top_hits": {
                     "sort": [
-                        {cls.EsKeys.WAITING_TIME_FIELD: {"order": "desc"}},
-                        {cls.EsKeys.QUEUE_LENGTH_FIELD: {"order": "desc"}},
+                        {EsKeys.WAITING_TIME_FIELD: {"order": "desc"}},
+                        {EsKeys.QUEUE_LENGTH_FIELD: {"order": "desc"}},
                     ],
                     "_source": {
                         "includes": [
-                            cls.EsKeys.WAITING_TIME_FIELD,
-                            cls.EsKeys.QUEUE_LENGTH_FIELD,
+                            EsKeys.WAITING_TIME_FIELD,
+                            EsKeys.QUEUE_LENGTH_FIELD,
                         ]
                     },
                     "size": 1,
@@ -149,6 +154,7 @@ class QueueMetrics:
         to_date: float,
         interval: int,
         queue_ids: Sequence[str],
+        refresh: bool = False,
     ) -> dict:
         """
         Get the company queue metrics in the specified time range.
@@ -158,7 +164,8 @@ class QueueMetrics:
         In case no queue ids are specified the avg across all the
         company queues is calculated for each metric
         """
-        # self._log_current_metrics(company, queue_ids=queue_ids)
+        if refresh:
+            self._log_current_metrics(company_id, queue_ids=queue_ids)
 
         if from_date >= to_date:
             raise bad_request.FieldsValueError("from_date must be less than to_date")
@@ -174,7 +181,7 @@ class QueueMetrics:
             "aggs": self._get_dates_agg(interval),
         }
 
-        with translate_errors_context(), TimingContext("es", "get_queue_metrics"):
+        with translate_errors_context():
             res = self._search_company_metrics(company_id, es_req)
 
         if "aggregations" not in res:
@@ -256,7 +263,52 @@ class QueueMetrics:
                 continue
             res = queue_data["top_avg_waiting"]["hits"]["hits"][0]["_source"]
             queue_metrics[queue_data["key"]] = {
-                "queue_length": res[cls.EsKeys.QUEUE_LENGTH_FIELD],
-                "avg_waiting_time": res[cls.EsKeys.WAITING_TIME_FIELD],
+                "queue_length": res[EsKeys.QUEUE_LENGTH_FIELD],
+                "avg_waiting_time": res[EsKeys.WAITING_TIME_FIELD],
             }
         return queue_metrics
+
+
+class MetricsRefresher:
+    threads = ThreadsManager()
+
+    @classproperty
+    def watch_interval_sec(self):
+        return _conf.get("metrics_refresh_interval_sec", 300)
+
+    @classmethod
+    @threads.register("queue_metrics_refresh_watchdog", daemon=True)
+    def start(cls, queue_metrics: QueueMetrics = None):
+        if not cls.watch_interval_sec:
+            return
+
+        if not queue_metrics:
+            from .queue_bll import QueueBLL
+
+            queue_metrics = QueueBLL().metrics
+
+        sleep(10)
+        while True:
+            try:
+                for queue in Queue.objects():
+                    timestamp = es_factory.get_timestamp_millis()
+                    doc_time = 0
+                    try:
+                        redis_key = _queue_metrics_key_pattern.format(queue=queue.id)
+                        data = redis.get(redis_key)
+                        if data:
+                            queue_doc = json.loads(data)
+                            doc_time = int(queue_doc.get(EsKeys.TIMESTAMP_FIELD))
+                    except Exception as ex:
+                        log.exception(
+                            f"Error reading queue metrics data for queue {queue.id}: {str(ex)}"
+                        )
+
+                    if (
+                        not doc_time
+                        or (timestamp - doc_time) > cls.watch_interval_sec * 1000
+                    ):
+                        queue_metrics.log_queue_metrics_to_es(queue.company, [queue])
+            except Exception as ex:
+                log.exception(f"Failed collecting queue metrics: {str(ex)}")
+            sleep(60)

apiserver/bll/redis_cache_manager.py

@@ -4,7 +4,6 @@ from typing import Optional, TypeVar, Generic, Type, Callable
 from redis import StrictRedis
 
 from apiserver import database
-from apiserver.timing_context import TimingContext
 
 T = TypeVar("T")
 
@@ -31,20 +30,17 @@ class RedisCacheManager(Generic[T]):
 
     def set_state(self, state: T) -> None:
         redis_key = self._get_redis_key(state.id)
-        with TimingContext("redis", "cache_set_state"):
-            self.redis.set(redis_key, state.to_json())
-            self.redis.expire(redis_key, self.expiration_interval)
+        self.redis.set(redis_key, state.to_json())
+        self.redis.expire(redis_key, self.expiration_interval)
 
     def get_state(self, state_id) -> Optional[T]:
         redis_key = self._get_redis_key(state_id)
-        with TimingContext("redis", "cache_get_state"):
-            response = self.redis.get(redis_key)
+        response = self.redis.get(redis_key)
         if response:
             return self.state_class.from_json(response)
 
     def delete_state(self, state_id) -> None:
-        with TimingContext("redis", "cache_delete_state"):
-            self.redis.delete(self._get_redis_key(state_id))
+        self.redis.delete(self._get_redis_key(state_id))
 
     def _get_redis_key(self, state_id):
         return f"{self.state_class}/{state_id}"

apiserver/bll/statistics/resource_monitor.py

@@ -1,6 +1,6 @@
 from datetime import datetime
 import operator
-from threading import Thread, Lock
+from threading import Lock
 from time import sleep
 
 import attr
@@ -9,76 +9,83 @@ import psutil
 from apiserver.utilities.threads_manager import ThreadsManager
 
 
-class ResourceMonitor(Thread):
-    @attr.s(auto_attribs=True)
-    class Sample:
-        cpu_usage: float = 0.0
-        mem_used_gb: float = 0
-        mem_free_gb: float = 0
+stat_threads = ThreadsManager("Statistics")
 
-        @classmethod
-        def _apply(cls, op, *samples):
-            return cls(
-                **{
-                    field: op(*(getattr(sample, field) for sample in samples))
-                    for field in attr.fields_dict(cls)
-                }
-            )
 
-        def min(self, sample):
-            return self._apply(min, self, sample)
-
-        def max(self, sample):
-            return self._apply(max, self, sample)
-
-        def avg(self, sample, count):
-            res = self._apply(lambda x: x * count, self)
-            res = self._apply(operator.add, res, sample)
-            res = self._apply(lambda x: x / (count + 1), res)
-            return res
-
-    def __init__(self, sample_interval_sec=5):
-        super(ResourceMonitor, self).__init__(daemon=True)
-        self.sample_interval_sec = sample_interval_sec
-        self._lock = Lock()
-        self._clear()
-
-    def _clear(self):
-        sample = self._get_sample()
-        self._avg = sample
-        self._min = sample
-        self._max = sample
-        self._clear_time = datetime.utcnow()
-        self._count = 1
+@attr.s(auto_attribs=True)
+class Sample:
+    cpu_usage: float = 0.0
+    mem_used_gb: float = 0
+    mem_free_gb: float = 0
 
     @classmethod
-    def _get_sample(cls) -> Sample:
-        return cls.Sample(
+    def _apply(cls, op, *samples):
+        return cls(
+            **{
+                field: op(*(getattr(sample, field) for sample in samples))
+                for field in attr.fields_dict(cls)
+            }
+        )
+
+    def min(self, sample):
+        return self._apply(min, self, sample)
+
+    def max(self, sample):
+        return self._apply(max, self, sample)
+
+    def avg(self, sample, count):
+        res = self._apply(lambda x: x * count, self)
+        res = self._apply(operator.add, res, sample)
+        res = self._apply(lambda x: x / (count + 1), res)
+        return res
+
+    @classmethod
+    def get_current_sample(cls) -> "Sample":
+        return cls(
             cpu_usage=psutil.cpu_percent(),
             mem_used_gb=psutil.virtual_memory().used / (1024 ** 3),
             mem_free_gb=psutil.virtual_memory().free / (1024 ** 3),
         )
 
-    def run(self):
-        while not ThreadsManager.terminating:
-            sleep(self.sample_interval_sec)
 
-            sample = self._get_sample()
+class ResourceMonitor:
+    class Accumulator:
+        def __init__(self):
+            sample = Sample.get_current_sample()
+            self.avg = sample
+            self.min = sample
+            self.max = sample
+            self.time = datetime.utcnow()
+            self.count = 1
 
-            with self._lock:
-                self._min = self._min.min(sample)
-                self._max = self._max.max(sample)
-                self._avg = self._avg.avg(sample, self._count)
-                self._count += 1
+        def add_sample(self, sample: Sample):
+            self.min = self.min.min(sample)
+            self.max = self.max.max(sample)
+            self.avg = self.avg.avg(sample, self.count)
+            self.count += 1
 
-    def get_stats(self) -> dict:
+    sample_interval_sec = 5
+    _lock = Lock()
+    accumulator = Accumulator()
+
+    @classmethod
+    @stat_threads.register("resource_monitor", daemon=True)
+    def start(cls):
+        while True:
+            sleep(cls.sample_interval_sec)
+            sample = Sample.get_current_sample()
+            with cls._lock:
+                cls.accumulator.add_sample(sample)
+
+    @classmethod
+    def get_stats(cls) -> dict:
         """ Returns current resource statistics and clears internal resource statistics """
-        with self._lock:
-            min_ = attr.asdict(self._min)
-            max_ = attr.asdict(self._max)
-            avg = attr.asdict(self._avg)
-            interval = datetime.utcnow() - self._clear_time
-            self._clear()
+        with cls._lock:
+            min_ = attr.asdict(cls.accumulator.min)
+            max_ = attr.asdict(cls.accumulator.max)
+            avg = attr.asdict(cls.accumulator.avg)
+            interval = datetime.utcnow() - cls.accumulator.time
+            cls.accumulator = cls.Accumulator()
 
         return {
             "interval_sec": interval.total_seconds(),

apiserver/bll/statistics/stats_reporter.py

@@ -8,8 +8,7 @@ from typing import Sequence, Optional
 
 import dpath
 import requests
-from requests.adapters import HTTPAdapter
-from requests.packages.urllib3.util.retry import Retry
+from requests.adapters import HTTPAdapter, Retry
 
 from apiserver.bll.query import Builder as QueryBuilder
 from apiserver.bll.util import get_server_uuid
@@ -21,9 +20,8 @@ from apiserver.database.model.queue import Queue
 from apiserver.database.model.task.task import Task
 from apiserver.tools import safe_get
 from apiserver.utilities.json import dumps
-from apiserver.utilities.threads_manager import ThreadsManager
 from apiserver.version import __version__ as current_version
-from .resource_monitor import ResourceMonitor
+from .resource_monitor import ResourceMonitor, stat_threads
 
 log = config.logger(__file__)
 
@@ -31,17 +29,19 @@ worker_bll = WorkerBLL()
 
 
 class StatisticsReporter:
-    threads = ThreadsManager("Statistics", resource_monitor=ResourceMonitor)
     send_queue = queue.Queue()
     supported = config.get("apiserver.statistics.supported", True)
 
     @classmethod
     def start(cls):
+        if not cls.supported:
+            return
+        ResourceMonitor.start()
         cls.start_sender()
         cls.start_reporter()
 
     @classmethod
-    @threads.register("reporter", daemon=True)
+    @stat_threads.register("reporter", daemon=True)
     def start_reporter(cls):
         """
         Periodically send statistics reports for companies who have opted in.
@@ -54,7 +54,7 @@ class StatisticsReporter:
             hours=config.get("apiserver.statistics.report_interval_hours", 24)
         )
         sleep(report_interval.total_seconds())
-        while not ThreadsManager.terminating:
+        while True:
             try:
                 for company in Company.objects(
                     defaults__stats_option__enabled=True
@@ -68,7 +68,7 @@ class StatisticsReporter:
             sleep(report_interval.total_seconds())
 
     @classmethod
-    @threads.register("sender", daemon=True)
+    @stat_threads.register("sender", daemon=True)
     def start_sender(cls):
         if not cls.supported:
             return
@@ -85,7 +85,7 @@ class StatisticsReporter:
 
         WarningFilter.attach()
 
-        while not ThreadsManager.terminating:
+        while True:
             try:
                 report = cls.send_queue.get()
 
@@ -111,7 +111,7 @@ class StatisticsReporter:
                 "uuid": get_server_uuid(),
                 "queues": {"count": Queue.objects(company=company_id).count()},
                 "users": {"count": User.objects(company=company_id).count()},
-                "resources": cls.threads.resource_monitor.get_stats(),
+                "resources": ResourceMonitor.get_stats(),
                 "experiments": next(
                     iter(cls._get_experiments_stats(company_id).values()), {}
                 ),
@@ -254,6 +254,14 @@ class StatisticsReporter:
                     **({"last_worker": {"$in": workers}} if workers else {}),
                 }
             },
+            {
+                "$project": {
+                    "last_worker": 1,
+                    "last_update": 1,
+                    "started": 1,
+                    "last_iteration": 1,
+                }
+            },
             {
                 "$group": {
                     "_id": "$last_worker" if workers else None,

apiserver/bll/storage/__init__.py

@@ -0,0 +1,48 @@
+from copy import copy
+
+from boltons.cacheutils import cachedproperty
+from clearml.backend_config.bucket_config import (
+    S3BucketConfigurations,
+    AzureContainerConfigurations,
+    GSBucketConfigurations,
+)
+
+from apiserver.config_repo import config
+
+
+log = config.logger(__file__)
+
+
+class StorageBLL:
+    default_aws_configs: S3BucketConfigurations = None
+    conf = config.get("services.storage_credentials")
+
+    @cachedproperty
+    def _default_aws_configs(self) -> S3BucketConfigurations:
+        return S3BucketConfigurations.from_config(self.conf.get("aws.s3"))
+
+    @cachedproperty
+    def _default_azure_configs(self) -> AzureContainerConfigurations:
+        return AzureContainerConfigurations.from_config(self.conf.get("azure.storage"))
+
+    @cachedproperty
+    def _default_gs_configs(self) -> GSBucketConfigurations:
+        return GSBucketConfigurations.from_config(self.conf.get("google.storage"))
+
+    def get_azure_settings_for_company(
+        self,
+        company_id: str,
+    ) -> AzureContainerConfigurations:
+        return copy(self._default_azure_configs)
+
+    def get_gs_settings_for_company(
+        self,
+        company_id: str,
+    ) -> GSBucketConfigurations:
+        return copy(self._default_gs_configs)
+
+    def get_aws_settings_for_company(
+        self,
+        company_id: str,
+    ) -> S3BucketConfigurations:
+        return copy(self._default_aws_configs)

apiserver/bll/task/__init__.py

@@ -1,6 +1,5 @@
 from .task_bll import TaskBLL
 from .utils import (
     ChangeStatusRequest,
-    update_project_time,
     validate_status_change,
 )

apiserver/bll/task/artifacts.py

@@ -5,7 +5,7 @@ from apiserver.apimodels.tasks import Artifact as ApiArtifact, ArtifactId
 from apiserver.bll.task.utils import get_task_for_update, update_task
 from apiserver.database.model.task.task import DEFAULT_ARTIFACT_MODE, Artifact
 from apiserver.database.utils import hash_field_name
-from apiserver.timing_context import TimingContext
+from apiserver.service_repo.auth import Identity
 from apiserver.utilities.dicts import nested_get, nested_set
 from apiserver.utilities.parameter_key_escaper import mongoengine_safe
 
@@ -49,49 +49,45 @@ class Artifacts:
     def add_or_update_artifacts(
         cls,
         company_id: str,
+        identity: Identity,
         task_id: str,
         artifacts: Sequence[ApiArtifact],
         force: bool,
     ) -> int:
-        with TimingContext("mongo", "update_artifacts"):
-            task = get_task_for_update(
-                company_id=company_id,
-                task_id=task_id,
-                force=force,
-            )
+        task = get_task_for_update(
+            company_id=company_id, task_id=task_id, force=force, identity=identity
+        )
 
-            artifacts = {
-                get_artifact_id(a): Artifact(**a)
-                for a in (api_artifact.to_struct() for api_artifact in artifacts)
-            }
+        artifacts = {
+            get_artifact_id(a): Artifact(**a)
+            for a in (api_artifact.to_struct() for api_artifact in artifacts)
+        }
 
-            update_cmds = {
-                f"set__execution__artifacts__{mongoengine_safe(name)}": value
-                for name, value in artifacts.items()
-            }
-            return update_task(task, update_cmds=update_cmds)
+        update_cmds = {
+            f"set__execution__artifacts__{mongoengine_safe(name)}": value
+            for name, value in artifacts.items()
+        }
+        return update_task(task, user_id=identity.user, update_cmds=update_cmds)
 
     @classmethod
     def delete_artifacts(
         cls,
         company_id: str,
+        identity: Identity,
         task_id: str,
         artifact_ids: Sequence[ArtifactId],
         force: bool,
     ) -> int:
-        with TimingContext("mongo", "delete_artifacts"):
-            task = get_task_for_update(
-                company_id=company_id,
-                task_id=task_id,
-                force=force,
-            )
+        task = get_task_for_update(
+            company_id=company_id, task_id=task_id, force=force, identity=identity
+        )
 
-            artifact_ids = [
-                get_artifact_id(a)
-                for a in (artifact_id.to_struct() for artifact_id in artifact_ids)
-            ]
-            delete_cmds = {
-                f"unset__execution__artifacts__{id_}": 1 for id_ in set(artifact_ids)
-            }
+        artifact_ids = [
+            get_artifact_id(a)
+            for a in (artifact_id.to_struct() for artifact_id in artifact_ids)
+        ]
+        delete_cmds = {
+            f"unset__execution__artifacts__{id_}": 1 for id_ in set(artifact_ids)
+        }
 
-            return update_task(task, update_cmds=delete_cmds)
+        return update_task(task, user_id=identity.user, update_cmds=delete_cmds)

apiserver/bll/task/hyperparams.py

@@ -15,7 +15,7 @@ from apiserver.bll.task import TaskBLL
 from apiserver.bll.task.utils import get_task_for_update, update_task
 from apiserver.config_repo import config
 from apiserver.database.model.task.task import ParamsItem, Task, ConfigurationItem
-from apiserver.timing_context import TimingContext
+from apiserver.service_repo.auth import Identity
 from apiserver.utilities.parameter_key_escaper import (
     ParameterKeyEscaper,
     mongoengine_safe,
@@ -32,7 +32,10 @@ class HyperParams:
     def get_params(cls, company_id: str, task_ids: Sequence[str]) -> Dict[str, dict]:
         only = ("id", "hyperparams")
         tasks = task_bll.assert_exists(
-            company_id=company_id, task_ids=task_ids, only=only, allow_public=True,
+            company_id=company_id,
+            task_ids=task_ids,
+            only=only,
+            allow_public=True,
         )
 
         return {
@@ -64,78 +67,84 @@ class HyperParams:
     def delete_params(
         cls,
         company_id: str,
+        identity: Identity,
         task_id: str,
         hyperparams: Sequence[HyperParamKey],
         force: bool,
     ) -> int:
-        with TimingContext("mongo", "delete_hyperparams"):
-            properties_only = cls._normalize_params(hyperparams)
-            task = get_task_for_update(
-                company_id=company_id,
-                task_id=task_id,
-                allow_all_statuses=properties_only,
-                force=force,
-            )
+        properties_only = cls._normalize_params(hyperparams)
+        task = get_task_for_update(
+            company_id=company_id,
+            task_id=task_id,
+            allow_all_statuses=properties_only,
+            force=force,
+            identity=identity,
+        )
 
-            with_param, without_param = iterutils.partition(
-                hyperparams, key=lambda p: bool(p.name)
-            )
-            sections_to_delete = {p.section for p in without_param}
-            delete_cmds = {
-                f"unset__hyperparams__{ParameterKeyEscaper.escape(section)}": 1
-                for section in sections_to_delete
-            }
+        with_param, without_param = iterutils.partition(
+            hyperparams, key=lambda p: bool(p.name)
+        )
+        sections_to_delete = {p.section for p in without_param}
+        delete_cmds = {
+            f"unset__hyperparams__{ParameterKeyEscaper.escape(section)}": 1
+            for section in sections_to_delete
+        }
 
-            for item in with_param:
-                section = ParameterKeyEscaper.escape(item.section)
-                if item.section in sections_to_delete:
-                    raise errors.bad_request.FieldsConflict(
-                        "Cannot delete section field if the whole section was scheduled for deletion"
-                    )
-                name = ParameterKeyEscaper.escape(item.name)
-                delete_cmds[f"unset__hyperparams__{section}__{name}"] = 1
+        for item in with_param:
+            section = ParameterKeyEscaper.escape(item.section)
+            if item.section in sections_to_delete:
+                raise errors.bad_request.FieldsConflict(
+                    "Cannot delete section field if the whole section was scheduled for deletion"
+                )
+            name = ParameterKeyEscaper.escape(item.name)
+            delete_cmds[f"unset__hyperparams__{section}__{name}"] = 1
 
-            return update_task(
-                task, update_cmds=delete_cmds, set_last_update=not properties_only
-            )
+        return update_task(
+            task,
+            user_id=identity.user,
+            update_cmds=delete_cmds,
+            set_last_update=not properties_only,
+        )
 
     @classmethod
     def edit_params(
         cls,
         company_id: str,
+        identity: Identity,
         task_id: str,
         hyperparams: Sequence[HyperParamItem],
         replace_hyperparams: str,
         force: bool,
     ) -> int:
-        with TimingContext("mongo", "edit_hyperparams"):
-            properties_only = cls._normalize_params(hyperparams)
-            task = get_task_for_update(
-                company_id=company_id,
-                task_id=task_id,
-                allow_all_statuses=properties_only,
-                force=force,
-            )
+        properties_only = cls._normalize_params(hyperparams)
+        task = get_task_for_update(
+            company_id=company_id,
+            task_id=task_id,
+            allow_all_statuses=properties_only,
+            force=force,
+            identity=identity,
+        )
 
-            update_cmds = dict()
-            hyperparams = cls._db_dicts_from_list(hyperparams)
-            if replace_hyperparams == ReplaceHyperparams.all:
-                update_cmds["set__hyperparams"] = hyperparams
-            elif replace_hyperparams == ReplaceHyperparams.section:
-                for section, value in hyperparams.items():
+        update_cmds = dict()
+        hyperparams = cls._db_dicts_from_list(hyperparams)
+        if replace_hyperparams == ReplaceHyperparams.all:
+            update_cmds["set__hyperparams"] = hyperparams
+        elif replace_hyperparams == ReplaceHyperparams.section:
+            for section, value in hyperparams.items():
+                update_cmds[f"set__hyperparams__{mongoengine_safe(section)}"] = value
+        else:
+            for section, section_params in hyperparams.items():
+                for name, value in section_params.items():
                     update_cmds[
-                        f"set__hyperparams__{mongoengine_safe(section)}"
+                        f"set__hyperparams__{section}__{mongoengine_safe(name)}"
                     ] = value
-            else:
-                for section, section_params in hyperparams.items():
-                    for name, value in section_params.items():
-                        update_cmds[
-                            f"set__hyperparams__{section}__{mongoengine_safe(name)}"
-                        ] = value
 
-            return update_task(
-                task, update_cmds=update_cmds, set_last_update=not properties_only
-            )
+        return update_task(
+            task,
+            user_id=identity.user,
+            update_cmds=update_cmds,
+            set_last_update=not properties_only,
+        )
 
     @classmethod
     def _db_dicts_from_list(cls, items: Sequence[HyperParamItem]) -> Dict[str, dict]:
@@ -160,7 +169,10 @@ class HyperParams:
         else:
             only.append("configuration")
         tasks = task_bll.assert_exists(
-            company_id=company_id, task_ids=task_ids, only=only, allow_public=True,
+            company_id=company_id,
+            task_ids=task_ids,
+            only=only,
+            allow_public=True,
         )
 
         return {
@@ -191,57 +203,60 @@ class HyperParams:
             {"$group": {"_id": "$_id", "names": {"$addToSet": "$items.k"}}},
         ]
 
-        with TimingContext("mongo", "get_configuration_names"):
-            tasks = Task.aggregate(pipeline)
+        tasks = Task.aggregate(pipeline)
 
-            return {
-                task["_id"]: {
-                    "names": sorted(
-                        ParameterKeyEscaper.unescape(name) for name in task["names"]
-                    )
-                }
-                for task in tasks
+        return {
+            task["_id"]: {
+                "names": sorted(
+                    ParameterKeyEscaper.unescape(name) for name in task["names"]
+                )
             }
+            for task in tasks
+        }
 
     @classmethod
     def edit_configuration(
         cls,
         company_id: str,
+        identity: Identity,
         task_id: str,
         configuration: Sequence[Configuration],
         replace_configuration: bool,
         force: bool,
     ) -> int:
-        with TimingContext("mongo", "edit_configuration"):
-            task = get_task_for_update(
-                company_id=company_id, task_id=task_id, force=force
-            )
+        task = get_task_for_update(
+            company_id=company_id, task_id=task_id, force=force, identity=identity
+        )
 
-            update_cmds = dict()
-            configuration = {
-                ParameterKeyEscaper.escape(c.name): ConfigurationItem(**c.to_struct())
-                for c in configuration
-            }
-            if replace_configuration:
-                update_cmds["set__configuration"] = configuration
-            else:
-                for name, value in configuration.items():
-                    update_cmds[f"set__configuration__{mongoengine_safe(name)}"] = value
+        update_cmds = dict()
+        configuration = {
+            ParameterKeyEscaper.escape(c.name): ConfigurationItem(**c.to_struct())
+            for c in configuration
+        }
+        if replace_configuration:
+            update_cmds["set__configuration"] = configuration
+        else:
+            for name, value in configuration.items():
+                update_cmds[f"set__configuration__{mongoengine_safe(name)}"] = value
 
-            return update_task(task, update_cmds=update_cmds)
+        return update_task(task, user_id=identity.user, update_cmds=update_cmds)
 
     @classmethod
     def delete_configuration(
-        cls, company_id: str, task_id: str, configuration: Sequence[str], force: bool
+        cls,
+        company_id: str,
+        identity: Identity,
+        task_id: str,
+        configuration: Sequence[str],
+        force: bool,
     ) -> int:
-        with TimingContext("mongo", "delete_configuration"):
-            task = get_task_for_update(
-                company_id=company_id, task_id=task_id, force=force
-            )
+        task = get_task_for_update(
+            company_id=company_id, task_id=task_id, force=force, identity=identity
+        )
 
-            delete_cmds = {
-                f"unset__configuration__{ParameterKeyEscaper.escape(name)}": 1
-                for name in set(configuration)
-            }
+        delete_cmds = {
+            f"unset__configuration__{ParameterKeyEscaper.escape(name)}": 1
+            for name in set(configuration)
+        }
 
-            return update_task(task, update_cmds=delete_cmds)
+        return update_task(task, user_id=identity.user, update_cmds=delete_cmds)

apiserver/bll/task/non_responsive_tasks_watchdog.py

@@ -1,7 +1,7 @@
 from datetime import timedelta, datetime
 from time import sleep
 
-from apiserver.bll.task import update_project_time
+from apiserver.bll.util import update_project_time
 from apiserver.config_repo import config
 from apiserver.database.model.task.task import TaskStatus, Task
 from apiserver.utilities.threads_manager import ThreadsManager
@@ -39,7 +39,7 @@ class NonResponsiveTasksWatchdog:
     @threads.register("non_responsive_tasks_watchdog", daemon=True)
     def start(cls):
         sleep(cls.settings.watch_interval_sec)
-        while not ThreadsManager.terminating:
+        while True:
             watch_interval = cls.settings.watch_interval_sec
             if cls.settings.enabled:
                 try:
@@ -85,6 +85,7 @@ class NonResponsiveTasksWatchdog:
                     status_changed=now,
                     last_update=now,
                     last_change=now,
+                    last_changed_by="__apiserver__",
                 )
                 if updated:
                     project_ids.add(task.project)

apiserver/bll/task/param_utils.py

@@ -121,18 +121,31 @@ def params_prepare_for_save(fields: dict, previous_task: Task = None):
             nested_set(fields, new_path, new_param)
         nested_delete(fields, old_params_field)
 
-    for param_field in ("hyperparams", "configuration"):
-        params = fields.get(param_field)
-        if params:
-            escaped_params = {
-                ParameterKeyEscaper.escape(key): {
-                    ParameterKeyEscaper.escape(k): v for k, v in value.items()
-                }
-                if isinstance(value, dict)
-                else value
-                for key, value in params.items()
+    def ensure_non_empty(k: str, desc: str) -> str:
+        if not k:
+            raise errors.bad_request.ValidationError(
+                f"Empty {desc} name is not allowed"
+            )
+        return k
+
+    params = fields.get("hyperparams")
+    if params:
+        escaped_params = {
+            ParameterKeyEscaper.escape(ensure_non_empty(key, "section")): {
+                ParameterKeyEscaper.escape(ensure_non_empty(k, "parameter")): v
+                for k, v in value.items()
             }
-            fields[param_field] = escaped_params
+            for key, value in params.items()
+        }
+        fields["hyperparams"] = escaped_params
+
+    params = fields.get("configuration")
+    if params:
+        escaped_params = {
+            ParameterKeyEscaper.escape(ensure_non_empty(key, "configuration")): value
+            for key, value in params.items()
+        }
+        fields["configuration"] = escaped_params
 
 
 def params_unprepare_from_saved(fields, copy_to_legacy=False):
@@ -186,7 +199,7 @@ def escape_paths(paths: Sequence[str]) -> Sequence[str]:
     for old_prefix, new_prefix in (
         ("execution.parameters", f"hyperparams.{hyperparams_default_section}"),
         ("execution.model_desc", "configuration"),
-        ("execution.docker_cmd", "container")
+        ("execution.docker_cmd", "container"),
     ):
         path: str
         paths = [path.replace(old_prefix, new_prefix) for path in paths]

apiserver/bll/task/task_bll.py

@@ -1,5 +1,5 @@
 from datetime import datetime
-from typing import Collection, Sequence, Tuple, Any, Optional, Dict
+from typing import Collection, Sequence, Tuple, Optional, Dict
 
 import six
 from mongoengine import Q
@@ -7,11 +7,12 @@ from redis import StrictRedis
 from six import string_types
 
 import apiserver.database.utils as dbutils
-from apiserver.apierrors import errors
+from apiserver.apierrors import errors, APIError
 from apiserver.apimodels.tasks import TaskInputModel
 from apiserver.bll.queue import QueueBLL
 from apiserver.bll.organization import OrgBLL, Tags
 from apiserver.bll.project import ProjectBLL
+from apiserver.bll.util import update_project_time
 from apiserver.config_repo import config
 from apiserver.database.errors import translate_errors_context
 from apiserver.database.model.model import Model
@@ -30,18 +31,20 @@ from apiserver.database.model.task.task import (
     TaskModelTypes,
 )
 from apiserver.database.model import EntityVisibility
-from apiserver.database.utils import get_company_or_none_constraint, id as create_id
+from apiserver.database.model.queue import Queue
+from apiserver.database.utils import (
+    get_company_or_none_constraint,
+    id as create_id,
+)
 from apiserver.es_factory import es_factory
 from apiserver.redis_manager import redman
-from apiserver.service_repo import APICall
 from apiserver.services.utils import validate_tags, escape_dict_field, escape_dict
-from apiserver.timing_context import TimingContext
 from .artifacts import artifacts_prepare_for_save
 from .param_utils import params_prepare_for_save
 from .utils import (
     ChangeStatusRequest,
-    update_project_time,
     deleted_prefix,
+    get_last_metric_updates,
 )
 
 log = config.logger(__file__)
@@ -55,31 +58,13 @@ class TaskBLL:
         self.events_es = events_es or es_factory.connect("events")
         self.redis: StrictRedis = redis or redman.connection("apiserver")
 
