Usama.saqib/test automatic job submission #44073
Draft
Conversation
This file contains hidden or 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
github-actions
bot
added
the
short review
Contributor
Gitlab CI Configuration ChangesModified Jobs.single-machine-performance-run_regression_detector .single-machine-performance-run_regression_detector:
allow_failure: false
artifacts:
expire_in: 1 weeks
paths:
- submission_metadata
- outputs/report.md
- outputs/regression_signal.json
- outputs/bounds_check_signal.json
- outputs/junit.xml
- outputs/report.json
- outputs/decision_record.md
when: always
image: registry.ddbuild.io/ci/datadog-agent-buildimages/docker_x64$CI_IMAGE_DOCKER_X64_SUFFIX:$CI_IMAGE_DOCKER_X64
retry:
exit_codes:
- 42
max: 2
when:
- runner_system_failure
- stuck_or_timeout_failure
- unknown_failure
- api_failure
- scheduler_failure
- stale_schedule
- data_integrity_failure
+ rules:
+ - if: $E2E_COVERAGE_PIPELINE == "true"
+ when: never
+ - if: $CI_COMMIT_BRANCH == "main"
+ when: never
+ - if: $CI_COMMIT_BRANCH =~ /^[0-9]+\.[0-9]+\.x$/
+ when: never
+ - if: $CI_COMMIT_BRANCH =~ /^mq-working-branch-/
+ when: never
+ - if: $CI_COMMIT_TAG != null
+ when: never
+ - when: on_success
script:
+ - ''
- DATADOG_API_KEY="$("$CI_PROJECT_DIR"/tools/ci/fetch_secret.sh "$AGENT_API_KEY_ORG2"
token)" || exit $?; export DATADOG_API_KEY
- datadog-ci tag --level job --tags smp_failure_mode:"timeout"
- mkdir outputs
- AWS_NAMED_PROFILE="single-machine-performance"
- "SMP_ACCOUNT_ID=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $SMP_ACCOUNT account_id)\
\ || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-secrets\"\n exit $exit_code\n}\n"
- SMP_ECR_URL=${SMP_ACCOUNT_ID}.dkr.ecr.us-west-2.amazonaws.com
- "SMP_TEAM_ID=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $SMP_ACCOUNT \"${SMP_TEAM_NAME}_team_id\"\
) || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-secrets\"\n exit $exit_code\n}\n"
- "SMP_API=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $SMP_ACCOUNT $SMP_API_URL)\
\ || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-secrets\"\n exit $exit_code\n}\n"
- "SMP_BOT_ID=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $SMP_ACCOUNT $BOT_LOGIN)\
\ || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-secrets\"\n exit $exit_code\n}\n"
- "SMP_BOT_KEY=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $SMP_ACCOUNT $BOT_TOKEN)\
\ || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-secrets\"\n exit $exit_code\n}\n"
- aws configure set aws_access_key_id "$SMP_BOT_ID" --profile ${AWS_NAMED_PROFILE}
- aws configure set aws_secret_access_key "$SMP_BOT_KEY" --profile ${AWS_NAMED_PROFILE}
- aws configure set region us-west-2 --profile ${AWS_NAMED_PROFILE}
- "aws --profile single-machine-performance s3 cp s3://smp-cli-releases/${SMP_VERSION}/x86_64-unknown-linux-musl/smp\
\ smp || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-fetch-cli\"\n exit $exit_code\n}\n"
- chmod +x smp
- source regression_detector.env
- echo "Baseline SHA is ${BASELINE_SHA}"
- echo -n "${BASELINE_SHA}" > "${CI_COMMIT_SHA}-baseline_sha"
- aws s3 cp --profile single-machine-performance --only-show-errors "${CI_COMMIT_SHA}-baseline_sha"
"s3://${SMP_TEAM_ID}-smp-artifacts/information/"
- BASELINE_IMAGE=${SMP_ECR_URL}/${SMP_TEAM_ID}-agent:${BASELINE_SHA}-7-full-amd64
- echo "${BASELINE_SHA} | ${BASELINE_IMAGE}"
- COMPARISON_IMAGE=${SMP_ECR_URL}/${SMP_TEAM_ID}-agent:${CI_COMMIT_SHA}-7-full-amd64
- echo "${CI_COMMIT_SHA} | ${COMPARISON_IMAGE}"
- SMP_TAGS="ci_pipeline_id=${CI_PIPELINE_ID},ci_job_id=${CI_JOB_ID},ci_commit_branch=${CI_COMMIT_BRANCH},purpose=agent_ci"
- echo "Tags passed through SMP are ${SMP_TAGS}"
- RUST_LOG="info,aws_config::profile::credentials=error"
- RUST_LOG_DEBUG="debug,aws_config::profile::credentials=error"
