Update clearml.conf

clearml_agent/backend_api/config/default/agent.conf

@@ -137,6 +137,12 @@
     },
 
     translate_ssh: true,
+
+    # set "disable_ssh_mount: true" to disable the automatic mount of ~/.ssh folder into the docker containers
+    # default is false, automatically mounts ~/.ssh
+    # Must be set to True if using "clearml-session" with this agent!
+    # disable_ssh_mount: false
+
     # reload configuration file every daemon execution
     reload_config: false,
 

clearml_agent/backend_api/config/default/api.conf

@@ -28,6 +28,9 @@
 
         pool_maxsize: 512
         pool_connections: 512
+
+        # Override the default http method, use "put" if working behind GCP load balancer (default: "get")
+        # default_method: "get"
     }
 
     auth {

clearml_agent/backend_api/session/request.py

@@ -8,13 +8,14 @@ from .datamodel import DataModel
 from .defs import ENV_API_DEFAULT_REQ_METHOD
 
 
-if ENV_API_DEFAULT_REQ_METHOD.get().upper() not in ("GET", "POST"):
+if ENV_API_DEFAULT_REQ_METHOD.get().upper() not in ("GET", "POST", "PUT"):
     raise ValueError(
         "CLEARML_API_DEFAULT_REQ_METHOD environment variable must be 'get' or 'post' (any case is allowed)."
     )
 
 
 class Request(ApiModel):
+    def_method = ENV_API_DEFAULT_REQ_METHOD.get(default="get")
     _method = ENV_API_DEFAULT_REQ_METHOD.get(default="get")
 
     def __init__(self, **kwargs):

clearml_agent/backend_api/session/session.py

@@ -14,8 +14,9 @@ from requests.auth import HTTPBasicAuth
 from six.moves.urllib.parse import urlparse, urlunparse
 
 from .callresult import CallResult
-from .defs import ENV_VERBOSE, ENV_HOST, ENV_ACCESS_KEY, ENV_SECRET_KEY, ENV_WEB_HOST, ENV_FILES_HOST, ENV_AUTH_TOKEN, \
-    ENV_NO_DEFAULT_SERVER, ENV_DISABLE_VAULT_SUPPORT, ENV_INITIAL_CONNECT_RETRY_OVERRIDE, ENV_API_DEFAULT_REQ_METHOD
+from .defs import (
+    ENV_VERBOSE, ENV_HOST, ENV_ACCESS_KEY, ENV_SECRET_KEY, ENV_WEB_HOST, ENV_FILES_HOST, ENV_AUTH_TOKEN,
+    ENV_NO_DEFAULT_SERVER, ENV_DISABLE_VAULT_SUPPORT, ENV_INITIAL_CONNECT_RETRY_OVERRIDE, ENV_API_DEFAULT_REQ_METHOD, )
 from .request import Request, BatchRequest
 from .token_manager import TokenManager
 from ..config import load
@@ -110,6 +111,19 @@ class Session(TokenManager):
         self._logger = logger
         self.__auth_token = None
 