-    @staticmethod
-    def get_task_with_access(
-        task_id, company_id, only=None, allow_public=False, requires_write_access=False
-    ) -> Task:
-        """
-        Gets a task that has a required write access
-        :except errors.bad_request.InvalidTaskId: if the task is not found
-        :except errors.forbidden.NoWritePermission: if write_access was required and the task cannot be modified
-        """
-        with translate_errors_context():
-            query = dict(id=task_id, company=company_id)
-            with TimingContext("mongo", "task_with_access"):
-                if requires_write_access:
-                    task = Task.get_for_writing(_only=only, **query)
-                else:
-                    task = Task.get(_only=only, **query, include_public=allow_public)
-
-            if not task:
-                raise errors.bad_request.InvalidTaskId(**query)
-
-            return task
-
     @staticmethod
     def get_by_id(
-        company_id, task_id, required_status=None, only_fields=None, allow_public=False,
+        company_id,
+        task_id,
+        required_status=None,
+        only_fields=None,
+        allow_public=False,
     ):
         if only_fields:
             if isinstance(only_fields, string_types):
@@ -88,15 +73,14 @@ class TaskBLL:
                 only_fields = list(only_fields)
             only_fields = only_fields + ["status"]
 
-        with TimingContext("mongo", "task_by_id_all"):
-            tasks = Task.get_many(
-                company=company_id,
-                query=Q(id=task_id),
-                allow_public=allow_public,
-                override_projection=only_fields,
-                return_dicts=False,
-            )
-            task = None if not tasks else tasks[0]
+        tasks = Task.get_many(
+            company=company_id,
+            query=Q(id=task_id),
+            allow_public=allow_public,
+            override_projection=only_fields,
+            return_dicts=False,
+        )
+        task = None if not tasks else tasks[0]
 
         if not task:
             raise errors.bad_request.InvalidTaskId(id=task_id)
@@ -111,7 +95,7 @@ class TaskBLL:
         company_id, task_ids, only=None, allow_public=False, return_tasks=True
     ) -> Optional[Sequence[Task]]:
         task_ids = [task_ids] if isinstance(task_ids, six.string_types) else task_ids
-        with translate_errors_context(), TimingContext("mongo", "task_exists"):
+        with translate_errors_context():
             ids = set(task_ids)
             q = Task.get_many(
                 company=company_id,
@@ -131,16 +115,16 @@ class TaskBLL:
                 return list(q)
 
     @staticmethod
-    def create(call: APICall, fields: dict):
-        identity = call.identity
+    def create(company: str, user: str, fields: dict):
         now = datetime.utcnow()
         return Task(
             id=create_id(),
-            user=identity.user,
-            company=identity.company,
+            user=user,
+            company=company,
             created=now,
             last_update=now,
             last_change=now,
+            last_changed_by=user,
             **fields,
         )
 
@@ -260,58 +244,66 @@ class TaskBLL:
                 not in [TaskSystemTags.development, EntityVisibility.archived.value]
             ]
 
-        with TimingContext("mongo", "clone task"):
-            parent_task = (
-                task.parent
-                if task.parent and not task.parent.startswith(deleted_prefix)
-                else None
-            )
-            new_task = Task(
-                id=create_id(),
-                user=user_id,
-                company=company_id,
-                created=now,
-                last_update=now,
-                last_change=now,
-                name=name or task.name,
-                comment=comment or task.comment,
-                parent=parent or parent_task,
-                project=project or task.project,
-                tags=tags or task.tags,
-                system_tags=system_tags or clean_system_tags(task.system_tags),
-                type=task.type,
-                script=task.script,
-                output=Output(destination=task.output.destination)
-                if task.output
-                else None,
-                models=Models(input=input_models or task.models.input),
-                container=escape_dict(container) or task.container,
-                execution=execution_dict,
-                configuration=params_dict.get("configuration") or task.configuration,
-                hyperparams=params_dict.get("hyperparams") or task.hyperparams,
-            )
-            cls.validate(
-                new_task,
-                validate_models=validate_references or input_models,
-                validate_parent=validate_references or parent,
-                validate_project=validate_references or project,
-            )
-            new_task.save()
+        def ensure_int_labels(execution: dict) -> dict:
+            if not execution:
+                return execution
 
-            if task.project == new_task.project:
-                updated_tags = tags
-                updated_system_tags = system_tags
-            else:
-                updated_tags = new_task.tags
-                updated_system_tags = new_task.system_tags
-            org_bll.update_tags(
-                company_id,
-                Tags.Task,
-                project=new_task.project,
-                tags=updated_tags,
-                system_tags=updated_system_tags,
-            )
-            update_project_time(new_task.project)
+            model_labels = execution.get("model_labels")
+            if model_labels:
+                execution["model_labels"] = {k: int(v) for k, v in model_labels.items()}
+
+            return execution
+
+        parent_task = (
+            task.parent
+            if task.parent and not task.parent.startswith(deleted_prefix)
+            else task.id
+        )
+        new_task = Task(
+            id=create_id(),
+            user=user_id,
+            company=company_id,
+            created=now,
+            last_update=now,
+            last_change=now,
+            last_changed_by=user_id,
+            name=name or task.name,
+            comment=comment or task.comment,
+            parent=parent or parent_task,
+            project=project or task.project,
+            tags=tags or task.tags,
+            system_tags=system_tags or clean_system_tags(task.system_tags),
+            type=task.type,
+            script=task.script,
+            output=Output(destination=task.output.destination) if task.output else None,
+            models=Models(input=input_models or task.models.input),
+            container=escape_dict(container) or task.container,
+            execution=ensure_int_labels(execution_dict),
+            configuration=params_dict.get("configuration") or task.configuration,
+            hyperparams=params_dict.get("hyperparams") or task.hyperparams,
+        )
+        cls.validate(
+            new_task,
+            validate_models=validate_references or input_models,
+            validate_parent=validate_references or parent,
+            validate_project=validate_references or project,
+        )
+        new_task.save()
+
+        if task.project == new_task.project:
+            updated_tags = tags
+            updated_system_tags = system_tags
+        else:
+            updated_tags = new_task.tags
+            updated_system_tags = new_task.system_tags
+        org_bll.update_tags(
+            company_id,
+            Tags.Task,
+            projects=[new_task.project],
+            tags=updated_tags,
+            system_tags=updated_system_tags,
+        )
+        update_project_time(new_task.project)
 
         return new_task, new_project_data
 
@@ -350,6 +342,7 @@ class TaskBLL:
     def set_last_update(
         task_ids: Collection[str],
         company_id: str,
+        user_id: str,
         last_update: datetime,
         **extra_updates,
     ):
@@ -370,6 +363,7 @@ class TaskBLL:
                 upsert=False,
                 last_update=last_update,
                 last_change=last_update,
+                last_changed_by=user_id,
                 **updates,
             )
         return count
@@ -378,10 +372,11 @@ class TaskBLL:
     def update_statistics(
         task_id: str,
         company_id: str,
+        user_id: str,
         last_update: datetime = None,
         last_iteration: int = None,
         last_iteration_max: int = None,
-        last_scalar_values: Sequence[Tuple[Tuple[str, ...], Any]] = None,
+        last_scalar_events: Dict[str, Dict[str, dict]] = None,
         last_events: Dict[str, Dict[str, dict]] = None,
         **extra_updates,
     ):
@@ -406,25 +401,21 @@ class TaskBLL:
         elif last_iteration_max is not None:
             extra_updates.update(max__last_iteration=last_iteration_max)
 
-        if last_scalar_values is not None:
-
-            def op_path(op, *path):
-                return "__".join((op, "last_metrics") + path)
-
-            for path, value in last_scalar_values:
-                if path[-1] == "min_value":
-                    extra_updates[op_path("min", *path[:-1], "min_value")] = value
-                elif path[-1] == "max_value":
-                    extra_updates[op_path("max", *path[:-1], "max_value")] = value
-                else:
-                    extra_updates[op_path("set", *path)] = value
+        raw_updates = {}
+        if last_scalar_events is not None:
+            get_last_metric_updates(
+                task_id=task_id,
+                last_scalar_events=last_scalar_events,
+                raw_updates=raw_updates,
+                extra_updates=extra_updates,
+            )
 
         if last_events is not None:
 
-            def events_per_type(metric_data: Dict[str, dict]) -> Dict[str, EventStats]:
+            def events_per_type(metric_data_: Dict[str, dict]) -> Dict[str, EventStats]:
                 return {
                     event_type: EventStats(last_update=event["timestamp"])
-                    for event_type, event in metric_data.items()
+                    for event_type, event in metric_data_.items()
                 }
 
             metric_stats = {
@@ -435,24 +426,54 @@ class TaskBLL:
             }
             extra_updates["metric_stats"] = metric_stats
 
-        return TaskBLL.set_last_update(
+        ret = TaskBLL.set_last_update(
             task_ids=[task_id],
             company_id=company_id,
+            user_id=user_id,
             last_update=last_update,
             **extra_updates,
         )
+        if ret and raw_updates:
+            Task.objects(id=task_id).update_one(__raw__=[{"$set": raw_updates}])
+
+        return ret
+
+    @staticmethod
+    def remove_task_from_all_queues(company_id: str, task_id: str) -> int:
+        return Queue.objects(company=company_id, entries__task=task_id).update(
+            pull__entries__task=task_id, last_update=datetime.utcnow()
+        )
 
     @classmethod
     def dequeue_and_change_status(
-        cls, task: Task, company_id: str, status_message: str, status_reason: str,
+        cls,
+        task: Task,
+        company_id: str,
+        user_id: str,
+        status_message: str,
+        status_reason: str,
+        remove_from_all_queues=False,
+        new_status=None,
     ):
-        cls.dequeue(task, company_id)
+        try:
+            cls.dequeue(task, company_id, silent_fail=True)
+        except APIError:
+            # dequeue may fail if the queue was deleted
+            pass
+
+        if remove_from_all_queues:
+            cls.remove_task_from_all_queues(company_id=company_id, task_id=task.id)
+
+        if task.status not in [TaskStatus.queued, TaskStatus.in_progress]:
+            return {"updated": 0}
 
         return ChangeStatusRequest(
             task=task,
-            new_status=task.enqueue_status or TaskStatus.created,
+            new_status=new_status or task.enqueue_status or TaskStatus.created,
             status_reason=status_reason,
             status_message=status_message,
+            user_id=user_id,
+            force=True,
         ).execute(enqueue_status=None)
 
     @classmethod

apiserver/bll/task/task_cleanup.py

@@ -1,64 +1,31 @@
+from datetime import datetime
 from itertools import chain
 from operator import attrgetter
-from typing import Sequence, Generic, Callable, Type, Iterable, TypeVar, List, Set
+from typing import Sequence, Set, Tuple, Union
 
 import attr
-from boltons.iterutils import partition
-from mongoengine import QuerySet, Document
+from boltons.iterutils import partition, bucketize, first, chunked_iter
+from furl import furl
+from mongoengine import NotUniqueError
+from pymongo.errors import DuplicateKeyError
 
 from apiserver.apierrors import errors
 from apiserver.bll.event import EventBLL
 from apiserver.bll.event.event_bll import PlotFields
-from apiserver.bll.event.event_common import EventType
 from apiserver.bll.task.utils import deleted_prefix
+from apiserver.config_repo import config
 from apiserver.database.model.model import Model
 from apiserver.database.model.task.task import Task, TaskStatus, ArtifactModes
-from apiserver.timing_context import TimingContext
+from apiserver.database.model.url_to_delete import (
+    StorageType,
+    UrlToDelete,
+    FileType,
+    DeletionStatus,
+)
+from apiserver.database.utils import id as db_id
 
+log = config.logger(__file__)
 event_bll = EventBLL()
-T = TypeVar("T", bound=Document)
-
-
-class DocumentGroup(List[T]):
-    """
-    Operate on a list of documents as if they were a query result
-    """
-
-    def __init__(self, document_type: Type[T], documents: Iterable[T]):
-        super(DocumentGroup, self).__init__(documents)
-        self.type = document_type
-
-    @property
-    def ids(self) -> Set[str]:
-        return {obj.id for obj in self}
-
-    def objects(self, *args, **kwargs) -> QuerySet:
-        return self.type.objects(id__in=self.ids, *args, **kwargs)
-
-
-class TaskOutputs(Generic[T]):
-    """
-    Split task outputs of the same type by the ready state
-    """
-
-    published: DocumentGroup[T]
-    draft: DocumentGroup[T]
-
-    def __init__(
-        self,
-        is_published: Callable[[T], bool],
-        document_type: Type[T],
-        children: Iterable[T],
-    ):
-        """
-        :param is_published: predicate returning whether items is considered published
-        :param document_type: type of output
-        :param children: output documents
-        """
-        self.published, self.draft = map(
-            lambda x: DocumentGroup(document_type, x),
-            partition(children, key=is_published),
-        )
 
 
 @attr.s(auto_attribs=True)
@@ -101,13 +68,16 @@ class CleanupResult:
         )
 
 
-def collect_plot_image_urls(company: str, task: str) -> Set[str]:
+def collect_plot_image_urls(
+    company: str, task_or_model: Union[str, Sequence[str]]
+) -> Set[str]:
     urls = set()
-    next_scroll_id = None
-    with TimingContext("es", "collect_plot_image_urls"):
+    task_ids = task_or_model if isinstance(task_or_model, list) else [task_or_model]
+    for tasks in chunked_iter(task_ids, 100):
+        next_scroll_id = None
         while True:
             events, next_scroll_id = event_bll.get_plot_image_urls(
-                company_id=company, task_id=task, scroll_id=next_scroll_id
+                company_id=company, task_ids=tasks, scroll_id=next_scroll_id
             )
             if not events:
                 break
@@ -119,46 +89,123 @@ def collect_plot_image_urls(company: str, task: str) -> Set[str]:
     return urls
 
 
-def collect_debug_image_urls(company: str, task: str) -> Set[str]:
+def collect_debug_image_urls(
+    company: str, task_or_model: Union[str, Sequence[str]]
+) -> Set[str]:
     """
     Return the set of unique image urls
     Uses DebugImagesIterator to make sure that we do not retrieve recycled urls
     """
-    metrics = event_bll.get_metrics_and_variants(
-        company_id=company, task_id=task, event_type=EventType.metrics_image
-    )
-    if not metrics:
-        return set()
-
-    task_metrics = {task: {m: [] for m in metrics}}
-    scroll_id = None
     urls = set()
-    while True:
-        res = event_bll.debug_images_iterator.get_task_events(
-            company_id=company,
-            task_metrics=task_metrics,
-            iter_count=10,
-            state_id=scroll_id,
-        )
-        if not res.metric_events or not any(
-            iterations for _, iterations in res.metric_events
-        ):
-            break
+    task_ids = task_or_model if isinstance(task_or_model, list) else [task_or_model]
+    for tasks in chunked_iter(task_ids, 100):
+        after_key = None
+        while True:
+            res, after_key = event_bll.get_debug_image_urls(
+                company_id=company,
+                task_ids=tasks,
+                after_key=after_key,
+            )
+            urls.update(res)
+            if not after_key:
+                break
 
-        scroll_id = res.next_scroll_id
-        for task, iterations in res.metric_events:
-            urls.update(ev.get("url") for it in iterations for ev in it["events"])
-
-    urls.discard({None})
     return urls
 
 
+supported_storage_types = {
+    "s3://": StorageType.s3,
+    "azure://": StorageType.azure,
+    "gs://": StorageType.gs,
+}
+
+supported_storage_types.update(
+    {
+        p: StorageType.fileserver
+        for p in config.get(
+            "services.async_urls_delete.fileserver.url_prefixes",
+            ["https://", "http://"],
+        )
+    }
+)
+
+
+def _schedule_for_delete(
+    company: str,
+    user: str,
+    task_id: str,
+    urls: Set[str],
+    can_delete_folders: bool,
+) -> Set[str]:
+    urls_per_storage = bucketize(
+        urls,
+        key=lambda u: first(
+            type_
+            for prefix, type_ in supported_storage_types.items()
+            if u.startswith(prefix)
+        ),
+    )
+    urls_per_storage.pop(None, None)
+
+    processed_urls = set()
+    for storage_type, storage_urls in urls_per_storage.items():
+        delete_folders = (storage_type == StorageType.fileserver) and can_delete_folders
+        scheduled_to_delete = set()
+        for url in storage_urls:
+            folder = None
+            if delete_folders:
+                try:
+                    parsed = furl(url)
+                    if parsed.path and len(parsed.path.segments) > 1:
+                        folder = parsed.remove(
+                            args=True, fragment=True, path=parsed.path.segments[-1]
+                        ).url.rstrip("/")
+                except Exception as ex:
+                    pass
+
+            to_delete = folder or url
+            if to_delete in scheduled_to_delete:
+                processed_urls.add(url)
+                continue
+
+            try:
+                UrlToDelete(
+                    id=db_id(),
+                    company=company,
+                    user=user,
+                    url=to_delete,
+                    task=task_id,
+                    created=datetime.utcnow(),
+                    storage_type=storage_type,
+                    type=FileType.folder if folder else FileType.file,
+                ).save()
+            except (DuplicateKeyError, NotUniqueError):
+                existing = UrlToDelete.objects(company=company, url=to_delete).first()
+                if existing:
+                    existing.update(
+                        user=user,
+                        task=task_id,
+                        created=datetime.utcnow(),
+                        retry_count=0,
+                        unset__last_failure_time=1,
+                        unset__last_failure_reason=1,
+                        status=DeletionStatus.created,
+                    )
+            processed_urls.add(url)
+            scheduled_to_delete.add(to_delete)
+
+    return processed_urls
+
+
 def cleanup_task(
+    company: str,
+    user: str,
     task: Task,
     force: bool = False,
     update_children=True,
     return_file_urls=False,
     delete_output_models=True,
+    delete_external_artifacts=True,
 ) -> CleanupResult:
     """
     Validate task deletion and delete/modify all its output.
@@ -166,10 +213,14 @@ def cleanup_task(
     :param force: whether to delete task with published outputs
     :return: count of delete and modified items
     """
-    models = verify_task_children_and_ouptuts(task, force)
-
+    published_models, draft_models, in_use_model_ids = verify_task_children_and_ouptuts(
+        task, force
+    )
+    delete_external_artifacts = delete_external_artifacts and config.get(
+        "services.async_urls_delete.enabled", True
+    )
     event_urls, artifact_urls, model_urls = set(), set(), set()
-    if return_file_urls:
+    if return_file_urls or delete_external_artifacts:
         event_urls = collect_debug_image_urls(task.company, task.id)
         event_urls.update(collect_plot_image_urls(task.company, task.id))
         if task.execution and task.execution.artifacts:
@@ -178,31 +229,73 @@ def cleanup_task(
                 for a in task.execution.artifacts.values()
                 if a.mode == ArtifactModes.output and a.uri
             }
-        model_urls = {m.uri for m in models.draft.objects().only("uri") if m.uri}
+        model_urls = {
+            m.uri for m in draft_models if m.uri and m.id not in in_use_model_ids
+        }
 
     deleted_task_id = f"{deleted_prefix}{task.id}"
+    updated_children = 0
+    now = datetime.utcnow()
     if update_children:
-        with TimingContext("mongo", "update_task_children"):
-            updated_children = Task.objects(parent=task.id).update(
-                parent=deleted_task_id
+        updated_children = Task.objects(parent=task.id).update(
+            parent=deleted_task_id,
+            last_change=now,
+            last_changed_by=user,
+        )
+
+    deleted_models = 0
+    updated_models = 0
+    for models, allow_delete in ((draft_models, True), (published_models, False)):
+        if not models:
+            continue
+        if delete_output_models and allow_delete:
+            model_ids = list({m.id for m in models if m.id not in in_use_model_ids})
+            if model_ids:
+                if return_file_urls or delete_external_artifacts:
+                    event_urls.update(collect_debug_image_urls(task.company, model_ids))
+                    event_urls.update(collect_plot_image_urls(task.company, model_ids))
+
+                event_bll.delete_multi_task_events(
+                    task.company,
+                    model_ids,
+                    model=True,
+                )
+                deleted_models += Model.objects(id__in=model_ids).delete()
+
+            if in_use_model_ids:
+                Model.objects(id__in=list(in_use_model_ids)).update(
+                    unset__task=1,
+                    set__last_change=now,
+                    set__last_changed_by=user,
+                )
+            continue
+
+        if update_children:
+            updated_models += Model.objects(id__in=[m.id for m in models]).update(
+                task=deleted_task_id,
+                last_change=now,
+                last_changed_by=user,
+            )
+        else:
+            Model.objects(id__in=[m.id for m in models]).update(
+                unset__task=1,
+                set__last_change=now,
+                set__last_changed_by=user,
             )
-    else:
-        updated_children = 0
-
-    if models.draft and delete_output_models:
-        with TimingContext("mongo", "delete_models"):
-            deleted_models = models.draft.objects().delete()
-    else:
-        deleted_models = 0
-
-    if models.published and update_children:
-        with TimingContext("mongo", "update_task_models"):
-            updated_models = models.published.objects().update(task=deleted_task_id)
-    else:
-        updated_models = 0
 
     event_bll.delete_task_events(task.company, task.id, allow_locked=force)
 
+    if delete_external_artifacts:
+        scheduled = _schedule_for_delete(
+            task_id=task.id,
+            company=company,
+            user=user,
+            urls=event_urls | model_urls | artifact_urls,
+            can_delete_folders=not in_use_model_ids and not published_models,
+        )
+        for urls in (event_urls, model_urls, artifact_urls):
+            urls.difference_update(scheduled)
+
     return CleanupResult(
         deleted_models=deleted_models,
         updated_children=updated_children,
@@ -217,62 +310,57 @@ def cleanup_task(
     )
 
 
-def verify_task_children_and_ouptuts(task: Task, force: bool) -> TaskOutputs[Model]:
+def verify_task_children_and_ouptuts(
+    task, force: bool
+) -> Tuple[Sequence[Model], Sequence[Model], Set[str]]:
     if not force:
-        with TimingContext("mongo", "count_published_children"):
-            published_children_count = Task.objects(
-                parent=task.id, status=TaskStatus.published
-            ).count()
-            if published_children_count:
-                raise errors.bad_request.TaskCannotBeDeleted(
-                    "has children, use force=True",
-                    task=task.id,
-                    children=published_children_count,
-                )
-
-    with TimingContext("mongo", "get_task_models"):
-        models = TaskOutputs(
-            attrgetter("ready"),
-            Model,
-            Model.objects(task=task.id).only("id", "task", "ready"),
-        )
-        if not force and models.published:
+        published_children_count = Task.objects(
+            parent=task.id, status=TaskStatus.published
+        ).count()
+        if published_children_count:
             raise errors.bad_request.TaskCannotBeDeleted(
-                "has output models, use force=True",
+                "has children, use force=True",
                 task=task.id,
-                models=len(models.published),
+                children=published_children_count,
             )
 
+    model_fields = ["id", "ready", "uri"]
+    published_models, draft_models = partition(
+        Model.objects(task=task.id).only(*model_fields),
+        key=attrgetter("ready"),
+    )
+    if not force and published_models:
+        raise errors.bad_request.TaskCannotBeDeleted(
+            "has output models, use force=True",
+            task=task.id,
+            models=len(published_models),
+        )
+
     if task.models and task.models.output:
-        with TimingContext("mongo", "get_task_output_model"):
-            model_ids = [m.model for m in task.models.output]
-            for output_model in Model.objects(id__in=model_ids):
-                if output_model.ready:
-                    if not force:
-                        raise errors.bad_request.TaskCannotBeDeleted(
-                            "has output model, use force=True",
-                            task=task.id,
-                            model=output_model.id,
-                        )
-                    models.published.append(output_model)
-                else:
-                    models.draft.append(output_model)
+        model_ids = [m.model for m in task.models.output]
+        for output_model in Model.objects(id__in=model_ids).only(*model_fields):
+            if output_model.ready:
+                if not force:
+                    raise errors.bad_request.TaskCannotBeDeleted(
+                        "has output model, use force=True",
+                        task=task.id,
+                        model=output_model.id,
+                    )
+                published_models.append(output_model)
+            else:
+                draft_models.append(output_model)
 
-    if models.draft:
-        with TimingContext("mongo", "get_execution_models"):
-            model_ids = models.draft.ids
-            dependent_tasks = Task.objects(models__input__model__in=model_ids).only(
-                "id", "models"
+    in_use_model_ids = {}
+    if draft_models:
+        model_ids = {m.id for m in draft_models}
+        dependent_tasks = Task.objects(models__input__model__in=list(model_ids)).only(
+            "id", "models"
+        )
+        in_use_model_ids = model_ids & {
+            m.model
+            for m in chain.from_iterable(
+                t.models.input for t in dependent_tasks if t.models
             )
-            input_models = {
-                m.model
-                for m in chain.from_iterable(
-                    t.models.input for t in dependent_tasks if t.models
-                )
-            }
-            if input_models:
-                models.draft = DocumentGroup(
-                    Model, (m for m in models.draft if m.id not in input_models)
-                )
+        }
 
-    return models
+    return published_models, draft_models, in_use_model_ids

apiserver/bll/task/task_operations.py

@@ -1,5 +1,5 @@
 from datetime import datetime
-from typing import Callable, Any, Tuple, Union
+from typing import Callable, Any, Tuple, Union, Sequence
 
 from apiserver.apierrors import errors, APIError
 from apiserver.bll.queue import QueueBLL
@@ -7,9 +7,10 @@ from apiserver.bll.task import (
     TaskBLL,
     validate_status_change,
     ChangeStatusRequest,
-    update_project_time,
 )
 from apiserver.bll.task.task_cleanup import cleanup_task, CleanupResult
+from apiserver.bll.task.utils import get_task_with_write_access
+from apiserver.bll.util import update_project_time
 from apiserver.config_repo import config
 from apiserver.database.model import EntityVisibility
 from apiserver.database.model.model import Model
@@ -23,35 +24,50 @@ from apiserver.database.model.task.task import (
     Execution,
     DEFAULT_LAST_ITERATION,
 )
+from apiserver.database.utils import get_options
+from apiserver.service_repo.auth import Identity
 from apiserver.utilities.dicts import nested_set
 
+log = config.logger(__file__)
 queue_bll = QueueBLL()
 
 
 def archive_task(
-    task: Union[str, Task], company_id: str, status_message: str, status_reason: str,
+    task: Union[str, Task],
+    company_id: str,
+    identity: Identity,
+    status_message: str,
+    status_reason: str,
 ) -> int:
     """
     Deque and archive task
     Return 1 if successful
     """
     if isinstance(task, str):
-        task = TaskBLL.get_task_with_access(
+        task = get_task_with_write_access(
             task,
             company_id=company_id,
+            identity=identity,
             only=(
                 "id",
+                "company",
                 "execution",
                 "status",
                 "project",
                 "system_tags",
                 "enqueue_status",
             ),
-            requires_write_access=True,
         )
+
+    user_id = identity.user
     try:
         TaskBLL.dequeue_and_change_status(
-            task, company_id, status_message, status_reason,
+            task,
+            company_id=company_id,
+            user_id=user_id,
+            status_message=status_message,
+            status_reason=status_reason,
+            remove_from_all_queues=True,
         )
     except APIError:
         # dequeue may fail if the task was not enqueued
@@ -62,42 +78,81 @@ def archive_task(
         status_reason=status_reason,
         add_to_set__system_tags=EntityVisibility.archived.value,
         last_change=datetime.utcnow(),
+        last_changed_by=user_id,
     )
 
 
 def unarchive_task(
-    task: str, company_id: str, status_message: str, status_reason: str,
+    task_id: str,
+    company_id: str,
+    identity: Identity,
+    status_message: str,
+    status_reason: str,
 ) -> int:
     """
     Unarchive task. Return 1 if successful
     """
-    task = TaskBLL.get_task_with_access(
-        task, company_id=company_id, only=("id",), requires_write_access=True,
+    task = get_task_with_write_access(
+        task_id,
+        company_id=company_id,
+        identity=identity,
+        only=("id",),
     )
     return task.update(
         status_message=status_message,
         status_reason=status_reason,
         pull__system_tags=EntityVisibility.archived.value,
         last_change=datetime.utcnow(),
+        last_changed_by=identity.user,
     )
 
 
 def dequeue_task(
     task_id: str,
     company_id: str,
+    identity: Identity,
     status_message: str,
     status_reason: str,
+    remove_from_all_queues: bool = False,
+    new_status=None,
 ) -> Tuple[int, dict]:
-    query = dict(id=task_id, company=company_id)
-    task = Task.get_for_writing(**query)
+    if new_status and new_status not in get_options(TaskStatus):
+        raise errors.bad_request.ValidationError(f"Invalid task status: {new_status}")
+
+    # get the task without write access to make sure that it actually exists
+    task = Task.get(
+        id=task_id,
+        company=company_id,
+        _only=("id",),
+        include_public=True,
+    )
     if not task:
-        raise errors.bad_request.InvalidTaskId(**query)
+        TaskBLL.remove_task_from_all_queues(company_id, task_id=task_id)
+        return 1, {"updated": 0}
+
+    user_id = identity.user
+    task = get_task_with_write_access(
+        task_id,
+        company_id=company_id,
+        identity=identity,
+        only=(
+            "id",
+            "company",
+            "execution",
+            "status",
+            "project",
+            "enqueue_status",
+        ),
+    )
 
     res = TaskBLL.dequeue_and_change_status(
         task,
-        company_id,
+        company_id=company_id,
+        user_id=user_id,
         status_message=status_message,
         status_reason=status_reason,
+        remove_from_all_queues=remove_from_all_queues,
+        new_status=new_status,
     )
     return 1, res
 
@@ -105,21 +160,36 @@ def dequeue_task(
 def enqueue_task(
     task_id: str,
     company_id: str,
+    identity: Identity,
     queue_id: str,
     status_message: str,
     status_reason: str,
+    queue_name: str = None,
     validate: bool = False,
     force: bool = False,
 ) -> Tuple[int, dict]:
+    if queue_id and queue_name:
+        raise errors.bad_request.ValidationError(
+            "Either queue id or queue name should be provided"
+        )
+
+    if queue_name:
+        queue = queue_bll.get_by_name(
+            company_id=company_id, queue_name=queue_name, only=("id",)
+        )
+        if not queue:
+            queue = queue_bll.create(company_id=company_id, name=queue_name)
+        queue_id = queue.id
+
     if not queue_id:
         # try to get default queue
         queue_id = queue_bll.get_default(company_id).id
 
-    query = dict(id=task_id, company=company_id)
-    task = Task.get_for_writing(**query)
-    if not task:
-        raise errors.bad_request.InvalidTaskId(**query)
+    task = get_task_with_write_access(
+        task_id=task_id, company_id=company_id, identity=identity
+    )
 