- "RUST_LOG=\"${RUST_LOG}\" ./smp --team-id ${SMP_TEAM_ID} --api-base ${SMP_API}\
\ --aws-named-profile ${AWS_NAMED_PROFILE} \\\njob submit \\\n--baseline-image\
\ ${BASELINE_IMAGE} \\\n--comparison-image ${COMPARISON_IMAGE} \\\n--baseline-sha\
\ ${BASELINE_SHA} \\\n--comparison-sha ${CI_COMMIT_SHA} \\\n--target-config-dir\
\ test/regression/ \\\n--submission-metadata submission_metadata \\\n--tags ${SMP_TAGS}\
\ || {\n exit_code=$?\n echo \"smp job submit command failed with code $exit_code\"\
\n datadog-ci tag --level job --tags smp_failure_mode:\"job-submission\"\n exit\
\ $exit_code\n}\n"
- SMP_JOB_ID=$(jq -r '.jobId' submission_metadata)
- echo "SMP Job Id is ${SMP_JOB_ID}"
- datadog-ci tag --level job --tags smp_job_id:${SMP_JOB_ID}
- "RUST_LOG=\"${RUST_LOG}\" ./smp --team-id ${SMP_TEAM_ID} --api-base ${SMP_API}\
\ --aws-named-profile ${AWS_NAMED_PROFILE} \\\njob status \\\n--wait \\\n--wait-delay-seconds\
\ 60 \\\n--submission-metadata submission_metadata || {\n exit_code=$?\n echo\
\ \"smp job status command failed with code $exit_code\"\n datadog-ci tag --level\
\ job --tags smp_failure_mode:\"job-status\"\n exit $exit_code\n}\n"
- "RUST_LOG=\"${RUST_LOG}\" ./smp --team-id ${SMP_TEAM_ID} --api-base ${SMP_API}\
\ --aws-named-profile ${AWS_NAMED_PROFILE} \\\njob sync \\\n--submission-metadata\
\ submission_metadata \\\n--output-path outputs || {\n exit_code=$?\n echo \"\
smp job sync command failed with code $exit_code\"\n datadog-ci tag --level job\
\ --tags smp_failure_mode:\"job-sync\"\n exit $exit_code\n}\n"
- cat outputs/report.md | sed "s/^\$/$(echo -ne '\uFEFF\u00A0\u200B')/g"
- datadog-ci junit upload --service datadog-agent outputs/junit.xml
- datadog-ci tag --level job --tags smp_failure_mode:"none"
- datadog-ci tag --level job --tags smp_optimization_goal:"passed"
- "RUST_LOG=\"${RUST_LOG}\" ./smp --team-id ${SMP_TEAM_ID} --api-base ${SMP_API}\
\ --aws-named-profile ${AWS_NAMED_PROFILE} \\\n job result \\\n --submission-metadata\
\ submission_metadata --signal regression-detector || {\n exit_code=$?\n echo\
\ \"smp regression detector has detected a regression\"\n datadog-ci tag --level\
\ job --tags smp_optimization_goal:\"failed\"\n}\n"
- datadog-ci tag --level job --tags smp_bounds_check:"passed"
- "RUST_LOG=\"${RUST_LOG}\" ./smp --team-id ${SMP_TEAM_ID} --api-base ${SMP_API}\
\ --aws-named-profile ${AWS_NAMED_PROFILE} \\\n job result \\\n --submission-metadata\
\ submission_metadata --signal bounds-check || {\n exit_code=$?\n echo \"smp\
\ regression detector has detected a failed bounds check\"\n datadog-ci tag --level\
\ job --tags smp_bounds_check:\"failed\"\n}\n"
- datadog-ci tag --level job --tags smp_quality_gates:"failed"
- "python3 <<'EOF'\nimport json\nimport sys\n\ntry:\n with open('outputs/report.json')\
\ as f:\n data = json.load(f)\nexcept FileNotFoundError:\n print(\"\
Machine readable report not found.\")\n sys.exit(1)\nexcept json.JSONDecodeError\
\ as e:\n print(f\"Error parsing JSON report: {e}\")\n sys.exit(1)\n\nexperiments\
\ = data.get('experiments', {})\nfailed = False\ndecision_record = []\n\nfor exp_name,\
\ exp_data in experiments.items():\n if exp_name.startswith('quality_gate_'):\n\
\ bounds_checks = exp_data.get('bounds_checks', {})\n for check_name,\
\ check_data in bounds_checks.items():\n results = check_data.get('results',\
\ {})\n comparison = results.get('comparison', [])\n num_total\
\ = len(comparison)\n failed_replicates = [\n replicate\
\ for replicate in comparison if not replicate.get('passed', False)\n \
\ ]\n num_failed = len(failed_replicates)\n num_passed\
\ = num_total - num_failed\n if failed_replicates:\n \
\ decision_record.append(\n f\"- **{exp_name}**, bounds check\
\ **{check_name}**: {num_passed}/{num_total} replicas passed. Failed {num_failed}\
