Merge branch 'master' into upgrade-api-server-dependencies

bisgaard-itis · bisgaard-itis · commit 92dc0b0d84b8 · 2024-12-09T15:04:03.000+01:00
diff --git a/.env-devel b/.env-devel
@@ -17,12 +17,12 @@ AGENT_VOLUMES_CLEANUP_S3_ENDPOINT=http://172.17.0.1:9001
 AGENT_VOLUMES_CLEANUP_S3_PROVIDER=MINIO
 AGENT_VOLUMES_CLEANUP_S3_REGION=us-east-1
 AGENT_VOLUMES_CLEANUP_S3_SECRET_KEY=12345678
-AGENT_TRACING={}
+AGENT_TRACING=null
 
 API_SERVER_DEV_FEATURES_ENABLED=0
 API_SERVER_LOGLEVEL=INFO
 API_SERVER_PROFILING=1
-API_SERVER_TRACING={}
+API_SERVER_TRACING=null
 TRAEFIK_API_SERVER_INFLIGHTREQ_AMOUNT=25
 
 AUTOSCALING_DASK=null
@@ -35,7 +35,7 @@ AUTOSCALING_LOGLEVEL=INFO
 AUTOSCALING_NODES_MONITORING=null
 AUTOSCALING_POLL_INTERVAL="00:00:10"
 AUTOSCALING_SSM_ACCESS=null
-AUTOSCALING_TRACING={}
+AUTOSCALING_TRACING=null
 
 AWS_S3_CLI_S3=null
 
@@ -47,7 +47,7 @@ CATALOG_PORT=8000
 CATALOG_PROFILING=1
 CATALOG_SERVICES_DEFAULT_RESOURCES='{"CPU": {"limit": 0.1, "reservation": 0.1}, "RAM": {"limit": 2147483648, "reservation": 2147483648}}'
 CATALOG_SERVICES_DEFAULT_SPECIFICATIONS='{}'
-CATALOG_TRACING={}
+CATALOG_TRACING=null
 
 CLUSTERS_KEEPER_COMPUTATIONAL_BACKEND_DEFAULT_CLUSTER_AUTH='{"type":"tls","tls_ca_file":"/home/scu/.dask/dask-crt.pem","tls_client_cert":"/home/scu/.dask/dask-crt.pem","tls_client_key":"/home/scu/.dask/dask-key.pem"}'
 CLUSTERS_KEEPER_COMPUTATIONAL_BACKEND_DOCKER_IMAGE_TAG=master-github-latest
@@ -61,7 +61,7 @@ CLUSTERS_KEEPER_MAX_MISSED_HEARTBEATS_BEFORE_CLUSTER_TERMINATION=5
 CLUSTERS_KEEPER_PRIMARY_EC2_INSTANCES=null
 CLUSTERS_KEEPER_TASK_INTERVAL=00:00:30
 CLUSTERS_KEEPER_WORKERS_EC2_INSTANCES=null
-CLUSTERS_KEEPER_TRACING={}
+CLUSTERS_KEEPER_TRACING=null
 
 DASK_SCHEDULER_HOST=dask-scheduler
 DASK_SCHEDULER_PORT=8786
@@ -81,7 +81,7 @@ DIRECTOR_PUBLISHED_HOST_NAME="127.0.0.1:9081"
 DIRECTOR_REGISTRY_CACHING_TTL=00:15:00
 DIRECTOR_REGISTRY_CACHING=True
 DIRECTOR_SERVICES_CUSTOM_CONSTRAINTS=null
-DIRECTOR_TRACING={}
+DIRECTOR_TRACING=null
 
 EFS_USER_ID=8006
 EFS_USER_NAME=efs
@@ -90,11 +90,11 @@ EFS_GROUP_NAME=efs-group
 EFS_DNS_NAME=fs-xxx.efs.us-east-1.amazonaws.com
 EFS_MOUNTED_PATH=/tmp/efs
 EFS_PROJECT_SPECIFIC_DATA_DIRECTORY=project-specific-data
-EFS_GUARDIAN_TRACING={}
+EFS_GUARDIAN_TRACING=null
 EFS_DEFAULT_USER_SERVICE_SIZE_BYTES=10000
 