+    user_id = identity.user
     if validate:
         TaskBLL.validate(task)
 
@@ -130,6 +200,7 @@ def enqueue_task(
         status_message=status_message,
         allow_same_state_transition=False,
         force=force,
+        user_id=user_id,
     ).execute(enqueue_status=task.status)
 
     try:
@@ -142,31 +213,59 @@ def enqueue_task(
             new_status=task.status,
             force=True,
             status_reason="failed enqueueing",
+            user_id=user_id,
         ).execute(enqueue_status=None)
         raise
 
     # set the current queue ID in the task
     if task.execution:
-        Task.objects(**query).update(execution__queue=queue_id, multi=False)
+        Task.objects(id=task_id).update(execution__queue=queue_id, multi=False)
     else:
-        Task.objects(**query).update(execution=Execution(queue=queue_id), multi=False)
+        Task.objects(id=task_id).update(execution=Execution(queue=queue_id), multi=False)
 
     nested_set(res, ("fields", "execution.queue"), queue_id)
     return 1, res
 
 
+def move_tasks_to_trash(tasks: Sequence[str]) -> int:
+    try:
+        collection_name = Task._get_collection_name()
+        trash_collection_name = f"{collection_name}__trash"
+        Task.aggregate(
+            [
+                {"$match": {"_id": {"$in": tasks}}},
+                {
+                    "$merge": {
+                        "into": trash_collection_name,
+                        "on": "_id",
+                        "whenMatched": "replace",
+                        "whenNotMatched": "insert",
+                    }
+                },
+            ],
+            allow_disk_use=True,
+        )
+    except Exception as ex:
+        log.error(f"Error copying tasks to trash {str(ex)}")
+
+    return Task.objects(id__in=tasks).delete()
+
+
 def delete_task(
     task_id: str,
     company_id: str,
+    identity: Identity,
     move_to_trash: bool,
     force: bool,
     return_file_urls: bool,
     delete_output_models: bool,
     status_message: str,
     status_reason: str,
+    delete_external_artifacts: bool,
 ) -> Tuple[int, Task, CleanupResult]:
-    task = TaskBLL.get_task_with_access(
-        task_id, company_id=company_id, requires_write_access=True
+    user_id = identity.user
+    task = get_task_with_write_access(
+        task_id, company_id=company_id, identity=identity
     )
 
     if (
@@ -185,33 +284,33 @@ def delete_task(
         TaskBLL.dequeue_and_change_status(
             task,
             company_id=company_id,
+            user_id=user_id,
             status_message=status_message,
             status_reason=status_reason,
+            remove_from_all_queues=True,
         )
     except APIError:
         # dequeue may fail if the task was not enqueued
         pass
 
     cleanup_res = cleanup_task(
-        task,
+        company=company_id,
+        user=user_id,
+        task=task,
         force=force,
         return_file_urls=return_file_urls,
         delete_output_models=delete_output_models,
+        delete_external_artifacts=delete_external_artifacts,
     )
 
     if move_to_trash:
-        collection_name = task._get_collection_name()
-        archived_collection = "{}__trash".format(collection_name)
-        task.switch_collection(archived_collection)
-        try:
-            # A simple save() won't do due to mongoengine caching (nothing will be saved), so we have to force
-            # an insert. However, if for some reason such an ID exists, let's make sure we'll keep going.
-            task.save(force_insert=True)
-        except Exception:
-            pass
-        task.switch_collection(collection_name)
+        # make sure that whatever changes were done to the task are saved
+        # the task itself will be deleted later in the move_tasks_to_trash operation
+        task.last_update = datetime.utcnow()
+        task.save()
+    else:
+        task.delete()
 
-    task.delete()
     update_project_time(task.project)
     return 1, task, cleanup_res
 
@@ -219,13 +318,16 @@ def delete_task(
 def reset_task(
     task_id: str,
     company_id: str,
+    identity: Identity,
     force: bool,
     return_file_urls: bool,
     delete_output_models: bool,
     clear_all: bool,
+    delete_external_artifacts: bool,
 ) -> Tuple[dict, CleanupResult, dict]:
-    task = TaskBLL.get_task_with_access(
-        task_id, company_id=company_id, requires_write_access=True
+    user_id = identity.user
+    task = get_task_with_write_access(
+        task_id, company_id=company_id, identity=identity
     )
 
     if not force and task.status == TaskStatus.published:
@@ -240,17 +342,23 @@ def reset_task(
         # dequeue may fail if the task was not enqueued
         pass
 
+    TaskBLL.remove_task_from_all_queues(company_id=company_id, task_id=task.id)
+
     cleaned_up = cleanup_task(
-        task,
+        company=company_id,
+        user=user_id,
+        task=task,
         force=force,
         update_children=False,
         return_file_urls=return_file_urls,
         delete_output_models=delete_output_models,
+        delete_external_artifacts=delete_external_artifacts,
     )
 
     updates.update(
         set__last_iteration=DEFAULT_LAST_ITERATION,
         set__last_metrics={},
+        set__unique_metrics=[],
         set__metric_stats={},
         set__models__output=[],
         set__runtime={},
@@ -258,11 +366,17 @@ def reset_task(
         unset__output__error=1,
         unset__last_worker=1,
         unset__last_worker_report=1,
+        unset__started=1,
+        unset__completed=1,
+        unset__published=1,
+        unset__active_duration=1,
+        unset__enqueue_status=1,
     )
 
     if clear_all:
         updates.update(
-            set__execution=Execution(), unset__script=1,
+            set__execution=Execution(),
+            unset__script=1,
         )
     else:
         updates.update(unset__execution__queue=1)
@@ -281,12 +395,8 @@ def reset_task(
         force=force,
         status_reason="reset",
         status_message="reset",
+        user_id=user_id,
     ).execute(
-        started=None,
-        completed=None,
-        published=None,
-        active_duration=None,
-        enqueue_status=None,
         **updates,
     )
 
@@ -296,13 +406,15 @@ def reset_task(
 def publish_task(
     task_id: str,
     company_id: str,
+    identity: Identity,
     force: bool,
-    publish_model_func: Callable[[str, str], Any] = None,
+    publish_model_func: Callable[[str, str, Identity], Any] = None,
     status_message: str = "",
     status_reason: str = "",
 ) -> dict:
-    task = TaskBLL.get_task_with_access(
-        task_id, company_id=company_id, requires_write_access=True
+    user_id = identity.user
+    task = get_task_with_write_access(
+        task_id, company_id=company_id, identity=identity
     )
     if not force:
         validate_status_change(task.status, TaskStatus.published)
@@ -325,7 +437,7 @@ def publish_task(
                 .first()
             )
             if model and not model.ready:
-                publish_model_func(model.id, company_id)
+                publish_model_func(model.id, company_id, identity)
 
         # set task status to published, and update (or set) it's new output (view and models)
         return ChangeStatusRequest(
@@ -334,6 +446,7 @@ def publish_task(
             force=force,
             status_reason=status_reason,
             status_message=status_message,
+            user_id=user_id,
         ).execute(published=datetime.utcnow(), output=output)
 
     except Exception as ex:
@@ -346,7 +459,12 @@ def publish_task(
 
 
 def stop_task(
-    task_id: str, company_id: str, user_name: str, status_reason: str, force: bool,
+    task_id: str,
+    company_id: str,
+    identity: Identity,
+    user_name: str,
+    status_reason: str,
+    force: bool,
 ) -> dict:
     """
     Stop a running task. Requires task status 'in_progress' and
@@ -356,10 +474,11 @@ def stop_task(
     is set to 'stopping' to allow the worker to stop the task and report by itself
     :return: updated task fields
     """
-
-    task = TaskBLL.get_task_with_access(
+    user_id = identity.user
+    task = get_task_with_write_access(
         task_id,
         company_id=company_id,
+        identity=identity,
         only=(
             "status",
             "project",
@@ -369,7 +488,6 @@ def stop_task(
             "last_update",
             "execution.queue",
         ),
-        requires_write_access=True,
     )
 
     def is_run_by_worker(t: Task) -> bool:
@@ -408,4 +526,5 @@ def stop_task(
         status_reason=status_reason,
         status_message=status_message,
         force=force,
+        user_id=user_id,
     ).execute()

apiserver/bll/task/utils.py

@@ -1,15 +1,18 @@
 from datetime import datetime
-from typing import Sequence, Union
+from typing import Sequence
 
 import attr
 import six
+from mongoengine import Q
 
 from apiserver.apierrors import errors
+from apiserver.bll.util import update_project_time
+from apiserver.config_repo import config
 from apiserver.database.errors import translate_errors_context
-from apiserver.database.model.project import Project
+from apiserver.database.model.model import Model
 from apiserver.database.model.task.task import Task, TaskStatus, TaskSystemTags
 from apiserver.database.utils import get_options
-from apiserver.timing_context import TimingContext
+from apiserver.service_repo.auth import Identity
 from apiserver.utilities.attrs import typed_attrs
 
 valid_statuses = get_options(TaskStatus)
@@ -27,6 +30,7 @@ class ChangeStatusRequest(object):
     force = attr.ib(type=bool, default=False)
     allow_same_state_transition = attr.ib(type=bool, default=True)
     current_status_override = attr.ib(default=None)
+    user_id = attr.ib(type=str, default=None)
 
     def execute(self, **kwargs):
         current_status = self.current_status_override or self.task.status
@@ -45,6 +49,7 @@ class ChangeStatusRequest(object):
             status_changed=now,
             last_update=now,
             last_change=now,
+            last_changed_by=self.user_id,
         )
 
         if self.new_status == TaskStatus.queued:
@@ -55,7 +60,7 @@ class ChangeStatusRequest(object):
 
         fields.update({safe_mongoengine_key(k): v for k, v in kwargs.items()})
 
-        with translate_errors_context(), TimingContext("mongo", "task_status"):
+        with translate_errors_context():
             # atomic change of task status by querying the task with the EXPECTED status before modifying it
             params = fields.copy()
             params.update(control)
@@ -155,25 +160,78 @@ def get_possible_status_changes(current_status):
     return possible
 
 
-def update_project_time(project_ids: Union[str, Sequence[str]]):
-    if not project_ids:
-        return
+def get_many_tasks_for_writing(
+    company_id: str,
+    identity: Identity,
+    query: Q = None,
+    only: Sequence = None,
+    throw_on_forbidden: bool = True,
+) -> Sequence[Task]:
+    if only:
+        missing = [f for f in ("company", ) if f not in only]
+        if missing:
+            only = [*only, *missing]
 
-    if isinstance(project_ids, str):
-        project_ids = [project_ids]
+    result = list(
+        Task.get_many(
+            company=company_id,
+            query=query,
+            override_projection=only,
+            allow_public=True,
+            return_dicts=False,
+        )
+    )
 
-    return Project.objects(id__in=project_ids).update(last_update=datetime.utcnow())
+    if not company_id:
+        return result
+
+    forbidden_tasks = {task.id for task in result if not task.company}
+    if forbidden_tasks:
+        if throw_on_forbidden:
+            raise errors.forbidden.NoWritePermission(
+                f"cannot modify public task(s), ids={tuple(forbidden_tasks)}"
+            )
+        result = [task for task in result if task.id not in forbidden_tasks]
+
+    return result
+
+
+def get_task_with_write_access(
+    task_id: str,
+    company_id: str,
+    identity: Identity,
+    only=None,
+) -> Task:
+    """
+    Gets a task that has a required write access
+    :except errors.bad_request.InvalidTaskId: if the task is not found
+    :except errors.forbidden.NoWritePermission: if write_access was required and the task cannot be modified
+    """
+    query = dict(id=task_id, company=company_id)
+
+    task = Task.get_for_writing(_only=only, **query)
+    if not task:
+        raise errors.bad_request.InvalidTaskId(**query)
+
+    return task
 
 
 def get_task_for_update(
-    company_id: str, task_id: str, allow_all_statuses: bool = False, force: bool = False
+    company_id: str,
+    task_id: str,
+    identity: Identity,
+    allow_all_statuses: bool = False,
+    force: bool = False
 ) -> Task:
     """
     Loads only task id and return the task only if it is updatable (status == 'created')
     """
-    task = Task.get_for_writing(company=company_id, id=task_id, _only=("id", "status"))
-    if not task:
-        raise errors.bad_request.InvalidTaskId(id=task_id)
+    task = get_task_with_write_access(
+        task_id=task_id,
+        company_id=company_id,
+        only=("id", "status"),
+        identity=identity,
+    )
 
     if allow_all_statuses:
         return task
@@ -188,9 +246,88 @@ def get_task_for_update(
     return task
 
 
-def update_task(task: Task, update_cmds: dict, set_last_update: bool = True):
+def update_task(
+    task: Task, user_id: str, update_cmds: dict, set_last_update: bool = True
+):
     now = datetime.utcnow()
-    last_updates = dict(last_change=now)
+    last_updates = dict(last_change=now, last_changed_by=user_id)
     if set_last_update:
         last_updates.update(last_update=now)
     return task.update(**update_cmds, **last_updates)
+
+
+def get_last_metric_updates(
+    task_id: str,
+    last_scalar_events: dict,
+    raw_updates: dict,
+    extra_updates: dict,
+    model_events: bool = False,
+):
+    max_values = config.get("services.tasks.max_last_metrics", 2000)
+    total_metrics = set()
+    if max_values:
+        query = dict(id=task_id)
+        to_add = sum(len(v) for m, v in last_scalar_events.items())
+        if to_add <= max_values:
+            query[f"unique_metrics__{max_values - to_add}__exists"] = True
+        db_cls = Model if model_events else Task
+        task = db_cls.objects(**query).only("unique_metrics").first()
+        if task and task.unique_metrics:
+            total_metrics = set(task.unique_metrics)
+
+    new_metrics = []
+
+    def add_last_metric_conditional_update(
+        metric_path: str, metric_value, iter_value: int, is_min: bool
+    ):
+        """
+        Build an aggregation for an atomic update of the min or max value and the corresponding iteration
+        """
+        if is_min:
+            field_prefix = "min"
+            op = "$gt"
+        else:
+            field_prefix = "max"
+            op = "$lt"
+
+        value_field = f"{metric_path}__{field_prefix}_value".replace("__", ".")
+        condition = {
+            "$or": [
+                {"$lte": [f"${value_field}", None]},
+                {op: [f"${value_field}", metric_value]},
+            ]
+        }
+        raw_updates[value_field] = {
+            "$cond": [condition, metric_value, f"${value_field}"]
+        }
+
+        value_iteration_field = f"{metric_path}__{field_prefix}_value_iteration".replace(
+            "__", "."
+        )
+        raw_updates[value_iteration_field] = {
+            "$cond": [condition, iter_value, f"${value_iteration_field}"]
+        }
+
+    for metric_key, metric_data in last_scalar_events.items():
+        for variant_key, variant_data in metric_data.items():
+            metric = f"{variant_data.get('metric')}/{variant_data.get('variant')}"
+            if max_values:
+                if len(total_metrics) >= max_values and metric not in total_metrics:
+                    continue
+                total_metrics.add(metric)
+
+            new_metrics.append(metric)
+            path = f"last_metrics__{metric_key}__{variant_key}"
+            for key, value in variant_data.items():
+                if key in ("min_value", "max_value"):
+                    add_last_metric_conditional_update(
+                        metric_path=path,
+                        metric_value=value,
+                        iter_value=variant_data.get(f"{key}_iter", 0),
+                        is_min=(key == "min_value"),
+                    )
+                elif key in ("metric", "variant", "value"):
+                    extra_updates[f"set__{path}__{key}"] = value
+
+    if new_metrics:
+        extra_updates["add_to_set__unique_metrics"] = new_metrics

apiserver/bll/user/__init__.py

@@ -1,3 +1,5 @@
+from datetime import datetime
+
 from apiserver.apierrors import errors
 from apiserver.apimodels.users import CreateRequest
 from apiserver.database.errors import translate_errors_context
@@ -12,7 +14,7 @@ class UserBLL:
             if user_id and User.objects(id=user_id).only("id"):
                 raise errors.bad_request.UserIdExists(id=user_id)
 
-            user = User(**request.to_struct())
+            user = User(**request.to_struct(), created=datetime.utcnow())
             user.save(force_insert=True)
 
     @staticmethod

apiserver/bll/util.py

@@ -1,76 +1,24 @@
 import functools
 import itertools
 from concurrent.futures.thread import ThreadPoolExecutor
+from datetime import datetime
 from typing import (
     Optional,
     Callable,
-    Dict,
-    Any,
-    Set,
     Iterable,
     Tuple,
     Sequence,
     TypeVar,
+    Union,
 )
 
 from boltons import iterutils
 
 from apiserver.apierrors import APIError
-from apiserver.database.model import AttributedDocument
+from apiserver.database.model.project import Project
 from apiserver.database.model.settings import Settings
 
 
-class SetFieldsResolver:
-    """
-    The class receives set fields dictionary
-    and for the set fields that require 'min' or 'max'
-    operation replace them with a simple set in case the
-    DB document does not have these fields set
-    """
-
-    SET_MODIFIERS = ("min", "max")
-
-    def __init__(self, set_fields: Dict[str, Any]):
-        self.orig_fields = {}
-        self.fields = {}
-        self.add_fields(**set_fields)
-
-    def add_fields(self, **set_fields: Any):
-        self.orig_fields.update(set_fields)
-        self.fields.update(
-            {
-                f: fname
-                for f, modifier, dunder, fname in (
-                    (f,) + f.partition("__") for f in set_fields.keys()
-                )
-                if dunder and modifier in self.SET_MODIFIERS
-            }
-        )
-
-    def _get_updated_name(self, doc: AttributedDocument, name: str) -> str:
-        if name in self.fields and doc.get_field_value(self.fields[name]) is None:
-            return self.fields[name]
-        return name
-
-    def get_fields(self, doc: AttributedDocument):
-        """
-        For the given document return the set fields instructions
-        with min/max operations replaced with a single set in case
-        the document does not have the field set
-        """
-        return {
-            self._get_updated_name(doc, name): value
-            for name, value in self.orig_fields.items()
-        }
-
-    def get_names(self) -> Set[str]:
-        """
-        Returns the names of the fields that had min/max modifiers
-        in the format suitable for projection (dot separated)
-        """
-        return set(name.replace("__", ".") for name in self.fields.values())
-
-
 @functools.lru_cache()
 def get_server_uuid() -> Optional[str]:
     return Settings.get_by_key("server.uuid")
@@ -132,3 +80,13 @@ def run_batch_operation(
                 }
             )
     return results, failures
+
+
+def update_project_time(project_ids: Union[str, Sequence[str]]):
+    if not project_ids:
+        return
+
+    if isinstance(project_ids, str):
+        project_ids = [project_ids]
+
+    return Project.objects(id__in=project_ids).update(last_update=datetime.utcnow())

apiserver/bll/workers/__init__.py

@@ -1,15 +1,17 @@
 import itertools
 from datetime import datetime, timedelta
+from time import time
 from typing import Sequence, Set, Optional
 
 import attr
 import elasticsearch.helpers
+from boltons.iterutils import partition, chunked_iter
+from pyhocon import ConfigTree
 
 from apiserver.es_factory import es_factory
 from apiserver.apierrors import APIError
 from apiserver.apierrors.errors import bad_request, server_error
 from apiserver.apimodels.workers import (
-    DEFAULT_TIMEOUT,
     IdNameEntry,
     WorkerEntry,
     StatusReportRequest,
@@ -25,16 +27,17 @@ from apiserver.database.model.project import Project
 from apiserver.database.model.queue import Queue
 from apiserver.database.model.task.task import Task
 from apiserver.redis_manager import redman
-from apiserver.timing_context import TimingContext
 from apiserver.tools import safe_get
 from .stats import WorkerStats
 
+
 log = config.logger(__file__)
 
 
 class WorkerBLL:
     def __init__(self, es=None, redis=None):
         self.es_client = es or es_factory.connect("workers")
+        self.config = config.get("services.workers", ConfigTree())
         self.redis = redis or redman.connection("workers")
         self._stats = WorkerStats(self.es_client)
 
@@ -51,6 +54,7 @@ class WorkerBLL:
         queues: Sequence[str] = None,
         timeout: int = 0,
         tags: Sequence[str] = None,
+        system_tags: Sequence[str] = None,
     ) -> WorkerEntry:
         """
         Register a worker
@@ -66,7 +70,7 @@ class WorkerBLL:
         """
         key = WorkerBLL._get_worker_key(company_id, user_id, worker)
 
-        timeout = timeout or DEFAULT_TIMEOUT
+        timeout = timeout or int(self.config.get("default_worker_timeout_sec", 10 * 60))
         queues = queues or []
 
         with translate_errors_context():
@@ -76,7 +80,7 @@ class WorkerBLL:
                 raise bad_request.InvalidUserId(**query)
             company = Company.objects(id=company_id).only("id", "name").first()
             if not company:
-                raise server_error.InternalError("invalid company", company=company_id)
+                raise bad_request.InvalidId("invalid company", company=company_id)
 
             queue_objs = Queue.objects(company=company_id, id__in=queues).only("id")
             if len(queue_objs) < len(queues):
@@ -95,9 +99,10 @@ class WorkerBLL:
                 register_timeout=timeout,
                 last_activity_time=now,
                 tags=tags,
+                system_tags=system_tags,
             )
 
-            self.redis.setex(key, timedelta(seconds=timeout), entry.to_json())
+            self._save_worker_data(entry)
 
         return entry
 
@@ -109,15 +114,20 @@ class WorkerBLL:
         :param worker: worker ID
         :raise bad_request.WorkerNotRegistered: the worker was not previously registered
         """
-        with TimingContext("redis", "workers_unregister"):
-            res = self.redis.delete(
-                company_id, self._get_worker_key(company_id, user_id, worker)
-            )
+        res = self.redis.delete(
+            company_id, self._get_worker_key(company_id, user_id, worker)
+        )
         if not res and not config.get("apiserver.workers.auto_unregister", False):
             raise bad_request.WorkerNotRegistered(worker=worker)
 
     def status_report(
-        self, company_id: str, user_id: str, ip: str, report: StatusReportRequest, tags: Sequence[str] = None,
+        self,
+        company_id: str,
+        user_id: str,
+        ip: str,
+        report: StatusReportRequest,
+        tags: Sequence[str] = None,
+        system_tags: Sequence[str] = None,
     ) -> None:
         """
         Write worker status report
@@ -133,22 +143,23 @@ class WorkerBLL:
 
         try:
             entry.ip = ip
-            now = datetime.utcnow()
-            entry.last_activity_time = now
 
             if tags is not None:
                 entry.tags = tags
+            if system_tags is not None:
+                entry.system_tags = system_tags
 
             if report.machine_stats:
-                self._log_stats_to_es(
+                self.log_stats_to_es(
                     company_id=company_id,
-                    company_name=entry.company.name,
-                    worker=report.worker,
+                    worker_id=report.worker,
                     timestamp=report.timestamp,
                     task=report.task,
                     machine_stats=report.machine_stats,
                 )
 
+            now = datetime.utcnow()
+            entry.last_activity_time = now
             entry.queue = report.queue
 
             if report.queues:
@@ -165,6 +176,7 @@ class WorkerBLL:
                         last_worker_report=now,
                         last_update=now,
                         last_change=now,
+                        last_changed_by=user_id,
                     )
                     # modify(new=True, ...) returns the modified object
                     task = Task.objects(**query).modify(new=True, **update)
@@ -176,7 +188,9 @@ class WorkerBLL:
                     if task.project:
                         project = Project.objects(id=task.project).only("name").first()
                         if project:
-                            entry.project = IdNameEntry(id=project.id, name=project.name)
+                            entry.project = IdNameEntry(
+                                id=project.id, name=project.name
+                            )
 
             entry.last_report_time = now
         except APIError:
@@ -188,8 +202,30 @@ class WorkerBLL:
         finally:
             self._save_worker(entry)
 
+    def get_count(
+        self,
+        company_id: str,
+        last_seen: Optional[int] = None,
+        tags: Sequence[str] = None,
+        system_tags: Sequence[str] = None,
+    ):
+        if not last_seen:
+            return len(
+                self._get_keys(company_id, user_tags=tags, system_tags=system_tags)
+            )
+
+        return len(
+            self.get_all(
+                company_id, last_seen=last_seen, tags=tags, system_tags=system_tags
+            )
+        )
+
     def get_all(
-        self, company_id: str, last_seen: Optional[int] = None
+        self,
+        company_id: str,
+        last_seen: Optional[int] = None,
+        tags: Sequence[str] = None,
+        system_tags: Sequence[str] = None,
     ) -> Sequence[WorkerEntry]:
         """
         Get all the company workers that were active during the last_seen period
@@ -198,7 +234,7 @@ class WorkerBLL:
         :return:
         """
         try:
-            workers = self._get(company_id)
+            workers = self._get(company_id, user_tags=tags, system_tags=system_tags)
         except Exception as e:
             raise server_error.DataError("failed loading worker entries", err=e.args[0])
 
@@ -213,15 +249,21 @@ class WorkerBLL:
         return workers
 
     def get_all_with_projection(
-        self, company_id: str, last_seen: int
+        self,
+        company_id: str,
+        last_seen: int,
+        tags: Sequence[str] = None,
+        system_tags: Sequence[str] = None,
     ) -> Sequence[WorkerResponseEntry]:
-
-        helpers = list(
-            map(
-                WorkerConversionHelper.from_worker_entry,
-                self.get_all(company_id=company_id, last_seen=last_seen),
+        helpers = [
+            WorkerConversionHelper.from_worker_entry(entry)
+            for entry in self.get_all(
+                company_id=company_id,
+                last_seen=last_seen,
+                tags=tags,
+                system_tags=system_tags,
             )
-        )
+        ]
 
         task_ids = set(filter(None, (helper.task_id for helper in helpers)))
         all_queues = set(
@@ -240,9 +282,7 @@ class WorkerBLL:
                     }
                 },
             ]
-            queues_info = {
-                res["_id"]: res for res in Queue.objects.aggregate(projection)
-            }
+            queues_info = {res["_id"]: res for res in Queue.aggregate(projection)}
             task_ids = task_ids.union(
                 filter(
                     None,
@@ -310,8 +350,7 @@ class WorkerBLL:
         """
         key = self._get_worker_key(company_id, user_id, worker)
 
-        with TimingContext("redis", "get_worker"):
-            data = self.redis.get(key)
+        data = self.redis.get(key)
 
         if data:
             try:
@@ -338,42 +377,149 @@ class WorkerBLL:
 
         raise bad_request.InvalidWorkerId(worker=worker)
 
+    @staticmethod
+    def _get_tagged_workers_key(company: str, tags_field: str, tag: str) -> str:
+        """Build redis key from company, user and worker_id"""
+        return f"workers.{tags_field}_{company}_{tag}"
+
+    @staticmethod
+    def _get_all_workers_key(company: str) -> str:
+        """Build redis key from company, user and worker_id"""
+        return f"workers_{company}"
+
+    def _save_worker_data(self, entry: WorkerEntry):
+        self.redis.setex(
+            entry.key, timedelta(seconds=entry.register_timeout), entry.to_json()
+        )
+        company_id = entry.company.id
+        expiration = int(time()) + entry.register_timeout
+        worker_item = {entry.key: expiration}
+        self.redis.zadd(self._get_all_workers_key(company_id), worker_item)
+        for tags, tags_field in (
+            (entry.tags, "tags"),
+            (entry.system_tags, "systemtags"),
+        ):
+            for tag in tags:
+                name = self._get_tagged_workers_key(company_id, tags_field, tag)
+                self.redis.zadd(name, worker_item)
+
     def _save_worker(self, entry: WorkerEntry) -> None:
         """Save worker entry in Redis"""
         try:
-            self.redis.setex(
-                entry.key, timedelta(seconds=entry.register_timeout), entry.to_json()
-            )
+            self._save_worker_data(entry)
         except Exception:
             msg = "Failed saving worker entry"
             log.exception(msg)
 
+    def _get_keys(
+        self,
+        company: str,
+        user: str = "*",
+        user_tags: Sequence[str] = None,
+        system_tags: Sequence[str] = None,
+    ) -> Sequence[bytes]:
+        if not (user_tags or system_tags):
+            match = self._get_worker_key(company, user, "*")
+            return list(self.redis.scan_iter(match))
+
+        def filter_by_user(in_keys: Set[bytes]) -> Set[bytes]:
+            if user == "*":
+                return in_keys
+            user_bytes = user.encode()
+            return {k for k in in_keys if user_bytes in k}
+
+        worker_keys = set()
+        for tags, tags_field in (
+            (user_tags, "tags"),
+            (system_tags, "systemtags"),
+        ):
+            if not tags:
+                continue
+
+            timestamp = int(time())
+            include, exclude = partition(tags, key=lambda x: x[0] != "-")
+            if include:
+                tagged_workers = set()
+                for tag in include:
+                    tagged_workers_key = self._get_tagged_workers_key(
+                        company, tags_field, tag
+                    )
+                    self.redis.zremrangebyscore(
+                        tagged_workers_key, min=0, max=timestamp
+                    )
+                    tagged_workers.update(self.redis.zrange(tagged_workers_key, 0, -1))
+
+                tagged_workers = filter_by_user(tagged_workers)
+                worker_keys = (
+                    worker_keys.intersection(tagged_workers)
+                    if worker_keys
+                    else tagged_workers
+                )
+                if not worker_keys:
+                    return []
+
+            if exclude:
+                if not worker_keys:
+                    all_workers_key = self._get_all_workers_key(company)
+                    self.redis.zremrangebyscore(all_workers_key, min=0, max=timestamp)
+                    worker_keys.update(self.redis.zrange(all_workers_key, 0, -1))
+                    worker_keys = filter_by_user(worker_keys)
+                    if not worker_keys:
+                        return []
+
+                for tag in exclude:
+                    tagged_workers_key = self._get_tagged_workers_key(
+                        company, tags_field, tag[1:]
+                    )
+                    self.redis.zremrangebyscore(
+                        tagged_workers_key, min=0, max=timestamp
+                    )
+                    worker_keys.difference_update(
+                        self.redis.zrange(tagged_workers_key, 0, -1)
+                    )
+                    if not worker_keys:
+                        return []
+
+        return list(worker_keys)
+
     def _get(
-        self, company: str, user: str = "*", worker_id: str = "*"
+        self,
+        company: str,
+        user: str = "*",
+        user_tags: Sequence[str] = None,
+        system_tags: Sequence[str] = None,
     ) -> Sequence[WorkerEntry]:
         """Get worker entries matching the company and user, worker patterns"""
-        match = self._get_worker_key(company, user, worker_id)
-        with TimingContext("redis", "workers_get_all"):
-            res = self.redis.scan_iter(match)
-        return [WorkerEntry.from_json(self.redis.get(r)) for r in res]
+
+        entries = []
+        for keys in chunked_iter(
+            self._get_keys(
+                company, user=user, user_tags=user_tags, system_tags=system_tags
+            ),
+            1000,
+        ):
+            data = self.redis.mget(keys)
+            if data:
+                entries.extend(WorkerEntry.from_json(d) for d in data if d)
+
+        return entries
 
     @staticmethod
     def _get_es_index_suffix():
         """Get the index name suffix for storing current month data"""
         return datetime.utcnow().strftime("%Y-%m")
 
