feat(engine): add composition metrics (#476)

Author: masontikhonov

charts/cf-runtime/Chart.yaml

@@ -1,7 +1,7 @@
 apiVersion: v2
 description: A Helm chart for Codefresh Runner
 name: cf-runtime
-version: 6.3.38
+version: 6.3.39
 keywords:
   - codefresh
   - runner
@@ -18,7 +18,20 @@ annotations:
   # Supported kinds: `added`, `changed`, `deprecated`, `removed`, `fixed`, `security`:
   artifacthub.io/changes: |
     - kind: changed
-      description: Downgrade dind image to 26.0.0-1.28.6
+      description: Engine image updated to 1.173.2
+    - kind: changed
+      description: Engine image size reduced by 70%
+    - kind: added
+      description: Added METRICS_PROMETHEUS_HOST and METRICS_PROMETHEUS_COLLECT_PROCESS_METRICS engine env variables
+    - kind: changed
+      description: [BREAKING CHANGE] By default, process metrics will not be collected by the engine. Use METRICS_PROMETHEUS_COLLECT_PROCESS_METRICS=true env variable to enable it
+    - kind: deprecated
+      description: The following engine metrics are deprecated and disabled by default: workflow_step_status, workflow_step_duration, workflow_phase_status, workflow_phase_duration, workflow_status, workflow_duration, workflow_docker_lib_reuse, workflow_cf_volume_reuse. Use METRICS_PROMETHEUS_ENABLE_LEGACY_METRICS=true env variable to enable them. These metrics will be removed in future versions, please consider migrating to new metrics.
+    - kind: added
+      description: New engine metrics are added. Please check the documentation for more details
+      links:
+        - name: Engine metrics documentation
+          url: https://codefresh.io/docs/docs/kb/articles/enable-engine-pod-metrics
 dependencies:
   - name: cf-common
     repository: oci://quay.io/codefresh/charts

charts/cf-runtime/README.md

@@ -1,6 +1,6 @@
 ## Codefresh Runner
 
-![Version: 6.3.38](https://img.shields.io/badge/Version-6.3.38-informational?style=flat-square)
+![Version: 6.3.39](https://img.shields.io/badge/Version-6.3.39-informational?style=flat-square)
 
 Helm chart for deploying [Codefresh Runner](https://codefresh.io/docs/docs/installation/codefresh-runner/) to Kubernetes.
 