\ which is > 0. Gate **FAILED**.\"\n )\n failed\
\ = True\n else:\n decision_record.append(\n \
\ f\"- **{exp_name}**, bounds check **{check_name}**: {num_passed}/{num_total}\
\ replicas passed. Gate passed.\"\n )\n\nwith open('outputs/decision_record.md',\
\ 'w') as f:\n # Extra newline since this is appended to another report\n \
\ f.write('\\n\\n## CI Pass/Fail Decision\\n\\n')\n if failed:\n f.write('\u274C\
\ **Failed.** Some Quality Gates were violated.\\n\\n')\n f.write('\\n'.join(decision_record))\n\
\ else:\n f.write('\u2705 **Passed.** All Quality Gates passed.\\n\\\
n')\n f.write('\\n'.join(decision_record))\n\nif failed:\n print(\"\
Quality gate failed, see decision record\")\n sys.exit(1)\nelse:\n print(\"\
Quality gate passed.\")\n sys.exit(0)\nEOF\n"
- datadog-ci tag --level job --tags smp_quality_gates:"passed"
stage: functional_test
tags:
- arch:amd64
- specific:true
timeout: 1h10msingle-machine-performance-metal-runners-regression_detector single-machine-performance-metal-runners-regression_detector:
- allow_failure: false
? ^^^^
+ allow_failure: true
? ^^^
artifacts:
expire_in: 1 weeks
paths:
- submission_metadata
- outputs/report.md
- outputs/regression_signal.json
- outputs/bounds_check_signal.json
- outputs/junit.xml
- outputs/report.json
- outputs/decision_record.md
when: always
image: registry.ddbuild.io/ci/datadog-agent-buildimages/docker_x64$CI_IMAGE_DOCKER_X64_SUFFIX:$CI_IMAGE_DOCKER_X64
needs:
- artifacts: true
job: single_machine_performance-regression_detector-merge_base_check
optional: true
- artifacts: false
job: single_machine_performance-full-amd64-a7
retry:
exit_codes:
- 42
max: 2
when:
- runner_system_failure
- stuck_or_timeout_failure
- unknown_failure
- api_failure
- scheduler_failure
- stale_schedule
- data_integrity_failure
rules:
- if: $E2E_COVERAGE_PIPELINE == "true"
when: never
+ - if: $CI_COMMIT_BRANCH == "main"
+ when: never
+ - if: $CI_COMMIT_BRANCH =~ /^[0-9]+\.[0-9]+\.x$/
+ when: never
- if: $CI_COMMIT_BRANCH =~ /^mq-working-branch-/
when: never
- - allow_failure: true
- when: manual
+ - if: $CI_COMMIT_TAG != null
+ when: never
- when: on_success
script:
+ - ''
- DATADOG_API_KEY="$("$CI_PROJECT_DIR"/tools/ci/fetch_secret.sh "$AGENT_API_KEY_ORG2"
token)" || exit $?; export DATADOG_API_KEY
- datadog-ci tag --level job --tags smp_failure_mode:"timeout"
- mkdir outputs
- AWS_NAMED_PROFILE="single-machine-performance"
- "SMP_ACCOUNT_ID=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $SMP_ACCOUNT account_id)\
\ || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-secrets\"\n exit $exit_code\n}\n"
- SMP_ECR_URL=${SMP_ACCOUNT_ID}.dkr.ecr.us-west-2.amazonaws.com
- "SMP_TEAM_ID=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $SMP_ACCOUNT \"${SMP_TEAM_NAME}_team_id\"\
) || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-secrets\"\n exit $exit_code\n}\n"
- "SMP_API=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $SMP_ACCOUNT $SMP_API_URL)\
\ || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-secrets\"\n exit $exit_code\n}\n"
- "SMP_BOT_ID=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $SMP_ACCOUNT $BOT_LOGIN)\
\ || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-secrets\"\n exit $exit_code\n}\n"
- "SMP_BOT_KEY=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $SMP_ACCOUNT $BOT_TOKEN)\
\ || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-secrets\"\n exit $exit_code\n}\n"
- aws configure set aws_access_key_id "$SMP_BOT_ID" --profile ${AWS_NAMED_PROFILE}
- aws configure set aws_secret_access_key "$SMP_BOT_KEY" --profile ${AWS_NAMED_PROFILE}
- aws configure set region us-west-2 --profile ${AWS_NAMED_PROFILE}
- "aws --profile single-machine-performance s3 cp s3://smp-cli-releases/${SMP_VERSION}/x86_64-unknown-linux-musl/smp\