-    def _log_stats_to_es(
+    def log_stats_to_es(
         self,
         company_id: str,
-        company_name: str,
-        worker: str,
+        worker_id: str,
         timestamp: int,
         task: str,
         machine_stats: MachineStats,
-    ) -> bool:
+    ) -> int:
         """
         Actually writing the worker statistics to Elastic
-        :return: True if successful, False otherwise
+        :return: The amount of logged documents
         """
         es_index = (
             f"{self._stats.worker_stats_prefix_for_company(company_id)}"
@@ -385,8 +531,7 @@ class WorkerBLL:
                 _index=es_index,
                 _source=dict(
                     timestamp=timestamp,
-                    worker=worker,
-                    company=company_name,
+                    worker=worker_id,
                     task=task,
                     category=category,
                     metric=metric,
@@ -411,7 +556,7 @@ class WorkerBLL:
 
         es_res = elasticsearch.helpers.bulk(self.es_client, actions)
         added, errors = es_res[:2]
-        return (added == len(actions)) and not errors
+        return added
 
 
 @attr.s(auto_attribs=True)

apiserver/bll/workers/stats.py

@@ -8,7 +8,6 @@ from apiserver.apimodels.workers import AggregationType, GetStatsRequest, StatIt
 from apiserver.bll.query import Builder as QueryBuilder
 from apiserver.config_repo import config
 from apiserver.database.errors import translate_errors_context
-from apiserver.timing_context import TimingContext
 
 log = config.logger(__file__)
 
@@ -20,7 +19,7 @@ class WorkerStats:
     @staticmethod
     def worker_stats_prefix_for_company(company_id: str) -> str:
         """Returns the es index prefix for the company"""
-        return f"worker_stats_{company_id}_"
+        return f"worker_stats_{company_id.lower()}_"
 
     def _search_company_stats(self, company_id: str, es_req: dict) -> dict:
         return self.es.search(
@@ -126,7 +125,7 @@ class WorkerStats:
             query_terms.append(QueryBuilder.terms("worker", request.worker_ids))
         es_req["query"] = {"bool": {"must": query_terms}}
 
-        with translate_errors_context(), TimingContext("es", "get_worker_stats"):
+        with translate_errors_context():
             data = self._search_company_stats(company_id, es_req)
 
         return self._extract_results(data, request.items, request.split_by_variant)
@@ -216,6 +215,10 @@ class WorkerStats:
                     "date_histogram": {
                         "field": "timestamp",
                         "fixed_interval": f"{interval}s",
+                        "extended_bounds": {
+                          "min": int(from_date) * 1000,
+                          "max": int(to_date) * 1000,
+                        }
                     },
                     "aggs": {"workers_count": {"cardinality": {"field": "worker"}}},
                 }
@@ -223,9 +226,7 @@ class WorkerStats:
             "query": {"bool": {"must": must}},
         }
 
-        with translate_errors_context(), TimingContext(
-            "es", "get_worker_activity_report"
-        ):
+        with translate_errors_context():
             data = self._search_company_stats(company_id, es_req)
 
         if "aggregations" not in data:

apiserver/config/default/apiserver.conf

@@ -41,10 +41,6 @@
         # controls whether FieldDoesNotExist exception will be raised for any extra attribute existing in stored data
         # but not declared in a data model
         strict: false
-
-        aggregate {
-            allow_disk_use: true
-        }
     }
 
     elastic {
@@ -76,6 +72,7 @@
             httponly: true  # allow only http to access the cookies (no JS etc)
             secure: false   # not using HTTPS
             domain: null    # Limit to localhost is not supported
+            samesite: Lax
             max_age: 99999999999
         }
 
@@ -117,6 +114,10 @@
         # Timeout in seconds on task status update. If exceeded
         # then task can be stopped without communicating to the worker
         task_update_timeout: 600
+
+        # Timeout in seconds for worker registration (or status report). If a worker did not report for this long,
+        # it is discarded from the server's table
+        default_timeout: 600
     }
 
     check_for_updates {
@@ -146,4 +147,11 @@
         max_backoff_sec: 5
     }
 
+    getting_started_info {
+        "agentName": "clearml",
+        "configure": "clearml-init",
+        "install": "pip install clearml",
+        "packageName": "clearml"
+    }
+
 }

apiserver/config/default/hosts.conf

@@ -1,3 +1,5 @@
+fileserver = "http://localhost:8081"
+
 elastic {
   events {
     hosts: [{host: "127.0.0.1", port: 9200}]

apiserver/config/default/secure.conf

@@ -23,6 +23,11 @@
             user_secret: "yfc8KQo*GMXb*9p((qcYC7ByFIpF7I&4VH3BfUYXH%o9vX1ZUZQEEw1Inc)S"
             revoke_in_fixed_mode: true
         }
+        services_agent {
+            role: "admin"
+            user_key: "P4BMJA7RK3TKBXGSY8OAA1FA8TOD11"
+            user_secret: "9LsgSfa0SYz0zli1_c500ZcLqanre2xkWOpepyt1w-BKK3_DKPHrtoj3JSHvyy8bIi0"
+        }
         tests {
             role: "user"
             display_name: "Default User"

apiserver/config/default/services/_mongo.conf

@@ -2,3 +2,8 @@ max_page_size: 500
 
 # expiration time in seconds for the redis scroll states in get_many family of apis
 scroll_state_expiration_seconds: 600
+
+allow_disk_use {
+    sort: true
+    aggregate: true
+}

apiserver/config/default/services/async_urls_delete.conf

@@ -0,0 +1,12 @@
+# if set to true then on task delete/reset external file urls for known storage types are scheduled for async delete
+# otherwise they are returned to a client for the client side delete
+enabled: true
+max_retries: 3
+retry_timeout_sec: 60
+
+fileserver {
+    # fileserver url prefixes. Evaluated in the order of priority
+    # Can be in the form <schema>://host:port/path or /path
+    url_prefixes: ["https://files.community-master.hosted.allegro.ai/"]
+    timeout_sec: 300
+}

apiserver/config/default/services/events.conf

@@ -12,15 +12,28 @@ events_retrieval {
     # should not exceed the amount of concurrent connections set in the ES driver
     max_metrics_concurrency: 4
 
+    # If set then max_metrics_count and max_variants_count are calculated dynamically on user data
+    dynamic_metrics_count: true
+
+    # The percentage from the ES aggs limit (10000) to use for the max_metrics and max_variants calculation
+    dynamic_metrics_count_threshold: 80
+
     # the max amount of metrics to aggregate on
     max_metrics_count: 100
 
     # the max amount of variants to aggregate on
     max_variants_count: 100
 
+    debug_images {
+        # Allow to return the debug images for the variants with uninitialized valid iterations border
+        allow_uninitialized_variants: true
+    }
+
     max_raw_scalars_size: 200000
 
     scroll_id_key: "cTN5VEtWEC6QrHvUl0FTx9kNyO0CcCK1p57akxma"
+
+    multi_plots_batch_size: 1000
 }
 
 # if set then plot str will be checked for the valid json on plot add
@@ -28,4 +41,7 @@ events_retrieval {
 validate_plot_str: false
 
 # If not 0 then the plots equal or greater to the size will be stored compressed in the DB
-plot_compression_threshold: 100000
+plot_compression_threshold: 100000
+
+# async events delete threshold
+max_async_deleted_events_per_sec: 1000

apiserver/config/default/services/models.conf

@@ -1,7 +1,4 @@
 metadata_values {
-    # maximal amount of distinct model values to retrieve
-    max_count: 100
-
     # cache ttl sec
     cache_ttl_sec: 86400
 }

apiserver/config/default/services/organization.conf

@@ -1,3 +1,9 @@
 tags_cache {
   expiration_seconds: 3600
+}
+download {
+    redis_timeout_sec: 300
+    batch_size: 500
+    max_download_items: 50000
+    max_project_name_length: 60
 }

apiserver/config/default/services/queues.conf

@@ -0,0 +1,8 @@
+{
+    metrics_before_from_date: 3600
+    # interval in seconds to update queue metrics. Put 0 to disable
+    metrics_refresh_interval_sec: 300
+    # the queues with these tags will not be returned from get_all/get_all_ex unless id or name specified
+    # or search_hidden is set
+    hidden_tags: [k8s-glue]
+}

apiserver/config/default/services/storage_credentials.conf

@@ -0,0 +1,54 @@
+aws {
+    s3 {
+        # S3 credentials, used for read/write access by various SDK elements
+        # default, used for any bucket not specified below
+        key: ""
+        secret: ""
+        region: ""
+        use_credentials_chain: false
+        # Additional ExtraArgs passed to boto3 when uploading files. Can also be set per-bucket under "credentials".
+        extra_args: {}
+        credentials: [
+            # specifies key/secret credentials to use when handling s3 urls (read or write)
+            # {
+            #     bucket: "my-bucket-name"
+            #     key: "my-access-key"
+            #     secret: "my-secret-key"
+            # },
+            {
+                # This will apply to all buckets in this host (unless key/value is specifically provided for a given bucket)
+                host: "localhost:9000"
+                key: "minioadmin"
+                secret: "minioadmin"
+                # region: my-server
+                multipart: false
+                secure: false
+            }
+        ]
+    }
+}
+google.storage {
+    # Default project and credentials file
+    # Will be used when no bucket configuration is found
+//    project: "clearml"
+//    credentials_json: "/path/to/credentials.json"
+//
+//    # Specific credentials per bucket and sub directory
+//    credentials = [
+//        {
+//            bucket: "my-bucket"
+//            subdir: "path/in/bucket" # Not required
+//            project: "clearml"
+//            credentials_json: "/path/to/credentials.json"
+//        },
+//    ]
+}
+azure.storage {
+    # containers: [
+    #     {
+    #         account_name: "clearml"
+    #         account_key: "secret"
+    #         # container_name:
+    #     }
+    # ]
+}

apiserver/config/default/services/tasks.conf

@@ -11,12 +11,18 @@ non_responsive_tasks_watchdog {
 multi_task_histogram_limit: 100
 
 hyperparam_values {
-    # maximal amount of distinct hyperparam values to retrieve
-    max_count: 100
-
     # max allowed outdate time for the cashed result
     cache_allowed_outdate_sec: 60
 
     # cache ttl sec
     cache_ttl_sec: 86400
-}
+}
+
+# the maximum amount of unique last metrics/variants combinations
+# for which the last values are stored in a task
+max_last_metrics: 2000
+
+# if set then call to tasks.delete/cleanup does not wait for ES events deletion
+async_events_delete: true
+# do not use async_delete if the deleted task has amount of events lower than this threshold
+async_events_delete_threshold: 100000

apiserver/database/__init__.py

@@ -29,6 +29,9 @@ OVERRIDE_PORT_ENV_KEY = (
 )
 
 OVERRIDE_CONNECTION_STRING_ENV_KEY = "CLEARML_MONGODB_SERVICE_CONNECTION_STRING"
+OVERRIDE_USERNAME_ENV_KEY = "CLEARML_MONGODB_SERVICE_USERNAME"
+OVERRIDE_PASSWORD_ENV_KEY = "CLEARML_MONGODB_SERVICE_PASSWORD"
+OVERRIDE_QUERY_ENV_KEY = "CLEARML_MONGODB_SERVICE_QUERY"
 
 
 class DatabaseEntry(models.Base):
@@ -52,14 +55,23 @@ class DatabaseFactory:
         override_connection_string = getenv(OVERRIDE_CONNECTION_STRING_ENV_KEY)
         override_hostname = first(map(getenv, OVERRIDE_HOST_ENV_KEY), None)
         override_port = first(map(getenv, OVERRIDE_PORT_ENV_KEY), None)
+        override_username = getenv(OVERRIDE_USERNAME_ENV_KEY)
+        override_password = getenv(OVERRIDE_PASSWORD_ENV_KEY)
+        override_query = getenv(OVERRIDE_QUERY_ENV_KEY)
 
         if override_connection_string:
-            log.info(f"Using override mongodb connection string {override_connection_string}")
+            log.info(f"Using override mongodb connection string template {override_connection_string}")
         else:
             if override_hostname:
                 log.info(f"Using override mongodb host {override_hostname}")
             if override_port:
                 log.info(f"Using override mongodb port {override_port}")
+            if override_username:
+                log.info(f"Using override mongodb username {override_username}")
+            if override_password:
+                log.info(f"Using override mongodb password ******")
+            if override_query:
+                log.info(f"Using override mongodb query {override_query}")
 
         for key, alias in get_items(Database).items():
             if key not in db_entries:
@@ -69,12 +81,20 @@ class DatabaseFactory:
             entry = cls._create_db_entry(alias=alias, settings=db_entries.get(key))
 
             if override_connection_string:
-                entry.host = override_connection_string
+                con_str = f"{override_connection_string.rstrip('/')}/{key}"
+                log.info(f"Using override mongodb connection string for {alias}: {con_str}")
+                entry.host = con_str
             else:
                 if override_hostname:
                     entry.host = furl(entry.host).set(host=override_hostname).url
                 if override_port:
                     entry.host = furl(entry.host).set(port=override_port).url
+                if override_username:
+                    entry.host = furl(entry.host).set(username=override_username).url
+                if override_password:
+                    entry.host = furl(entry.host).set(password=override_password).url
+                if override_query:
+                    entry.host = furl(entry.host).set(query=override_query).url
 
             try:
                 entry.validate()

apiserver/database/errors.py

@@ -16,7 +16,7 @@ from mongoengine.errors import (
     LookUpError,
     InvalidQueryError,
 )
-from pymongo.errors import PyMongoError, NotMasterError
+from pymongo.errors import PyMongoError, NotPrimaryError
 
 from apiserver.apierrors import errors
 
@@ -166,7 +166,10 @@ class MongoEngineErrorsHandler(object):
     @classmethod
     @throws_default_error(errors.server_error.InternalError)
     def invalid_query_error(cls, e, message, **_):
-        pass
+        if e.args:
+            inner = e.args[0]
+            if isinstance(inner, LookUpError):
+                cls.lookup_error(inner, message)
 
 
 @contextmanager
@@ -195,7 +198,7 @@ def translate_errors_context(message=None, **kwargs):
         MongoEngineErrorsHandler.invalid_query_error(e, message, **kwargs)
     except PyMongoError as e:
         raise errors.server_error.InternalError(message, err=str(e))
-    except NotMasterError as e:
+    except NotPrimaryError as e:
         raise errors.server_error.InternalError(message, err=str(e))
     except MakeGetAllQueryError as e:
         raise errors.bad_request.ValidationError(e.error, field=e.field)

apiserver/database/model/__init__.py

@@ -60,3 +60,4 @@ def validate_id(cls, company, **kwargs):
 class EntityVisibility(Enum):
     active = "active"
     archived = "archived"
+    hidden = "hidden"

apiserver/database/model/base.py

@@ -1,5 +1,6 @@
 import re
-from collections import namedtuple
+from collections import namedtuple, defaultdict
+from datetime import datetime
 from functools import reduce, partial
 from typing import (
     Collection,
@@ -11,22 +12,23 @@ from typing import (
     Mapping,
     Any,
     Callable,
-    Dict,
-    List,
+    Generator,
 )
 
+import attr
 from boltons.iterutils import first, partition
 from dateutil.parser import parse as parse_datetime
-from mongoengine import Q, Document, ListField, StringField, IntField
+from mongoengine import Q, Document, ListField, StringField, IntField, QuerySet
 from pymongo.command_cursor import CommandCursor
 
-from apiserver.apierrors import errors
+from apiserver.apierrors import errors, APIError
 from apiserver.apierrors.base import BaseError
+from apiserver.apierrors.errors.bad_request import FieldsValueError
 from apiserver.bll.redis_cache_manager import RedisCacheManager
 from apiserver.config_repo import config
 from apiserver.database import Database
 from apiserver.database.errors import MakeGetAllQueryError
-from apiserver.database.projection import project_dict, ProjectionHelper
+from apiserver.database.projection import ProjectionHelper
 from apiserver.database.props import PropsMixin
 from apiserver.database.query import RegexQ, RegexWrapper, RegexQCombination
 from apiserver.database.utils import (
@@ -36,9 +38,10 @@ from apiserver.database.utils import (
     field_exists,
 )
 from apiserver.redis_manager import redman
+from apiserver.utilities.dicts import project_dict, exclude_fields_from_dict
 
 log = config.logger("dbmodel")
-
+mongo_conf = config.get("services._mongo")
 ACCESS_REGEX = re.compile(r"^(?P<prefix>>=|>|<=|<)?(?P<value>.*)$")
 ACCESS_MODIFIER = {">=": "gte", ">": "gt", "<=": "lte", "<": "lt"}
 
@@ -55,17 +58,25 @@ class ProperDictMixin(object):
         strip_private=True,
         only=None,
         extra_dict=None,
+        exclude=None,
     ) -> dict:
         return self.properize_dict(
             self.to_mongo(use_db_field=False).to_dict(),
             strip_private=strip_private,
             only=only,
             extra_dict=extra_dict,
+            exclude=exclude,
         )
 
     @classmethod
     def properize_dict(
-        cls, d, strip_private=True, only=None, extra_dict=None, normalize_id=True
+        cls,
+        d,
+        strip_private=True,
+        only=None,
+        extra_dict=None,
+        exclude=None,
+        normalize_id=True,
     ):
         res = d
         if normalize_id and "_id" in res:
@@ -76,6 +87,9 @@ class ProperDictMixin(object):
             res = project_dict(res, only)
         if extra_dict:
             res.update(extra_dict)
+        if exclude:
+            exclude_fields_from_dict(res, exclude)
+
         return res
 
 
@@ -120,84 +134,134 @@ class GetMixin(PropsMixin):
             self.range_fields = range_fields
             self.pattern_fields = pattern_fields
 
-    class ListFieldBucketHelper:
+    class NewListFieldBucketHelper:
         op_prefix = "__$"
-        _legacy_exclude_prefix = "-"
-        _legacy_exclude_mongo_op = "nin"
-
-        default_mongo_op = "in"
-        _ops = {
-            # op -> (mongo_op, sticky)
-            "not": ("nin", False),
-            "nop": (default_mongo_op, False),
-            "all": ("all", True),
-            "and": ("all", True),
-            "any": (default_mongo_op, True),
-            "or": (default_mongo_op, True),
+        _unary_operators = {
+            "__$not": False,
+        }
+        _reset_operator = "__$nop"
+        _operators = {
+            "__$all": Q.AND,
+            "__$and": Q.AND,
+            "__$any": Q.OR,
+            "__$or": Q.OR,
+        }
+        default_global_operator = Q.AND
+        default_context = Q.OR
+        # not_all modifier currently not supported due to the backwards compatibility
+        mongo_modifiers = {
+            Q.AND: {True: "all", False: "nin"},
+            Q.OR: {True: "in", False: "nin"},
         }
 
-        def __init__(self, legacy=False):
-            self._current_op = None
-            self._sticky = False
-            self._support_legacy = legacy
+        @attr.s(auto_attribs=True)
+        class Term:
+            operator: str = None
+            reset: bool = False
+            include: bool = True
+            value: str = None
+
+        def __init__(self, field: str, data: Sequence[str], legacy=False):
+            self._field = field
             self.allow_empty = False
+            self.global_operator = None
+            self.actions = defaultdict(list)
 
-        def _get_op(self, v: str, translate: bool = False) -> Optional[str]:
-            op = (
-                v[len(self.op_prefix) :] if v and v.startswith(self.op_prefix) else None
-            )
-            if translate:
-                tup = self._ops.get(op, None)
-                return tup[0] if tup else None
-            return op
-
-        def _key(self, v) -> Optional[Union[str, bool]]:
-            if v is None:
-                self.allow_empty = True
-                return None
-
-            op = self._get_op(v)
-            if op is not None:
-                # operator - set state and return None
-                self._current_op, self._sticky = self._ops.get(
-                    op, (self.default_mongo_op, self._sticky)
-                )
-                return None
-            elif self._current_op:
-                current_op = self._current_op
-                if not self._sticky:
-                    self._current_op = None
-                return current_op
-            elif self._support_legacy and v.startswith(self._legacy_exclude_prefix):
-                self._current_op = None
-                return False
-
-            return self.default_mongo_op
-
-        def get_global_op(self, data: Sequence[str]) -> int:
-            op_to_res = {
-                "in": Q.OR,
-                "all": Q.AND,
-            }
-            data = (x for x in data if x is not None)
-            first_op = (
-                self._get_op(next(data, ""), translate=True) or self.default_mongo_op
-            )
-            return op_to_res.get(first_op, self.default_mongo_op)
-
-        def get_actions(self, data: Sequence[str]) -> Dict[str, List[Union[str, None]]]:
-            actions = {}
-
-            for val in data:
-                key = self._key(val)
-                if key is None:
+            self._support_legacy = legacy
+            current_context = self.default_context
+            for d in self._get_next_term(data):
+                if d.operator is not None:
+                    current_context = d.operator
+                    self._support_legacy = False
+                    if self.global_operator is None:
+                        self.global_operator = d.operator
                     continue
-                elif self._support_legacy and key is False:
-                    key = self._legacy_exclude_mongo_op
-                    val = val[len(self._legacy_exclude_prefix) :]
-                actions.setdefault(key, []).append(val)
 
-            return actions
+                if self.global_operator is None:
+                    self.global_operator = self.default_global_operator
+
+                if d.reset:
+                    current_context = self.default_context
+                    self._support_legacy = legacy
+                    continue
+
+                if d.value is None:
+                    self.allow_empty = True
+                    continue
+
+                self.actions[self.mongo_modifiers[current_context][d.include]].append(
+                    d.value
+                )
+
+            if self.global_operator is None:
+                self.global_operator = self.default_global_operator
+
+        def _get_next_term(self, data: Sequence[str]) -> Generator[Term, None, None]:
+            unary_operator = None
+            for value in data:
+                if value is None:
+                    unary_operator = None
+                    yield self.Term()
+                    continue
+
+                if not isinstance(value, str):
+                    raise FieldsValueError(
+                        "invalid value type, string expected",
+                        field=self._field,
+                        value=str(value),
+                    )
+
+                if value == self._reset_operator:
+                    unary_operator = None
+                    yield self.Term(reset=True)
+                    continue
+
+                if value.startswith(self.op_prefix):
+                    if unary_operator:
+                        raise FieldsValueError(
+                            "Value is expected after",
+                            field=self._field,
+                            operator=unary_operator,
+                        )
+                    if value in self._unary_operators:
+                        unary_operator = value
+                        continue
+
+                    operator = self._operators.get(value)
+                    if operator is None:
+                        raise FieldsValueError(
+                            "Unsupported operator",
+                            field=self._field,
+                            operator=value,
+                        )
+                    yield self.Term(operator=operator)
+                    continue
+
+                if (
+                    not unary_operator
+                    and self._support_legacy
+                    and value.startswith("-")
+                ):
+                    value = value[1:]
+                    if not value:
+                        raise FieldsValueError(
+                            "Missing value after the exclude prefix -",
+                            field=self._field,
+                            value=value,
+                        )
+                    yield self.Term(value=value, include=False)
+                    continue
+
+                term = self.Term(value=value)
+                if unary_operator:
+                    term.include = self._unary_operators[unary_operator]
+                    unary_operator = None
+                yield term
+
+            if unary_operator:
+                raise FieldsValueError(
+                    "Value is expected after", operator=unary_operator
+                )
 
     get_all_query_options = QueryParameterOptions()
 
@@ -215,8 +279,8 @@ class GetMixin(PropsMixin):
             cls._cache_manager = RedisCacheManager(
                 state_class=cls.GetManyScrollState,
                 redis=redman.connection("apiserver"),
-                expiration_interval=config.get(
-                    "services._mongo.scroll_state_expiration_seconds", 600
+                expiration_interval=mongo_conf.get(
+                    "scroll_state_expiration_seconds", 600
                 ),
             )
 
@@ -335,84 +399,121 @@ class GetMixin(PropsMixin):
         parameters_options = parameters_options or cls.get_all_query_options
         dict_query = {}
         query = RegexQ()
-        if parameters:
-            parameters = {
-                k: cls._get_fixed_field_value(k, v) for k, v in parameters.items()
-            }
-            opts = parameters_options
-            for field in opts.pattern_fields:
-                pattern = parameters.pop(field, None)
-                if pattern:
-                    dict_query[field] = RegexWrapper(pattern)
+        field = None
+        # noinspection PyBroadException
+        try:
+            if parameters:
+                parameters = {
+                    k: cls._get_fixed_field_value(k, v) for k, v in parameters.items()
+                }
+                filters = parameters.pop("filters", {})
+                if not isinstance(filters, dict):
+                    raise FieldsValueError(
+                        "invalid value type, string expected",
+                        field=filters,
+                        value=str(filters),
+                    )
+                opts = parameters_options
+                for field in opts.pattern_fields:
+                    pattern = parameters.pop(field, None)
+                    if pattern:
+                        dict_query[field] = RegexWrapper(pattern)
 
-            for field, data in cls._pop_matching_params(
-                patterns=opts.list_fields, parameters=parameters
-            ).items():
-                query &= cls.get_list_field_query(field, data)
+                for field, data in cls._pop_matching_params(
+                    patterns=opts.list_fields, parameters=filters
+                ).items():
+                    query &= cls.get_list_filter_query(field, data)
+                    parameters.pop(field, None)
 
-            for field, data in cls._pop_matching_params(
-                patterns=opts.range_fields, parameters=parameters
-            ).items():
-                query &= cls.get_range_field_query(field, data)
+                for field, data in cls._pop_matching_params(
+                    patterns=opts.list_fields, parameters=parameters
+                ).items():
+                    query &= cls.get_list_field_query(field, data)
 
-            for field, data in cls._pop_matching_params(
-                patterns=opts.fields or [], parameters=parameters
-            ).items():
-                if "._" in field or "_." in field:
-                    query &= RegexQ(__raw__={field: data})
-                else:
-                    dict_query[field.replace(".", "__")] = data
+                for field, data in cls._pop_matching_params(
+                    patterns=opts.range_fields, parameters=parameters
+                ).items():
+                    query &= cls.get_range_field_query(field, data)
 
-            for field in opts.datetime_fields or []:
-                data = parameters.pop(field, None)
-                if data is not None:
-                    if not isinstance(data, list):
-                        data = [data]
-                    for d in data:  # type: str
-                        m = ACCESS_REGEX.match(d)
-                        if not m:
+                for field, data in cls._pop_matching_params(
+                    patterns=opts.fields or [], parameters=parameters
+                ).items():
+                    if "._" in field or "_." in field:
+                        query &= RegexQ(__raw__={field: data})
+                    else:
+                        dict_query[field.replace(".", "__")] = data
+
+                for field in opts.datetime_fields or []:
+                    data = parameters.pop(field, None)
+                    if data is not None:
+                        if not isinstance(data, list):
+                            data = [data]
+                        # date time fields also support simplified range queries. Check if this is the case
+                        if len(data) == 2 and not any(
+                            d.startswith(mod)
+                            for d in data
+                            if d is not None
+                            for mod in ACCESS_MODIFIER
+                        ):
+                            query &= cls.get_range_field_query(field, data)
+                        else:
+                            for d in data:  # type: str
+                                m = ACCESS_REGEX.match(d)
+                                if not m:
+                                    continue
+                                try:
+                                    value = parse_datetime(m.group("value"))
+                                    prefix = m.group("prefix")
+                                    modifier = ACCESS_MODIFIER.get(prefix)
+                                    f = (
+                                        field
+                                        if not modifier
+                                        else "__".join((field, modifier))
+                                    )
+                                    dict_query[f] = value
+                                except (ValueError, OverflowError):
+                                    pass
+
+                for field, value in parameters.items():
+                    for keys, func in cls._multi_field_param_prefix.items():
+                        if field not in keys:
                             continue
                         try:
-                            value = parse_datetime(m.group("value"))
-                            prefix = m.group("prefix")
-                            modifier = ACCESS_MODIFIER.get(prefix)
-                            f = field if not modifier else "__".join((field, modifier))
-                            dict_query[f] = value
-                        except (ValueError, OverflowError):
-                            pass
-
-            for field, value in parameters.items():
-                for keys, func in cls._multi_field_param_prefix.items():
-                    if field not in keys:
-                        continue
-                    try:
-                        data = cls.MultiFieldParameters(**value)
-                    except Exception:
-                        raise MakeGetAllQueryError("incorrect field format", field)
-                    if not data.fields:
-                        break
-                    if any("._" in f for f in data.fields):
-                        q = reduce(
-                            lambda a, x: func(
-                                a,
-                                RegexQ(
-                                    __raw__={
-                                        x: {"$regex": data.pattern, "$options": "i"}
-                                    }
+                            data = cls.MultiFieldParameters(**value)
+                        except Exception:
+                            raise MakeGetAllQueryError("incorrect field format", field)
+                        if not data.fields:
+                            break
+                        if any("._" in f for f in data.fields):
+                            q = reduce(
+                                lambda a, x: func(
+                                    a,
+                                    RegexQ(
+                                        __raw__={
+                                            x: {"$regex": data.pattern, "$options": "i"}
+                                        }
+                                    ),
                                 ),
-                            ),
-                            data.fields,
-                            RegexQ(),
-                        )
-                    else:
-                        regex = RegexWrapper(data.pattern, flags=re.IGNORECASE)
-                        sep_fields = [f.replace(".", "__") for f in data.fields]
-                        q = reduce(
-                            lambda a, x: func(a, RegexQ(**{x: regex})),
-                            sep_fields,
-                            RegexQ(),
-                        )
-                    query = query & q
+                                data.fields,
+                                RegexQ(),
+                            )
+                        else:
+                            regex = RegexWrapper(data.pattern, flags=re.IGNORECASE)
+                            sep_fields = [f.replace(".", "__") for f in data.fields]
+                            q = reduce(
+                                lambda a, x: func(a, RegexQ(**{x: regex})),
+                                sep_fields,
+                                RegexQ(),
+                            )
+                        query = query & q
+        except APIError:
+            raise
+        except Exception as ex:
+            raise errors.bad_request.FieldsValueError(
+                "failed parsing query field",
+                error=str(ex),
+                **({"field": field} if field else {}),
+            )
 
         return query & RegexQ(**dict_query)
 