+        if ENV_API_DEFAULT_REQ_METHOD.get(default=None):
+            # Make sure we update the config object, so we pass it into the new containers when we map them
+            self.config["api.http.default_method"] = ENV_API_DEFAULT_REQ_METHOD.get()
+            # notice the default setting of Request.def_method are already set by the OS environment
+        elif self.config.get("api.http.default_method", None):
+            def_method = str(self.config.get("api.http.default_method", None)).strip()
+            if def_method.upper() not in ("GET", "POST", "PUT"):
+                raise ValueError(
+                    "api.http.default_method variable must be 'get' or 'post' (any case is allowed)."
+                )
+            Request.def_method = def_method
+            Request._method = Request.def_method
+
         if ENV_AUTH_TOKEN.get(
             value_cb=lambda key, value: print("Using environment access token {}=********".format(key))
         ):
@@ -251,7 +265,7 @@ class Session(TokenManager):
         service,
         action,
         version=None,
-        method="get",
+        method=Request.def_method,
         headers=None,
         auth=None,
         data=None,
@@ -328,7 +342,7 @@ class Session(TokenManager):
         service,
         action,
         version=None,
-        method="get",
+        method=Request.def_method,
         headers=None,
         data=None,
         json=None,
@@ -371,7 +385,7 @@ class Session(TokenManager):
         headers=None,
         data=None,
         json=None,
-        method="get",
+        method=Request.def_method,
     ):
         """
         Send a raw batch API request. Batch requests always use application/json-lines content type.
@@ -615,7 +629,7 @@ class Session(TokenManager):
         try:
             data = {"expiration_sec": exp} if exp else {}
             res = self._send_request(
-                method=ENV_API_DEFAULT_REQ_METHOD.get(default="get"),
+                method=Request.def_method,
                 service="auth",
                 action="login",
                 auth=auth,

clearml_agent/commands/resolver.py

@@ -1,6 +1,8 @@
 import json
 import re
 import shlex
+
+from clearml_agent.backend_api.session import Request
 from clearml_agent.helper.package.requirements import (
     RequirementsManager, MarkerRequirement,
     compare_version_rules, )
@@ -26,7 +28,7 @@ def resolve_default_container(session, task_id, container_config):
                               'script.repository', 'script.branch',
                               'project', 'container'],
               'search_hidden': True},
-        method='get',
+        method=Request.def_method,
         async_enable=False,
     )
     try:
@@ -53,7 +55,7 @@ def resolve_default_container(session, task_id, container_config):
                 'id': [task_info.get('project')],
                 'only_fields': ['name'],
             },
-            method='get',
+            method=Request.def_method,
             async_enable=False,
         )
         try:

clearml_agent/commands/worker.py

@@ -38,7 +38,7 @@ from clearml_agent.backend_api.services import auth as auth_api
 from clearml_agent.backend_api.services import queues as queues_api
 from clearml_agent.backend_api.services import tasks as tasks_api
 from clearml_agent.backend_api.services import workers as workers_api
-from clearml_agent.backend_api.session import CallResult
+from clearml_agent.backend_api.session import CallResult, Request
 from clearml_agent.backend_api.session.defs import (
     ENV_ENABLE_ENV_CONFIG_SECTION, ENV_ENABLE_FILES_CONFIG_SECTION,
     ENV_VENV_CONFIGURED, ENV_PROPAGATE_EXITCODE, )
@@ -71,6 +71,8 @@ from clearml_agent.definitions import (
     ENV_AGENT_SKIP_PYTHON_ENV_INSTALL,
     WORKING_STANDALONE_DIR,
     ENV_DEBUG_INFO,
+    ENV_CHILD_AGENTS_COUNT_CMD,
+    ENV_DOCKER_ARGS_FILTERS,
 )
 from clearml_agent.definitions import WORKING_REPOSITORY_DIR, PIP_EXTRA_INDICES
 from clearml_agent.errors import (
@@ -272,7 +274,7 @@ def get_task(session, task_id, **kwargs):
         action='get_all',
         version='2.14',
         json={"id": [task_id], "search_hidden": True, **kwargs},
-        method='get',
+        method=Request.def_method,
         async_enable=False,
     )
     result = CallResult.from_result(
@@ -304,7 +306,7 @@ def get_next_task(session, queue, get_task_info=False):
         action='get_next_task',
         version='2.14',
         json=request,
-        method='get',
+        method=Request.def_method,
         async_enable=False,
     )
     if not result.ok:
@@ -325,7 +327,7 @@ def get_task_container(session, task_id):
             action='get_all',
             version='2.14',
             json={'id': [task_id], 'only_fields': ['container'], 'search_hidden': True},
-            method='get',
+            method=Request.def_method,
             async_enable=False,
         )
         try:
@@ -366,7 +368,7 @@ def set_task_container(session, task_id, docker_image=None, docker_arguments=Non
             action='edit',
             version='2.13',
             json={'task': task_id, 'container': container, 'force': True},
-            method='get',
+            method=Request.def_method,
             async_enable=False,
         )
         return result.ok
@@ -685,6 +687,16 @@ class Worker(ServiceCommandSection):
         # str - not supported, version string indicates last server version
         self._runtime_props_support = None
 
