Add a retry mechanism to the job that trigger a pipelines in the images repository
#33924
+5
−0
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
FlorentClarret
changed the title
images repository
github-actions
bot
added
short review
FlorentClarret
added
changelog/no-changelog
qa/no-code-change
Gitlab CI Configuration ChangesModified Jobsdocker_trigger_cluster_agent_internal docker_trigger_cluster_agent_internal:
image: registry.ddbuild.io/ci/datadog-agent-buildimages/deb_x64$DATADOG_AGENT_BUILDIMAGES_SUFFIX:$DATADOG_AGENT_BUILDIMAGES
needs:
- artifacts: false
job: docker_build_cluster_agent_amd64
- artifacts: false
job: docker_build_cluster_agent_arm64
+ retry: 2
rules:
- if: $CI_COMMIT_BRANCH =~ /^mq-working-branch-/
when: never
- if: $DEPLOY_AGENT == "true" || $DDR_WORKFLOW_ID != null
variables:
RELEASE_PROD: 'true'
- allow_failure: true
variables:
RELEASE_PROD: 'false'
when: manual
script:
- GITLAB_TOKEN=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $GITLAB_TOKEN write_api)
|| exit $?; export GITLAB_TOKEN
- if [ "$BUCKET_BRANCH" = "beta" ] || [ "$BUCKET_BRANCH" = "stable" ]; then TMPL_SRC_REPO="${TMPL_SRC_REPO}-release";
fi
- "if [ \"$BUCKET_BRANCH\" = \"nightly\" ]; then\n RELEASE_TAG=\"${RELEASE_TAG}-${CI_COMMIT_SHORT_SHA}\"\
\n TMPL_SRC_REPO=\"${TMPL_SRC_REPO}-nightly\"\nfi\n"
- if [ "$BUCKET_BRANCH" = "dev" ]; then RELEASE_TAG="dev-${RELEASE_TAG}-${CI_COMMIT_SHORT_SHA}";
fi
- inv pipeline.trigger-child-pipeline --project-name DataDog/images --git-ref master
--timeout 3600 --variable IMAGE_VERSION --variable IMAGE_NAME --variable RELEASE_TAG
--variable BUILD_TAG --variable TMPL_SRC_IMAGE --variable TMPL_SRC_REPO --variable
RELEASE_STAGING --variable RELEASE_PROD --variable DYNAMIC_BUILD_RENDER_RULES
--variable APPS --variable BAZEL_TARGET --variable DDR --variable DDR_WORKFLOW_ID
--variable TARGET_ENV --variable DYNAMIC_BUILD_RENDER_TARGET_FORWARD_PARAMETERS
stage: internal_image_deploy
tags:
- arch:amd64
variables:
BUILD_TAG: ${CI_COMMIT_REF_SLUG}
DYNAMIC_BUILD_RENDER_RULES: agent-build-only
IMAGE_NAME: datadog-cluster-agent
IMAGE_VERSION: tmpl-v5
RELEASE_PROD: 'true'
RELEASE_STAGING: 'true'
RELEASE_TAG: ${CI_COMMIT_REF_SLUG}
TMPL_SRC_IMAGE: v${CI_PIPELINE_ID}-${CI_COMMIT_SHORT_SHA}
TMPL_SRC_REPO: ci/datadog-agent/cluster-agentdocker_trigger_cws_instrumentation_internal docker_trigger_cws_instrumentation_internal:
image: registry.ddbuild.io/ci/datadog-agent-buildimages/deb_x64$DATADOG_AGENT_BUILDIMAGES_SUFFIX:$DATADOG_AGENT_BUILDIMAGES
needs:
- artifacts: false
job: docker_build_cws_instrumentation_amd64
- artifacts: false
job: docker_build_cws_instrumentation_arm64
+ retry: 2
rules:
- if: $DEPLOY_AGENT == "true" || $DDR_WORKFLOW_ID != null
script:
- GITLAB_TOKEN=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $GITLAB_TOKEN write_api)
|| exit $?; export GITLAB_TOKEN
- if [ "$BUCKET_BRANCH" = "beta" ] || [ "$BUCKET_BRANCH" = "stable" ]; then TMPL_SRC_REPO="${TMPL_SRC_REPO}-release";
fi
- "if [ \"$BUCKET_BRANCH\" = \"nightly\" ]; then\n RELEASE_TAG=\"${RELEASE_TAG}-${CI_COMMIT_SHORT_SHA}\"\
\n TMPL_SRC_REPO=\"${TMPL_SRC_REPO}-nightly\"\nfi\n"
- if [ "$BUCKET_BRANCH" = "dev" ]; then RELEASE_TAG="dev-${RELEASE_TAG}-${CI_COMMIT_SHORT_SHA}";
fi