\ smp || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-fetch-cli\"\n exit $exit_code\n}\n"
- chmod +x smp
- source regression_detector.env
- echo "Baseline SHA is ${BASELINE_SHA}"
- echo -n "${BASELINE_SHA}" > "${CI_COMMIT_SHA}-baseline_sha"
- aws s3 cp --profile single-machine-performance --only-show-errors "${CI_COMMIT_SHA}-baseline_sha"
"s3://${SMP_TEAM_ID}-smp-artifacts/information/"
- BASELINE_IMAGE=${SMP_ECR_URL}/${SMP_TEAM_ID}-agent:${BASELINE_SHA}-7-full-amd64
- echo "${BASELINE_SHA} | ${BASELINE_IMAGE}"
- COMPARISON_IMAGE=${SMP_ECR_URL}/${SMP_TEAM_ID}-agent:${CI_COMMIT_SHA}-7-full-amd64
- echo "${CI_COMMIT_SHA} | ${COMPARISON_IMAGE}"
- SMP_TAGS="ci_pipeline_id=${CI_PIPELINE_ID},ci_job_id=${CI_JOB_ID},ci_commit_branch=${CI_COMMIT_BRANCH},purpose=agent_ci"
- echo "Tags passed through SMP are ${SMP_TAGS}"
- RUST_LOG="info,aws_config::profile::credentials=error"
- RUST_LOG_DEBUG="debug,aws_config::profile::credentials=error"
- "RUST_LOG=\"${RUST_LOG}\" ./smp --team-id ${SMP_TEAM_ID} --api-base ${SMP_API}\
\ --aws-named-profile ${AWS_NAMED_PROFILE} \\\njob submit \\\n--baseline-image\
\ ${BASELINE_IMAGE} \\\n--comparison-image ${COMPARISON_IMAGE} \\\n--baseline-sha\
\ ${BASELINE_SHA} \\\n--comparison-sha ${CI_COMMIT_SHA} \\\n--target-config-dir\
\ test/regression/ \\\n--submission-metadata submission_metadata \\\n--tags ${SMP_TAGS}\
\ || {\n exit_code=$?\n echo \"smp job submit command failed with code $exit_code\"\
\n datadog-ci tag --level job --tags smp_failure_mode:\"job-submission\"\n exit\
\ $exit_code\n}\n"
- SMP_JOB_ID=$(jq -r '.jobId' submission_metadata)
- echo "SMP Job Id is ${SMP_JOB_ID}"
- datadog-ci tag --level job --tags smp_job_id:${SMP_JOB_ID}
- "RUST_LOG=\"${RUST_LOG}\" ./smp --team-id ${SMP_TEAM_ID} --api-base ${SMP_API}\
\ --aws-named-profile ${AWS_NAMED_PROFILE} \\\njob status \\\n--wait \\\n--wait-delay-seconds\
\ 60 \\\n--submission-metadata submission_metadata || {\n exit_code=$?\n echo\
\ \"smp job status command failed with code $exit_code\"\n datadog-ci tag --level\
\ job --tags smp_failure_mode:\"job-status\"\n exit $exit_code\n}\n"
- "RUST_LOG=\"${RUST_LOG}\" ./smp --team-id ${SMP_TEAM_ID} --api-base ${SMP_API}\
\ --aws-named-profile ${AWS_NAMED_PROFILE} \\\njob sync \\\n--submission-metadata\
\ submission_metadata \\\n--output-path outputs || {\n exit_code=$?\n echo \"\
smp job sync command failed with code $exit_code\"\n datadog-ci tag --level job\
\ --tags smp_failure_mode:\"job-sync\"\n exit $exit_code\n}\n"
- cat outputs/report.md | sed "s/^\$/$(echo -ne '\uFEFF\u00A0\u200B')/g"
- datadog-ci junit upload --service datadog-agent outputs/junit.xml
- datadog-ci tag --level job --tags smp_failure_mode:"none"
- datadog-ci tag --level job --tags smp_optimization_goal:"passed"
- "RUST_LOG=\"${RUST_LOG}\" ./smp --team-id ${SMP_TEAM_ID} --api-base ${SMP_API}\
\ --aws-named-profile ${AWS_NAMED_PROFILE} \\\n job result \\\n --submission-metadata\
\ submission_metadata --signal regression-detector || {\n exit_code=$?\n echo\
\ \"smp regression detector has detected a regression\"\n datadog-ci tag --level\
\ job --tags smp_optimization_goal:\"failed\"\n}\n"
- datadog-ci tag --level job --tags smp_bounds_check:"passed"
- "RUST_LOG=\"${RUST_LOG}\" ./smp --team-id ${SMP_TEAM_ID} --api-base ${SMP_API}\
\ --aws-named-profile ${AWS_NAMED_PROFILE} \\\n job result \\\n --submission-metadata\
\ submission_metadata --signal bounds-check || {\n exit_code=$?\n echo \"smp\
\ regression detector has detected a failed bounds check\"\n datadog-ci tag --level\
\ job --tags smp_bounds_check:\"failed\"\n}\n"
- datadog-ci tag --level job --tags smp_quality_gates:"failed"
- "python3 <<'EOF'\nimport json\nimport sys\n\ntry:\n with open('outputs/report.json')\
\ as f:\n data = json.load(f)\nexcept FileNotFoundError:\n print(\"\
