k8s.io/test-infra@v0.0.0-20240520184403-27c6b4c223d8/config/jobs/kubernetes/sig-k8s-infra/trusted/sig-k8s-infra-test-infra.yaml (about)

     1  postsubmits:
     2    kubernetes/test-infra:
     3    - name: post-test-infra-upload-triage
     4      cluster: k8s-infra-prow-build-trusted
     5      branches:
     6      - ^master$
     7      max_concurrency: 1
     8      run_if_changed: '^triage/Makefile$|^triage/[^/]+(\.html|\.js|\.css)$'
     9      decorate: true
    10      spec:
    11        serviceAccountName: k8s-triage
    12        containers:
    13        - image: gcr.io/k8s-staging-infra-tools/k8s-infra:latest
    14          command:
    15          - make
    16          args:
    17          - -C
    18          - ./triage/
    19          - push-static
    20          resources:
    21            requests:
    22              memory: "1Gi"
    23      annotations:
    24        testgrid-dashboards: sig-testing-maintenance, sig-k8s-infra-prow
    25        testgrid-tab-name: triage-update
    26        testgrid-alert-email: kubernetes-sig-testing-alerts@googlegroups.com, k8s-infra-alerts@kubernetes.io
    27        testgrid-num-failures-to-alert: '1'
    28        description: Updates the html contents for go.k8s.io/triage.
    29  
    30  periodics:
    31  - name: metrics-bigquery
    32    cron: "03 0-23/12 * * *"  # like interval: 12h, but explicitly starting at 00:03 UTC
    33    cluster: k8s-infra-prow-build-trusted
    34    decorate: true
    35    max_concurrency: 1
    36    extra_refs:
    37    - org: kubernetes
    38      repo: test-infra
    39      base_ref: master
    40    annotations:
    41      testgrid-dashboards: sig-testing-misc, sig-k8s-infra-prow
    42      testgrid-alert-email: kubernetes-sig-testing-alerts@googlegroups.com, k8s-infra-alerts@kubernetes.io
    43      testgrid-num-failures-to-alert: '2'
    44      description: Runs BigQuery queries to generate data for metrics.
    45    rerun_auth_config:
    46      github_team_slugs:
    47      # proxy for sig-k8s-infra-oncall
    48      - org: kubernetes
    49        slug: sig-k8s-infra-leads
    50      # proxy for test-infra-oncall
    51      - org: kubernetes
    52        slug: test-infra-admins
    53    spec:
    54      serviceAccountName: k8s-metrics
    55      containers:
    56      - image: gcr.io/k8s-staging-test-infra/bigquery:v20240205-69ac5748ba
    57        args:
    58        - ./metrics/bigquery.py
    59        - --bucket=gs://k8s-metrics
    60        - --project=k8s-infra-prow-build-trusted
    61        - --jq=/usr/bin/jq
    62  
    63  - name: ci-test-infra-triage
    64    interval: 4h
    65    cluster: k8s-infra-prow-build-trusted
    66    decorate: true
    67    decoration_config:
    68      timeout: 3h
    69    max_concurrency: 1
    70    annotations:
    71      testgrid-num-failures-to-alert: '18'
    72      testgrid-alert-stale-results-hours: '12'
    73      testgrid-dashboards: sig-testing-misc, sig-k8s-infra-prow
    74      testgrid-tab-name: triage
    75      testgrid-alert-email: kubernetes-sig-testing-alerts@googlegroups.com, k8s-infra-alerts@kubernetes.io
    76      description: Runs BigQuery queries, summarizes results into clusters, and uploads to GCS for go.k8s.io/triage
    77    rerun_auth_config:
    78      github_team_slugs:
    79      # proxy for sig-k8s-infra-oncall
    80      - org: kubernetes
    81        slug: sig-k8s-infra-leads
    82      # proxy for test-infra-oncall
    83      - org: kubernetes
    84        slug: test-infra-admins
    85    spec:
    86      serviceAccountName: k8s-triage
    87      containers:
    88      - image: gcr.io/k8s-staging-test-infra/triage:latest
    89        imagePullPolicy: Always
    90        env:
    91        # Go incorrectly determines the number of CPUs in a pod, set manually to (2*CPUs-1)
    92        # TODO: determine the optimal number of workers, 2*CPU-1 is an assumption
    93        - name: NUM_WORKERS
    94          value: "13"
    95        - name: TRIAGE_DATASET_TABLE
    96          value: "kubernetes-public:k8s_triage.temp"
    97        - name: TRIAGE_TEMP_GCS_PATH
    98          value: "gs://k8s-triage/triage_tests"
    99        - name: TRIAGE_GCS_PATH
   100          value: "gs://k8s-triage"
   101        - name: TRIAGE_BQ_USAGE_PROJECT
   102          value: "k8s-infra-prow-build-trusted"
   103        command:
   104        - timeout
   105        args:
   106        - "10800"
   107        - /update_summaries.sh
   108        # When changing CPUs, also change NUM_WORKERS above
   109        resources:
   110          requests:
   111            cpu: 6
   112            memory: 32Gi
   113          limits:
   114            cpu: 6
   115            memory: 32Gi
   116  
   117  - name: ci-test-infra-autobump-prowjobs
   118    cron: "06 14-23 * * 1-5"  # Run every hour at 7:06 - 16:06 PDT (in UTC) Mon-Fri
   119    cluster: k8s-infra-prow-build-trusted
   120    decorate: true
   121    extra_refs:
   122    - org: kubernetes
   123      repo: test-infra
   124      base_ref: master
   125    spec:
   126      containers:
   127      - image: gcr.io/k8s-prow/generic-autobumper:v20240517-ea10bd814
   128        command:
   129        - generic-autobumper
   130        args:
   131        - --config=config/prow/autobump-config/prow-job-autobump-config.yaml
   132        volumeMounts:
   133        - name: github
   134          mountPath: /etc/github-token
   135          readOnly: true
   136      volumes:
   137      - name: github
   138        secret:
   139          secretName: k8s-infra-ci-robot-github-token
   140    annotations:
   141      testgrid-dashboards: sig-testing-prow
   142      testgrid-tab-name: autobump-prowjobs
   143      description: runs experiment/autobumper to create/update a PR that bumps prowjob images to latest published version
   144      testgrid-alert-email: k8s-infra-oncall@google.com
   145      testgrid-num-failures-to-alert: '3'