- inv pipeline.trigger-child-pipeline --project-name DataDog/images --git-ref master
--timeout 3600 --variable IMAGE_VERSION --variable IMAGE_NAME --variable RELEASE_TAG
--variable BUILD_TAG --variable TMPL_SRC_IMAGE --variable TMPL_SRC_REPO --variable
RELEASE_STAGING --variable RELEASE_PROD --variable DYNAMIC_BUILD_RENDER_RULES
--variable APPS --variable BAZEL_TARGET --variable DDR --variable DDR_WORKFLOW_ID
--variable TARGET_ENV --variable DYNAMIC_BUILD_RENDER_TARGET_FORWARD_PARAMETERS
stage: internal_image_deploy
tags:
- arch:amd64
variables:
BUILD_TAG: ${CI_COMMIT_REF_SLUG}
DYNAMIC_BUILD_RENDER_RULES: agent-build-only
IMAGE_NAME: datadog-cws-instrumentation
IMAGE_VERSION: tmpl-v2
RELEASE_PROD: 'true'
RELEASE_STAGING: 'true'
RELEASE_TAG: ${CI_COMMIT_REF_SLUG}
TMPL_SRC_IMAGE: v${CI_PIPELINE_ID}-${CI_COMMIT_SHORT_SHA}
TMPL_SRC_REPO: ci/datadog-agent/cws-instrumentationdocker_trigger_internal docker_trigger_internal:
image: registry.ddbuild.io/ci/datadog-agent-buildimages/deb_x64$DATADOG_AGENT_BUILDIMAGES_SUFFIX:$DATADOG_AGENT_BUILDIMAGES
needs:
- artifacts: false
job: docker_build_agent7_jmx
- artifacts: false
job: docker_build_agent7_jmx_arm64
+ retry: 2
rules:
- if: $CI_COMMIT_BRANCH =~ /^mq-working-branch-/
when: never
- if: $DEPLOY_AGENT == "true" || $DDR_WORKFLOW_ID != null
variables:
RELEASE_PROD: 'true'
- allow_failure: true
variables:
RELEASE_PROD: 'false'
when: manual
script:
- GITLAB_TOKEN=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $GITLAB_TOKEN write_api)
|| exit $?; export GITLAB_TOKEN
- if [ "$BUCKET_BRANCH" = "beta" ] || [ "$BUCKET_BRANCH" = "stable" ]; then TMPL_SRC_REPO="${TMPL_SRC_REPO}-release";
fi
- "if [ \"$BUCKET_BRANCH\" = \"nightly\" ]; then\n RELEASE_TAG=\"${RELEASE_TAG}-${CI_COMMIT_SHORT_SHA}\"\
\n TMPL_SRC_REPO=\"${TMPL_SRC_REPO}-nightly\"\nfi\n"
- if [ "$BUCKET_BRANCH" = "dev" ]; then RELEASE_TAG="dev-${RELEASE_TAG}-${CI_COMMIT_SHORT_SHA}";
fi
- inv pipeline.trigger-child-pipeline --project-name DataDog/images --git-ref master
--timeout 3600 --variable IMAGE_VERSION --variable IMAGE_NAME --variable RELEASE_TAG
--variable BUILD_TAG --variable TMPL_SRC_IMAGE --variable TMPL_SRC_REPO --variable
RELEASE_STAGING --variable RELEASE_PROD --variable DYNAMIC_BUILD_RENDER_RULES
--variable APPS --variable BAZEL_TARGET --variable DDR --variable DDR_WORKFLOW_ID
--variable TARGET_ENV --variable DYNAMIC_BUILD_RENDER_TARGET_FORWARD_PARAMETERS
stage: internal_image_deploy
tags:
- arch:amd64
variables:
BUILD_TAG: ${CI_COMMIT_REF_SLUG}-jmx
DYNAMIC_BUILD_RENDER_RULES: agent-build-only
IMAGE_NAME: datadog-agent
IMAGE_VERSION: tmpl-v11
RELEASE_STAGING: 'true'
RELEASE_TAG: ${CI_COMMIT_REF_SLUG}-jmx
TMPL_SRC_IMAGE: v${CI_PIPELINE_ID}-${CI_COMMIT_SHORT_SHA}-7-jmx
TMPL_SRC_REPO: ci/datadog-agent/agentdocker_trigger_internal-fips docker_trigger_internal-fips:
image: registry.ddbuild.io/ci/datadog-agent-buildimages/deb_x64$DATADOG_AGENT_BUILDIMAGES_SUFFIX:$DATADOG_AGENT_BUILDIMAGES
needs:
- artifacts: false
job: docker_build_fips_agent7_jmx
- artifacts: false
job: docker_build_fips_agent7_arm64_jmx
+ retry: 2
rules:
- if: $CI_COMMIT_BRANCH =~ /^mq-working-branch-/
when: never
- if: $DEPLOY_AGENT == "true" || $DDR_WORKFLOW_ID != null
variables:
RELEASE_PROD: 'true'
- allow_failure: true