Machine readable report not found.\")\n sys.exit(1)\nexcept json.JSONDecodeError\
\ as e:\n print(f\"Error parsing JSON report: {e}\")\n sys.exit(1)\n\nexperiments\
\ = data.get('experiments', {})\nfailed = False\ndecision_record = []\n\nfor exp_name,\
\ exp_data in experiments.items():\n if exp_name.startswith('quality_gate_'):\n\
\ bounds_checks = exp_data.get('bounds_checks', {})\n for check_name,\
\ check_data in bounds_checks.items():\n results = check_data.get('results',\
\ {})\n comparison = results.get('comparison', [])\n num_total\
\ = len(comparison)\n failed_replicates = [\n replicate\
\ for replicate in comparison if not replicate.get('passed', False)\n \
\ ]\n num_failed = len(failed_replicates)\n num_passed\
\ = num_total - num_failed\n if failed_replicates:\n \
\ decision_record.append(\n f\"- **{exp_name}**, bounds check\
\ **{check_name}**: {num_passed}/{num_total} replicas passed. Failed {num_failed}\
\ which is > 0. Gate **FAILED**.\"\n )\n failed\
\ = True\n else:\n decision_record.append(\n \
\ f\"- **{exp_name}**, bounds check **{check_name}**: {num_passed}/{num_total}\
\ replicas passed. Gate passed.\"\n )\n\nwith open('outputs/decision_record.md',\
\ 'w') as f:\n # Extra newline since this is appended to another report\n \
\ f.write('\\n\\n## CI Pass/Fail Decision\\n\\n')\n if failed:\n f.write('\u274C\
\ **Failed.** Some Quality Gates were violated.\\n\\n')\n f.write('\\n'.join(decision_record))\n\
\ else:\n f.write('\u2705 **Passed.** All Quality Gates passed.\\n\\\
n')\n f.write('\\n'.join(decision_record))\n\nif failed:\n print(\"\
Quality gate failed, see decision record\")\n sys.exit(1)\nelse:\n print(\"\
Quality gate passed.\")\n sys.exit(0)\nEOF\n"
- datadog-ci tag --level job --tags smp_quality_gates:"passed"
stage: functional_test
tags:
- arch:amd64
- specific:true
timeout: 1h10m
variables:
BOT_LOGIN: bot_login_metal-runners
BOT_TOKEN: bot_token_metal-runners
SMP_API_URL: metal-runners_api_url
SMP_TEAM_NAME: metal-runners
- SMP_VERSION: dev-pr3629-bea43153
+ SMP_VERSION: dev-pr3796-e7f7a988single-machine-performance-regression_detector single-machine-performance-regression_detector:
allow_failure: false
artifacts:
expire_in: 1 weeks
paths:
- submission_metadata
- outputs/report.md
- outputs/regression_signal.json
- outputs/bounds_check_signal.json
- outputs/junit.xml
- outputs/report.json
- outputs/decision_record.md
when: always
image: registry.ddbuild.io/ci/datadog-agent-buildimages/docker_x64$CI_IMAGE_DOCKER_X64_SUFFIX:$CI_IMAGE_DOCKER_X64
needs:
- artifacts: true
job: single_machine_performance-regression_detector-merge_base_check
- artifacts: false
job: single_machine_performance-full-amd64-a7
retry:
exit_codes:
- 42
max: 2
when:
- runner_system_failure
- stuck_or_timeout_failure
- unknown_failure
- api_failure
- scheduler_failure
- stale_schedule
- data_integrity_failure
rules:
- if: $E2E_COVERAGE_PIPELINE == "true"
when: never
- if: $CI_COMMIT_BRANCH == "main"
when: never
- if: $CI_COMMIT_BRANCH =~ /^[0-9]+\.[0-9]+\.x$/
when: never
- if: $CI_COMMIT_BRANCH =~ /^mq-working-branch-/
when: never
- if: $CI_COMMIT_TAG != null
when: never
- when: on_success
script:
+ - ''
- DATADOG_API_KEY="$("$CI_PROJECT_DIR"/tools/ci/fetch_secret.sh "$AGENT_API_KEY_ORG2"
token)" || exit $?; export DATADOG_API_KEY
- datadog-ci tag --level job --tags smp_failure_mode:"timeout"
- mkdir outputs
- AWS_NAMED_PROFILE="single-machine-performance"
- "SMP_ACCOUNT_ID=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $SMP_ACCOUNT account_id)\
\ || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-secrets\"\n exit $exit_code\n}\n"
- SMP_ECR_URL=${SMP_ACCOUNT_ID}.dkr.ecr.us-west-2.amazonaws.com
- "SMP_TEAM_ID=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $SMP_ACCOUNT \"${SMP_TEAM_NAME}_team_id\"\
) || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-secrets\"\n exit $exit_code\n}\n"
- "SMP_API=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $SMP_ACCOUNT $SMP_API_URL)\
\ || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-secrets\"\n exit $exit_code\n}\n"
- "SMP_BOT_ID=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $SMP_ACCOUNT $BOT_LOGIN)\
\ || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-secrets\"\n exit $exit_code\n}\n"
- "SMP_BOT_KEY=$($CI_PROJECT_DIR/tools/ci/fetch_secret.sh $SMP_ACCOUNT $BOT_TOKEN)\
\ || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-secrets\"\n exit $exit_code\n}\n"
- aws configure set aws_access_key_id "$SMP_BOT_ID" --profile ${AWS_NAMED_PROFILE}
- aws configure set aws_secret_access_key "$SMP_BOT_KEY" --profile ${AWS_NAMED_PROFILE}
- aws configure set region us-west-2 --profile ${AWS_NAMED_PROFILE}
- "aws --profile single-machine-performance s3 cp s3://smp-cli-releases/${SMP_VERSION}/x86_64-unknown-linux-musl/smp\
\ smp || {\n exit_code=$?\n datadog-ci tag --level job --tags smp_failure_mode:\"\
setup-fetch-cli\"\n exit $exit_code\n}\n"
- chmod +x smp
- source regression_detector.env
- echo "Baseline SHA is ${BASELINE_SHA}"
- echo -n "${BASELINE_SHA}" > "${CI_COMMIT_SHA}-baseline_sha"
- aws s3 cp --profile single-machine-performance --only-show-errors "${CI_COMMIT_SHA}-baseline_sha"
"s3://${SMP_TEAM_ID}-smp-artifacts/information/"
- BASELINE_IMAGE=${SMP_ECR_URL}/${SMP_TEAM_ID}-agent:${BASELINE_SHA}-7-full-amd64
- echo "${BASELINE_SHA} | ${BASELINE_IMAGE}"
- COMPARISON_IMAGE=${SMP_ECR_URL}/${SMP_TEAM_ID}-agent:${CI_COMMIT_SHA}-7-full-amd64
- echo "${CI_COMMIT_SHA} | ${COMPARISON_IMAGE}"
- SMP_TAGS="ci_pipeline_id=${CI_PIPELINE_ID},ci_job_id=${CI_JOB_ID},ci_commit_branch=${CI_COMMIT_BRANCH},purpose=agent_ci"
- echo "Tags passed through SMP are ${SMP_TAGS}"
- RUST_LOG="info,aws_config::profile::credentials=error"
- RUST_LOG_DEBUG="debug,aws_config::profile::credentials=error"
- "RUST_LOG=\"${RUST_LOG}\" ./smp --team-id ${SMP_TEAM_ID} --api-base ${SMP_API}\
\ --aws-named-profile ${AWS_NAMED_PROFILE} \\\njob submit \\\n--baseline-image\
\ ${BASELINE_IMAGE} \\\n--comparison-image ${COMPARISON_IMAGE} \\\n--baseline-sha\
\ ${BASELINE_SHA} \\\n--comparison-sha ${CI_COMMIT_SHA} \\\n--target-config-dir\
\ test/regression/ \\\n--submission-metadata submission_metadata \\\n--tags ${SMP_TAGS}\
\ || {\n exit_code=$?\n echo \"smp job submit command failed with code $exit_code\"\
\n datadog-ci tag --level job --tags smp_failure_mode:\"job-submission\"\n exit\
\ $exit_code\n}\n"
- SMP_JOB_ID=$(jq -r '.jobId' submission_metadata)
- echo "SMP Job Id is ${SMP_JOB_ID}"
- datadog-ci tag --level job --tags smp_job_id:${SMP_JOB_ID}
- "RUST_LOG=\"${RUST_LOG}\" ./smp --team-id ${SMP_TEAM_ID} --api-base ${SMP_API}\
\ --aws-named-profile ${AWS_NAMED_PROFILE} \\\njob status \\\n--wait \\\n--wait-delay-seconds\
\ 60 \\\n--submission-metadata submission_metadata || {\n exit_code=$?\n echo\
\ \"smp job status command failed with code $exit_code\"\n datadog-ci tag --level\
\ job --tags smp_failure_mode:\"job-status\"\n exit $exit_code\n}\n"
- "RUST_LOG=\"${RUST_LOG}\" ./smp --team-id ${SMP_TEAM_ID} --api-base ${SMP_API}\
\ --aws-named-profile ${AWS_NAMED_PROFILE} \\\njob sync \\\n--submission-metadata\
\ submission_metadata \\\n--output-path outputs || {\n exit_code=$?\n echo \"\
smp job sync command failed with code $exit_code\"\n datadog-ci tag --level job\
\ --tags smp_failure_mode:\"job-sync\"\n exit $exit_code\n}\n"
- cat outputs/report.md | sed "s/^\$/$(echo -ne '\uFEFF\u00A0\u200B')/g"
- datadog-ci junit upload --service datadog-agent outputs/junit.xml
- datadog-ci tag --level job --tags smp_failure_mode:"none"
- datadog-ci tag --level job --tags smp_optimization_goal:"passed"