+        # allow docker sanitization, needs backend support
+        if ENV_DOCKER_ARGS_FILTERS.get():
+            self._docker_args_filters = \
+                [re.compile(f) for f in shlex.split(ENV_DOCKER_ARGS_FILTERS.get())]
+        elif self._session.config.get('agent.docker_args_filters', None):
+            self._docker_args_filters = \
+                [re.compile(f) for f in self._session.config.get('agent.docker_args_filters', [])]
+        else:
+            self._docker_args_filters = []
+
     @classmethod
     def _verify_command_states(cls, kwargs):
         """
@@ -3268,6 +3280,11 @@ class Worker(ServiceCommandSection):
             first_time=first_time,
         )
 
+        # print message so users know they can enable cache
+        if not self.package_api.is_cached_enabled():
+            print('::: Python virtual environment cache is disabled. '
+                  'To accelerate spin-up time set `agent.venvs_cache.path=~/.clearml/venvs-cache` :::\n')
+
         # check if we have a cached folder
         if cached_requirements and not skip_pip_venv_install and self.package_api.get_cached_venv(
             requirements=cached_requirements,
@@ -3438,7 +3455,7 @@ class Worker(ServiceCommandSection):
                     '-v', '{}:{}'.format(ENV_SSH_AUTH_SOCK.get(), ENV_SSH_AUTH_SOCK.get()),
                     '-e', ssh_auth_sock_env,
                 ]
-        elif ENV_AGENT_DISABLE_SSH_MOUNT.get():
+        elif ENV_AGENT_DISABLE_SSH_MOUNT.get() or self._session.config.get("agent.disable_ssh_mount", None):
             self._host_ssh_cache = None
         else:
             self._host_ssh_cache = mkdtemp(prefix='clearml_agent.ssh.')
@@ -3589,15 +3606,11 @@ class Worker(ServiceCommandSection):
     def _get_child_agents_count_for_worker(self):
         """Get the amount of running child agents. In case of any error return 0"""
         parent_worker_label = self._parent_worker_label.format(self.worker_id)
-        cmd = [
-            'docker',
-            'ps',
-            '--filter',
-            'label={}'.format(parent_worker_label),
-            '--format',
-            # get some fields for debugging
-            '{"ID":"{{ .ID }}", "Image": "{{ .Image }}", "Names":"{{ .Names }}", "Labels":"{{ .Labels }}"}'
-        ]
+
+        default_cmd = 'docker ps --filter label={parent_worker_label} --format {{{{.ID}}}}'
+        child_agents_cmd = ENV_CHILD_AGENTS_COUNT_CMD.get() or default_cmd
+
+        cmd = shlex.split(child_agents_cmd.format(parent_worker_label=parent_worker_label))
         try:
             output = Argv(*cmd).get_output(
                 stderr=subprocess.STDOUT
@@ -3608,6 +3621,31 @@ class Worker(ServiceCommandSection):
 
