Print error on resource monitor failure

clearml_agent/backend_api/utils.py

@@ -86,7 +86,10 @@ def get_http_session_with_retry(
     session = requests.Session()
 
     if backoff_max is not None:
-        Retry.BACKOFF_MAX = backoff_max
+        if "BACKOFF_MAX" in vars(Retry):
+            Retry.BACKOFF_MAX = backoff_max
+        else:
+            Retry.DEFAULT_BACKOFF_MAX = backoff_max
 
     retry = Retry(
         total=total, connect=connect, read=read, redirect=redirect, status=status,

clearml_agent/backend_config/config.py

@@ -297,6 +297,9 @@ class Config(object):
     def put(self, key, value):
         self._config.put(key, value)
 
+    def pop(self, key, default=None):
+        return self._config.pop(key, default=default)
+
     def to_dict(self):
         return self._config.as_plain_ordered_dict()
 

clearml_agent/commands/worker.py

@@ -40,6 +40,7 @@ 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, )
+from clearml_agent.backend_config import Config
 from clearml_agent.backend_config.defs import UptimeConf
 from clearml_agent.backend_config.utils import apply_environment, apply_files
 from clearml_agent.backend_config.converters import text_to_int
@@ -71,6 +72,7 @@ from clearml_agent.definitions import (
     ENV_DOCKER_ARGS_FILTERS,
     ENV_FORCE_SYSTEM_SITE_PACKAGES,
     ENV_SERVICES_DOCKER_RESTART,
+    ENV_CONFIG_BC_IN_STANDALONE,
 )
 from clearml_agent.definitions import WORKING_REPOSITORY_DIR, PIP_EXTRA_INDICES
 from clearml_agent.errors import (
@@ -3515,6 +3517,11 @@ class Worker(ServiceCommandSection):
         requirements_manager.translator.enabled = False
         print(requirements_manager.replace(contents))
 
+    def remove_non_backwards_compatible_entries(self, config: Config):
+        if not self._standalone_mode or not ENV_CONFIG_BC_IN_STANDALONE.get() or self._session.feature_set == "basic":
+            return
+        config.pop("agent.package_manager.pip_version")  # removed due to a breaking change in v1.5.1
+
     def get_docker_config_cmd(self, docker_args, clean_api_credentials=False):
         docker_image = str(ENV_DOCKER_IMAGE.get() or
                            self._session.config.get("agent.default_docker.image", "nvidia/cuda")) \
@@ -3537,6 +3544,7 @@ class Worker(ServiceCommandSection):
             DockerArgsSanitizer.sanitize_docker_command(self._session, self._docker_arguments) or ''))
 
         temp_config = deepcopy(self._session.config)
+        self.remove_non_backwards_compatible_entries(temp_config)
         mounted_cache_dir = temp_config.get(
             "agent.docker_internal_mounts.sdk_cache", self._docker_fixed_user_cache)
         mounted_pip_dl_dir = temp_config.get(

clearml_agent/definitions.py

@@ -177,6 +177,8 @@ 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_DOCKER_ARGS_HIDE_ENV = EnvironmentConfig("CLEARML_AGENT_DOCKER_ARGS_HIDE_ENV")
+ENV_CONFIG_BC_IN_STANDALONE = EnvironmentConfig("CLEARML_AGENT_STANDALONE_CONFIG_BC", type=bool)
+""" Maintain backwards compatible configuration when launching in standalone mode """
 
 ENV_SERVICES_DOCKER_RESTART = EnvironmentConfig("CLEARML_AGENT_SERVICES_DOCKER_RESTART")
 """

clearml_agent/helper/package/external_req.py

@@ -92,21 +92,14 @@ class ExternalRequirements(SimpleSubstitution):
                 vcs_url = req_line[4:]
                 # reverse replace
                 vcs_url = vcs_url[::-1].replace(fragment[::-1], '', 1)[::-1]
-                # remove ssh:// or git:// prefix for git detection and credentials
-                scheme = ''
-                full_vcs_url = vcs_url
-                if vcs_url and (vcs_url.startswith('ssh://') or vcs_url.startswith('git://')):
-                    scheme = 'ssh://'  # notice git:// is actually ssh://
-                    vcs_url = vcs_url[6:]
+                # notice git:// is actually ssh://
+                if vcs_url and vcs_url.startswith('git://'):
+                    vcs_url = vcs_url.replace('git://', 'ssh://', 1)
 