 # DATCORE_ADAPTER
-DATCORE_ADAPTER_TRACING={}
+DATCORE_ADAPTER_TRACING=null
 
 # DIRECTOR_V2 ----
 COMPUTATIONAL_BACKEND_DEFAULT_CLUSTER_AUTH='{"type":"tls","tls_ca_file":"/home/scu/.dask/dask-crt.pem","tls_client_cert":"/home/scu/.dask/dask-crt.pem","tls_client_key":"/home/scu/.dask/dask-key.pem"}'
@@ -121,14 +121,14 @@ DYNAMIC_SIDECAR_LOG_LEVEL=DEBUG
 DYNAMIC_SIDECAR_PROMETHEUS_MONITORING_NETWORKS=[]
 DYNAMIC_SIDECAR_PROMETHEUS_SERVICE_LABELS={}
 DYNAMIC_SIDECAR_API_SAVE_RESTORE_STATE_TIMEOUT=01:00:00
-DIRECTOR_V2_TRACING={}
+DIRECTOR_V2_TRACING=null
 
 # DYNAMIC_SCHEDULER ----
 DYNAMIC_SCHEDULER_LOGLEVEL=DEBUG
 DYNAMIC_SCHEDULER_PROFILING=1
 DYNAMIC_SCHEDULER_USE_INTERNAL_SCHEDULER=0
 DYNAMIC_SCHEDULER_STOP_SERVICE_TIMEOUT=01:00:00
-DYNAMIC_SCHEDULER_TRACING={}
+DYNAMIC_SCHEDULER_TRACING=null
 DYNAMIC_SCHEDULER_UI_STORAGE_SECRET=adminadmin
 
 FUNCTION_SERVICES_AUTHORS='{"UN": {"name": "Unknown", "email": "unknown@osparc.io", "affiliation": "unknown"}}'
@@ -143,7 +143,7 @@ INVITATIONS_PORT=8000
 INVITATIONS_SECRET_KEY='REPLACE_ME_with_result__Fernet_generate_key='
 INVITATIONS_SWAGGER_API_DOC_ENABLED=1
 INVITATIONS_USERNAME=admin
-INVITATIONS_TRACING={}
+INVITATIONS_TRACING=null
 
 LOG_FORMAT_LOCAL_DEV_ENABLED=1
 LOG_FILTER_MAPPING='{}'
@@ -168,7 +168,7 @@ PAYMENTS_STRIPE_API_SECRET='REPLACE_ME_with_api_secret'
 PAYMENTS_STRIPE_URL=https://api.stripe.com
 PAYMENTS_SWAGGER_API_DOC_ENABLED=1
 PAYMENTS_USERNAME=admin
-PAYMENTS_TRACING={}
+PAYMENTS_TRACING=null
 
 POSTGRES_DB=simcoredb
 POSTGRES_ENDPOINT=postgres:5432
@@ -209,7 +209,7 @@ RESOURCE_USAGE_TRACKER_MISSED_HEARTBEAT_CHECK_ENABLED=1
 RESOURCE_USAGE_TRACKER_MISSED_HEARTBEAT_COUNTER_FAIL=6
 RESOURCE_USAGE_TRACKER_MISSED_HEARTBEAT_INTERVAL_SEC=300
 RESOURCE_USAGE_TRACKER_S3=null
-RESOURCE_USAGE_TRACKER_TRACING={}
+RESOURCE_USAGE_TRACKER_TRACING=null
 
 # NOTE: 172.17.0.1 is the docker0 interface, which redirect from inside a container onto the host network interface.
 R_CLONE_OPTION_BUFFER_SIZE=16M
@@ -243,7 +243,7 @@ STORAGE_HOST=storage
 STORAGE_LOGLEVEL=INFO
 STORAGE_PORT=8080
 STORAGE_PROFILING=1
-STORAGE_TRACING={}
+STORAGE_TRACING=null
 # STORAGE ----
 