@@ -447,6 +548,149 @@ class GetMixin(PropsMixin):
 
         return q
 
+    @attr.s(auto_attribs=True)
+    class ListQueryFilter:
+        """
+        Deserialize filters data and build db_query object that represents it with the corresponding
+        mongo engine operations
+        Each part has include and exclude lists that map to mongoengine operations as following:
+        "any"
+          - include -> 'in'
+          - exclude -> 'not_all'
+          - combined by 'or' operation
+        "all"
+          - include -> 'all'
+          - exclude -> 'nin'
+          - combined by 'and' operation
+        "op" optional parameter for combining "and" and "all" parts. Can be "and" or "or". The default is "and"
+        """
+
+        _and_op = "and"
+        _or_op = "or"
+        _allowed_op = [_and_op, _or_op]
+        _db_modifiers: Mapping = {
+            (Q.OR, True): "in",
+            (Q.OR, False): "not__all",
+            (Q.AND, True): "all",
+            (Q.AND, False): "nin",
+        }
+
+        @attr.s(auto_attribs=True)
+        class ListFilter:
+            include: Sequence[str] = []
+            exclude: Sequence[str] = []
+
+            @classmethod
+            def from_dict(cls, d: Mapping):
+                if d is None:
+                    return None
+                return cls(**d)
+
+        any: ListFilter = attr.ib(converter=ListFilter.from_dict, default=None)
+        all: ListFilter = attr.ib(converter=ListFilter.from_dict, default=None)
+        op: str = attr.ib(default="and")
+        db_query: dict = attr.ib(init=False)
+
+        # noinspection PyUnresolvedReferences
+        @op.validator
+        def op_validator(self, _, value):
+            if value not in self._allowed_op:
+                raise ValueError(
+                    f"Invalid list query filter operator: {value}. "
+                    f"Should be one of {str(self._allowed_op)}"
+                )
+
+        @property
+        def and_op(self) -> bool:
+            return self.op == self._and_op
+
+        def __attrs_post_init__(self):
+            self.db_query = {}
+            for op, conditions in ((Q.OR, self.any), (Q.AND, self.all)):
+                if not conditions:
+                    continue
+
+                operations = {}
+                for vals, include in (
+                    (conditions.include, True),
+                    (conditions.exclude, False),
+                ):
+                    if not vals:
+                        continue
+
+                    unique = set(vals)
+                    if None in unique:
+                        # noinspection PyTypeChecker
+                        unique.remove(None)
+                        if include:
+                            operations["size"] = 0
+                        else:
+                            operations["not__size"] = 0
+
+                    if not unique:
+                        continue
+
+                    operations[self._db_modifiers[(op, include)]] = list(unique)
+
+                self.db_query[op] = operations
+
+        @classmethod
+        def from_data(cls, field, data: Mapping):
+            if not isinstance(data, dict):
+                raise errors.bad_request.ValidationError(
+                    "invalid filter for field, dictionary expected",
+                    field=field,
+                    value=str(data),
+                )
+
+            try:
+                return cls(**data)
+            except Exception as ex:
+                raise errors.bad_request.ValidationError(
+                    field=field,
+                    value=str(ex),
+                )
+
+    @classmethod
+    def get_list_filter_query(
+        cls, field: str, data: Mapping
+    ) -> Union[RegexQ, RegexQCombination]:
+        if not data:
+            return RegexQ()
+
+        filter_ = cls.ListQueryFilter.from_data(field, data)
+
+        mongoengine_field = field.replace(".", "__")
+        queries = []
+        for op, actions in filter_.db_query.items():
+            if not actions:
+                continue
+
+            ops = []
+            for action, vals in actions.items():
+                # cannot just check vals here since 0 is acceptable value
+                if vals is None or vals == []:
+                    continue
+
+                ops.append(RegexQ(**{f"{mongoengine_field}__{action}": vals}))
+
+            if not ops:
+                continue
+
+            if len(ops) == 1:
+                queries.extend(ops)
+                continue
+
+            queries.append(RegexQCombination(operation=op, children=ops))
+
+        if not queries:
+            return RegexQ()
+        if len(queries) == 1:
+            return queries[0]
+
+        operation = Q.AND if filter_.and_op else Q.OR
+        return RegexQCombination(operation=operation, children=queries)
+
     @classmethod
     def get_list_field_query(cls, field: str, data: Sequence[Optional[str]]) -> RegexQ:
         """
@@ -461,15 +705,15 @@ class GetMixin(PropsMixin):
         if not isinstance(data, (list, tuple)):
             data = [data]
 
-        helper = cls.ListFieldBucketHelper(legacy=True)
-        global_op = helper.get_global_op(data)
-        actions = helper.get_actions(data)
+        helper = cls.NewListFieldBucketHelper(field, data=data, legacy=True)
+        global_op = helper.global_operator
+        actions = helper.actions
 
         mongoengine_field = field.replace(".", "__")
 
         queries = [
-            RegexQ(**{f"{mongoengine_field}__{action}": list(set(actions[action]))})
-            for action in filter(None, actions)
+            RegexQ(**{f"{mongoengine_field}__{action}": list(set(values))})
+            for action, values in actions.items()
         ]
 
         if not queries:
@@ -497,6 +741,8 @@ class GetMixin(PropsMixin):
     def validate_order_by(cls, parameters, search_text) -> Sequence:
         """
         Validate and extract order_by params as a list
+        If ordering is specified then make sure that id field is part of it
+        This guarantees the unique order when paging
         """
         order_by = parameters.get(cls._ordering_key)
         if not order_by:
@@ -509,6 +755,9 @@ class GetMixin(PropsMixin):
                 "text score cannot be used in order_by when search text is not used"
             )
 
+        if not any(id_field in order_by for id_field in ("id", "-id")):
+            order_by.append("id")
+
         return order_by
 
     @classmethod
@@ -525,7 +774,7 @@ class GetMixin(PropsMixin):
         if start is not None:
             return start, cls.validate_scroll_size(parameters)
 
-        max_page_size = config.get("services._mongo.max_page_size", 500)
+        max_page_size = mongo_conf.get("max_page_size", 500)
         page = parameters.get("page", default_page)
         if page is not None and page < 0:
             raise errors.bad_request.ValidationError("page must be >=0", field="page")
@@ -550,7 +799,7 @@ class GetMixin(PropsMixin):
 
     @classmethod
     def get_projection(cls, parameters, override_projection=None, **__):
-        """ Extract a projection list from the provided dictionary. Supports an override projection. """
+        """Extract a projection list from the provided dictionary. Supports an override projection."""
         if override_projection is not None:
             return override_projection
         if not parameters:
@@ -564,7 +813,8 @@ class GetMixin(PropsMixin):
         """Return include and exclude lists based on passed projection and class definition"""
         if projection:
             include, exclude = partition(
-                projection, key=lambda x: x[0] != ProjectionHelper.exclusion_prefix,
+                projection,
+                key=lambda x: x[0] != ProjectionHelper.exclusion_prefix,
             )
         else:
             include, exclude = [], []
@@ -648,6 +898,7 @@ class GetMixin(PropsMixin):
         allow_public=False,
         override_projection=None,
         expand_reference_ids=True,
+        projection_fields: dict = None,
         ret_params: dict = None,
     ):
         """
@@ -684,6 +935,7 @@ class GetMixin(PropsMixin):
             query=query,
             query_options=query_options,
             allow_public=allow_public,
+            projection_fields=projection_fields,
             ret_params=ret_params,
         )
 
@@ -701,9 +953,50 @@ class GetMixin(PropsMixin):
     @classmethod
     def _get_collation_override(cls, field: str) -> Optional[dict]:
         return first(
-            v for k, v in cls._field_collation_overrides.items() if field.startswith(k)
+            v
+            for k, v in cls._field_collation_overrides.items()
+            if field.startswith(k) or field.startswith(f"-{k}")
         )
 
+    @classmethod
+    def get_count(
+        cls: Union["GetMixin", Document],
+        company,
+        query_dict: dict = None,
+        query_options: QueryParameterOptions = None,
+        query: Q = None,
+        allow_public=False,
+    ) -> int:
+        _query = cls._get_combined_query(
+            company=company,
+            query_dict=query_dict,
+            query_options=query_options,
+            query=query,
+            allow_public=allow_public,
+        )
+        return cls.objects(_query).count()
+
+    @classmethod
+    def _get_combined_query(
+        cls,
+        company,
+        query_dict: dict = None,
+        query_options: QueryParameterOptions = None,
+        query: Q = None,
+        allow_public=False,
+    ) -> Q:
+        if query_dict is not None:
+            q = cls.prepare_query(
+                parameters=query_dict,
+                company=company,
+                parameters_options=query_options,
+                allow_public=allow_public,
+            )
+        else:
+            q = cls._prepare_perm_query(company, allow_public=allow_public)
+
+        return (q & query) if query else q
+
     @classmethod
     def get_many(
         cls,
@@ -715,6 +1008,7 @@ class GetMixin(PropsMixin):
         allow_public=False,
         override_projection: Collection[str] = None,
         return_dicts=True,
+        projection_fields: dict = None,
         ret_params: dict = None,
     ):
         """
@@ -749,16 +1043,13 @@ class GetMixin(PropsMixin):
                 if override_collation:
                     break
 
-        if query_dict is not None:
-            q = cls.prepare_query(
-                parameters=query_dict,
-                company=company,
-                parameters_options=query_options,
-                allow_public=allow_public,
-            )
-        else:
-            q = cls._prepare_perm_query(company, allow_public=allow_public)
-        _query = (q & query) if query else q
+        _query = cls._get_combined_query(
+            company=company,
+            query_dict=query_dict,
+            query_options=query_options,
+            query=query,
+            allow_public=allow_public,
+        )
 
         if return_dicts:
             data_getter = partial(
@@ -767,9 +1058,12 @@ class GetMixin(PropsMixin):
                 parameters=parameters,
                 override_projection=override_projection,
                 override_collation=override_collation,
+                projection_fields=projection_fields,
             )
             return cls.get_data_with_scroll_support(
-                query_dict=query_dict, data_getter=data_getter, ret_params=ret_params,
+                query_dict=query_dict,
+                data_getter=data_getter,
+                ret_params=ret_params,
             )
 
         return cls._get_many_no_company(
@@ -777,11 +1071,14 @@ class GetMixin(PropsMixin):
             parameters=parameters,
             override_projection=override_projection,
             override_collation=override_collation,
+            projection_fields=projection_fields,
         )
 
     @classmethod
     def get_many_public(
-        cls, query: Q = None, projection: Collection[str] = None,
+        cls,
+        query: Q = None,
+        projection: Collection[str] = None,
     ):
         """
         Fetch all public documents matching a provided query.
@@ -794,6 +1091,13 @@ class GetMixin(PropsMixin):
 
         return cls._get_many_no_company(query=_query, override_projection=projection)
 
+    @staticmethod
+    def _get_qs_with_ordering(qs: QuerySet, order_by: Sequence):
+        disk_use_setting = mongo_conf.get("allow_disk_use.sort", None)
+        if disk_use_setting is not None:
+            qs = qs.allow_disk_use(disk_use_setting)
+        return qs.order_by(*order_by)
+
     @classmethod
     def _get_many_no_company(
         cls: Union["GetMixin", Document],
@@ -801,6 +1105,7 @@ class GetMixin(PropsMixin):
         parameters=None,
         override_projection=None,
         override_collation=None,
+        projection_fields: dict = None,
     ):
         """
         Fetch all documents matching a provided query.
@@ -834,7 +1139,7 @@ class GetMixin(PropsMixin):
             qs = qs.search_text(search_text)
         if order_by:
             # add ordering
-            qs = qs.order_by(*order_by)
+            qs = cls._get_qs_with_ordering(qs, order_by)
 
         if include:
             # add projection
@@ -843,6 +1148,9 @@ class GetMixin(PropsMixin):
         if exclude:
             qs = qs.exclude(*exclude)
 
+        if projection_fields:
+            qs = qs.fields(**projection_fields)
+
         if start is not None and size:
             # add paging
             qs = qs.skip(start).limit(size)
@@ -884,6 +1192,7 @@ class GetMixin(PropsMixin):
         parameters: dict = None,
         override_projection: Collection[str] = None,
         override_collation: dict = None,
+        projection_fields: dict = None,
     ) -> Sequence[dict]:
         """
         Fetch all documents matching a provided query. For the first order by field
@@ -922,7 +1231,7 @@ class GetMixin(PropsMixin):
             res = cls._get_queries_for_order_field(query, order_field)
             if res:
                 query_sets = [cls.objects(q) for q in res]
-            query_sets = [qs.order_by(*order_by) for qs in query_sets]
+            query_sets = [cls._get_qs_with_ordering(qs, order_by) for qs in query_sets]
             if order_field and not override_collation:
                 override_collation = cls._get_collation_override(order_field)
 
@@ -941,8 +1250,15 @@ class GetMixin(PropsMixin):
         if exclude:
             query_sets = [qs.exclude(*exclude) for qs in query_sets]
 
+        if projection_fields:
+            query_sets = [qs.fields(**projection_fields) for qs in query_sets]
+
         if start is None or not size:
-            return [obj.to_proper_dict(only=include) for qs in query_sets for obj in qs]
+            return [
+                obj.to_proper_dict(only=include, exclude=exclude)
+                for qs in query_sets
+                for obj in qs
+            ]
 
         # add paging
         ret = []
@@ -950,7 +1266,7 @@ class GetMixin(PropsMixin):
         for i, qs in enumerate(query_sets):
             last_size = len(ret)
             ret.extend(
-                obj.to_proper_dict(only=include)
+                obj.to_proper_dict(only=include, exclude=exclude)
                 for obj in (qs.skip(start) if start else qs).limit(size)
             )
             added = len(ret) - last_size
@@ -980,21 +1296,6 @@ class GetMixin(PropsMixin):
             )
         return result
 
-    @classmethod
-    def get_many_for_writing(cls, company, *args, **kwargs):
-        result = cls.get_many(
-            company=company,
-            *args,
-            **dict(return_dicts=False, **kwargs),
-            allow_public=True,
-        )
-        forbidden_objects = {obj.id for obj in result if not obj.company}
-        if forbidden_objects:
-            object_name = cls.__name__.lower()
-            raise errors.forbidden.NoWritePermission(
-                f"cannot modify public {object_name}(s), ids={tuple(forbidden_objects)}"
-            )
-        return result
 
 
 class UpdateMixin(object):
@@ -1055,7 +1356,7 @@ class UpdateMixin(object):
 
 
 class DbModelMixin(GetMixin, ProperDictMixin, UpdateMixin):
-    """ Provide convenience methods for a subclass of mongoengine.Document """
+    """Provide convenience methods for a subclass of mongoengine.Document"""
 
     @classmethod
     def aggregate(
@@ -1075,7 +1376,7 @@ class DbModelMixin(GetMixin, ProperDictMixin, UpdateMixin):
         kwargs.update(
             allowDiskUse=allow_disk_use
             if allow_disk_use is not None
-            else config.get("apiserver.mongo.aggregate.allow_disk_use", True)
+            else mongo_conf.get("allow_disk_use.aggregate", True)
         )
         return cls.objects.aggregate(pipeline, **kwargs)
 
@@ -1083,25 +1384,31 @@ class DbModelMixin(GetMixin, ProperDictMixin, UpdateMixin):
     def set_public(
         cls: Type[Document],
         company_id: str,
+        user_id: str,
         ids: Sequence[str],
         invalid_cls: Type[BaseError],
         enabled: bool = True,
     ):
         if enabled:
             items = list(cls.objects(id__in=ids, company=company_id).only("id"))
-            update = dict(set__company_origin=company_id, set__company="")
+            update: dict = dict(set__company_origin=company_id, set__company="")
         else:
             items = list(
                 cls.objects(
                     id__in=ids, company__in=(None, ""), company_origin=company_id
                 ).only("id")
             )
-            update = dict(set__company=company_id, unset__company_origin=1)
+            update: dict = dict(set__company=company_id, unset__company_origin=1)
 
         if len(items) < len(ids):
             missing = tuple(set(ids).difference(i.id for i in items))
             raise invalid_cls(ids=missing)
 
+        if hasattr(cls, "last_change"):
+            update["set__last_change"] = datetime.utcnow()
+        if hasattr(cls, "last_changed_by"):
+            update["set__last_changed_by"] = user_id
+
         return {"updated": cls.objects(id__in=ids).update(**update)}
 
 

apiserver/database/model/model.py

@@ -3,6 +3,8 @@ from mongoengine import (
     DateTimeField,
     BooleanField,
     EmbeddedDocumentField,
+    IntField,
+    ListField,
 )
 
 from apiserver.database import Database, strict
@@ -17,12 +19,14 @@ from apiserver.database.model.base import GetMixin
 from apiserver.database.model.metadata import MetadataItem
 from apiserver.database.model.model_labels import ModelLabels
 from apiserver.database.model.project import Project
+from apiserver.database.model.task.metrics import MetricEvent
 from apiserver.database.model.task.task import Task
 
 
 class Model(AttributedDocument):
     _field_collation_overrides = {
         "metadata.": AttributedDocument._numeric_locale,
+        "last_metrics.": AttributedDocument._numeric_locale,
     }
 
     meta = {
@@ -36,6 +40,7 @@ class Model(AttributedDocument):
             ("company", "framework"),
             ("company", "name"),
             ("company", "user"),
+            ("company", "uri"),
             {
                 "name": "%s.model.main_text_index" % Database.backend,
                 "fields": ["$name", "$id", "$comment", "$parent", "$task", "$project"],
@@ -66,6 +71,7 @@ class Model(AttributedDocument):
             "parent",
             "metadata.*",
         ),
+        range_fields=("last_metrics.*", "last_iteration"),
         datetime_fields=("last_update",),
     )
 
@@ -84,6 +90,8 @@ class Model(AttributedDocument):
     labels = ModelLabels()
     ready = BooleanField(required=True)
     last_update = DateTimeField()
+    last_change = DateTimeField()
+    last_changed_by = StringField()
     ui_cache = SafeDictField(
         default=dict, user_set_allowed=True, exclude_by_default=True
     )
@@ -91,3 +99,9 @@ class Model(AttributedDocument):
     metadata = SafeMapField(
         field=EmbeddedDocumentField(MetadataItem), user_set_allowed=True
     )
+    last_iteration = IntField(default=0)
+    last_metrics = SafeMapField(field=SafeMapField(EmbeddedDocumentField(MetricEvent)))
+    unique_metrics = ListField(StringField(required=True), exclude_by_default=True)
+
+    def get_index_company(self) -> str:
+        return self.company or self.company_origin or ""

apiserver/database/model/project.py

@@ -9,7 +9,7 @@ from apiserver.database.model.base import GetMixin
 class Project(AttributedDocument):
 
     get_all_query_options = GetMixin.QueryParameterOptions(
-        pattern_fields=("name", "description"),
+        pattern_fields=("name", "basename", "description"),
         list_fields=("tags", "system_tags", "id", "parent", "path"),
         range_fields=("last_update",),
     )
@@ -21,6 +21,7 @@ class Project(AttributedDocument):
             "parent",
             "path",
             ("company", "name"),
+            ("company", "basename"),
             {
                 "name": "%s.project.main_text_index" % Database.backend,
                 "fields": ["$name", "$id", "$description"],
@@ -37,6 +38,7 @@ class Project(AttributedDocument):
         min_length=3,
         sparse=True,
     )
+    basename = StrippedStringField(required=True)
     description = StringField()
     created = DateTimeField(required=True)
     tags = SafeSortedListField(StringField(required=True))

apiserver/database/model/task/metrics.py

@@ -4,6 +4,7 @@ from mongoengine import (
     DynamicField,
     LongField,
     EmbeddedDocumentField,
+    IntField,
 )
 
 from apiserver.database.fields import SafeMapField
@@ -19,7 +20,9 @@ class MetricEvent(EmbeddedDocument):
     variant = StringField(required=True)
     value = DynamicField(required=True)
     min_value = DynamicField()  # for backwards compatibility reasons
+    min_value_iteration = IntField()
     max_value = DynamicField()  # for backwards compatibility reasons
+    max_value_iteration = IntField()
 
 
 class EventStats(EmbeddedDocument):

apiserver/database/model/task/task.py

@@ -19,6 +19,7 @@ from apiserver.database.fields import (
     SafeSortedListField,
     EmbeddedDocumentListField,
     NullableStringField,
+    NoneType,
 )
 from apiserver.database.model import AttributedDocument
 from apiserver.database.model.base import ProperDictMixin, GetMixin
@@ -89,7 +90,9 @@ class Artifact(EmbeddedDocument):
     content_size = LongField()
     timestamp = LongField()
     type_data = EmbeddedDocumentField(ArtifactTypeData)
-    display_data = SafeSortedListField(ListField(UnionField((int, float, str))))
+    display_data = SafeSortedListField(
+        ListField(UnionField((int, float, str, NoneType)))
+    )
 
 
 class ParamsItem(EmbeddedDocument, ProperDictMixin):
@@ -149,6 +152,7 @@ class TaskType(object):
     application = "application"
     monitor = "monitor"
     controller = "controller"
+    report = "report"
     optimizer = "optimizer"
     service = "service"
     qc = "qc"
@@ -175,6 +179,8 @@ class Task(AttributedDocument):
             "active_duration",
             "parent",
             "project",
+            "last_update",
+            "status_changed",
             "models.input.model",
             ("company", "name"),
             ("company", "user"),
@@ -193,6 +199,7 @@ class Task(AttributedDocument):
                     "$name",
                     "$id",
                     "$comment",
+                    "$report",
                     "$models.input.model",
                     "$models.output.model",
                     "$script.repository",
@@ -203,6 +210,7 @@ class Task(AttributedDocument):
                     "name": 10,
                     "id": 10,
                     "comment": 10,
+                    "report": 10,
                     "models.output.model": 2,
                     "models.input.model": 2,
                     "script.repository": 1,
@@ -222,10 +230,12 @@ class Task(AttributedDocument):
             "project",
             "parent",
             "hyperparams.*",
+            "execution.queue",
         ),
         range_fields=("started", "active_duration", "last_metrics.*", "last_iteration"),
         datetime_fields=("status_changed", "last_update"),
-        pattern_fields=("name", "comment"),
+        pattern_fields=("name", "comment", "report"),
+        fields=("runtime.*", "models.input.model"),
     )
 
     id = StringField(primary_key=True)
@@ -239,6 +249,8 @@ class Task(AttributedDocument):
     status_message = StringField(user_set_allowed=True)
     status_changed = DateTimeField()
     comment = StringField(user_set_allowed=True)
+    report = StringField()
+    report_assets = ListField(StringField())
     created = DateTimeField(required=True, user_set_allowed=True)
     started = DateTimeField()
     completed = DateTimeField()
@@ -257,9 +269,10 @@ class Task(AttributedDocument):
     last_change = DateTimeField()
     last_iteration = IntField(default=DEFAULT_LAST_ITERATION)
     last_metrics = SafeMapField(field=SafeMapField(EmbeddedDocumentField(MetricEvent)))
+    unique_metrics = ListField(StringField(required=True), exclude_by_default=True)
     metric_stats = SafeMapField(field=EmbeddedDocumentField(MetricEventStats))
     company_origin = StringField(exclude_by_default=True)
-    duration = IntField()  # task duration in seconds
+    duration = IntField()  # obsolete, do not use
     hyperparams = SafeMapField(field=SafeMapField(EmbeddedDocumentField(ParamsItem)))
     configuration = SafeMapField(field=EmbeddedDocumentField(ConfigurationItem))
     runtime = SafeDictField(default=dict)
@@ -268,6 +281,7 @@ class Task(AttributedDocument):
     enqueue_status = StringField(
         choices=get_options(TaskStatus), exclude_by_default=True
     )
+    last_changed_by = StringField()
 
     def get_index_company(self) -> str:
         """

apiserver/database/model/url_to_delete.py

@@ -0,0 +1,52 @@
+from enum import Enum
+
+from mongoengine import StringField, DateTimeField, IntField, EnumField
+
+from apiserver.database import Database, strict
+from apiserver.database.model import AttributedDocument
+
+
+class StorageType(str, Enum):
+    fileserver = "fileserver"
+    s3 = "s3"
+    azure = "azure"
+    gs = "gs"
+    unknown = "unknown"
+
+
+class FileType(str, Enum):
+    file = "file"
+    folder = "folder"
+
+
+class DeletionStatus(str, Enum):
+    created = "created"
+    retrying = "retrying"
+    failed = "failed"
+
+
+class UrlToDelete(AttributedDocument):
+    _field_collation_overrides = {
+        "url": AttributedDocument._numeric_locale,
+    }
+
+    meta = {
+        "db_alias": Database.backend,
+        "strict": strict,
+        "indexes": [
+            ("company", "user", "task"),
+            ("company", "storage_type", "url"),
+            ("status", "retry_count", "storage_type"),
+        ],
+    }
+
+    id = StringField(primary_key=True)
+    url = StringField(required=True, unique_with="company")
+    task = StringField(required=True)
+    created = DateTimeField(required=True)
+    storage_type = EnumField(StorageType, default=StorageType.unknown)
+    type = EnumField(FileType, default=FileType.file)
+    retry_count = IntField(default=0)
+    last_failure_time = DateTimeField()
+    last_failure_reason = StringField()
+    status = EnumField(DeletionStatus, default=DeletionStatus.created)

apiserver/database/model/user.py

@@ -1,4 +1,4 @@
-from mongoengine import Document, StringField, DynamicField
+from mongoengine import Document, StringField, DynamicField, DateTimeField
 
 from apiserver.database import Database, strict
 from apiserver.database.model import DbModelMixin
@@ -20,3 +20,4 @@ class User(DbModelMixin, Document):
     given_name = StringField(user_set_allowed=True)
     avatar = StringField()
     preferences = DynamicField(default="", exclude_by_default=True)
+    created = DateTimeField()

apiserver/database/projection.py

@@ -1,73 +1,16 @@
 import threading
 from concurrent.futures import ThreadPoolExecutor
 from itertools import groupby, chain
-from typing import Sequence, Dict, Callable, Tuple, Any, Type
+from typing import Sequence, Dict, Callable
 
-import dpath.path
+from boltons import iterutils
 
 from apiserver.apierrors import errors
+from apiserver.config_repo import config
 from apiserver.database.props import PropsMixin
 
 SEP = "."
-
-
-def project_dict(data, projection, separator=SEP):
-    """
-    Project partial data from a dictionary into a new dictionary
-    :param data: Input dictionary
-    :param projection: List of dictionary paths (each a string with field names separated using a separator)
-    :param separator: Separator (default is '.')
-    :return: A new dictionary containing only the projected parts from the original dictionary
-    """
-    assert isinstance(data, dict)
-    result = {}
-
-    def copy_path(path_parts, source, destination):
-        src, dst = source, destination
-        try:
-            for depth, path_part in enumerate(path_parts[:-1]):
-                src_part = src[path_part]
-                if isinstance(src_part, dict):
-                    src = src_part
-                    dst = dst.setdefault(path_part, {})
-                elif isinstance(src_part, (list, tuple)):
-                    if path_part not in dst:
-                        dst[path_part] = [{} for _ in range(len(src_part))]
-                    elif not isinstance(dst[path_part], (list, tuple)):
-                        raise TypeError(
-                            "Incompatible destination type %s for %s (list expected)"
-                            % (type(dst), separator.join(path_parts[: depth + 1]))
-                        )
-                    elif not len(dst[path_part]) == len(src_part):
-                        raise ValueError(
-                            "Destination list length differs from source length for %s"
-                            % separator.join(path_parts[: depth + 1])
-                        )
-
-                    dst[path_part] = [
-                        copy_path(path_parts[depth + 1 :], s, d)
-                        for s, d in zip(src_part, dst[path_part])
-                    ]
-
-                    return destination
-                else:
-                    raise TypeError(
-                        "Unsupported projection type %s for %s"
-                        % (type(src), separator.join(path_parts[: depth + 1]))
-                    )
-
-            last_part = path_parts[-1]
-            dst[last_part] = src[last_part]
-        except KeyError:
-            # Projection field not in source, no biggie.
-            pass
-        return destination
-
-    for projection_path in sorted(projection):
-        copy_path(
-            path_parts=projection_path.split(separator), source=data, destination=result
-        )
-    return result
+max_items_per_fetch = config.get("services._mongo.max_page_size", 500)
 
 
 class _ReferenceProxy(dict):
@@ -110,9 +53,6 @@ class ProjectionHelper(object):
         self._ref_projection = None
         self._proxy_manager = _ProxyManager()
 
-        # Cached dpath paths for each of the result documents
-        self._cached_results_paths: Dict[int, Sequence[Tuple[Any, Type]]] = {}
-
         self._parse_projection(projection)
 
     def _collect_projection_fields(self, doc_cls, projection):
@@ -275,25 +215,26 @@ class ProjectionHelper(object):
         norm_path = doc_cls.get_dpath_translated_path(path)
         globlist = norm_path.strip(SEP).split(SEP)
 
-        obj_paths = self._cached_results_paths.get(id(obj))
-        if obj_paths is None:
-            obj_paths = self._cached_results_paths[id(obj)] = list(
-                dpath.path.paths(obj, dirs=True, skip=True)
-            )
-
-        paths = [p for p in obj_paths if dpath.path.match(p, globlist)]
-
-        def search_and_replace(p: Sequence[Tuple[str, Type]]) -> Any:
+        def _search_and_replace(target: dict, p: Sequence[str]) -> Sequence[str]:
             parent = None
-            target = obj
-            for part in p:
-                parent = target
-                target = target[part[0]]
-            if parent and factory:
-                parent[p[-1][0]] = factory(target)
-            return target
+            for idx, part in enumerate(p):
+                if isinstance(target, dict) and part in target:
+                    parent = target
+                    target = target[part]
+                elif isinstance(target, list) and part == "*":
+                    return list(
+                        chain.from_iterable(
+                            _search_and_replace(t, p[idx + 1 :]) for t in target
+                        )
+                    )
+                else:
+                    return []
 
-        return [search_and_replace(p) for p in paths]
+            if parent and factory:
+                parent[p[-1]] = factory(target)
+            return [target]
+
+        return _search_and_replace(obj, globlist)
 
     def project(self, results, projection_func):
         """
@@ -341,10 +282,11 @@ class ProjectionHelper(object):
                     doc_only = list(filter(None, data["only"]))
                     doc_only = list({"id"} | set(doc_only)) if doc_only else None
 
-                    for res in projection_func(
-                        doc_type=doc_type, projection=doc_only, ids=ids
-                    ):
-                        self._proxy_manager.update(res)
+                    for ids_chunk in iterutils.chunked_iter(ids, max_items_per_fetch):
+                        for res in projection_func(
+                            doc_type=doc_type, projection=doc_only, ids=ids_chunk
+                        ):
+                            self._proxy_manager.update(res)
 
                 if len(ref_projection) == 1:
                     do_projection(items[0])

apiserver/database/utils.py

@@ -1,6 +1,6 @@
 import hashlib
 from inspect import ismethod, getmembers
-from typing import Sequence, Tuple, Set, Optional, Callable, Any
+from typing import Sequence, Tuple, Set, Optional, Callable, Any, Mapping
 from uuid import uuid4
 
 from mongoengine import EmbeddedDocumentField, ListField, Document, Q
@@ -203,18 +203,22 @@ def _names_set(*names: str) -> Set[str]:
     return set(names) | set(f"-{name}" for name in names)
 
 
-system_tag_names = {
+_system_tag_names = {
     "model": _names_set("active", "archived"),
     "project": _names_set("archived", "public", "default"),
     "task": _names_set("active", "archived", "development"),
     "queue": _names_set("default"),
 }
 