@@ -1142,17 +1142,20 @@ Go to [https://<YOUR_ONPREM_DOMAIN_HERE>/admin/runtime-environments/system](http
 | runtime.dind.userVolumeMounts | object | `{}` | Add extra volume mounts |
 | runtime.dind.userVolumes | object | `{}` | Add extra volumes |
 | runtime.dindDaemon | object | See below | DinD pod daemon config |
-| runtime.engine | object | `{"affinity":{},"command":["npm","run","start"],"env":{"CONTAINER_LOGGER_EXEC_CHECK_INTERVAL_MS":1000,"DOCKER_REQUEST_TIMEOUT_MS":30000,"FORCE_COMPOSE_SERIAL_PULL":false,"LOGGER_LEVEL":"debug","LOG_OUTGOING_HTTP_REQUESTS":false,"METRICS_PROMETHEUS_ENABLED":true},"image":{"pullPolicy":"IfNotPresent","registry":"quay.io","repository":"codefresh/engine","tag":"1.171.3"},"nodeSelector":{},"podAnnotations":{},"podLabels":{},"resources":{"limits":{"cpu":"1000m","memory":"2048Mi"},"requests":{"cpu":"100m","memory":"128Mi"}},"runtimeImages":{"COMPOSE_IMAGE":"quay.io/codefresh/compose:v2.20.3-1.4.0","CONTAINER_LOGGER_IMAGE":"quay.io/codefresh/cf-container-logger:1.11.4","CR_6177_FIXER":"quay.io/codefresh/alpine:edge","DOCKER_BUILDER_IMAGE":"quay.io/codefresh/cf-docker-builder:1.3.11","DOCKER_PULLER_IMAGE":"quay.io/codefresh/cf-docker-puller:8.0.17","DOCKER_PUSHER_IMAGE":"quay.io/codefresh/cf-docker-pusher:6.0.15","DOCKER_TAG_PUSHER_IMAGE":"quay.io/codefresh/cf-docker-tag-pusher:1.3.13","FS_OPS_IMAGE":"quay.io/codefresh/fs-ops:1.2.3","GC_BUILDER_IMAGE":"quay.io/codefresh/cf-gc-builder:0.5.3","GIT_CLONE_IMAGE":"quay.io/codefresh/cf-git-cloner:10.1.26","KUBE_DEPLOY":"quay.io/codefresh/cf-deploy-kubernetes:16.1.11","PIPELINE_DEBUGGER_IMAGE":"quay.io/codefresh/cf-debugger:1.3.0","TEMPLATE_ENGINE":"quay.io/codefresh/pikolo:0.14.0"},"schedulerName":"","serviceAccount":"codefresh-engine","tolerations":[],"userEnvVars":[],"workflowLimits":{"MAXIMUM_ALLOWED_TIME_BEFORE_PRE_STEPS_SUCCESS":600,"MAXIMUM_ALLOWED_WORKFLOW_AGE_BEFORE_TERMINATION":86400,"MAXIMUM_ELECTED_STATE_AGE_ALLOWED":900,"MAXIMUM_RETRY_ATTEMPTS_ALLOWED":20,"MAXIMUM_TERMINATING_STATE_AGE_ALLOWED":900,"MAXIMUM_TERMINATING_STATE_AGE_ALLOWED_WITHOUT_UPDATE":300,"TIME_ENGINE_INACTIVE_UNTIL_TERMINATION":300,"TIME_ENGINE_INACTIVE_UNTIL_UNHEALTHY":60,"TIME_INACTIVE_UNTIL_TERMINATION":2700}}` | Parameters for Engine pod (aka "pipeline" orchestrator). |
+| runtime.engine | object | `{"affinity":{},"command":["npm","run","start"],"env":{"CONTAINER_LOGGER_EXEC_CHECK_INTERVAL_MS":1000,"DOCKER_REQUEST_TIMEOUT_MS":30000,"FORCE_COMPOSE_SERIAL_PULL":false,"LOGGER_LEVEL":"debug","LOG_OUTGOING_HTTP_REQUESTS":false,"METRICS_PROMETHEUS_COLLECT_PROCESS_METRICS":false,"METRICS_PROMETHEUS_ENABLED":true,"METRICS_PROMETHEUS_HOST":"0.0.0.0","METRICS_PROMETHEUS_PORT":9100},"image":{"pullPolicy":"IfNotPresent","registry":"quay.io","repository":"codefresh/engine","tag":"1.173.2"},"nodeSelector":{},"podAnnotations":{},"podLabels":{},"resources":{"limits":{"cpu":"1000m","memory":"2048Mi"},"requests":{"cpu":"100m","memory":"128Mi"}},"runtimeImages":{"COMPOSE_IMAGE":"quay.io/codefresh/compose:v2.20.3-1.4.0","CONTAINER_LOGGER_IMAGE":"quay.io/codefresh/cf-container-logger:1.11.4","CR_6177_FIXER":"quay.io/codefresh/alpine:edge","DOCKER_BUILDER_IMAGE":"quay.io/codefresh/cf-docker-builder:1.3.11","DOCKER_PULLER_IMAGE":"quay.io/codefresh/cf-docker-puller:8.0.17","DOCKER_PUSHER_IMAGE":"quay.io/codefresh/cf-docker-pusher:6.0.15","DOCKER_TAG_PUSHER_IMAGE":"quay.io/codefresh/cf-docker-tag-pusher:1.3.13","FS_OPS_IMAGE":"quay.io/codefresh/fs-ops:1.2.3","GC_BUILDER_IMAGE":"quay.io/codefresh/cf-gc-builder:0.5.3","GIT_CLONE_IMAGE":"quay.io/codefresh/cf-git-cloner:10.1.26","KUBE_DEPLOY":"quay.io/codefresh/cf-deploy-kubernetes:16.1.11","PIPELINE_DEBUGGER_IMAGE":"quay.io/codefresh/cf-debugger:1.3.0","TEMPLATE_ENGINE":"quay.io/codefresh/pikolo:0.14.0"},"schedulerName":"","serviceAccount":"codefresh-engine","tolerations":[],"userEnvVars":[],"workflowLimits":{"MAXIMUM_ALLOWED_TIME_BEFORE_PRE_STEPS_SUCCESS":600,"MAXIMUM_ALLOWED_WORKFLOW_AGE_BEFORE_TERMINATION":86400,"MAXIMUM_ELECTED_STATE_AGE_ALLOWED":900,"MAXIMUM_RETRY_ATTEMPTS_ALLOWED":20,"MAXIMUM_TERMINATING_STATE_AGE_ALLOWED":900,"MAXIMUM_TERMINATING_STATE_AGE_ALLOWED_WITHOUT_UPDATE":300,"TIME_ENGINE_INACTIVE_UNTIL_TERMINATION":300,"TIME_ENGINE_INACTIVE_UNTIL_UNHEALTHY":60,"TIME_INACTIVE_UNTIL_TERMINATION":2700}}` | Parameters for Engine pod (aka "pipeline" orchestrator). |
 | runtime.engine.affinity | object | `{}` | Set affinity |
 | runtime.engine.command | list | `["npm","run","start"]` | Set container command. |
-| runtime.engine.env | object | `{"CONTAINER_LOGGER_EXEC_CHECK_INTERVAL_MS":1000,"DOCKER_REQUEST_TIMEOUT_MS":30000,"FORCE_COMPOSE_SERIAL_PULL":false,"LOGGER_LEVEL":"debug","LOG_OUTGOING_HTTP_REQUESTS":false,"METRICS_PROMETHEUS_ENABLED":true}` | Set additional env vars. |
+| runtime.engine.env | object | `{"CONTAINER_LOGGER_EXEC_CHECK_INTERVAL_MS":1000,"DOCKER_REQUEST_TIMEOUT_MS":30000,"FORCE_COMPOSE_SERIAL_PULL":false,"LOGGER_LEVEL":"debug","LOG_OUTGOING_HTTP_REQUESTS":false,"METRICS_PROMETHEUS_COLLECT_PROCESS_METRICS":false,"METRICS_PROMETHEUS_ENABLED":true,"METRICS_PROMETHEUS_HOST":"0.0.0.0","METRICS_PROMETHEUS_PORT":9100}` | Set additional env vars. |
 | runtime.engine.env.CONTAINER_LOGGER_EXEC_CHECK_INTERVAL_MS | int | `1000` | Interval to check the exec status in the container-logger |
 | runtime.engine.env.DOCKER_REQUEST_TIMEOUT_MS | int | `30000` | Timeout while doing requests to the Docker daemon |
 | runtime.engine.env.FORCE_COMPOSE_SERIAL_PULL | bool | `false` | If "true", composition images will be pulled sequentially |
 | runtime.engine.env.LOGGER_LEVEL | string | `"debug"` | Level of logging for engine |
 | runtime.engine.env.LOG_OUTGOING_HTTP_REQUESTS | bool | `false` | Enable debug-level logging of outgoing HTTP/HTTPS requests |
+| runtime.engine.env.METRICS_PROMETHEUS_COLLECT_PROCESS_METRICS | bool | `false` | Enable collecting process metrics |
 | runtime.engine.env.METRICS_PROMETHEUS_ENABLED | bool | `true` | Enable emitting metrics from engine |
-| runtime.engine.image | object | `{"pullPolicy":"IfNotPresent","registry":"quay.io","repository":"codefresh/engine","tag":"1.171.3"}` | Set image. |
+| runtime.engine.env.METRICS_PROMETHEUS_HOST | string | `"0.0.0.0"` | Host for Prometheus metrics server |
+| runtime.engine.env.METRICS_PROMETHEUS_PORT | int | `9100` | Port for Prometheus metrics server |
+| runtime.engine.image | object | `{"pullPolicy":"IfNotPresent","registry":"quay.io","repository":"codefresh/engine","tag":"1.173.2"}` | Set image. |
 | runtime.engine.nodeSelector | object | `{}` | Set node selector. |
 | runtime.engine.podAnnotations | object | `{}` | Set pod annotations. |
 | runtime.engine.podLabels | object | `{}` | Set pod labels. |