 SWARM_STACK_NAME=master-simcore
@@ -389,6 +389,6 @@ WEBSERVER_SOCKETIO=1
 WEBSERVER_STATICWEB={}
 WEBSERVER_STUDIES_DISPATCHER={}
 WEBSERVER_TAGS=1
-WEBSERVER_TRACING={}
+WEBSERVER_TRACING=null
 WEBSERVER_USERS={}
 WEBSERVER_VERSION_CONTROL=1
diff --git a/.github/workflows/ci-testing-deploy.yml b/.github/workflows/ci-testing-deploy.yml
@@ -2664,11 +2664,14 @@ jobs:
 
   system-api-specs:
     needs: [changes]
-    if: ${{ needs.changes.outputs.anything-py == 'true' && github.event_name == 'push' && github.event.pull_request != null }}
+    if: ${{ needs.changes.outputs.anything-py == 'true' || github.event_name == 'push' }}
     timeout-minutes: 10
     name: "[sys] check api-specs are up to date"
     runs-on: ubuntu-latest
     steps:
+      - name: Ensure job passes if not PR # ensure pass so upstream jobs which depend on this will run (dockerhub deployment)
+        if: ${{ github.event.pull_request == null }}
+        run: echo "::notice Passing job because not in PR"; exit 0
       - name: setup python environment
         uses: actions/setup-python@v5
         with:
@@ -2690,11 +2693,14 @@ jobs:
 
   system-backwards-compatibility:
     needs: [changes, system-api-specs]
-    if: ${{ needs.changes.outputs.anything-py == 'true' && github.event_name == 'push' && github.event.pull_request != null }}
+    if: ${{ needs.changes.outputs.anything-py == 'true' || github.event_name == 'push' }}
     timeout-minutes: 10
     name: "[sys] api-server backwards compatibility"
     runs-on: ubuntu-latest
     steps:
+      - name: Ensure job passes if not PR # ensure pass so upstream jobs which depend on this will run (dockerhub deployment)
+        if: ${{ github.event.pull_request == null }}
+        run: echo "::notice Passing job because not in PR"; exit 0
       - name: setup python environment
         uses: actions/setup-python@v5
         with:
diff --git a/services/resource-usage-tracker/src/simcore_service_resource_usage_tracker/api/rest/routes.py b/services/resource-usage-tracker/src/simcore_service_resource_usage_tracker/api/rest/routes.py
@@ -1,16 +1,26 @@
+import logging
+
 from fastapi import APIRouter, FastAPI
+from servicelib.logging_utils import log_context
 
 from ..._meta import API_VTAG
 from . import _health, _meta, _resource_tracker
 
+_logger = logging.getLogger(__name__)
+
 
 def setup_api_routes(app: FastAPI):
     """
     Composes resources/sub-resources routers
     """
-    app.include_router(_health.router)
+    with log_context(
+        _logger,
+        logging.INFO,
+        msg="RUT setup_api_routes",
+    ):
+        app.include_router(_health.router)
 
-    api_router = APIRouter(prefix=f"/{API_VTAG}")
-    api_router.include_router(_meta.router, tags=["meta"])
-    api_router.include_router(_resource_tracker.router)
-    app.include_router(api_router)
+        api_router = APIRouter(prefix=f"/{API_VTAG}")
+        api_router.include_router(_meta.router, tags=["meta"])
+        api_router.include_router(_resource_tracker.router)
+        app.include_router(api_router)
diff --git a/services/resource-usage-tracker/src/simcore_service_resource_usage_tracker/api/rpc/routes.py b/services/resource-usage-tracker/src/simcore_service_resource_usage_tracker/api/rpc/routes.py
@@ -1,23 +1,34 @@
+import logging
+
 from fastapi import FastAPI
 from models_library.api_schemas_resource_usage_tracker import (
     RESOURCE_USAGE_TRACKER_RPC_NAMESPACE,
 )
+from servicelib.logging_utils import log_context
 from servicelib.rabbitmq import RPCRouter
 
 from ...services.modules.rabbitmq import get_rabbitmq_rpc_server
 from . import _resource_tracker
 