variables:
RELEASE_PROD: 'false'
when: manual
script:
- GITLAB_TOKEN=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $GITLAB_TOKEN write_api)
|| exit $?; export GITLAB_TOKEN
- if [ "$BUCKET_BRANCH" = "beta" ] || [ "$BUCKET_BRANCH" = "stable" ]; then TMPL_SRC_REPO="${TMPL_SRC_REPO}-release";
fi
- "if [ \"$BUCKET_BRANCH\" = \"nightly\" ]; then\n RELEASE_TAG=\"${RELEASE_TAG}-${CI_COMMIT_SHORT_SHA}\"\
\n TMPL_SRC_REPO=\"${TMPL_SRC_REPO}-nightly\"\nfi\n"
- if [ "$BUCKET_BRANCH" = "dev" ]; then RELEASE_TAG="dev-${RELEASE_TAG}-${CI_COMMIT_SHORT_SHA}";
fi
- inv pipeline.trigger-child-pipeline --project-name DataDog/images --git-ref master
--timeout 3600 --variable IMAGE_VERSION --variable IMAGE_NAME --variable RELEASE_TAG
--variable BUILD_TAG --variable TMPL_SRC_IMAGE --variable TMPL_SRC_REPO --variable
RELEASE_STAGING --variable RELEASE_PROD --variable DYNAMIC_BUILD_RENDER_RULES
--variable APPS --variable BAZEL_TARGET --variable DDR --variable DDR_WORKFLOW_ID
--variable TARGET_ENV --variable DYNAMIC_BUILD_RENDER_TARGET_FORWARD_PARAMETERS
stage: internal_image_deploy
tags:
- arch:amd64
variables:
BUILD_TAG: ${CI_COMMIT_REF_SLUG}-fips-jmx
DYNAMIC_BUILD_RENDER_RULES: agent-build-only
IMAGE_NAME: datadog-agent
IMAGE_VERSION: tmpl-v11
RELEASE_STAGING: 'true'
RELEASE_TAG: ${CI_COMMIT_REF_SLUG}-fips-jmx
TMPL_SRC_IMAGE: v${CI_PIPELINE_ID}-${CI_COMMIT_SHORT_SHA}-7-fips-jmx
TMPL_SRC_REPO: ci/datadog-agent/agentdocker_trigger_internal-ot docker_trigger_internal-ot:
image: registry.ddbuild.io/ci/datadog-agent-buildimages/deb_x64$DATADOG_AGENT_BUILDIMAGES_SUFFIX:$DATADOG_AGENT_BUILDIMAGES
needs:
- artifacts: false
job: docker_build_ot_agent7_jmx
- artifacts: false
job: docker_build_ot_agent7_jmx_arm64
+ retry: 2
rules:
- if: $CI_COMMIT_BRANCH =~ /^mq-working-branch-/
when: never
- if: $DEPLOY_AGENT == "true" || $DDR_WORKFLOW_ID != null
variables:
RELEASE_PROD: 'true'
- allow_failure: true
variables:
RELEASE_PROD: 'false'
when: manual
script:
- GITLAB_TOKEN=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $GITLAB_TOKEN write_api)
|| exit $?; export GITLAB_TOKEN
- if [ "$BUCKET_BRANCH" = "beta" ] || [ "$BUCKET_BRANCH" = "stable" ]; then TMPL_SRC_REPO="${TMPL_SRC_REPO}-release";
fi
- "if [ \"$BUCKET_BRANCH\" = \"nightly\" ]; then\n RELEASE_TAG=\"${RELEASE_TAG}-${CI_COMMIT_SHORT_SHA}\"\
\n TMPL_SRC_REPO=\"${TMPL_SRC_REPO}-nightly\"\nfi\n"
- if [ "$BUCKET_BRANCH" = "dev" ]; then RELEASE_TAG="dev-${RELEASE_TAG}-${CI_COMMIT_SHORT_SHA}";
fi
- inv pipeline.trigger-child-pipeline --project-name DataDog/images --git-ref master
--timeout 3600 --variable IMAGE_VERSION --variable IMAGE_NAME --variable RELEASE_TAG
--variable BUILD_TAG --variable TMPL_SRC_IMAGE --variable TMPL_SRC_REPO --variable
RELEASE_STAGING --variable RELEASE_PROD --variable DYNAMIC_BUILD_RENDER_RULES
--variable APPS --variable BAZEL_TARGET --variable DDR --variable DDR_WORKFLOW_ID
--variable TARGET_ENV --variable DYNAMIC_BUILD_RENDER_TARGET_FORWARD_PARAMETERS
stage: internal_image_deploy
tags:
- arch:amd64
variables:
BUILD_TAG: ${CI_COMMIT_REF_SLUG}-ot-beta-jmx
DYNAMIC_BUILD_RENDER_RULES: agent-build-only
IMAGE_NAME: datadog-agent
IMAGE_VERSION: tmpl-v11
RELEASE_STAGING: 'true'
RELEASE_TAG: ${CI_COMMIT_REF_SLUG}-ot-beta-jmx