- "RUST_LOG=\"${RUST_LOG}\" ./smp --team-id ${SMP_TEAM_ID} --api-base ${SMP_API}\
\ --aws-named-profile ${AWS_NAMED_PROFILE} \\\n job result \\\n --submission-metadata\
\ submission_metadata --signal regression-detector || {\n exit_code=$?\n echo\
\ \"smp regression detector has detected a regression\"\n datadog-ci tag --level\
\ job --tags smp_optimization_goal:\"failed\"\n}\n"
- datadog-ci tag --level job --tags smp_bounds_check:"passed"
- "RUST_LOG=\"${RUST_LOG}\" ./smp --team-id ${SMP_TEAM_ID} --api-base ${SMP_API}\
\ --aws-named-profile ${AWS_NAMED_PROFILE} \\\n job result \\\n --submission-metadata\
\ submission_metadata --signal bounds-check || {\n exit_code=$?\n echo \"smp\
\ regression detector has detected a failed bounds check\"\n datadog-ci tag --level\
\ job --tags smp_bounds_check:\"failed\"\n}\n"
- datadog-ci tag --level job --tags smp_quality_gates:"failed"
- "python3 <<'EOF'\nimport json\nimport sys\n\ntry:\n with open('outputs/report.json')\
\ as f:\n data = json.load(f)\nexcept FileNotFoundError:\n print(\"\
Machine readable report not found.\")\n sys.exit(1)\nexcept json.JSONDecodeError\
\ as e:\n print(f\"Error parsing JSON report: {e}\")\n sys.exit(1)\n\nexperiments\
\ = data.get('experiments', {})\nfailed = False\ndecision_record = []\n\nfor exp_name,\
\ exp_data in experiments.items():\n if exp_name.startswith('quality_gate_'):\n\
\ bounds_checks = exp_data.get('bounds_checks', {})\n for check_name,\
\ check_data in bounds_checks.items():\n results = check_data.get('results',\
\ {})\n comparison = results.get('comparison', [])\n num_total\
\ = len(comparison)\n failed_replicates = [\n replicate\
\ for replicate in comparison if not replicate.get('passed', False)\n \
\ ]\n num_failed = len(failed_replicates)\n num_passed\
\ = num_total - num_failed\n if failed_replicates:\n \
\ decision_record.append(\n f\"- **{exp_name}**, bounds check\
\ **{check_name}**: {num_passed}/{num_total} replicas passed. Failed {num_failed}\
\ which is > 0. Gate **FAILED**.\"\n )\n failed\
\ = True\n else:\n decision_record.append(\n \
\ f\"- **{exp_name}**, bounds check **{check_name}**: {num_passed}/{num_total}\
\ replicas passed. Gate passed.\"\n )\n\nwith open('outputs/decision_record.md',\
\ 'w') as f:\n # Extra newline since this is appended to another report\n \
\ f.write('\\n\\n## CI Pass/Fail Decision\\n\\n')\n if failed:\n f.write('\u274C\
\ **Failed.** Some Quality Gates were violated.\\n\\n')\n f.write('\\n'.join(decision_record))\n\
\ else:\n f.write('\u2705 **Passed.** All Quality Gates passed.\\n\\\
n')\n f.write('\\n'.join(decision_record))\n\nif failed:\n print(\"\
Quality gate failed, see decision record\")\n sys.exit(1)\nelse:\n print(\"\
Quality gate passed.\")\n sys.exit(0)\nEOF\n"
- datadog-ci tag --level job --tags smp_quality_gates:"passed"
stage: functional_test
tags:
- arch:amd64
- specific:true
timeout: 1h10m
variables:
BOT_LOGIN: bot_login
BOT_TOKEN: bot_token
SMP_API_URL: api_url
SMP_TEAM_NAME: agent
SMP_VERSION: v0.25.1Changes Summary
ℹ️ Diff available in the job log. |
Contributor
Static quality checks✅ Please find below the results from static quality gates Successful checksInfo
|
Regression DetectorRegression Detector ResultsMetrics dashboard Baseline: 8a0c427 Optimization Goals: ✅ No significant changes detected
|
| perf | experiment | goal | Δ mean % | Δ mean % CI | trials | links |
|---|---|---|---|---|---|---|
| ➖ | docker_containers_cpu | % cpu utilization | -2.08 | [-5.01, +0.84] | 1 | Logs |
Fine details of change detection per experiment
| perf | experiment | goal | Δ mean % | Δ mean % CI | trials | links |
|---|---|---|---|---|---|---|
| ➖ | ddot_logs | memory utilization | +0.87 | [+0.81, +0.94] | 1 | Logs |
| ➖ | docker_containers_memory | memory utilization | +0.16 | [+0.08, +0.24] | 1 | Logs |