                 from ..repo import Git
-                vcs = Git(session=session, url=full_vcs_url, location=None, revision=None)
+                vcs = Git(session=session, url=vcs_url, location=None, revision=None)
                 vcs._set_ssh_url()
-                new_req_line = 'git+{}{}{}'.format(
-                    '' if scheme and '://' in vcs.url else scheme,
-                    vcs_url if session.config.get('agent.force_git_ssh_protocol', None) else vcs.url_with_auth,
-                    fragment
-                )
+                new_req_line = 'git+{}{}'.format(vcs.url_with_auth, fragment)
                 if new_req_line != req_line:
                     furl_line = furl(new_req_line)
                     print('Replacing original pip vcs \'{}\' with \'{}\''.format(

clearml_agent/helper/repo.py

@@ -320,6 +320,7 @@ class VCS(object):
                         self.url, new_url))
                     self.url = new_url
                 return
+
             # rewrite ssh URLs only if either ssh port or ssh user are forced in config
             if parsed_url.scheme == "ssh" and (
                 self.session.config.get('agent.force_git_ssh_port', None) or
@@ -334,6 +335,9 @@ class VCS(object):
                     print("Using SSH credentials - ssh url '{}' with ssh url '{}'".format(
                         self.url, new_url))
                     self.url = new_url
+                return
+            elif parsed_url.scheme == "ssh":
+                return
 
         if not self.session.config.agent.translate_ssh:
             return
@@ -343,7 +347,7 @@ class VCS(object):
                 (ENV_AGENT_GIT_PASS.get() or self.session.config.get('agent.git_pass', None)):
             # only apply to a specific domain (if requested)
             config_domain = \
-                ENV_AGENT_GIT_HOST.get() or self.session.config.get("git_host", None)
+                ENV_AGENT_GIT_HOST.get() or self.session.config.get("agent.git_host", None)
             if config_domain and config_domain != furl(self.url).host:
                 return
 

clearml_agent/helper/resource_monitor.py

@@ -139,42 +139,45 @@ class ResourceMonitor(object):
     def _daemon(self):
         seconds_since_started = 0
         reported = 0
-        while True:
-            last_report = time()
-            current_report_frequency = (
-                self._report_frequency if reported != 0 else self._first_report_sec
-            )
-            while (time() - last_report) < current_report_frequency:
-                # wait for self._sample_frequency seconds, if event set quit
-                if self._exit_event.wait(1 / self._sample_frequency):
-                    return
-                # noinspection PyBroadException
-                try:
-                    self._update_readouts()
-                except Exception as ex:
-                    log.warning("failed getting machine stats: %s", report_error(ex))
-                    self._failure()
+        try:
+            while True:
+                last_report = time()
+                current_report_frequency = (
+                    self._report_frequency if reported != 0 else self._first_report_sec
+                )
+                while (time() - last_report) < current_report_frequency:
+                    # wait for self._sample_frequency seconds, if event set quit
+                    if self._exit_event.wait(1 / self._sample_frequency):
+                        return
+                    # noinspection PyBroadException
+                    try:
+                        self._update_readouts()
+                    except Exception as ex:
+                        log.warning("failed getting machine stats: %s", report_error(ex))
+                        self._failure()
 
-            seconds_since_started += int(round(time() - last_report))
-            # check if we do not report any metric (so it means the last iteration will not be changed)
+                seconds_since_started += int(round(time() - last_report))
+                # check if we do not report any metric (so it means the last iteration will not be changed)
 
-            # if we do not have last_iteration, we just use seconds as iteration
+                # if we do not have last_iteration, we just use seconds as iteration
 
-            # start reporting only when we figured out, if this is seconds based, or iterations based
-            average_readouts = self._get_average_readouts()
-            stats = {
-                # 3 points after the dot
-                key: round(value, 3) if isinstance(value, float) else [round(v, 3) for v in value]
-                for key, value in average_readouts.items()
-            }
+                # start reporting only when we figured out, if this is seconds based, or iterations based
+                average_readouts = self._get_average_readouts()
+                stats = {
+                    # 3 points after the dot
+                    key: round(value, 3) if isinstance(value, float) else [round(v, 3) for v in value]
+                    for key, value in average_readouts.items()
+                }
 
-            # send actual report
-            if self.send_report(stats):
-                # clear readouts if this is update was sent
-                self._clear_readouts()
+                # send actual report
+                if self.send_report(stats):
+                    # clear readouts if this is update was sent
+                    self._clear_readouts()
 
-            # count reported iterations
-            reported += 1
+                # count reported iterations
+                reported += 1
+        except Exception as ex:
+            log.exception("Error reporting monitoring info: %s", str(ex))
 
     def _update_readouts(self):
         readouts = self._machine_stats()