TMPL_SRC_IMAGE: v${CI_PIPELINE_ID}-${CI_COMMIT_SHORT_SHA}-7-ot-beta-jmx
TMPL_SRC_REPO: ci/datadog-agent/agentChanges Summary
ℹ️ Diff available in the job log. |
CelianR
approved these changes
Feb 11, 2025
AliDatadog
approved these changes
Feb 11, 2025
|
/merge |
Devflow running:
|
Uncompressed package size comparisonComparison with ancestor Diff per package
Decision✅ Passed |
Static quality checks ✅Please find below the results from static quality gates Info
|
|
[Fast Unit Tests Report] On pipeline 55519299 (CI Visibility). The following jobs did not run any unit tests: Jobs:
If you modified Go files and expected unit tests to run in these jobs, please double check the job logs. If you think tests should have been executed reach out to #agent-devx-help |
Regression DetectorRegression Detector ResultsMetrics dashboard Baseline: f7b5400 Optimization Goals: ✅ No significant changes detected
|
| perf | experiment | goal | Δ mean % | Δ mean % CI | trials | links |
|---|---|---|---|---|---|---|
| ➖ | quality_gate_idle | memory utilization | +0.54 | [+0.49, +0.59] | 1 | Logs bounds checks dashboard |
| ➖ | quality_gate_idle_all_features | memory utilization | +0.38 | [+0.30, +0.45] | 1 | Logs bounds checks dashboard |
| ➖ | file_tree | memory utilization | +0.37 | [+0.31, +0.43] | 1 | Logs |
| ➖ | file_to_blackhole_500ms_latency | egress throughput | +0.06 | [-0.73, +0.86] | 1 | Logs |
| ➖ | file_to_blackhole_100ms_latency | egress throughput | +0.03 | [-0.69, +0.76] | 1 | Logs |
| ➖ | file_to_blackhole_1000ms_latency_linear_load | egress throughput | +0.01 | [-0.45, +0.47] | 1 | Logs |
| ➖ | uds_dogstatsd_to_api | ingress throughput | +0.00 | [-0.28, +0.29] | 1 | Logs |
| ➖ | tcp_dd_logs_filter_exclude | ingress throughput | -0.00 | [-0.01, +0.01] | 1 | Logs |
| ➖ | file_to_blackhole_300ms_latency | egress throughput | -0.01 | [-0.65, +0.63] | 1 | Logs |
| ➖ | file_to_blackhole_0ms_latency | egress throughput | -0.01 | [-0.87, +0.85] | 1 | Logs |
| ➖ | file_to_blackhole_0ms_latency_http1 | egress throughput | -0.03 | [-0.90, +0.84] | 1 | Logs |
| ➖ | file_to_blackhole_0ms_latency_http2 | egress throughput | -0.09 | [-0.94, +0.76] | 1 | Logs |
| ➖ | tcp_syslog_to_blackhole | ingress throughput | -0.17 | [-0.24, -0.10] | 1 | Logs |
| ➖ | file_to_blackhole_1000ms_latency | egress throughput | -0.26 | [-1.05, +0.52] | 1 | Logs |
| ➖ | uds_dogstatsd_to_api_cpu | % cpu utilization | -0.49 | [-1.37, +0.39] | 1 | Logs |
| ➖ | quality_gate_logs | % cpu utilization | -1.11 | [-4.16, +1.94] | 1 | Logs |
Bounds Checks: ✅ Passed
| perf | experiment | bounds_check_name | replicates_passed | links |
|---|---|---|---|---|
| ✅ | file_to_blackhole_0ms_latency | lost_bytes | 10/10 | |
| ✅ | file_to_blackhole_0ms_latency | memory_usage | 10/10 | |
| ✅ | file_to_blackhole_0ms_latency_http1 | lost_bytes | 10/10 | |
| ✅ | file_to_blackhole_0ms_latency_http1 | memory_usage | 10/10 | |
| ✅ | file_to_blackhole_0ms_latency_http2 | lost_bytes | 10/10 | |
| ✅ | file_to_blackhole_0ms_latency_http2 | memory_usage | 10/10 | |
| ✅ | file_to_blackhole_1000ms_latency | memory_usage | 10/10 | |
| ✅ | file_to_blackhole_1000ms_latency_linear_load | memory_usage | 10/10 | |
| ✅ | file_to_blackhole_100ms_latency | lost_bytes | 10/10 | |