| ➖ | quality_gate_idle_all_features | memory utilization | +0.14 | [+0.11, +0.17] | 1 | Logs bounds checks dashboard |
| ➖ | ddot_metrics_sum_cumulativetodelta_exporter | memory utilization | +0.10 | [-0.14, +0.33] | 1 | Logs |
| ➖ | ddot_metrics_sum_delta | memory utilization | +0.07 | [-0.14, +0.27] | 1 | Logs |
| ➖ | ddot_metrics | memory utilization | +0.06 | [-0.16, +0.29] | 1 | Logs |
| ➖ | uds_dogstatsd_20mb_12k_contexts_20_senders | memory utilization | +0.03 | [-0.03, +0.09] | 1 | Logs |
| ➖ | file_to_blackhole_500ms_latency | egress throughput | +0.01 | [-0.37, +0.38] | 1 | Logs |
| ➖ | uds_dogstatsd_to_api_v3 | ingress throughput | +0.01 | [-0.11, +0.12] | 1 | Logs |
| ➖ | file_tree | memory utilization | +0.00 | [-0.06, +0.06] | 1 | Logs |
| ➖ | uds_dogstatsd_to_api | ingress throughput | -0.00 | [-0.12, +0.12] | 1 | Logs |
| ➖ | tcp_dd_logs_filter_exclude | ingress throughput | -0.01 | [-0.08, +0.07] | 1 | Logs |
| ➖ | quality_gate_logs | % cpu utilization | -0.01 | [-1.48, +1.47] | 1 | Logs bounds checks dashboard |
| ➖ | file_to_blackhole_100ms_latency | egress throughput | -0.02 | [-0.07, +0.03] | 1 | Logs |
| ➖ | file_to_blackhole_0ms_latency | egress throughput | -0.03 | [-0.42, +0.37] | 1 | Logs |
| ➖ | file_to_blackhole_1000ms_latency | egress throughput | -0.03 | [-0.44, +0.39] | 1 | Logs |
| ➖ | quality_gate_idle | memory utilization | -0.22 | [-0.26, -0.18] | 1 | Logs bounds checks dashboard |
| ➖ | tcp_syslog_to_blackhole | ingress throughput | -0.40 | [-0.47, -0.33] | 1 | Logs |
| ➖ | otlp_ingest_metrics | memory utilization | -0.42 | [-0.56, -0.27] | 1 | Logs |
| ➖ | quality_gate_metrics_logs | memory utilization | -0.51 | [-0.73, -0.30] | 1 | Logs bounds checks dashboard |
| ➖ | ddot_metrics_sum_cumulative | memory utilization | -0.53 | [-0.70, -0.37] | 1 | Logs |
| ➖ | otlp_ingest_logs | memory utilization | -0.57 | [-0.67, -0.47] | 1 | Logs |
| ➖ | docker_containers_cpu | % cpu utilization | -2.08 | [-5.01, +0.84] | 1 | Logs |
Bounds Checks: ✅ Passed
| perf | experiment | bounds_check_name | replicates_passed | links |
|---|---|---|---|---|
| ✅ | docker_containers_cpu | simple_check_run | 10/10 | |
| ✅ | docker_containers_memory | memory_usage | 10/10 | |
| ✅ | docker_containers_memory | simple_check_run | 10/10 | |
| ✅ | file_to_blackhole_0ms_latency | lost_bytes | 10/10 | |
| ✅ | file_to_blackhole_0ms_latency | memory_usage | 10/10 | |
| ✅ | file_to_blackhole_1000ms_latency | lost_bytes | 10/10 | |
| ✅ | file_to_blackhole_1000ms_latency | 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_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 | bounds checks dashboard |
| ✅ | quality_gate_logs | lost_bytes | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_logs | memory_usage | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_metrics_logs | cpu_usage | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_metrics_logs | intake_connections | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_metrics_logs | lost_bytes | 10/10 | bounds checks dashboard |
| ✅ | quality_gate_metrics_logs | memory_usage | 10/10 | bounds checks dashboard |
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_metrics_logs, bounds check cpu_usage: 10/10 replicas passed. Gate passed.
- quality_gate_metrics_logs, bounds check intake_connections: 10/10 replicas passed. Gate passed.
- quality_gate_metrics_logs, bounds check memory_usage: 10/10 replicas passed. Gate passed.
- quality_gate_metrics_logs, bounds check lost_bytes: 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.
- 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_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.
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?
Motivation
Describe how you validated your changes
Additional Notes