+_logger = logging.getLogger(__name__)
+
+
 ROUTERS: list[RPCRouter] = [
     _resource_tracker.router,
 ]
 
 
 def setup_rpc_api_routes(app: FastAPI) -> None:
     async def startup() -> None:
-        rpc_server = get_rabbitmq_rpc_server(app)
-        for router in ROUTERS:
-            await rpc_server.register_router(
-                router, RESOURCE_USAGE_TRACKER_RPC_NAMESPACE, app
-            )
+        with log_context(
+            _logger,
+            logging.INFO,
+            msg="RUT startup RPC API Routes",
+        ):
+            rpc_server = get_rabbitmq_rpc_server(app)
+            for router in ROUTERS:
+                await rpc_server.register_router(
+                    router, RESOURCE_USAGE_TRACKER_RPC_NAMESPACE, app
+                )
 
     app.add_event_handler("startup", startup)
diff --git a/services/resource-usage-tracker/src/simcore_service_resource_usage_tracker/services/modules/db/__init__.py b/services/resource-usage-tracker/src/simcore_service_resource_usage_tracker/services/modules/db/__init__.py
@@ -1,13 +1,28 @@
+import logging
+
 from fastapi import FastAPI
 from servicelib.fastapi.db_asyncpg_engine import close_db_connection, connect_to_db
+from servicelib.logging_utils import log_context
+
+_logger = logging.getLogger(__name__)
 
 
 def setup(app: FastAPI):
     async def on_startup() -> None:
-        await connect_to_db(app, app.state.settings.RESOURCE_USAGE_TRACKER_POSTGRES)
+        with log_context(
+            _logger,
+            logging.INFO,
+            msg="RUT startup DB",
+        ):
+            await connect_to_db(app, app.state.settings.RESOURCE_USAGE_TRACKER_POSTGRES)
 
     async def on_shutdown() -> None:
-        await close_db_connection(app)
+        with log_context(
+            _logger,
+            logging.INFO,
+            msg="RUT shutdown DB",
+        ):
+            await close_db_connection(app)
 
     app.add_event_handler("startup", on_startup)
     app.add_event_handler("shutdown", on_shutdown)
diff --git a/services/resource-usage-tracker/src/simcore_service_resource_usage_tracker/services/modules/rabbitmq.py b/services/resource-usage-tracker/src/simcore_service_resource_usage_tracker/services/modules/rabbitmq.py
@@ -3,6 +3,7 @@
 
 from fastapi import FastAPI
 from fastapi.requests import Request
+from servicelib.logging_utils import log_context
 from servicelib.rabbitmq import (
     RabbitMQClient,
     RabbitMQRPCClient,
@@ -12,32 +13,42 @@
 
 from ...exceptions.errors import ConfigurationError
 
-logger = logging.getLogger(__name__)
+_logger = logging.getLogger(__name__)
 
 
 def setup(app: FastAPI) -> None:
     async def on_startup() -> None:
-        app.state.rabbitmq_client = None
-        settings: RabbitSettings | None = (
-            app.state.settings.RESOURCE_USAGE_TRACKER_RABBITMQ
-        )
-        if not settings:
-            raise ConfigurationError(
-                msg="Rabbit MQ client is de-activated in the settings"
+        with log_context(
+            _logger,
+            logging.INFO,
+            msg="RUT startup Rabbitmq",
+        ):
+            app.state.rabbitmq_client = None
+            settings: RabbitSettings | None = (
+                app.state.settings.RESOURCE_USAGE_TRACKER_RABBITMQ
+            )
+            if not settings:
+                raise ConfigurationError(
+                    msg="Rabbit MQ client is de-activated in the settings"
+                )
+            await wait_till_rabbitmq_responsive(settings.dsn)
+            app.state.rabbitmq_client = RabbitMQClient(
+                client_name="resource-usage-tracker", settings=settings
+            )
+            app.state.rabbitmq_rpc_server = await RabbitMQRPCClient.create(
+                client_name="resource_usage_tracker_rpc_server", settings=settings
             )
-        await wait_till_rabbitmq_responsive(settings.dsn)
-        app.state.rabbitmq_client = RabbitMQClient(
-            client_name="resource-usage-tracker", settings=settings
-        )
-        app.state.rabbitmq_rpc_server = await RabbitMQRPCClient.create(
-            client_name="resource_usage_tracker_rpc_server", settings=settings
-        )
 