charts/cf-runtime/tests/private-registry/private_registry_test.yaml

@@ -43,7 +43,10 @@ tests:
                 FORCE_COMPOSE_SERIAL_PULL: 'false'
                 LOGGER_LEVEL: debug
                 LOG_OUTGOING_HTTP_REQUESTS: 'false'
+                METRICS_PROMETHEUS_COLLECT_PROCESS_METRICS: 'false'
                 METRICS_PROMETHEUS_ENABLED: 'true'
+                METRICS_PROMETHEUS_HOST: 0.0.0.0
+                METRICS_PROMETHEUS_PORT: '9100'
                 COMPOSE_IMAGE: 'somedomain.io/codefresh/compose:tagoverride'
                 CONTAINER_LOGGER_IMAGE: 'somedomain.io/codefresh/cf-container-logger:tagoverride'
                 DOCKER_BUILDER_IMAGE: 'somedomain.io/codefresh/cf-docker-builder:tagoverride'

charts/cf-runtime/tests/runtime/runtime_onprem_test.yaml

@@ -51,7 +51,10 @@ tests:
                 FORCE_COMPOSE_SERIAL_PULL: 'false'
                 LOGGER_LEVEL: debug
                 LOG_OUTGOING_HTTP_REQUESTS: 'false'
+                METRICS_PROMETHEUS_COLLECT_PROCESS_METRICS: 'false'
                 METRICS_PROMETHEUS_ENABLED: 'true'
+                METRICS_PROMETHEUS_HOST: 0.0.0.0
+                METRICS_PROMETHEUS_PORT: '9100'
                 COMPOSE_IMAGE: 'quay.io/codefresh/compose:tagoverride'
                 CONTAINER_LOGGER_IMAGE: 'quay.io/codefresh/cf-container-logger:tagoverride'
                 DOCKER_BUILDER_IMAGE: 'quay.io/codefresh/cf-docker-builder:tagoverride'

charts/cf-runtime/tests/runtime/runtime_test.yaml

@@ -52,7 +52,10 @@ tests:
                 FORCE_COMPOSE_SERIAL_PULL: 'false'
                 LOGGER_LEVEL: debug
                 LOG_OUTGOING_HTTP_REQUESTS: 'false'
+                METRICS_PROMETHEUS_COLLECT_PROCESS_METRICS: 'false'
                 METRICS_PROMETHEUS_ENABLED: 'true'
+                METRICS_PROMETHEUS_HOST: 0.0.0.0
+                METRICS_PROMETHEUS_PORT: '9100'
                 COMPOSE_IMAGE: 'quay.io/codefresh/compose:tagoverride'
                 CONTAINER_LOGGER_IMAGE: 'quay.io/codefresh/cf-container-logger:tagoverride'
                 DOCKER_BUILDER_IMAGE: 'quay.io/codefresh/cf-docker-builder:tagoverride'

charts/cf-runtime/values.yaml

@@ -501,7 +501,7 @@ runtime:
     image:
       registry: quay.io
       repository: codefresh/engine
-      tag: 1.171.3
+      tag: 1.173.2
       pullPolicy: IfNotPresent
     # -- Set container command.
     command:
@@ -546,6 +546,12 @@ runtime:
       LOG_OUTGOING_HTTP_REQUESTS: false
       # -- Enable emitting metrics from engine
       METRICS_PROMETHEUS_ENABLED: true
+      # -- Enable collecting process metrics
+      METRICS_PROMETHEUS_COLLECT_PROCESS_METRICS: false
+      # -- Host for Prometheus metrics server
+      METRICS_PROMETHEUS_HOST: '0.0.0.0'
+      # -- Port for Prometheus metrics server
+      METRICS_PROMETHEUS_PORT: 9100
     # -- Set workflow limits.
     workflowLimits:
       # -- Maximum time allowed to the engine to wait for the pre-steps (aka "Initializing Process") to succeed; seconds.