         return len(output.splitlines()) if output else 0
 
+    def _filter_docker_args(self, docker_args):
+        # type: (List[str]) -> List[str]
+        """
+        Filter docker args matching specific flags.
+        Supports list of Regular expressions, e.g self._docker_args_filters = ["^--env$", "^-e$"]
+
+        :argument docker_args: List of docker argument strings (flags and values)
+        """
+        # if no filtering, do nothing
+        if not docker_args or not self._docker_args_filters:
+            return docker_args
+
+        args = docker_args[:]
+        results = []
+        while args:
+            cmd = args.pop(0).strip()
+            if any(f.match(cmd) for f in self._docker_args_filters):
+                results.append(cmd)
+                if "=" not in cmd and args and not args[0].startswith("-"):
+                    try:
+                        results.append(args.pop(0).strip())
+                    except IndexError:
+                        pass
+        return results
+
     def _get_docker_cmd(
             self,
             worker_id, parent_worker_id,
@@ -3661,6 +3699,7 @@ class Worker(ServiceCommandSection):
         if docker_arguments:
             docker_arguments = list(docker_arguments) \
                 if isinstance(docker_arguments, (list, tuple)) else [docker_arguments]
+            docker_arguments = self._filter_docker_args(docker_arguments)
             base_cmd += [a for a in docker_arguments if a]
 
         if extra_docker_arguments:

clearml_agent/definitions.py

@@ -149,6 +149,8 @@ ENV_DOCKER_HOST_MOUNT = EnvironmentConfig('CLEARML_AGENT_K8S_HOST_MOUNT', 'CLEAR
 ENV_VENV_CACHE_PATH = EnvironmentConfig('CLEARML_AGENT_VENV_CACHE_PATH')
 ENV_EXTRA_DOCKER_ARGS = EnvironmentConfig('CLEARML_AGENT_EXTRA_DOCKER_ARGS', type=list)
 ENV_DEBUG_INFO = EnvironmentConfig('CLEARML_AGENT_DEBUG_INFO')
+ENV_CHILD_AGENTS_COUNT_CMD = EnvironmentConfig('CLEARML_AGENT_CHILD_AGENTS_COUNT_CMD')
+ENV_DOCKER_ARGS_FILTERS = EnvironmentConfig('CLEARML_AGENT_DOCKER_ARGS_FILTERS')
 
 ENV_CUSTOM_BUILD_SCRIPT = EnvironmentConfig('CLEARML_AGENT_CUSTOM_BUILD_SCRIPT')
 """

clearml_agent/glue/k8s.py

@@ -27,8 +27,8 @@ from clearml_agent.helper.dicts import merge_dicts
 from clearml_agent.helper.process import get_bash_output
 from clearml_agent.helper.resource_monitor import ResourceMonitor
 from clearml_agent.interface.base import ObjectID
-
-from .definitions import ENV_START_AGENT_SCRIPT_PATH
+from clearml_agent.backend_api.session import Request
+from clearml_agent.glue.definitions import ENV_START_AGENT_SCRIPT_PATH
 
 
 class K8sIntegration(Worker):
@@ -299,7 +299,7 @@ class K8sIntegration(Worker):
                             service='tasks',
                             action='update',
                             json={"task": task_id, "status_message": "K8S glue status: {}".format(msg)},
-                            method='get',
+                            method=Request.def_method,
                             async_enable=False,
                         )
                         if not result.ok:

clearml_agent/helper/package/base.py

@@ -213,6 +213,13 @@ class PackageManager(object):
             return
         return self._get_cache_manager().get_last_copied_entry()
 
+    def is_cached_enabled(self):
+        if not self._cache_manager:
+            cache_folder = ENV_VENV_CACHE_PATH.get() or self.session.config.get(self._config_cache_folder, None)
+            if not cache_folder:
+                return False
+        return True
+
     @classmethod
     def _generate_reqs_hash_keys(cls, requirements_list, docker_cmd, python_version, cuda_version):
         # type: (Union[Dict, List[Dict]], Optional[Union[dict, str]], Optional[str], Optional[str]) -> List[str]

clearml_agent/helper/package/pytorch.py

@@ -53,17 +53,16 @@ class PytorchWheel(object):
     python = attr.ib(type=str, converter=lambda x: str(x).replace(".", ""))
     torch_version = attr.ib(type=str, converter=fix_version)
 