     async def on_shutdown() -> None:
-        if app.state.rabbitmq_client:
-            await app.state.rabbitmq_client.close()
-        if app.state.rabbitmq_rpc_server:
-            await app.state.rabbitmq_rpc_server.close()
+        with log_context(
+            _logger,
+            logging.INFO,
+            msg="RUT shutdown Rabbitmq",
+        ):
+            if app.state.rabbitmq_client:
+                await app.state.rabbitmq_client.close()
+            if app.state.rabbitmq_rpc_server:
+                await app.state.rabbitmq_rpc_server.close()
 
     app.add_event_handler("startup", on_startup)
     app.add_event_handler("shutdown", on_shutdown)
diff --git a/services/resource-usage-tracker/src/simcore_service_resource_usage_tracker/services/modules/redis.py b/services/resource-usage-tracker/src/simcore_service_resource_usage_tracker/services/modules/redis.py
@@ -2,28 +2,39 @@
 from typing import cast
 
 from fastapi import FastAPI
+from servicelib.logging_utils import log_context
 from servicelib.redis import RedisClientSDK
 from settings_library.redis import RedisDatabase, RedisSettings
 
 from ..._meta import APP_NAME
 
-logger = logging.getLogger(__name__)
+_logger = logging.getLogger(__name__)
 
 
 def setup(app: FastAPI) -> None:
     async def on_startup() -> None:
-        app.state.redis_client_sdk = None
-        settings: RedisSettings = app.state.settings.RESOURCE_USAGE_TRACKER_REDIS
-        redis_locks_dsn = settings.build_redis_dsn(RedisDatabase.LOCKS)
-        app.state.redis_client_sdk = client = RedisClientSDK(
-            redis_locks_dsn, client_name=APP_NAME
-        )
-        await client.setup()
+        with log_context(
+            _logger,
+            logging.INFO,
+            msg="RUT startup Redis",
+        ):
+            app.state.redis_client_sdk = None
+            settings: RedisSettings = app.state.settings.RESOURCE_USAGE_TRACKER_REDIS
+            redis_locks_dsn = settings.build_redis_dsn(RedisDatabase.LOCKS)
+            app.state.redis_client_sdk = client = RedisClientSDK(
+                redis_locks_dsn, client_name=APP_NAME
+            )
+            await client.setup()
 
     async def on_shutdown() -> None:
-        redis_client_sdk: None | RedisClientSDK = app.state.redis_client_sdk
-        if redis_client_sdk:
-            await redis_client_sdk.shutdown()
+        with log_context(
+            _logger,
+            logging.INFO,
+            msg="RUT shutdown Redis",
+        ):
+            redis_client_sdk: None | RedisClientSDK = app.state.redis_client_sdk
+            if redis_client_sdk:
+                await redis_client_sdk.shutdown()
 
     app.add_event_handler("startup", on_startup)
     app.add_event_handler("shutdown", on_shutdown)
diff --git a/services/resource-usage-tracker/src/simcore_service_resource_usage_tracker/services/modules/s3.py b/services/resource-usage-tracker/src/simcore_service_resource_usage_tracker/services/modules/s3.py
diff --git a/services/resource-usage-tracker/src/simcore_service_resource_usage_tracker/services/process_message_running_service_setup.py b/services/resource-usage-tracker/src/simcore_service_resource_usage_tracker/services/process_message_running_service_setup.py