-system_tag_prefixes = {"task": _names_set("annotat")}
+_system_tag_prefixes = {"task": _names_set("annotat")}
 
 
 def partition_tags(
-    entity: str, tags: Sequence[str], system_tags: Optional[Sequence[str]] = ()
+    entity: str,
+    tags: Sequence[str],
+    system_tags: Optional[Sequence[str]] = (),
+    system_tag_names: Mapping = _system_tag_names,
+    system_tag_prefixes: Mapping = _system_tag_prefixes,
 ) -> Tuple[Sequence[str], Sequence[str]]:
     """
     Partition the given tags sequence into system and user-defined tags

apiserver/documentation/api_versions.md

@@ -0,0 +1,19 @@
+### Supported api versions
+
+| Release | ApiVersion |
+|---------|------------|
+| v1.13   | 2.27       |
+| v1.12   | 2.26       |
+| v1.11   | 2.25       |
+| v1.10   | 2.24       |
+| v1.9    | 2.23       |
+| v1.8    | 2.22       |
+| v1.7    | 2.21       |
+| v1.6    | 2.20       |
+| v1.5    | 2.19       |
+| v1.4    | 2.18       |
+| v1.3    | 2.17       |
+| v1.2    | 2.16       |
+| v1.1    | 2.15       |
+| v1.0    | 2.14       |
+| v0.17   | 2.13       |

apiserver/elastic/apply_mappings.py

@@ -21,7 +21,7 @@ def apply_mappings_to_cluster(
         with f.open() as json_data:
             data = json.load(json_data)
             template_name = f.stem
-            res = es.indices.put_template(template_name, body=data)
+            res = es.indices.put_template(name=template_name, body=data)
             return {"mapping": template_name, "result": res}
 
     p = HERE / "mappings"

apiserver/elastic/initialize.py

@@ -85,7 +85,7 @@ def check_elastic_empty() -> bool:
                 es = Elasticsearch(
                     hosts=cluster_conf.get("hosts", None),
                     http_auth=es_factory.get_credentials("events", cluster_conf),
-                    **cluster_conf.get("args", {})
+                    **cluster_conf.get("args", {}),
                 )
                 return not es.indices.get_template(name="events*")
             except exceptions.NotFoundError as ex:
@@ -115,5 +115,7 @@ def init_es_data():
         args = cluster_conf.get("args", {})
         http_auth = es_factory.get_credentials(name)
 
-        res = apply_mappings_to_cluster(hosts_config, name, es_args=args, http_auth=http_auth)
+        res = apply_mappings_to_cluster(
+            hosts_config, name, es_args=args, http_auth=http_auth
+        )
         log.info(res)

apiserver/elastic/mappings/events/events.json

@@ -1,8 +1,8 @@
 {
   "index_patterns": "events-*",
   "settings": {
-    "number_of_shards": 1,
-    "number_of_replicas": 0
+    "number_of_replicas": 0,
+    "number_of_shards": 1
   },
   "mappings": {
     "_source": {
@@ -35,6 +35,12 @@
       },
       "value": {
         "type": "float"
+      },
+      "company_id": {
+        "type": "keyword"
+      },
+      "model_event": {
+        "type": "boolean"
       }
     }
   }

apiserver/elastic/mappings/workers/queue_metrics.json

@@ -1,8 +1,8 @@
 {
   "index_patterns": "queue_metrics_*",
   "settings": {
-    "number_of_shards": 1,
-    "number_of_replicas": 0
+    "number_of_replicas": 0,
+    "number_of_shards": 1
   },
   "mappings": {
     "_source": {
@@ -20,6 +20,9 @@
       },
       "queue_length": {
         "type": "integer"
+      },
+      "company_id": {
+        "type": "keyword"
       }
     }
   }

apiserver/elastic/mappings/workers/worker_stats.json

@@ -1,8 +1,8 @@
 {
   "index_patterns": "worker_stats_*",
   "settings": {
-    "number_of_shards": 1,
-    "number_of_replicas": 0
+    "number_of_replicas": 0,
+    "number_of_shards": 1
   },
   "mappings": {
     "_source": {
@@ -32,6 +32,9 @@
       },
       "task": {
         "type": "keyword"
+      },
+      "company_id": {
+        "type": "keyword"
       }
     }
   }

apiserver/es_factory.py

@@ -67,7 +67,7 @@ class MissingPasswordForElasticUser(Exception):
 
 class ESFactory:
     @classmethod
-    def connect(cls, cluster_name):
+    def connect(cls, cluster_name) -> Elasticsearch:
         """
         Returns the es client for the cluster.
         Connects to the cluster if did not connect previously

apiserver/jobs/async_urls_delete.py

@@ -0,0 +1,612 @@
+import os
+from abc import ABC, ABCMeta, abstractmethod
+from argparse import ArgumentParser
+from collections import defaultdict
+from datetime import datetime, timedelta
+from functools import partial
+from itertools import chain
+from pathlib import Path
+from time import sleep
+from typing import Sequence, Optional, Tuple, Mapping, TypeVar, Hashable, Generic
+from urllib.parse import urlparse
+
+import boto3
+import requests
+from azure.storage.blob import ContainerClient, PartialBatchErrorException
+from boltons.iterutils import bucketize, chunked_iter
+from furl import furl
+from google.cloud import storage as google_storage
+from mongoengine import Q
+from mypy_boto3_s3.service_resource import Bucket as AWSBucket
+
+from apiserver.bll.storage import StorageBLL
+from apiserver.config_repo import config
+from apiserver.database import db
+from apiserver.database.model.url_to_delete import UrlToDelete, StorageType, DeletionStatus
+
+log = config.logger(f"JOB-{Path(__file__).name}")
+conf = config.get("services.async_urls_delete")
+max_retries = conf.get("max_retries", 3)
+retry_timeout = timedelta(seconds=conf.get("retry_timeout_sec", 60))
+storage_bll = StorageBLL()
+
+
+def mark_retry_failed(ids: Sequence[str], reason: str):
+    UrlToDelete.objects(id__in=ids).update(
+        last_failure_time=datetime.utcnow(),
+        last_failure_reason=reason,
+        inc__retry_count=1,
+    )
+    UrlToDelete.objects(id__in=ids, retry_count__gte=max_retries).update(
+        status=DeletionStatus.failed
+    )
+
+
+def mark_failed(query: Q, reason: str):
+    UrlToDelete.objects(query).update(
+        status=DeletionStatus.failed,
+        last_failure_time=datetime.utcnow(),
+        last_failure_reason=reason,
+    )
+
+
+def scheme_prefix(scheme: str) -> str:
+    return str(furl(scheme=scheme, netloc=""))
+
+
+T = TypeVar("T", bound=Hashable)
+
+
+class Storage(Generic[T], metaclass=ABCMeta):
+    class Client(ABC):
+        @property
+        @abstractmethod
+        def chunk_size(self) -> int:
+            pass
+
+        def get_path(self, url: UrlToDelete) -> str:
+            pass
+
+        def delete_many(
+            self, paths: Sequence[str]
+        ) -> Tuple[Sequence[str], Mapping[str, Sequence[str]]]:
+            pass
+
+    @property
+    @abstractmethod
+    def name(self) -> str:
+        pass
+
+    def group_urls(
+        self, urls: Sequence[UrlToDelete]
+    ) -> Mapping[T, Sequence[UrlToDelete]]:
+        pass
+
+    def get_client(self, base: T, urls: Sequence[UrlToDelete]) -> Client:
+        pass
+
+
+def delete_urls(urls_query: Q, storage: Storage):
+    to_delete = list(UrlToDelete.objects(urls_query).order_by("url").limit(10000))
+    if not to_delete:
+        return
+
+    grouped_urls = storage.group_urls(to_delete)
+    for base, urls in grouped_urls.items():
+        if not base:
+            msg = f"Invalid {storage.name} url or missing {storage.name} configuration for account"
+            mark_failed(
+                Q(id__in=[url.id for url in urls]), msg,
+            )
+            log.warning(
+                f"Failed to delete {len(urls)} files from {storage.name} due to: {msg}"
+            )
+            continue
+
+        try:
+            client = storage.get_client(base, urls)
+        except Exception as ex:
+            failed = [url.id for url in urls]
+            mark_retry_failed(failed, reason=str(ex))
+            log.warning(
+                f"Failed to delete {len(failed)} files from {storage.name} due to: {str(ex)}"
+            )
+            continue
+
+        for chunk in chunked_iter(urls, client.chunk_size):
+            paths = []
+            path_to_id_mapping = defaultdict(list)
+            ids_to_delete = set()
+            for url in chunk:
+                try:
+                    path = client.get_path(url)
+                except Exception as ex:
+                    err = str(ex)
+                    mark_failed(Q(id=url.id), err)
+                    log.warning(f"Error getting path for {url.url}: {err}")
+                    continue
+
+                paths.append(path)
+                path_to_id_mapping[path].append(url.id)
+                ids_to_delete.add(url.id)
+
+            if not paths:
+                continue
+
+            try:
+                deleted_paths, errors = client.delete_many(paths)
+            except Exception as ex:
+                mark_retry_failed([url.id for url in urls], str(ex))
+                log.warning(
+                    f"Error deleting {len(paths)} files from {storage.name}: {str(ex)}"
+                )
+                continue
+
+            failed_ids = set()
+            for reason, err_paths in errors.items():
+                error_ids = set(
+                    chain.from_iterable(
+                        path_to_id_mapping.get(p, []) for p in err_paths
+                    )
+                )
+                mark_retry_failed(list(error_ids), reason)
+                log.warning(
+                    f"Failed to delete {len(error_ids)} files from {storage.name} storage due to: {reason}"
+                )
+                failed_ids.update(error_ids)
+
+            deleted_ids = set(
+                chain.from_iterable(
+                    path_to_id_mapping.get(p, []) for p in deleted_paths
+                )
+            )
+            if deleted_ids:
+                UrlToDelete.objects(id__in=list(deleted_ids)).delete()
+                log.info(
+                    f"{len(deleted_ids)} files deleted from {storage.name} storage"
+                )
+
+            missing_ids = ids_to_delete - deleted_ids - failed_ids
+            if missing_ids:
+                mark_retry_failed(list(missing_ids), "Not succeeded")
+
+
+class FileserverStorage(Storage):
+    class Client(Storage.Client):
+        timeout = conf.get("fileserver.timeout_sec", 300)
+
+        def __init__(self, session: requests.Session, host: str):
+            self.session = session
+            self.delete_url = furl(host).add(path="delete_many").url
+
+        @property
+        def chunk_size(self) -> int:
+            return 10000
+
+        def get_path(self, url: UrlToDelete) -> str:
+            path = url.url.strip("/")
+            if not path:
+                raise ValueError("Empty path")
+
+            return path
+
+        def delete_many(
+            self, paths: Sequence[str]
+        ) -> Tuple[Sequence[str], Mapping[str, Sequence[str]]]:
+            res = self.session.post(
+                url=self.delete_url, json={"files": list(paths)}, timeout=self.timeout
+            )
+            res.raise_for_status()
+            res_data = res.json()
+            return list(res_data.get("deleted", {})), res_data.get("errors", {})
+
+    def __init__(self, company: str, fileserver_host: str = None):
+        fileserver_host = fileserver_host or config.get("hosts.fileserver", None)
+        self.host = fileserver_host.rstrip("/")
+        if not self.host:
+            log.warning(f"Fileserver host not configured")
+
+        def _parse_url_prefix(prefix) -> Tuple[str, str]:
+            url = furl(prefix)
+            host = f"{url.scheme}://{url.netloc}" if url.scheme else None
+            return host, str(url.path).rstrip("/")
+
+        url_prefixes = [
+            _parse_url_prefix(p) for p in conf.get("fileserver.url_prefixes", [])
+        ]
+        if not any(self.host == host for host, _ in url_prefixes):
+            url_prefixes.append((self.host, ""))
+        self.url_prefixes = url_prefixes
+
+        self.company = company
+
+    # @classmethod
+    # def validate_fileserver_access(cls, fileserver_host: str):
+    #     res = requests.get(
+    #         url=fileserver_host
+    #     )
+    #     res.raise_for_status()
+
+    @property
+    def name(self) -> str:
+        return "Fileserver"
+
+    def _resolve_base_url(self, url: UrlToDelete) -> Optional[str]:
+        """
+        For the url return the base_url containing schema, optional host and bucket name
+        """
+        if not url.url:
+            return None
+
+        try:
+            parsed = furl(url.url)
+            url_host = f"{parsed.scheme}://{parsed.netloc}" if parsed.scheme else None
+            url_path = str(parsed.path)
+        except Exception:
+            return None
+
+        for host, path_prefix in self.url_prefixes:
+            if host and url_host != host:
+                continue
+            if path_prefix and not url_path.startswith(path_prefix + "/"):
+                continue
+            url.url = url_path[len(path_prefix or "") :]
+            return self.host
+
+    def group_urls(
+        self, urls: Sequence[UrlToDelete]
+    ) -> Mapping[str, Sequence[UrlToDelete]]:
+        return bucketize(urls, key=self._resolve_base_url)
+
+    def get_client(self, base: str, urls: Sequence[UrlToDelete]) -> Client:
+        host = base
+        session = requests.session()
+        res = session.get(url=host, timeout=self.Client.timeout)
+        res.raise_for_status()
+
+        return self.Client(session, host)
+
+
+class AzureStorage(Storage):
+    class Client(Storage.Client):
+        def __init__(self, container: ContainerClient):
+            self.container = container
+
+        @property
+        def chunk_size(self) -> int:
+            return 256
+
+        def get_path(self, url: UrlToDelete) -> str:
+            parsed = furl(url.url)
+            if (
+                not parsed.path
+                or not parsed.path.segments
+                or len(parsed.path.segments) <= 1
+            ):
+                raise ValueError("No path found following container name")
+
+            return os.path.join(*parsed.path.segments[1:])
+
+        @staticmethod
+        def _path_from_request_url(request_url: str) -> str:
+            try:
+                return furl(request_url).path.segments[-1]
+            except Exception:
+                return request_url
+
+        def delete_many(
+            self, paths: Sequence[str]
+        ) -> Tuple[Sequence[str], Mapping[str, Sequence[str]]]:
+            try:
+                res = self.container.delete_blobs(*paths)
+            except PartialBatchErrorException as pex:
+                deleted = []
+                errors = defaultdict(list)
+                for part in pex.parts:
+                    if 300 >= part.status_code >= 200:
+                        deleted.append(self._path_from_request_url(part.request.url))
+                    else:
+                        errors[part.reason].append(
+                            self._path_from_request_url(part.request.url)
+                        )
+                return deleted, errors
+
+            return [self._path_from_request_url(part.request.url) for part in res], {}
+
+    def __init__(self, company: str):
+        self.configs = storage_bll.get_azure_settings_for_company(company)
+        self.scheme = "azure"
+
+    @property
+    def name(self) -> str:
+        return "Azure"
+
+    def _resolve_base_url(self, url: UrlToDelete) -> Optional[Tuple]:
+        """
+        For the url return the base_url containing schema, optional host and bucket name
+        """
+        try:
+            parsed = urlparse(url.url)
+            if parsed.scheme != self.scheme:
+                return None
+
+            azure_conf = self.configs.get_config_by_uri(url.url)
+            if azure_conf is None:
+                return None
+
+            account_url = parsed.netloc
+            return account_url, azure_conf.container_name
+        except Exception as ex:
+            log.warning(f"Error resolving base url for {url.url}: " + str(ex))
+            return None
+
+    def group_urls(
+        self, urls: Sequence[UrlToDelete]
+    ) -> Mapping[Tuple, Sequence[UrlToDelete]]:
+        return bucketize(urls, key=self._resolve_base_url)
+
+    def get_client(self, base: Tuple, urls: Sequence[UrlToDelete]) -> Client:
+        account_url, container_name = base
+        sample_url = urls[0].url
+        cfg = self.configs.get_config_by_uri(sample_url)
+        if not cfg or not cfg.account_name or not cfg.account_key:
+            raise ValueError(
+                f"Missing account name or key for Azure Blob Storage "
+                f"account: {account_url}, container: {container_name}"
+            )
+
+        return self.Client(
+            ContainerClient(
+                account_url=account_url,
+                container_name=cfg.container_name,
+                credential={
+                    "account_name": cfg.account_name,
+                    "account_key": cfg.account_key,
+                },
+            )
+        )
+
+
+class AWSStorage(Storage):
+    class Client(Storage.Client):
+        def __init__(self, base_url: str, container: AWSBucket):
+            self.container = container
+            self.base_url = base_url
+
+        @property
+        def chunk_size(self) -> int:
+            return 1000
+
+        def get_path(self, url: UrlToDelete) -> str:
+            """ Normalize remote path. Remove any prefix that is already handled by the container """
+            path = url.url
+            if path.startswith(self.base_url):
+                path = path[len(self.base_url) :]
+            path = path.lstrip("/")
+            return path
+
+        @staticmethod
+        def _path_from_request_url(request_url: str) -> str:
+            try:
+                return furl(request_url).path.segments[-1]
+            except Exception:
+                return request_url
+
+        def delete_many(
+            self, paths: Sequence[str]
+        ) -> Tuple[Sequence[str], Mapping[str, Sequence[str]]]:
+            res = self.container.delete_objects(
+                Delete={"Objects": [{"Key": p} for p in paths]}
+            )
+            errors = defaultdict(list)
+            for err in res.get("Errors", []):
+                msg = err.get("Message", "")
+                errors[msg].append(err.get("Key"))
+
+            return [d.get("Key") for d in res.get("Deleted", [])], errors
+
+    def __init__(self, company: str):
+        self.configs = storage_bll.get_aws_settings_for_company(company)
+        self.scheme = "s3"
+
+    @property
+    def name(self) -> str:
+        return "AWS"
+
+    def _resolve_base_url(self, url: UrlToDelete) -> Optional[str]:
+        """
+        For the url return the base_url containing schema, optional host and bucket name
+        """
+        try:
+            parsed = urlparse(url.url)
+            if parsed.scheme != self.scheme:
+                return None
+
+            s3_conf = self.configs.get_config_by_uri(url.url)
+            if s3_conf is None:
+                return None
+
+            s3_bucket = s3_conf.bucket
+            if not s3_bucket:
+                parts = Path(parsed.path.strip("/")).parts
+                if parts:
+                    s3_bucket = parts[0]
+            return "/".join(filter(None, ("s3:/", s3_conf.host, s3_bucket)))
+        except Exception as ex:
+            log.warning(f"Error resolving base url for {url.url}: " + str(ex))
+            return None
+
+    def group_urls(
+        self, urls: Sequence[UrlToDelete]
+    ) -> Mapping[str, Sequence[UrlToDelete]]:
+        return bucketize(urls, key=self._resolve_base_url)
+
+    def get_client(self, base: str, urls: Sequence[UrlToDelete]) -> Client:
+        sample_url = urls[0].url
+        cfg = self.configs.get_config_by_uri(sample_url)
+        boto_kwargs = {
+            "endpoint_url": (("https://" if cfg.secure else "http://") + cfg.host)
+            if cfg.host
+            else None,
+            "use_ssl": cfg.secure,
+            "verify": cfg.verify,
+            "region_name": cfg.region or None,
+        }
+        name = base[len(scheme_prefix(self.scheme)) :]
+        bucket_name = name[len(cfg.host) + 1 :] if cfg.host else name
+        if not cfg.use_credentials_chain:
+            if not cfg.key or not cfg.secret:
+                raise ValueError(
+                    f"Missing key or secret for AWS S3 host: {cfg.host}, bucket: {str(bucket_name)}"
+                )
+
+            boto_kwargs["aws_access_key_id"] = cfg.key
+            boto_kwargs["aws_secret_access_key"] = cfg.secret
+            if cfg.token:
+                boto_kwargs["aws_session_token"] = cfg.token
+
+        return self.Client(
+            base, boto3.resource("s3", **boto_kwargs).Bucket(bucket_name)
+        )
+
+
+class GoogleCloudStorage(Storage):
+    class Client(Storage.Client):
+        def __init__(self, base_url: str, container: google_storage.Bucket):
+            self.container = container
+            self.base_url = base_url
+
+        @property
+        def chunk_size(self) -> int:
+            return 100
+
+        def get_path(self, url: UrlToDelete) -> str:
+            """ Normalize remote path. Remove any prefix that is already handled by the container """
+            path = url.url
+            if path.startswith(self.base_url):
+                path = path[len(self.base_url) :]
+            path = path.lstrip("/")
+            return path
+
+        def delete_many(
+            self, paths: Sequence[str]
+        ) -> Tuple[Sequence[str], Mapping[str, Sequence[str]]]:
+            not_found = set()
+
+            def error_callback(blob: google_storage.Blob):
+                not_found.add(blob.name)
+
+            self.container.delete_blobs(
+                [self.container.blob(p) for p in paths], on_error=error_callback,
+            )
+            errors = {"Not found": list(not_found)} if not_found else {}
+            return list(set(paths) - not_found), errors
+
+    def __init__(self, company: str):
+        self.configs = storage_bll.get_gs_settings_for_company(company)
+        self.scheme = "gs"
+
+    @property
+    def name(self) -> str:
+        return "Google Storage"
+
+    def _resolve_base_url(self, url: UrlToDelete) -> Optional[str]:
+        """
+        For the url return the base_url containing schema, optional host and bucket name
+        """
+        try:
+            parsed = urlparse(url.url)
+            if parsed.scheme != self.scheme:
+                return None
+
+            gs_conf = self.configs.get_config_by_uri(url.url)
+            if gs_conf is None:
+                return None
+
+            return str(furl(scheme=parsed.scheme, netloc=gs_conf.bucket))
+        except Exception as ex:
+            log.warning(f"Error resolving base url for {url.url}: " + str(ex))
+            return None
+
+    def group_urls(
+        self, urls: Sequence[UrlToDelete]
+    ) -> Mapping[str, Sequence[UrlToDelete]]:
+        return bucketize(urls, key=self._resolve_base_url)
+
+    def get_client(self, base: str, urls: Sequence[UrlToDelete]) -> Client:
+        sample_url = urls[0].url
+        cfg = self.configs.get_config_by_uri(sample_url)
+        if cfg.credentials_json:
+            from google.oauth2 import service_account
+
+            credentials = service_account.Credentials.from_service_account_file(
+                cfg.credentials_json
+            )
+        else:
+            credentials = None
+
+        bucket_name = base[len(scheme_prefix(self.scheme)) :]
+        return self.Client(
+            base,
+            google_storage.Client(project=cfg.project, credentials=credentials).bucket(
+                bucket_name
+            ),
+        )
+
+
+def run_delete_loop(fileserver_host: str):
+    storage_helpers = {
+        StorageType.fileserver: partial(
+            FileserverStorage, fileserver_host=fileserver_host
+        ),
+        StorageType.s3: AWSStorage,
+        StorageType.azure: AzureStorage,
+        StorageType.gs: GoogleCloudStorage,
+    }
+    while True:
+        now = datetime.utcnow()
+        urls_query = (
+            Q(status__ne=DeletionStatus.failed)
+            & Q(retry_count__lt=max_retries)
+            & (
+                Q(last_failure_time__exists=False)
+                | Q(last_failure_time__lt=now - retry_timeout)
+            )
+        )
+
+        url_to_delete: UrlToDelete = UrlToDelete.objects(
+            urls_query & Q(storage_type__in=list(storage_helpers))
+        ).order_by("retry_count").limit(1).first()
+        if not url_to_delete:
+            sleep(10)
+            continue
+
+        company = url_to_delete.company
+        user = url_to_delete.user
+        storage_type = url_to_delete.storage_type
+        log.info(
+            f"Deleting {storage_type} objects for company: {company}, user: {user}"
+        )
+        company_storage_urls_query = urls_query & Q(
+            company=company, storage_type=storage_type,
+        )
+        delete_urls(
+            urls_query=company_storage_urls_query,
+            storage=storage_helpers[storage_type](company=company),
+        )
+
+
+def main():
+    parser = ArgumentParser(description=__doc__)
+
+    parser.add_argument(
+        "--fileserver-host", "-fh", help="Fileserver host address", type=str,
+    )
+    args = parser.parse_args()
+
+    db.initialize()
+    run_delete_loop(args.fileserver_host)
+
+
+if __name__ == "__main__":
+    main()

apiserver/mongo/initialize/migration.py

@@ -1,8 +1,10 @@
 import importlib.util
 from datetime import datetime
+from inspect import signature
 from logging import Logger
 from pathlib import Path
 
+import pymongo.database
 from mongoengine.connection import get_db
 from packaging.version import Version, parse
 
@@ -16,9 +18,15 @@ _migration_dir = _parent_dir / _migrations
 
 
 def check_mongo_empty() -> bool:
-    return not all(
-        get_db(alias).collection_names() for alias in utils.get_options(Database)
-    )
+    for alias in utils.get_options(Database):
+        collection_names = get_db(alias).list_collection_names()
+        if collection_names and any(
+            name in collection_names
+            for name in ["company", "user", "versions"]
+        ):
+            return False
+
+    return True
 
 
 def get_last_server_version() -> Version:
@@ -80,8 +88,15 @@ def _apply_migrations(log: Logger):
                 if not func:
                     continue
                 try:
+                    sig = signature(func)
+                    kwargs = {}
+                    if len(sig.parameters) == 2:
+                        name, param = list(sig.parameters.items())[-1]
+                        key = name.replace("_", "-")
+                        if issubclass(param.annotation, pymongo.database.Database) and key in dbs:
+                            kwargs[name] = get_db(key)
                     log.info(f"Applying {script.stem}/{func_name}()")
-                    func(get_db(alias))
+                    func(get_db(alias), **kwargs)
                 except Exception:
                     log.exception(f"Failed applying {script}:{func_name}()")
                     raise ValueError(

apiserver/mongo/initialize/pre_populate.py

@@ -24,6 +24,7 @@ from typing import (
     Callable,
 )
 from urllib.parse import unquote, urlparse
+from uuid import uuid4, UUID, uuid5
 from zipfile import ZipFile, ZIP_BZIP2
 
 import mongoengine
@@ -43,6 +44,7 @@ from apiserver.bll.task.param_utils import (
 from apiserver.config_repo import config
 from apiserver.config.info import get_default_company
 from apiserver.database.model import EntityVisibility, User
+from apiserver.database.model.auth import Role, User as AuthUser
 from apiserver.database.model.model import Model
 from apiserver.database.model.project import Project
 from apiserver.database.model.task.task import (
@@ -53,6 +55,7 @@ from apiserver.database.model.task.task import (
     TaskModelNames,
 )
 from apiserver.database.utils import get_options
+from apiserver.service_repo.auth import Identity
 from apiserver.utilities import json
 from apiserver.utilities.dicts import nested_get, nested_set, nested_delete
 from apiserver.utilities.parameter_key_escaper import ParameterKeyEscaper
@@ -65,16 +68,20 @@ class PrePopulate:
     export_tag_prefix = "Exported:"
     export_tag = f"{export_tag_prefix} %Y-%m-%d %H:%M:%S"
     metadata_filename = "metadata.json"
+    users_filename = "users.json"
     zip_args = dict(mode="w", compression=ZIP_BZIP2)
     artifacts_ext = ".artifacts"
     img_source_regex = re.compile(
         r"['\"]source['\"]:\s?['\"](https?://(?:localhost:8081|files.*?)/.*?)['\"]",
         flags=re.IGNORECASE,
     )
+    _name_guid_ns = UUID("bda3acc1-e612-506c-bade-80071b6cf039")
+    _example_id_prefix = "e-"
     task_cls: Type[Task]
     project_cls: Type[Project]
     model_cls: Type[Model]
     user_cls: Type[User]
+    auth_user_cls: Type[AuthUser]
 
     # noinspection PyTypeChecker
     @classmethod
@@ -87,6 +94,8 @@ class PrePopulate:
             cls.project_cls = cls._get_entity_type("database.model.project.Project")
         if not hasattr(cls, "user_cls"):
             cls.user_cls = cls._get_entity_type("database.model.User")
+        if not hasattr(cls, "auth_user_cls"):
+            cls.auth_user_cls = cls._get_entity_type("database.model.auth.User")
 
     class JsonLinesWriter:
         def __init__(self, file: BinaryIO):
@@ -202,6 +211,8 @@ class PrePopulate:
         task_statuses: Sequence[str] = None,
         tag_exported_entities: bool = False,
         metadata: Mapping[str, Any] = None,
+        export_events: bool = True,
+        export_users: bool = False,
     ) -> Sequence[str]:
         cls._init_entity_types()
 
@@ -237,11 +248,15 @@ class PrePopulate:
         with ZipFile(file, **cls.zip_args) as zfile:
             if metadata:
                 zfile.writestr(cls.metadata_filename, meta_str)
+            if export_users:
+                cls._export_users(zfile)
             artifacts = cls._export(
                 zfile,
                 entities=entities,
                 hash_=hash_,
                 tag_entities=tag_exported_entities,
+                export_events=export_events,
+                cleanup_users=not export_users,
             )
 
         file_with_hash = file.with_name(f"{file.stem}_{hash_.hexdigest()}{file.suffix}")
@@ -262,6 +277,9 @@ class PrePopulate:
             metadata_hash=metadata_hash,
         )
 
+        if created_files:
+            print("Created files:\n" + "\n".join(file for file in created_files))
+
         return created_files
 
     @classmethod
@@ -293,18 +311,26 @@ class PrePopulate:
             except Exception:
                 pass
 
-            if not user_id:
-                user_id, user_name = "__allegroai__", "Allegro.ai"
-
             # Make sure we won't end up with an invalid company ID
             if company_id is None:
                 company_id = ""
 
+            user_mapping = cls._import_users(zfile, company_id)
+
+            if not user_id:
+                user_id, user_name = "__allegroai__", "Allegro.ai"
+
             existing_user = cls.user_cls.objects(id=user_id).only("id").first()
             if not existing_user:
                 cls.user_cls(id=user_id, name=user_name, company=company_id).save()
 
-            cls._import(zfile, company_id, user_id, metadata)
+            cls._import(
+                zfile,
+                company_id=company_id,
+                user_id=user_id,
+                metadata=metadata,
+                user_mapping=user_mapping,
+            )
 
         if artifacts_path and os.path.isdir(artifacts_path):
             artifacts_file = Path(filename).with_suffix(cls.artifacts_ext)
@@ -435,7 +461,7 @@ class PrePopulate:
         projects: Sequence[str] = None,
         task_statuses: Sequence[str] = None,
     ) -> Dict[Type[mongoengine.Document], Set[mongoengine.Document]]:
-        entities = defaultdict(set)
+        entities: Dict[Any] = defaultdict(set)
 
         if projects:
             print("Reading projects...")
@@ -494,7 +520,6 @@ class PrePopulate:
     @classmethod
     def _cleanup_model(cls, model: Model):
         model.company = ""
-        model.user = ""
         model.tags = cls._filter_out_export_tags(model.tags)
 
     @classmethod
@@ -502,7 +527,6 @@ class PrePopulate:
         task.comment = "Auto generated by Allegro.ai"
         task.status_message = ""
         task.status_reason = ""
-        task.user = ""
         task.company = ""
         task.tags = cls._filter_out_export_tags(task.tags)
         if task.output:
@@ -510,17 +534,32 @@ class PrePopulate:
 
     @classmethod
     def _cleanup_project(cls, project: Project):
-        project.user = ""
         project.company = ""
         project.tags = cls._filter_out_export_tags(project.tags)
 
     @classmethod
-    def _cleanup_entity(cls, entity_cls, entity):
+    def _cleanup_auth_user(cls, user: AuthUser):
+        user.company = ""
+        for cred in user.credentials:
+            if getattr(cred, "company", None):
+                cred["company"] = ""
+        return user
+
+    @classmethod
+    def _cleanup_be_user(cls, user: User):
+        user.company = ""
+        user.preferences = None
+        return user
+
+    @classmethod
+    def _cleanup_entity(cls, entity_cls, entity, cleanup_users):
+        if cleanup_users:
+            entity.user = ""
         if entity_cls == cls.task_cls:
             cls._cleanup_task(entity)
         elif entity_cls == cls.model_cls:
             cls._cleanup_model(entity)
-        elif entity == cls.project_cls:
+        elif entity_cls == cls.project_cls:
             cls._cleanup_project(entity)
 