| ✅ | file_to_blackhole_100ms_latency | memory_usage | 10/10 | |
| ✅ | file_to_blackhole_300ms_latency | lost_bytes | 10/10 | |
| ✅ | file_to_blackhole_300ms_latency | memory_usage | 10/10 | |
| ✅ | file_to_blackhole_500ms_latency | lost_bytes | 10/10 | |
| ✅ | file_to_blackhole_500ms_latency | memory_usage | 10/10 | |
| ✅ | quality_gate_idle | intake_connections | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_idle | memory_usage | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_idle_all_features | intake_connections | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_idle_all_features | memory_usage | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_logs | intake_connections | 10/10 | |
| ✅ | quality_gate_logs | lost_bytes | 10/10 | |
| ✅ | quality_gate_logs | memory_usage | 10/10 |
Explanation
Confidence level: 90.00%
Effect size tolerance: |Δ mean %| ≥ 5.00%
Performance changes are noted in the perf column of each table:
- ✅ = significantly better comparison variant performance
- ❌ = significantly worse comparison variant performance
- ➖ = no significant change in performance
A regression test is an A/B test of target performance in a repeatable rig, where "performance" is measured as "comparison variant minus baseline variant" for an optimization goal (e.g., ingress throughput). Due to intrinsic variability in measuring that goal, we can only estimate its mean value for each experiment; we report uncertainty in that value as a 90.00% confidence interval denoted "Δ mean % CI".
For each experiment, we decide whether a change in performance is a "regression" -- a change worth investigating further -- if all of the following criteria are true:
-
Its estimated |Δ mean %| ≥ 5.00%, indicating the change is big enough to merit a closer look.
-
Its 90.00% confidence interval "Δ mean % CI" does not contain zero, indicating that if our statistical model is accurate, there is at least a 90.00% chance there is a difference in performance between baseline and comparison variants.
-
Its configuration does not mark it "erratic".
CI Pass/Fail Decision
✅ Passed. All Quality Gates passed.
- quality_gate_logs, bounds check lost_bytes: 10/10 replicas passed. Gate passed.
- quality_gate_logs, bounds check intake_connections: 10/10 replicas passed. Gate passed.
- quality_gate_logs, bounds check memory_usage: 10/10 replicas passed. Gate passed.
- quality_gate_idle, bounds check intake_connections: 10/10 replicas passed. Gate passed.
- quality_gate_idle, bounds check memory_usage: 10/10 replicas passed. Gate passed.
- quality_gate_idle_all_features, bounds check memory_usage: 10/10 replicas passed. Gate passed.
- quality_gate_idle_all_features, bounds check intake_connections: 10/10 replicas passed. Gate passed.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Add a retry mechanism to the job that trigger a pipelines in the
imagesrepositoryMotivation
We have some infra issues on the
imagesside and the ci-infra-team asked us to retry to give them time to investigate the underlying error: https://gitlab.ddbuild.io/DataDog/images/-/jobs/802277483Describe how you validated your changes
Possible Drawbacks / Trade-offs
Additional Notes
Discussed with DevX as well