-    url_template = (
-        "http://download.pytorch.org/whl/"
-        "{0.cuda_version}/torch-{0.torch_version}-cp{0.python}-cp{0.python}m{0.unicode}-{0.os_name}.whl"
-    )
+    url_template_prefix = "http://download.pytorch.org/whl/"
+    url_template = "{0.cuda_version}/torch-{0.torch_version}" \
+                   "-cp{0.python}-cp{0.python}m{0.unicode}-{0.os_name}.whl"
 
     def __attrs_post_init__(self):
         self.unicode = "u" if self.python.startswith("2") else ""
 
     def make_url(self):
         # type: () -> Text
-        return self.url_template.format(self)
+        return (self.url_template_prefix + self.url_template).format(self)
 
 
 class PytorchResolutionError(FatalSpecsResolutionError):
@@ -183,6 +182,19 @@ class PytorchRequirement(SimpleSubstitution):
         self._fix_setuptools = None
         self.exceptions = []
         self._original_req = []
+        # allow override pytorch lookup pages
+        if self.config.get("agent.package_manager.torch_page", None):
+            SimplePytorchRequirement.page_lookup_template = \
+                self.config.get("agent.package_manager.torch_page", None)
+        if self.config.get("agent.package_manager.torch_nightly_page", None):
+            SimplePytorchRequirement.nightly_page_lookup_template = \
+                self.config.get("agent.package_manager.torch_nightly_page", None)
+        if self.config.get("agent.package_manager.torch_url_template_prefix", None):
+            PytorchWheel.url_template_prefix = \
+                self.config.get("agent.package_manager.torch_url_template_prefix", None)
+        if self.config.get("agent.package_manager.torch_url_template", None):
+            PytorchWheel.url_template = \
+                self.config.get("agent.package_manager.torch_url_template", None)
 
     def _init_python_ver_cuda_ver(self):
         if self.cuda is None:

clearml_agent/helper/resource_monitor.py

@@ -92,9 +92,10 @@ class ResourceMonitor(object):
             # None means no filtering, report all gpus
             self._active_gpus = None
             try:
-                active_gpus = Session.get_nvidia_visible_env() or ""
-                if active_gpus:
-                    self._active_gpus = [g.strip() for g in active_gpus.split(',')]
+                active_gpus = Session.get_nvidia_visible_env()
+                # None means no filtering, report all gpus
+                if active_gpus and active_gpus != "all":
+                    self._active_gpus = [g.strip() for g in str(active_gpus).split(',')]
             except Exception:
                 pass
 

clearml_agent/session.py

@@ -288,7 +288,7 @@ class Session(_Session):
     def get(self, service, action, version=None, headers=None,
             data=None, json=None, async_enable=False, **kwargs):
         return self._manual_request(service=service, action=action,
-                                    version=version, method="get", headers=headers,
+                                    version=version, method=Request.def_method, headers=headers,
                                     data=data, async_enable=async_enable,
                                     json=json or kwargs)
 
@@ -299,7 +299,7 @@ class Session(_Session):
                                     data=data, async_enable=async_enable,
                                     json=json or kwargs)
 
-    def _manual_request(self, service, action, version=None, method="get", headers=None,
+    def _manual_request(self, service, action, version=None, method=Request.def_method, headers=None,
             data=None, json=None, async_enable=False, **kwargs):
 
         res = self.send_request(service=service, action=action,

clearml_agent/version.py

@@ -1 +1 @@
-__version__ = '1.3.0'
+__version__ = '1.4.1'

docs/clearml.conf

@@ -136,6 +136,12 @@ agent {
     },
 
     translate_ssh: true,
+
+    # set "disable_ssh_mount: true" to disable the automatic mount of ~/.ssh folder into the docker containers
+    # default is false, automatically mounts ~/.ssh
+    # Must be set to True if using "clearml-session" with this agent!
+    # disable_ssh_mount: false
+
     # reload configuration file every daemon execution
     reload_config: false,