     @classmethod
@@ -630,6 +669,38 @@ class PrePopulate:
             else:
                 print(f"Artifact {full_path} not found")
 
+    @classmethod
+    def _export_users(cls, writer: ZipFile):
+        auth_users = {
+            user.id: cls._cleanup_auth_user(user)
+            for user in cls.auth_user_cls.objects(role__in=(Role.admin, Role.user))
+        }
+        if not auth_users:
+            return
+
+        be_users = {
+            user.id: cls._cleanup_be_user(user)
+            for user in cls.user_cls.objects(id__in=list(auth_users))
+        }
+        if not be_users:
+            return
+
+        auth_users = {uid: data for uid, data in auth_users.items() if uid in be_users}
+        print(f"Writing {len(auth_users)} users into {writer.filename}")
+        data = {}
+        for field, users in (("auth", auth_users), ("backend", be_users)):
+            with BytesIO() as f:
+                with cls.JsonLinesWriter(f) as w:
+                    for user in users.values():
+                        w.write(user.to_json())
+                data[field] = f.getvalue()
+
+        def get_field_bytes(k: str, v: bytes) -> bytes:
+            return f'"{k}": '.encode("utf-8") + v
+
+        data_str = b",\n".join(get_field_bytes(k, v) for k, v in data.items())
+        writer.writestr(cls.users_filename, b"{\n" + data_str + b"\n}")
+
     @classmethod
     def _get_base_filename(cls, cls_: type):
         name = f"{cls_.__module__}.{cls_.__name__}"
@@ -639,7 +710,13 @@ class PrePopulate:
 
     @classmethod
     def _export(
-        cls, writer: ZipFile, entities: dict, hash_, tag_entities: bool = False
+        cls,
+        writer: ZipFile,
+        entities: dict,
+        hash_,
+        tag_entities: bool = False,
+        export_events: bool = True,
+        cleanup_users: bool = True,
     ) -> Sequence[str]:
         """
         Export the requested experiments, projects and models and return the list of artifact files
@@ -653,18 +730,19 @@ class PrePopulate:
             if not items:
                 continue
             base_filename = cls._get_base_filename(cls_)
-            for item in items:
-                artifacts.extend(
-                    cls._export_entity_related_data(
-                        cls_, item, base_filename, writer, hash_
+            if export_events:
+                for item in items:
+                    artifacts.extend(
+                        cls._export_entity_related_data(
+                            cls_, item, base_filename, writer, hash_
+                        )
                     )
-                )
             filename = base_filename + ".json"
             print(f"Writing {len(items)} items into {writer.filename}:{filename}")
             with BytesIO() as f:
                 with cls.JsonLinesWriter(f) as w:
                     for item in items:
-                        cls._cleanup_entity(cls_, item)
+                        cls._cleanup_entity(cls_, item, cleanup_users=cleanup_users)
                         w.write(item.to_json())
                 data = f.getvalue()
                 hash_.update(data)
@@ -690,6 +768,123 @@ class PrePopulate:
                 continue
             yield clean
 
+    @staticmethod
+    def _new_id(_):
+        return str(uuid4()).replace("-", "")
+
+    @classmethod
+    def _hash_id(cls, name: str):
+        return str(uuid5(cls._name_guid_ns, name)).replace("-", "")
+
+    @classmethod
+    def _example_id(cls, orig_id: str):
+        if not orig_id or orig_id.startswith(cls._example_id_prefix):
+            return orig_id
+
+        return cls._example_id_prefix + orig_id
+
+    @classmethod
+    def _private_id(cls, orig_id: str):
+        if not orig_id or not orig_id.startswith(cls._example_id_prefix):
+            return orig_id
+
+        return orig_id[len(cls._example_id_prefix) :]
+
+    @classmethod
+    def _generate_new_ids(
+        cls,
+        reader: ZipFile,
+        entity_files: Sequence,
+        metadata: Mapping[str, Any],
+    ) -> Mapping[str, str]:
+        if not metadata or not any(
+            metadata.get(key) for key in ("new_ids", "example_ids", "private_ids")
+        ):
+            return {}
+
+        ids = {}
+        for entity_file in entity_files:
+            with reader.open(entity_file) as f:
+                is_project = splitext(entity_file.orig_filename)[0].endswith(".Project")
+                if metadata.get("new_ids"):
+                    id_func = cls._new_id
+                elif metadata.get("example_ids"):
+                    id_func = cls._example_id if not is_project else cls._hash_id
+                elif metadata.get("private_ids"):
+                    id_func = cls._private_id if not is_project else cls._new_id
+                for item in cls.json_lines(f):
+                    doc = json.loads(item)
+                    orig_id = doc.get("_id")
+                    if orig_id:
+                        ids[orig_id] = (
+                            id_func(orig_id)
+                            if id_func != cls._hash_id
+                            else id_func(doc.get("name"))
+                        )
+        return ids
+
+    @classmethod
+    def _import_users(cls, reader: ZipFile, company_id: str = "") -> dict:
+        """
+        Import users to db and return the mapping of old user ids to the new ones
+        If no users were in the users file then the mapping was empty
+        If the user in the file has the same email as one of the existing ones then this user is skipped
+        and its id is mapped to the existing user with the same email
+        If the user with the same id exists in backend or auth db then its creation is skipped
+        """
+        users_file = first(
+            fi for fi in reader.filelist if fi.orig_filename == cls.users_filename
+        )
+        if not users_file:
+            return {}
+
+        existing_user_ids = set(cls.user_cls.objects().scalar("id")) | set(
+            cls.auth_user_cls.objects().scalar("id")
+        )
+        existing_user_emails = {u.email: u.id for u in cls.auth_user_cls.objects()}
+        user_id_mappings = {}
+
+        with reader.open(users_file) as f:
+            data = json.loads(f.read())
+
+        auth_users = {u["_id"]: u for u in data["auth"]}
+        be_users = {u["_id"]: u for u in data["backend"]}
+        for uid, user in auth_users.items():
+            email = user.get("email")
+            existing_user_id = existing_user_emails.get(email)
+            if existing_user_id:
+                user_id_mappings[uid] = existing_user_id
+                continue
+
+            user_id_mappings[uid] = uid
+            if uid in existing_user_ids:
+                continue
+
+            credentials = user.get("credentials", [])
+            for c in credentials:
+                if c.get("company") == "":
+                    c["company"] = company_id
+
+            if hasattr(cls.auth_user_cls, "sec_groups"):
+                user_role = user.get("role", Role.user)
+                if user_role == Role.user:
+                    user["sec_groups"] = ["30795571-a470-4717-a80d-e8705fc776bf"]
+                else:
+                    user["sec_groups"] = [
+                        "c14a3cc6-1144-4896-8ea6-fb186ee19896",
+                        "30795571-a470-4717-a80d-e8705fc776bf",
+                        "30795571a4704717a80de8705897ytuyg",
+                    ]
+
+            auth_user = cls.auth_user_cls.from_json(json.dumps(user), created=True)
+            auth_user.company = company_id
+            auth_user.save()
+            be_user = cls.user_cls.from_json(json.dumps(be_users[uid]), created=True)
+            be_user.company = company_id
+            be_user.save()
+
+        return user_id_mappings
+
     @classmethod
     def _import(
         cls,
@@ -698,43 +893,55 @@ class PrePopulate:
         user_id: str = None,
         metadata: Mapping[str, Any] = None,
         sort_tasks_by_last_updated: bool = True,
+        user_mapping: Mapping[str, str] = None,
     ):
         """
         Import entities and events from the zip file
         Start from entities since event import will require the tasks already in DB
         """
         event_file_ending = cls.events_file_suffix + ".json"
-        entity_files = (
+        entity_files = [
             fi
             for fi in reader.filelist
             if not fi.orig_filename.endswith(event_file_ending)
-            and fi.orig_filename != cls.metadata_filename
-        )
+            and fi.orig_filename not in (cls.metadata_filename, cls.users_filename)
+        ]
         metadata = metadata or {}
+        old_to_new_ids = cls._generate_new_ids(reader, entity_files, metadata)
         tasks = []
         for entity_file in entity_files:
             with reader.open(entity_file) as f:
                 full_name = splitext(entity_file.orig_filename)[0]
                 print(f"Reading {reader.filename}:{full_name}...")
-                res = cls._import_entity(f, full_name, company_id, user_id, metadata)
+                res = cls._import_entity(
+                    f,
+                    full_name=full_name,
+                    company_id=company_id,
+                    user_id=user_id,
+                    metadata=metadata,
+                    old_to_new_ids=old_to_new_ids,
+                    user_mapping=user_mapping,
+                )
                 if res:
                     tasks = res
 
         if sort_tasks_by_last_updated:
             tasks = sorted(tasks, key=attrgetter("last_update"))
 
+        new_to_old_ids = {v: k for k, v in old_to_new_ids.items()}
         for task in tasks:
+            old_task_id = new_to_old_ids.get(task.id, task.id)
             events_file = first(
                 fi
                 for fi in reader.filelist
-                if fi.orig_filename.endswith(task.id + event_file_ending)
+                if fi.orig_filename.endswith(old_task_id + event_file_ending)
             )
             if not events_file:
                 continue
             with reader.open(events_file) as f:
                 full_name = splitext(events_file.orig_filename)[0]
                 print(f"Reading {reader.filename}:{full_name}...")
-                cls._import_events(f, full_name, company_id, user_id)
+                cls._import_events(f, company_id, task.user, task.id)
 
     @classmethod
     def _get_entity_type(cls, full_name) -> Type[mongoengine.Document]:
@@ -746,6 +953,15 @@ class PrePopulate:
         module = importlib.import_module(module_name)
         return getattr(module, class_name)
 
+    @staticmethod
+    def _upgrade_project_data(project_data: dict) -> dict:
+        if not project_data.get("basename"):
+            name: str = project_data["name"]
+            _, _, basename = name.rpartition("/")
+            project_data["basename"] = basename
+
+        return project_data
+
     @staticmethod
     def _upgrade_model_data(model_data: dict) -> dict:
         metadata_key = "metadata"
@@ -805,7 +1021,7 @@ class PrePopulate:
         ):
             old_path = old_field.split(".")
             old_model = nested_get(task_data, old_path)
-            new_models = models.get(type_, [])
+            new_models = [m for m in models.get(type_, []) if m.get("model") is not None]
             name = TaskModelNames[type_]
             if old_model and not any(
                 m
@@ -838,7 +1054,10 @@ class PrePopulate:
         company_id: str,
         user_id: str,
         metadata: Mapping[str, Any],
+        old_to_new_ids: Mapping[str, str] = None,
+        user_mapping: Mapping[str, str] = None,
     ) -> Optional[Sequence[Task]]:
+        user_mapping = user_mapping or {}
         cls_ = cls._get_entity_type(full_name)
         print(f"Writing {cls_.__name__.lower()}s into database")
         tasks = []
@@ -846,15 +1065,21 @@ class PrePopulate:
         data_upgrade_funcs: Mapping[Type, Callable] = {
             cls.task_cls: cls._upgrade_task_data,
             cls.model_cls: cls._upgrade_model_data,
+            cls.project_cls: cls._upgrade_project_data,
         }
         for item in cls.json_lines(f):
+            if old_to_new_ids:
+                for old_id, new_id in old_to_new_ids.items():
+                    # replace ids only when they are standalone strings
+                    # otherwise artifacts uris that contain old ids may get damaged
+                    item = item.replace(f'"{old_id}"', f'"{new_id}"')
             upgrade_func = data_upgrade_funcs.get(cls_)
             if upgrade_func:
                 item = json.dumps(upgrade_func(json.loads(item)))
 
             doc = cls_.from_json(item, created=True)
             if hasattr(doc, "user"):
-                doc.user = user_id
+                doc.user = user_mapping.get(doc.user, user_id) if doc.user else user_id
             if hasattr(doc, "company"):
                 doc.company = company_id
             if isinstance(doc, cls.project_cls):
@@ -884,11 +1109,17 @@ class PrePopulate:
             return tasks
 
     @classmethod
-    def _import_events(cls, f: IO[bytes], full_name: str, company_id: str, _):
-        _, _, task_id = full_name[0 : -len(cls.events_file_suffix)].rpartition("_")
+    def _import_events(cls, f: IO[bytes], company_id: str, user_id: str, task_id: str):
         print(f"Writing events for task {task_id} into database")
         for events_chunk in chunked_iter(cls.json_lines(f), 1000):
             events = [json.loads(item) for item in events_chunk]
+            for ev in events:
+                ev["task"] = task_id
+                ev["company_id"] = company_id
+                ev["allow_locked"] = True
             cls.event_bll.add_events(
-                company_id, events=events, worker="", allow_locked_tasks=True
+                company_id=company_id,
+                identity=Identity(user_id, company=company_id, role=Role.admin),
+                events=events,
+                worker="",
             )

apiserver/mongo/initialize/user.py

@@ -53,6 +53,7 @@ def _ensure_backend_user(user_id: str, company_id: str, user_name: str):
         name=user_name,
         given_name=given_name,
         family_name=family_name,
+        created=datetime.utcnow(),
     ).save()
 
     return user_id

apiserver/mongo/migrations/1_6_0.py

@@ -0,0 +1,12 @@
+from pymongo.collection import Collection
+from pymongo.database import Database
+
+
+def migrate_backend(db: Database):
+    projects: Collection = db["project"]
+    for doc in projects.find({"basename": None}):
+        name: str = doc["name"]
+        _, _, basename = name.rpartition("/")
+        projects.update_one(
+            {"_id": doc["_id"]}, {"$set": {"basename": basename}},
+        )

apiserver/mongo/migrations/1_7_0.py

@@ -0,0 +1,15 @@
+from pymongo.collection import Collection
+from pymongo.database import Database
+
+
+def migrate_backend(db: Database, auth_db: Database):
+    users: Collection = db["user"]
+    auth_users: Collection = auth_db["user"]
+    created_field = "created"
+    for doc in users.find({created_field: {"$exists": False}}):
+        auth_user = auth_users.find_one({"_id": doc["_id"]}, projection=[created_field])
+        if not auth_user or created_field not in auth_user:
+            continue
+        users.update_one(
+            {"_id": doc["_id"]}, {"$set": {created_field: auth_user[created_field]}}
+        )

apiserver/mongo/migrations/1_9_0.py

@@ -0,0 +1,17 @@
+import logging as log
+
+from pymongo.collection import Collection
+from pymongo.database import Database
+from pymongo.errors import OperationFailure
+
+
+def migrate_backend(db: Database):
+    """
+    Drop task text index so that the new one including reports field is created
+    """
+    tasks: Collection = db["task"]
+    try:
+        tasks.drop_index("backend-db.task.main_text_index")
+    except OperationFailure as ex:
+        log.warning(f"Could not delete task text index due to: {str(ex)}")
+        pass

apiserver/redis_manager.py

@@ -2,7 +2,7 @@ from os import getenv
 
 from boltons.iterutils import first
 from redis import StrictRedis
-from rediscluster import RedisCluster
+from redis.cluster import RedisCluster
 
 from apiserver.apierrors.errors.server_error import ConfigError, GeneralError
 from apiserver.config_repo import config
@@ -83,7 +83,7 @@ class RedisManager(object):
     def host(self, alias):
         r = self.connection(alias)
         if isinstance(r, RedisCluster):
-            connections = first(r.connection_pool._available_connections.values())
+            connections = r.get_default_node().redis_connection.connection_pool._available_connections
         else:
             connections = r.connection_pool._available_connections
 

apiserver/requirements.txt

@@ -1,34 +1,37 @@
-attrs>=19.1.0
+attrs>=22.1.0,<23
+azure-storage-blob>=12.13.1
 bcrypt>=3.1.4
 boltons>=19.1.0
-boto3==1.14.13
+boto3>=1.26
+boto3-stubs[s3]>=1.26
+clearml>=1.10.3
 dpath>=1.4.2,<2.0
-elasticsearch==7.13.3
+elasticsearch==7.17.9
 fastjsonschema>=2.8
 flask-compress>=1.4.0
 flask-cors>=3.0.5
-flask>=0.12.2
-funcsigs==1.0.2
+flask>=2.3.3
 furl>=2.0.0
-gunicorn>=19.7.1
-humanfriendly==4.18
-jinja2==2.11.3
+google-cloud-storage>=2.8.0
+gunicorn>=20.1.0
+humanfriendly>=4.17
+jinja2
 jsonmodels>=2.3
 jsonschema>=2.6.0
 luqum>=0.10.0
-mongoengine==0.23.1
+mongoengine==0.27.0
 nested_dict>=1.61
 packaging==20.3
 psutil>=5.6.5
-pyhocon>=0.3.35
-pyjwt<2.0.0
-pymongo[srv]==3.12.0
+pyhocon>=0.3.35r
+pyjwt>=2.4.0
+pymongo==4.4.0
 python-rapidjson>=0.6.3
-redis==3.5.3
-redis-py-cluster>=2.1.3
-related>=0.7.2
+redis>=4.5.4,<5
 requests>=2.13.0
 semantic_version>=2.8.3,<3
+setuptools>=65.5.1
 six
-tqdm
 validators>=0.12.4
+urllib3>=1.26.18
+werkzeug>=3.0.1

apiserver/schema/services/_common.conf

@@ -1,3 +1,43 @@
+field_filter {
+    type: object
+    description: Filter on a field that includes combination of 'any' or 'all' included and excluded terms
+    properties {
+        any {
+            type: object
+            description: All the terms in 'any' condition are combined with 'or' operation
+            properties {
+                "include" {
+                    type: array
+                    items {type: string}
+                }
+                exclude {
+                    type: array
+                    items {type: string}
+                }
+            }
+        }
+        all {
+            type: object
+            description: All the terms in 'all' condition are combined with 'and' operation
+            properties {
+                "include" {
+                    type: array
+                    items {type: string}
+                }
+                exclude {
+                    type: array
+                    items {type: string}
+                }
+            }
+        }
+        op {
+            type: string
+            description: The operation between 'any' and 'all' parts of the filter if both are provided
+            default: and
+            enum: [and, or]
+        }
+    }
+}
 metadata_item {
     type: object
     properties {
@@ -15,6 +55,35 @@ metadata_item {
         }
     }
 }
+task_status_enum {
+    type: string
+    enum: [
+        created
+        queued
+        in_progress
+        stopped
+        published
+        publishing
+        closed
+        failed
+        completed
+        unknown
+    ]
+}
+multi_field_pattern_data {
+    type: object
+    properties {
+        pattern {
+            description: "Pattern string (regex)"
+            type: string
+        }
+        fields {
+            description: "List of field names"
+            type: array
+            items { type: string }
+        }
+    }
+}
 credentials {
     type: object
     properties {

apiserver/schema/services/_events_common.conf

@@ -0,0 +1,141 @@
+scalar_key_enum {
+    type: string
+    enum: [
+        iter
+        timestamp
+        iso_time
+    ]
+}
+metric_variants {
+    type: object
+    properties {
+        metric {
+            description: The metric name
+            type: string
+        }
+        variants {
+            type: array
+            description: The names of the metric variants
+            items {type: string}
+        }
+    }
+}
+debug_images_response_task_metrics {
+    type: object
+    properties {
+        task {
+            type: string
+            description: Task ID
+        }
+        iterations {
+            type: array
+            items {
+                type: object
+                properties {
+                    iter {
+                        type: integer
+                        description: Iteration number
+                    }
+                    events {
+                        type: array
+                        items {
+                            type: object
+                            description: Debug image event
+                        }
+                    }
+                }
+            }
+        }
+    }
+}
+debug_images_response {
+    type: object
+    properties {
+        scroll_id {
+            type: string
+            description: "Scroll ID for getting more results"
+        }
+        metrics {
+            type: array
+            description: "Debug image events grouped by tasks and iterations"
+            items {"$ref": "#/definitions/debug_images_response_task_metrics"}
+        }
+    }
+}
+plots_response_task_metrics {
+    type: object
+    properties {
+        task {
+            type: string
+            description: Task ID
+        }
+        iterations {
+            type: array
+            items {
+                type: object
+                properties {
+                    iter {
+                        type: integer
+                        description: Iteration number
+                    }
+                    events {
+                        type: array
+                        items {
+                            type: object
+                            description: Plot event
+                        }
+                    }
+                }
+            }
+        }
+    }
+}
+plots_response {
+    type: object
+    properties {
+        scroll_id {
+            type: string
+            description: "Scroll ID for getting more results"
+        }
+        metrics {
+            type: array
+            description: "Plot events grouped by tasks and iterations"
+            items {"$ref": "#/definitions/plots_response_task_metrics"}
+        }
+    }
+}
+single_value_task_metrics {
+    type: object
+    properties {
+        task {
+            type: string
+            description: Task ID
+        }
+        task_name {
+            type: string
+            description: Task name
+        }
+        values {
+            type: array
+            items {
+                type: object
+                properties {
+                    metric { type: string }
+                    variant { type: string}
+                    value { type: number }
+                    timestamp { type: number }
+                }
+            }
+        }
+    }
+}
+single_value_metrics_response {
+    type: object
+    properties {
+        tasks {
+            description: Single value metrics grouped by task
+            type: array
+            items {"$ref": "#/definitions/single_value_task_metrics"}
+        }
+    }
+}

apiserver/schema/services/_tasks_common.conf

@@ -0,0 +1,506 @@
+include "_common.conf"
+task_type_enum {
+    type: string
+    enum: [
+        training
+        testing
+        inference
+        data_processing
+        application
+        monitor
+        controller
+        optimizer
+        service
+        qc
+        custom
+    ]
+}
+script {
+    type: object
+    properties {
+        binary {
+            description: "Binary to use when running the script"
+            type: string
+            default: python
+        }
+        repository {
+            description: "Name of the repository where the script is located"
+            type: string
+        }
+        tag {
+            description: "Repository tag"
+            type: string
+        }
+        branch  {
+            description: "Repository branch id If not provided and tag not provided, default repository branch is used."
+            type: string
+        }
+        version_num {
+            description: "Version (changeset) number. Optional (default is head version) Unused if tag is provided."
+            type: string
+        }
+        entry_point {
+            description: "Path to execute within the repository"
+            type: string
+        }
+        working_dir {
+            description: "Path to the folder from which to run the script Default - root folder of repository"
+            type: string
+        }
+        requirements {
+            description: "A JSON object containing requirements strings by key"
+            type: object
+        }
+        diff {
+            description: "Uncommitted changes found in the repository when task was run"
+            type: string
+        }
+    }
+}
+model_type_enum {
+    type: string
+    enum: ["input", "output"]
+}
+task_model_item {
+    type: object
+    required: [ name, model]
+    properties {
+        name {
+            description: "The task model name"
+            type: string
+        }
+        model {
+            description: "The model ID"
+            type: string
+        }
+    }
+}
+output {
+        type: object
+        properties {
+            destination {
+                description: "Storage id. This is where output files will be stored."
+                type: string
+            }
+            model {
+                description: "Model id."
+                type: string
+            }
+            result {
+                description: "Task result. Values: 'success', 'failure'"
+                type: string
+            }
+            error {
+                description: "Last error text"
+                type: string
+            }
+        }
+    }
+task_execution_progress_enum {
+    type: string
+    enum: [
+        unknown
+        running
+        stopping
+        stopped
+    ]
+}
+artifact_type_data {
+    type: object
+    properties {
+        preview {
+            description: "Description or textual data"
+            type: string
+        }
+        content_type {
+            description: "System defined raw data content type"
+            type: string
+        }
+        data_hash {
+            description: "Hash of raw data, without any headers or descriptive parts"
+            type: string
+        }
+    }
+}
+artifact_mode_enum {
+    type: string
+    enum: [
+        input
+        output
+    ]
+    default: output
+}
+artifact {
+    type: object
+    required: [key, type]
+    properties {
+        key {
+            description: "Entry key"
+            type: string
+        }
+        type {
+            description: "System defined type"
+            type: string
+        }
+        mode {
+            description: "System defined input/output indication"
+            "$ref": "#/definitions/artifact_mode_enum"
+        }
+        uri {
+            description: "Raw data location"
+            type: string
+        }
+        content_size {
+            description: "Raw data length in bytes"
+            type: integer
+        }
+        hash {
+            description: "Hash of entire raw data"
+            type: string
+        }
+        timestamp {
+            description: "Epoch time when artifact was created"
+            type: integer
+        }
+        type_data {
+            description: "Additional fields defined by the system"
+            "$ref": "#/definitions/artifact_type_data"
+        }
+        display_data {
+            description: "User-defined list of key/value pairs, sorted"
+            type: array
+            items {
+                type: array
+                items {
+                    type: string  # can also be a number... TODO: upgrade the generator
+                }
+            }
+        }
+    }
+}
+artifact_id {
+    type: object
+    required: [key]
+    properties {
+        key {
+            description: "Entry key"
+            type: string
+        }
+        mode {
+            description: "System defined input/output indication"
+            "$ref": "#/definitions/artifact_mode_enum"
+        }
+    }
+}
+task_models {
+    type: object
+    properties {
+        input {
+            description: "The list of task input models"
+            type: array
+            items {"$ref": "#/definitions/task_model_item"}
+
+        }
+        output {
+            description: "The list of task output models"
+            type: array
+            items {"$ref": "#/definitions/task_model_item"}
+        }
+    }
+}
+execution {
+    type: object
+    properties {
+        queue {
+            description: "Queue ID where task was queued."
+            type: string
+        }
+        parameters {
+            description: "Json object containing the Task parameters"
+            type: object
+            additionalProperties: true
+        }
+        model {
+            description: "Execution input model ID Not applicable for Register (Import) tasks"
+            type: string
+        }
+        model_desc {
+            description: "Json object representing the Model descriptors"
+            type: object
+            additionalProperties: true
+        }
+        model_labels {
+            description: """Json object representing the ids of the labels in the model.
+            The keys are the layers' names and the values are the IDs.
+            Not applicable for Register (Import) tasks.
+            Mandatory for Training tasks"""
+            type: object
+            additionalProperties: { type: integer }
+        }
+        framework {
+            description: """Framework related to the task. Case insensitive. Mandatory for Training tasks. """
+            type: string
+        }
+        docker_cmd {
+            description: "Command for running docker script for the execution of the task"
+            type: string
+        }
+        artifacts {
+            description: "Task artifacts"
+            type: array
+            items { "$ref": "#/definitions/artifact" }
+        }
+    }
+}
+last_metrics_event {
+    type: object
+    properties {
+        metric {
+            description: "Metric name"
+            type: string
+        }
+        variant {
+            description: "Variant name"
+            type: string
+        }
+        value {
+            description: "Last value reported"
+            type: number
+        }
+        min_value {
+            description: "Minimum value reported"
+            type: number
+        }
+        min_value_iteration {
+            description: "The iteration at which the minimum value was reported"
+            type: integer
+        }
+        max_value {
+            description: "Maximum value reported"
+            type: number
+        }
+        max_value_iteration {
+            description: "The iteration at which the maximum value was reported"
+            type: integer
+        }
+    }
+}
+last_metrics_variants {
+    type: object
+    description: "Last metric events, one for each variant hash"
+    additionalProperties {
+        "$ref": "#/definitions/last_metrics_event"
+    }
+}
+params_item {
+    type: object
+    properties {
+        section {
+            description: "Section that the parameter belongs to"
+            type: string
+        }
+        name {
+            description: "Name of the parameter. The combination of section and name should be unique"
+            type: string
+        }
+        value {
+            description: "Value of the parameter"
+            type: string
+        }
+        type {
+            description: "Type of the parameter. Optional"
+            type: string
+        }
+        description {
+            description: "The parameter description. Optional"
+            type: string
+        }
+    }
+}
+configuration_item {
+    type: object
+    properties {
+        name {
+            description: "Name of the parameter. Should be unique"
+            type: string
+        }
+        value {
+            description: "Value of the parameter"
+            type: string
+        }
+        type {
+            description: "Type of the parameter. Optional"
+            type: string
+        }
+        description {
+            description: "The parameter description. Optional"
+            type: string
+        }
+    }
+}
+section_params {
+    description: "Task section params"
+    type: object
+    additionalProperties {
+        "$ref": "#/definitions/params_item"
+    }
+}
+task {
+    type: object
+    properties {
+        id {
+            description: "Task id"
+            type: string
+        }
+        name {
+            description: "Task Name"
+            type: string
+        }
+        user {
+            description: "Associated user id"
+            type: string
+        }
+        company {
+            description: "Company ID"
+            type: string
+        }
+        type {
+            description: "Type of task. Values: 'training', 'testing'"
+            "$ref": "#/definitions/task_type_enum"
+        }
+        status {
+            description: ""
+            "$ref": "#/definitions/task_status_enum"
+        }
+        comment {
+            description: "Free text comment"
+            type: string
+        }
+        created {
+            description: "Task creation time (UTC) "
+            type: string
+            format: "date-time"
+        }
+        started {
+            description: "Task start time (UTC)"
+            type: string
+            format: "date-time"
+        }
+        completed {
+            description: "Task end time (UTC)"
+            type: string
+            format: "date-time"
+        }
+        active_duration {
+            description: "Task duration time (seconds)"
+            type: integer
+        }
+        parent {
+            description: "Parent task id"
+            type: string
+        }
+        project {
+            description: "Project ID of the project to which this task is assigned"
+            type: string
+        }
+        output {
+            description: "Task output params"
+            "$ref": "#/definitions/output"
+        }
+        execution {
+            description: "Task execution params"
+            "$ref": "#/definitions/execution"
+        }
+        container {
+            description: "Docker container parameters"
+            type: object
+            additionalProperties { type: string }
+        }
+        models {
+            description: "Task models"
+            "$ref": "#/definitions/task_models"
+        }
+        // TODO: will be removed
+        script {
+            description: "Script info"
+            "$ref": "#/definitions/script"
+        }
+        tags {
+            description: "User-defined tags list"
+            type: array
+            items { type: string }
+        }
+        system_tags {
+            description: "System tags list. This field is reserved for system use, please don't use it."
+            type: array
+            items { type: string }
+        }
+        status_changed {
+            description: "Last status change time"
+            type: string
+            format: "date-time"
+        }
+        status_message {
+            description: "free text string representing info about the status"
+            type: string
+        }
+        status_reason {
+            description: "Reason for last status change"
+            type: string
+        }
+        published {
+            description: "Task publish time"
+            type: string
+            format: "date-time"
+        }
+        last_worker {
+            description: "ID of last worker that handled the task"
+            type: string
+        }
+        last_worker_report {
+            description: "Last time a worker reported while working on this task"
+            type: string
+            format: "date-time"
+        }
+        last_update {
+            description: "Last time this task was created, edited, changed or events for this task were reported"
+            type: string
+            format: "date-time"
+        }
+        last_change {
+            description: "Last time any update was done to the task"
+            type: string
+            format: "date-time"
+        }
+        last_iteration {
+            description: "Last iteration reported for this task"
+            type: integer
+        }
+        last_metrics {
+            description: "Last metric variants (hash to events), one for each metric hash"
+            type: object
+            additionalProperties {
+                "$ref": "#/definitions/last_metrics_variants"
+            }
+        }
+        hyperparams {
+            description: "Task hyper params per section"
+            type: object
+            additionalProperties {
+                "$ref": "#/definitions/section_params"
+            }
+        }
+        configuration {
+            description: "Task configuration params"
+            type: object
+            additionalProperties {
+                "$ref": "#/definitions/configuration_item"
+            }
+        }
+        runtime {
+            description: "Task runtime mapping"
+            type: object
+            additionalProperties: true
+        }
+    }
+}

apiserver/schema/services/auth.conf

@@ -262,6 +262,38 @@ get_credentials {
     }
 }
 
+edit_credentials {
+    allow_roles = [ "*" ]
+    internal: false
+    "2.19" {
+        description: """Updates the label of the existing credentials for the authenticated user."""
+        request {
+            type: object
+            required: [ access_key ]
+            properties {
+                access_key {
+                    type: string
+                    description: Existing credentials key
+                }
+                label {
+                    type: string
+                    description: New credentials label
+                }
+            }
+        }
+        response {
+            type: object
+            properties {
+                updated {
+                    description: "Number of credentials updated"
+                    type: integer
+                    enum: [0, 1]
+                }
+            }
+        }
+    }
+}
+
 revoke_credentials {
     allow_roles = [ "*" ]
     internal: false

apiserver/schema/services/events.conf

@@ -1,17 +1,6 @@
 _description : "Provides an API for running tasks to report events collected by the system."
 _definitions {
-    metric_variants {
-        type: object
-        metric {
-            description: The metric name
-            type: string
-        }
-        variants {
-            type: array
-            description: The names of the metric variants
-            items {type: string}
-        }
-    }
+    include "_events_common.conf"
     metrics_scalar_event {
         description: "Used for reporting scalar metrics during training task"
         type: object
@@ -22,8 +11,8 @@ _definitions {
                 type: number
             }
             type {
-                description: "training_stats_vector"
-                const: "training_stats_scalar"
+                description: "'training_stats_scalar'"
+                type: string
             }
             task {
                 description: "Task ID (required)"
@@ -57,8 +46,8 @@ _definitions {
                 type: number
             }
             type {
-                description: "training_stats_vector"
-                const: "training_stats_vector"
+                description: "'training_stats_vector'"
+                type: string
             }
             task {
                 description: "Task ID (required)"
@@ -93,8 +82,8 @@ _definitions {
                 type: number
             }
             type {
-                description: ""
-                const: "training_debug_image"
+                description: "'training_debug_image'"
+                type: string
             }
             task {
                 description: "Task ID (required)"
@@ -134,7 +123,7 @@ _definitions {
             }
             type {
                 description: "'plot'"
-                const: "plot"
+                type: string
             }
             task {
                 description: "Task ID (required)"
@@ -164,14 +153,6 @@ _definitions {
             }
         }
     }
-    scalar_key_enum {
-        type: string
-        enum: [
-            iter
-            timestamp
-            iso_time
-        ]
-    }
     log_level_enum {
         type: string
         enum: [
@@ -240,7 +221,7 @@ _definitions {
             }
             type {
                 description: "'log'"
-                const: "log"
+                type: string
             }
             task {
                 description: "Task ID (required)"
@@ -260,48 +241,6 @@ _definitions {
             }
         }
     }
-    debug_images_response_task_metrics {
-        type: object
-        properties {
-            task {
-                type: string
-                description: Task ID
-            }
-            iterations {
-                type: array
-                items {
-                    type: object
-                    properties {
-                        iter {
-                            type: integer
-                            description: Iteration number
-                        }
-                        events {
-                            type: array
-                            items {
-                                type: object
-                                description: Debug image event
-                            }
-                        }
-                    }
-                }
-            }
-        }
-    }
-    debug_images_response {
-        type: object
-        properties {
-            scroll_id {
-                type: string
-                description: "Scroll ID for getting more results"
-            }
-            metrics {
-                type: array
-                description: "Debug image events grouped by tasks and iterations"
-                items {"$ref": "#/definitions/debug_images_response_task_metrics"}
-            }
-        }
-    }
     debug_image_sample_response {
         type: object
         properties {
@@ -323,6 +262,28 @@ _definitions {
             }
         }
     }
+    plot_sample_response {
+        type: object
+        properties {
+            scroll_id {
+                type: string
+                description: "Scroll ID to pass to the next calls to get_plot_sample or next_plot_sample"
+            }
+            events {
+                description: "Plot events"
+                type: array
+                items { type: object}
+            }
+            min_iteration {
+                type: integer
+                description: "minimal valid iteration for the metric"
+            }
+            max_iteration {
+                type: integer
+                description: "maximal valid iteration for the metric"
+            }
+        }
+    }
 }
 add {
     "2.1" {
@@ -342,13 +303,27 @@ add {
             additionalProperties: true
         }
     }
+    "2.22": ${add."2.1"} {
+        request.properties {
+            model_event {
+                type: boolean
+                description: If set then the event is for a model. Otherwise for a task. Cannot be used with task log events. If used in batch then all the events should be marked the same
+                default: false
+            }
+            allow_locked {
+                type: boolean
+                description: Allow adding events to published tasks or models
+                default: false
+            }
+        }
+    }
 }
 add_batch {
     "2.1" {
         description: "Adds a batch of events in a single call (json-lines format, stream-friendly)"
         batch_request: {
             action: add
-            version: 1.5
+            version: 2.1
         }
         response {
             type: object
@@ -359,10 +334,16 @@ add_batch {
             }
         }
     }
+    "2.22": ${add_batch."2.1"} {
+        batch_request: {
+            action: add
+            version: 2.22
+        }
+    }
 }
 delete_for_task {
     "2.1" {
-        description: "Delete all task event. *This cannot be undone!*"
+        description: "Delete all task events. *This cannot be undone!*"
         request {
             type: object
             required: [
@@ -391,6 +372,37 @@ delete_for_task {
         }
     }
 }
+delete_for_model {
+    "2.22" {
+        description: "Delete all model events. *This cannot be undone!*"
+        request {
+            type: object
+            required: [
+                model
+            ]
+            properties {
+                model {
+                    type: string
+                    description: "Model ID"
+                }
+                allow_locked {
+                    type: boolean
+                    description: "Allow deleting events even if the model is locked"
+                    default: false
+                }
+            }
+        }
+        response {
+            type: object
+            properties {
+                deleted {
+                    type: boolean
+                    description: "Number of deleted events"
+                }
+            }
+        }
+    }
+}
 debug_images {
     "2.1" {
         description: "Get all debug images of a task"
@@ -432,7 +444,7 @@ debug_images {
                 }
                 total {
                     type: number
-                    description: "Total number of results available for this query"
+                    description: "Total number of results available for this query. In case there are more than 10000 results it is set to 10000"
                 }
                 scroll_id {
                     type: string
@@ -485,6 +497,55 @@ debug_images {
             }
         }
     }
+    "2.22": ${debug_images."2.14"} {
+        request.properties.model_events {
+            type: boolean
+            description: If set then the retrieving model events. Otherwise task events
+            default: false
+        }
+    }
+}
+plots {
+    "2.20" {
+        description: "Get plot events for the requested amount of iterations per each task"
+        request {
+            type: object
+            required: [
+                metrics
+            ]
+            properties {
+                metrics {
+                    type: array
+                    description: List of metrics and variants
+                    items { "$ref": "#/definitions/task_metric_variants" }
+                }
+                iters {
+                    type: integer
+                    description: "Max number of latest iterations for which to return plots"
+                }
+                navigate_earlier {
+                    type: boolean
+                    description: "If set then events are retreived from latest iterations to earliest ones. Otherwise from earliest iterations to the latest. The default is True"
+                }
+                refresh {
+                    type: boolean
+                    description: "If set then scroll will be moved to the latest iterations. The default is False"
+                }
+                scroll_id {
+                    type: string
+                    description: "Scroll ID of previous call (used for getting more results)"
+                }
+            }
+        }
+        response {"$ref": "#/definitions/plots_response"}
+    }
+    "2.22": ${plots."2.20"} {
+        request.properties.model_events {
+            type: boolean
+            description: If set then the retrieving model plots. Otherwise task plots
+            default: false
+        }
+    }
 }
 get_debug_image_sample {
     "2.12": {
@@ -521,6 +582,20 @@ get_debug_image_sample {
         }
         response {"$ref": "#/definitions/debug_image_sample_response"}
     }
+    "2.20": ${get_debug_image_sample."2.12"} {
+        request.properties.navigate_current_metric {
+            description: If set then subsequent navigation with next_debug_image_sample is done on the debug images for the passed metric only. Otherwise for all the metrics
+            type: boolean
+            default: true
+        }
+    }
+    "2.22": ${get_debug_image_sample."2.20"} {
+        request.properties.model_events {
+            type: boolean
+            description: If set then the retrieving model debug images. Otherwise task debug images
+            default: false
+        }
+    }
 }
 next_debug_image_sample {
     "2.12": {
@@ -546,6 +621,99 @@ next_debug_image_sample {
         }
         response {"$ref": "#/definitions/debug_image_sample_response"}
     }
+    "2.22": ${next_debug_image_sample."2.12"} {
+        request.properties.next_iteration {
+            type: boolean
+            default: false
+            description: If set then navigate to the next/previous iteration
+        }
+        request.properties.model_events {
+            type: boolean
+            description: If set then the retrieving model debug images. Otherwise task debug images
+            default: false
+        }
+    }
+}
+get_plot_sample {
+    "2.20": {
+        description: "Return plots for the provided iteration"
+        request {
+            type: object
+            required: [task, metric]
+            properties {
+                task {
+                    description: "Task ID"
+                    type: string
+                }
+                metric {
+                    description: "Metric name"
+                    type: string
+                }
+                iteration {
+                    description: "The iteration to bring plot from. If not specified then the latest reported plot is retrieved"
+                    type: integer
+                }
+                refresh {
+                    description: "If set then scroll state will be refreshed to reflect the latest changes in the plots"
+                    type: boolean
+                }
+                scroll_id {
+                    type: string
+                    description: "Scroll ID from the previous call to get_plot_sample or empty"
+                }
+                navigate_current_metric {
+                    description: If set then subsequent navigation with next_plot_sample is done on the plots for the passed metric only. Otherwise for all the metrics
+                    type: boolean
+                    default: true
+                }
+            }
+        }
+        response {"$ref": "#/definitions/plot_sample_response"}
+    }
+    "2.22": ${get_plot_sample."2.20"} {
+        request.properties.model_events {
+            type: boolean
+            description: If set then the retrieving model plots. Otherwise task plots
+            default: false
+        }
+    }
+}
+next_plot_sample {
+    "2.20": {
+        description: "Get the plot for the next metric for the same iteration or for the next iteration"
+        request {
+            type: object
+            required: [task, scroll_id]
+            properties {
+                task {
+                    description: "Task ID"
+                    type: string
+                }
+                scroll_id {
+                    type: string
+                    description: "Scroll ID from the previous call to get_plot_sample"
+                }
+                navigate_earlier {
+                    type: boolean
+                    description: """If set then get the either previous metric events from the current iteration or (if does not exist) the last metric events from the previous iteration.
+                    Otherwise next metric events from the current iteration or first metric events from the next iteration"""
+                }
+            }
+        }
+        response {"$ref": "#/definitions/plot_sample_response"}
+    }
+    "2.22": ${next_plot_sample."2.20"} {
+        request.properties.next_iteration {
+            type: boolean
+            default: false
+            description: If set then navigate to the next/previous iteration
+        }
+        request.properties.model_events {
+            type: boolean
+            description: If set then the retrieving model plots. Otherwise task plots
+            default: false
+        }
+    }
 }
 get_task_metrics{
     "2.7": {
@@ -578,6 +746,49 @@ get_task_metrics{
             }
         }
     }
+    "2.22": ${get_task_metrics."2.7"} {
+        request.properties.model_events {
+            type: boolean
+            description: If set then get metrics from model events. Otherwise from task events
+            default: false
+        }
+    }
+}
+get_multi_task_metrics {
+    "2.28" {
+        description: """Get unique metrics and variants from the events of the specified type.
+        Only events reported for the passed task or model ids are analyzed."""
+        request {
+            type: object
+            required: [ tasks ]
+            properties {
+                tasks {
+                    description: task ids to get metrics from
+                    type: array
+                    items {type: string}
+                }
+                model_events {
+                    description: If not set or set to false then passed ids are task ids otherwise model ids
+                    type: boolean
+                    default: false
+                }
+                event_type {
+                    "description": Event type. If not specified then metrics are collected from the reported events of all types
+                    "$ref": "#/definitions/event_type_enum"
+                }
+            }
+        }
+        response {
+            type: object
+            properties {
+                metrics {
+                    type: array
+                    description: List of metrics and variants
+                    items { "$ref": "#/definitions/metric_variants" }
+                }
+            }
+        }
+    }
 }
 get_task_log {
     "1.5" {
@@ -677,7 +888,7 @@ get_task_log {
                 }
                 total {
                     type: number
-                    description: "Total number of results available for this query"
+                    description: "Total number of results available for this query. In case there are more than 10000 results it is set to 10000"
                 }
                 scroll_id {
                     type: string
@@ -731,7 +942,7 @@ get_task_log {
                 }
                 total {
                     type: number
-                    description: "Total number of log events available for this query"
+                    description: "Total number of log events available for this query. In case there are more than 10000 events it is set to 10000"
                 }
             }
         }
@@ -786,7 +997,7 @@ get_task_events {
                 }
                 total {
                     type: number
-                    description: "Total number of results available for this query"
+                    description: "Total number of results available for this query. In case there are more than 10000 results it is set to 10000"
                 }
                 scroll_id {
                     type: string
@@ -795,6 +1006,20 @@ get_task_events {
             }
         }
     }
+    "2.22": ${get_task_events."2.1"} {
+        request.properties {
+            model_events {
+                type: boolean
+                description: If set then get retrieving model events. Otherwise task events
+                default: false
+            }
+            metrics {
+                type: array
+                description: List of metrics and variants
+                items { "$ref": "#/definitions/metric_variants" }
+            }
+        }
+    }
 }
 
 download_task_log {
@@ -845,7 +1070,7 @@ get_task_plots {
                 }
                 iters {
                     type: integer
-                    description: "Max number of latest iterations for which to return debug images"
+                    description: "Max number of latest iterations for which to return plots"
                 }
                 scroll_id {
                     type: string
@@ -869,7 +1094,7 @@ get_task_plots {
                 }
                 total {
                     type: number
-                    description: "Total number of results available for this query"
+                    description: "Total number of results available for this query. In case there are more than 10000 results it is set to 10000"
                 }
                 scroll_id {
                     type: string
@@ -896,6 +1121,13 @@ get_task_plots {
             default: false
         }
     }
+    "2.22": ${get_task_plots."2.16"} {
+        request.properties.model_events {
+            type: boolean
+            description: If set then the retrieving model events. Otherwise task events
+            default: false
+        }
+    }
 }
 get_multi_task_plots {
     "2.1" {
@@ -916,7 +1148,7 @@ get_multi_task_plots {
                 }
                 iters {
                     type: integer
-                    description: "Max number of latest iterations for which to return debug images"
+                    description: "Max number of latest iterations for which to return plots"
                 }
                 scroll_id {
                     type: string
@@ -937,7 +1169,7 @@ get_multi_task_plots {
                 }
                 total {
                     type: number
-                    description: "Total number of results available for this query"
+                    description: "Total number of results available for this query. In case there are more than 10000 results it is set to 10000"
                 }
                 scroll_id {
                     type: string
@@ -953,6 +1185,27 @@ get_multi_task_plots {
             default: false
         }
     }
+    "2.22": ${get_multi_task_plots."2.16"} {
+        request.properties.model_events {
+            type: boolean
+            description: If set then the retrieving model events. Otherwise task events
+            default: false
+        }
+    }
+    "2.26": ${get_multi_task_plots."2.22"} {
+        request.properties.last_iters_per_task_metric {
+            type: boolean
+            description: If set to 'true' and iters passed then last iterations for each task metrics are retrieved. Otherwise last iterations for the whole task are retrieved
+            default: true
+        }
+    }
+    "2.28": ${get_multi_task_plots."2.26"} {
+        request.properties.metrics {
+            type: array
+            description: List of metrics and variants
+            items { "$ref": "#/definitions/metric_variants" }
+        }
+    }
 }
 get_vector_metrics_and_variants {
     "2.1" {
@@ -981,6 +1234,13 @@ get_vector_metrics_and_variants {
             }
         }
     }
+    "2.22": ${get_vector_metrics_and_variants."2.1"} {
+        request.properties.model_events {
+            type: boolean
+            description: If set then the retrieving model events. Otherwise task events
+            default: false
+        }
+    }
 }
 vector_metrics_iter_histogram {
     "2.1" {
@@ -1019,6 +1279,13 @@ vector_metrics_iter_histogram {
             }
         }
     }
+    "2.22": ${vector_metrics_iter_histogram."2.1"} {
+        request.properties.model_events {
+            type: boolean
+            description: If set then the retrieving model events. Otherwise task events
+            default: false
+        }
+    }
 }
 scalar_metrics_iter_histogram {
     "2.1" {
@@ -1072,6 +1339,13 @@ scalar_metrics_iter_histogram {
             }
         }
     }
+    "2.22": ${scalar_metrics_iter_histogram."2.14"} {
+        request.properties.model_events {
+            type: boolean
+            description: If set then the retrieving model events. Otherwise task events
+            default: false
+        }
+    }
 }
 multi_task_scalar_metrics_iter_histogram {
     "2.1" {
@@ -1083,11 +1357,11 @@ multi_task_scalar_metrics_iter_histogram {
             ]
             properties {
                 tasks {
-                    description: "List of task Task IDs. Maximum amount of tasks is 10"
+                    description: "List of task Task IDs. Maximum amount of tasks is 100"
                     type: array
                     items {
                         type: string
-                        description: "List of task Task IDs"
+                        description: "Task ID"
                     }
                 }
                 samples {
@@ -1111,6 +1385,54 @@ multi_task_scalar_metrics_iter_histogram {
             additionalProperties: true
         }
     }
+    "2.22": ${multi_task_scalar_metrics_iter_histogram."2.1"} {
+        request.properties.model_events {
+            type: boolean
+            description: If set then the retrieving model events. Otherwise task events
+            default: false
+        }
+    }
+    "2.28": ${multi_task_scalar_metrics_iter_histogram."2.22"} {
+        request.properties.metrics {
+            type: array
+            description: List of metrics and variants
+            items { "$ref": "#/definitions/metric_variants" }
+        }
+    }
+}
+get_task_single_value_metrics {
+    "2.20" {
+        description: Get single value metrics for the passed tasks
+        request {
+            type: object
+            required: [tasks]
+            properties {
+                tasks {
+                    description: "List of task Task IDs"
+                    type: array
+                    items {
+                        type: string
+                        description: "Task ID"
+                    }
+                }
+            }
+        }
+        response {"$ref": "#/definitions/single_value_metrics_response"}
+    }
+    "2.22": ${get_task_single_value_metrics."2.20"} {
+        request.properties.model_events {
+            type: boolean
+            description: If set then the retrieving model events. Otherwise task events
+            default: false
+        }
+    }
+    "2.28": ${get_task_single_value_metrics."2.22"} {
+        request.properties.metrics {
+            type: array
+            description: List of metrics and variants
+            items { "$ref": "#/definitions/metric_variants" }
+        }
+    }
 }
 get_task_latest_scalar_values {
     "2.1" {
@@ -1190,6 +1512,13 @@ get_scalar_metrics_and_variants {
             }
         }
     }
+    "2.22": ${get_scalar_metrics_and_variants."2.1"} {
+        request.properties.model_events {
+            type: boolean
+            description: If set then the retrieving model events. Otherwise task events
+            default: false
+        }
+    }
 }
 get_scalar_metric_data {
     "2.1" {
@@ -1205,6 +1534,10 @@ get_scalar_metric_data {
                     type: string
                     description: type of metric
                 }
+                scroll_id {
+                    type: string
+                    description: "Scroll ID of previous call (used for getting more results)"
+                }
             }
         }
         response {
@@ -1227,7 +1560,7 @@ get_scalar_metric_data {
                 }
                 scroll_id {
                     type: string
-                    description: "Scroll ID of previous call (used for getting more results)"
+                    description: "Scroll ID for getting more results"
                 }
             }
         }
@@ -1239,6 +1572,13 @@ get_scalar_metric_data {
             default: false
         }
     }
+    "2.22": ${get_scalar_metric_data."2.16"} {
+        request.properties.model_events {
+            type: boolean
+            description: If set then the retrieving model events. Otherwise task events
+            default: false
+        }
+    }
 }
 scalar_metrics_iter_raw {
     "2.16" {
@@ -1303,4 +1643,66 @@ scalar_metrics_iter_raw {
             }
         }
     }
+    "2.22": ${scalar_metrics_iter_raw."2.16"} {
+        request.properties.model_events {
+            type: boolean
+            description: If set then the retrieving model events. Otherwise task events
+            default: false
+        }
+    }
+}
+clear_scroll {
+    "2.18" {
+        description: "Clear an open Scroll ID"
+        request {
+            type: object
+            required: [
+                scroll_id
+            ]
+            properties {
+                scroll_id {
+                    description: "Scroll ID as returned by previous events service calls"
+                    type: string
+                }
+            }
+        }
+        response {
+            type: object
+            additionalProperties: false
+        }
+    }
+}
+
+clear_task_log {
+    "2.19" {
+        description: Remove old logs from task
+        request {
+            type: object
+            required: [task]
+            properties {
+                task {
+                    description: Task ID
+                    type: string
+                }
+                allow_locked {
+                    type: boolean
+                    description: Allow deleting events even if the task is locked
+                    default: false
+                }
+                threshold_sec {
+                    description: The amount of seconds ago to retain the log records. The older log records will be deleted. If not passed or 0 then all the log records for the task will be deleted
+                    type: integer
+                }
+            }
+        }
+        response {
+            type: object
+            properties {
+                deleted {
+                    description: The number of deleted log records
+                    type: integer
+                }
+            }
+        }
+    }
 }

apiserver/schema/services/login.conf

@@ -6,21 +6,12 @@ _default {
 }
 
 supported_modes {
-    authorize: false
+    authorize: null
     "2.9" {
         description:  """ Return supported login modes."""
         request {
             type: object
-            properties {
-                state {
-                    description: "ASCII base64 encoded application state"
-                    type: string
-                }
-                callback_url_prefix {
-                    description: "URL prefix used to generate the callback URL for each supported SSO provider"
-                    type: string
-                }
-            }
+            additionalProperties: false
         }
         response {
             type: object
@@ -59,7 +50,7 @@ supported_modes {
                     description: "SSO authentication providers"
                     type: object
                     additionalProperties {
-                        desctiprion: "Provider redirect URL"
+                        description: "Provider redirect URL"
                         type: string
                     }
                 }
@@ -95,7 +86,7 @@ supported_modes {
 }
 
 logout {
-    authorize: false
+    authorize: null
     allow_roles = [ "*" ]
     "2.13" {
         description: """ Logout (including SSO, if used)) """

apiserver/schema/services/models.conf

@@ -1,6 +1,6 @@
 _description: """This service provides a management interface for models (results of training tasks) stored in the system."""
 _definitions {
-    include "_common.conf"
+    include "_tasks_common.conf"
     multi_field_pattern_data {
         type: object
         properties {
@@ -104,6 +104,27 @@ _definitions {
                     "$ref": "#/definitions/metadata_item"
                 }
             }
+            last_iteration {
+                description: "Last iteration reported for this model"
+                type: integer
+            }
+            last_metrics {
+                description: "Last metric variants (hash to events), one for each metric hash"
+                type: object
+                additionalProperties {
+                    "$ref": "#/definitions/last_metrics_variants"
+                }
+            }
+            stats {
+                description: "Model statistics"
+                type: object
+                properties {
+                    labels_count {
+                        description: Number of the model labels
+                        type: integer
+                    }
+                }
+            }
         }
     }
     published_task_item {
@@ -224,6 +245,30 @@ get_all_ex {
             description: "Scroll ID that can be used with the next calls to get_all_ex to retrieve more data"
         }
     }
+    "2.20": ${get_all_ex."2.15"} {
+        request.properties.include_stats {
+            description: "If true, include models statistic in response"
+            type: boolean
+            default: false
+        }
+    }
+    "2.23": ${get_all_ex."2.20"} {
+        request.properties {
+            allow_public {
+                description: "Allow public models to be returned in the results"
+                type: boolean
+                default: true
+            }
+        }
+    }
+    "2.27": ${get_all_ex."2.23"} {
+        request.properties {
+            filters {
+                type: object
+                additionalProperties: ${_definitions.field_filter}
+            }
+        }
+    }
 }
 get_all {
     "2.1" {
@@ -303,6 +348,14 @@ get_all {
                     type: array
                     items { type: string }
                 }
+                last_update {
+                    description: "List of last_update constraint strings (utcformat, epoch) with an optional prefix modifier (>, >=, <, <=)"
+                    type: array
+                    items {
+                        type: string
+                        pattern: "^(>=|>|<=|<)?.*$"
+                    }
+                }
                 _all_ {
                     description: "Multi-field pattern condition (all fields match pattern)"
                     "$ref": "#/definitions/multi_field_pattern_data"
@@ -312,9 +365,6 @@ get_all {
                     "$ref": "#/definitions/multi_field_pattern_data"
                 }
             }
-            dependencies {
-                page: [ page_size ]
-            }
         }
         response {
             type: object
@@ -350,6 +400,17 @@ get_all {
             description: "Scroll ID that can be used with the next calls to get_all to retrieve more data"
         }
     }
+    "2.26": ${get_all."2.15"} {
+        request {
+            properties {
+                include_subprojects {
+                    description: "If set to 'true' and project field is set then models from the subprojects are searched too"
+                    type: boolean
+                    default: false
+                }
+            }
+        }
+    }
 }
 get_frameworks {
     "2.8" {
@@ -951,7 +1012,7 @@ move {
                     items { type: string }
                 }
                 project {
-                    description: "Target project ID. If not provided, `project_name` must be provided."
+                    description: "Target project ID. If not provided, `project_name` must be provided. Use null for the root project"
                     type: string
                 }
                 project_name {
@@ -1030,4 +1091,38 @@ delete_metadata {
             }
         }
     }
+}
+update_tags {
+    "2.27" {
+        description: Add or remove tags from multiple models
+        request {
+            type: object
+            properties {
+                ids {
+                    type: array
+                    description: IDs of the models to update
+                    items {type: string}
+                }
+                add_tags {
+                    type: array
+                    description: User tags to add
+                    items {type: string}
+                }
+                remove_tags {
+                    type: array
+                    description: User tags to remove
+                    items {type: string}
+                }
+            }
+        }
+        response {
+            type: object
+            properties {
+                updated {
+                    type: integer
+                    description: The number of updated models
+                }
+            }
+        }
+    }
 }

apiserver/schema/services/organization.conf

@@ -1,5 +1,38 @@
 _description: "This service provides organization level operations"
-
+_definitions {
+    value_mapping {
+        type: object
+        required: [key, value]
+        properties {
+            key {
+                description: Original value
+                type: object
+            }
+            value {
+                description: Translated value
+                type: object
+            }
+        }
+    }
+    field_mapping {
+        type: object
+        required: [field]
+        properties {
+            field {
+                description: The source field name as specified in the only_fields
+                type: string
+            }
+            name {
+                description: The column name in the exported csv file
+                type: string
+            }
+            values {
+                type: array
+                items { "$ref": "#/definitions/value_mapping"}
+            }
+        }
+    }
+}
 get_tags {
     "2.8" {
         description: "Get all the user and system tags used for the company tasks and models"
@@ -102,4 +135,164 @@ get_user_companies {
             }
         }
     }
+}
+get_entities_count {
+    "2.20": {
+        description: "Get counts for the company entities according to the passed search criteria"
+        request {
+            type: object
+            properties {
+                projects {
+                    type: object
+                    additionalProperties: true
+                    description: Search criteria for projects
+                }
+                tasks {
+                    type: object
+                    additionalProperties: true
+                    description: Search criteria for experiments
+                }
+                models {
+                    type: object
+                    additionalProperties: true
+                    description: Search criteria for models
+                }
+                pipelines {
+                    type: object
+                    additionalProperties: true
+                    description: Search criteria for pipelines
+                }
+                datasets {
+                    type: object
+                    additionalProperties: true
+                    description: Search criteria for datasets
+                }
+            }
+        }
+        response {
+            type: object
+            properties {
+                projects {
+                    type: integer
+                    description: The number of projects matching the criteria
+                }
+                tasks {
+                    type: integer
+                    description: The number of experiments matching the criteria
+                }
+                models {
+                    type: integer
+                    description: The number of models matching the criteria
+                }
+                pipelines {
+                    type: integer
+                    description: The number of pipelines matching the criteria
+                }
+                datasets {
+                    type: integer
+                    description: The number of datasets matching the criteria
+                }
+            }
+        }
+    }
+    "2.22": ${get_entities_count."2.20"} {
+        request.properties {
+            search_hidden {
+                description: "If set to 'true' then hidden projects and tasks are included in the search results"
+                type: boolean
+                default: false
+            }
+            active_users {
+                description: "The list of users that were active in the project. If passes then the resulting projects are filtered to the ones that have tasks created by these users"
+                type: array
+                items: {type: string}
+            }
+        }
+    }
+    "2.23": ${get_entities_count."2.22"} {
+        request.properties {
+            reports {
+                type: object
+                additionalProperties: true
+                description: Search criteria for reports
+            }
+            allow_public {
+                description: "Allow public entities to be counted in the results"
+                type: boolean
+                default: true
+            }
+        }
+        response.properties {
+            reports {
+                type: integer
+                description: The number of reports matching the criteria
+            }
+        }
+    }
+}
+prepare_download_for_get_all {
+    "2.26": {
+        description: Prepares download from get_all_ex parameters
+        request {
+            type: object
+            required: [ entity_type,  only_fields, field_mappings]
+            properties {
+                only_fields {
+                    description: "List of task field names (nesting is supported using '.', e.g. execution.model_labels). If provided, this list defines the query's projection (only these fields will be returned for each result entry)"
+                    type: array
+                    items {type: string}
+                }
+                allow_public {
+                    description: "Allow public entities to be returned in the results"
+                    type: boolean
+                    default: true
+                }
+                search_hidden {
+                    description: "If set to 'true' then hidden entities are included in the search results"
+                    type: boolean
+                    default: false
+                }
+                entity_type {
+                    description: "The type of the entity to retrieve"
+                    type: string
+                    enum: [
+                        task
+                        model
+                    ]
+                }
+                field_mappings {
+                    description: The name and value mappings for the exported fields. The fields that are not in the mappings will not be exported
+                    type: array
+                    items { "$ref": "#/definitions/field_mapping"}
+                }
+            }
+        }
+        response {
+            type: object
+            properties {
+                prepare_id {
+                    description: "Prepare ID (use when calling 'download_for_get_all')"
+                    type: string
+                }
+            }
+        }
+    }
+}
+download_for_get_all {
+    "2.26": {
+        description: Generates a file for the download
+        request {
+            type: object
+            required: [ prepare_id ]
+            properties {
+                prepare_id {
+                    description: "Call ID returned by a call to prepare_download_for_get_all"
+                    type: string
+                }
+            }
+        }
+        response {
+            type: string
+        }
+    }
 }