fix(ci): 僵尸run复活防护——重负载job自检+dedupe竞态增强 [P1] #1562

Merged
xiaoxia merged 3 commits from ci/selfcheck-zombie-run-and-dedupe into develop 2026-08-31 11:58:00 +08:00
2 changed files with 109 additions and 2 deletions
+75 -2
View File
@@ -58,10 +58,11 @@ jobs:
echo "::warning::PR #${PR_NUMBER} 已合并,测试由合并后 push 流水线承接,PR 侧测试类 job 跳过"
exit 0
fi
# 情形2:同一 head_sha 已有在跑/排队的 push 流水线(rebase/ff 合并竞态
# 情形2:同一 head_sha 已有在跑/排队/已成功的 push 流水线(rebase/ff 合并竞态
# 已成功也去重——竞态窗口内两边都通过判断时,PR侧再跑全量测试纯属重复)
DUP=$(curl -sfH "Authorization: token $GITHUB_TOKEN" \
"${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/actions/runs?head_sha=${HEAD_SHA}&per_page=30" \
| python3 -c "import json,sys; d=json.load(sys.stdin); runs=d if isinstance(d,list) else d.get('workflow_runs',d.get('runs',[])); hit=[r for r in runs if r.get('event')=='push' and r.get('status') in ('in_progress','queued','waiting','pending')]; print('true' if hit else 'false')" || echo false)
| python3 -c "import json,sys; d=json.load(sys.stdin); runs=d if isinstance(d,list) else d.get('workflow_runs',d.get('runs',[])); hit=[r for r in runs if r.get('event')=='push' and (r.get('status') in ('in_progress','queued','waiting','pending') or r.get('conclusion')=='success')]; print('true' if hit else 'false')" || echo false)
if [ "$DUP" = "true" ]; then
echo "skip_tests=true" >> $GITHUB_OUTPUT
echo "reason=duplicate-push-run-active" >> $GITHUB_OUTPUT
@@ -144,6 +145,12 @@ jobs:
GITHUB_TOKEN: ${{ github.token }}
run: |
curl -sfH "Authorization: token $GITHUB_TOKEN" -o /tmp/_ci_checkout.sh "${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/raw/scripts/ci/step_checkout.sh?ref=${GITHUB_SHA}" && bash /tmp/_ci_checkout.sh
- name: Zombie run selfcheck
shell: sh
env:
GITHUB_TOKEN: ${{ github.token }}
GITHUB_RUN_ID: ${{ github.run_id }}
run: bash scripts/ci/ci_run_selfcheck.sh
- name: Record job start time
shell: sh
run: bash scripts/ci/step_timer_start.sh
@@ -244,6 +251,12 @@ jobs:
GITHUB_TOKEN: ${{ github.token }}
run: |
curl -sfH "Authorization: token $GITHUB_TOKEN" -o /tmp/_ci_checkout.sh "${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/raw/scripts/ci/step_checkout.sh?ref=${GITHUB_SHA}" && bash /tmp/_ci_checkout.sh
- name: Zombie run selfcheck
shell: sh
env:
GITHUB_TOKEN: ${{ github.token }}
GITHUB_RUN_ID: ${{ github.run_id }}
run: bash scripts/ci/ci_run_selfcheck.sh
- name: Record job start time
shell: sh
run: bash scripts/ci/step_timer_start.sh
@@ -325,6 +338,12 @@ jobs:
GITHUB_TOKEN: ${{ github.token }}
run: |
curl -sfH "Authorization: token $GITHUB_TOKEN" -o /tmp/_ci_checkout.sh "${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/raw/scripts/ci/step_checkout.sh?ref=${GITHUB_SHA}" && bash /tmp/_ci_checkout.sh
- name: Zombie run selfcheck
shell: sh
env:
GITHUB_TOKEN: ${{ github.token }}
GITHUB_RUN_ID: ${{ github.run_id }}
run: bash scripts/ci/ci_run_selfcheck.sh
- name: Record job start time
shell: sh
run: bash scripts/ci/step_timer_start.sh
@@ -408,6 +427,12 @@ jobs:
GITHUB_TOKEN: ${{ github.token }}
run: |
curl -sfH "Authorization: token $GITHUB_TOKEN" -o /tmp/_ci_checkout.sh "${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/raw/scripts/ci/step_checkout.sh?ref=${GITHUB_SHA}" && bash /tmp/_ci_checkout.sh
- name: Zombie run selfcheck
shell: sh
env:
GITHUB_TOKEN: ${{ github.token }}
GITHUB_RUN_ID: ${{ github.run_id }}
run: bash scripts/ci/ci_run_selfcheck.sh
- name: Record job start time
shell: sh
run: bash scripts/ci/step_timer_start.sh
@@ -488,6 +513,12 @@ jobs:
GITHUB_TOKEN: ${{ github.token }}
run: |
curl -sfH "Authorization: token $GITHUB_TOKEN" -o /tmp/_ci_checkout.sh "${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/raw/scripts/ci/step_checkout.sh?ref=${GITHUB_SHA}" && bash /tmp/_ci_checkout.sh
- name: Zombie run selfcheck
shell: sh
env:
GITHUB_TOKEN: ${{ github.token }}
GITHUB_RUN_ID: ${{ github.run_id }}
run: bash scripts/ci/ci_run_selfcheck.sh
- name: Record job start time
shell: sh
run: bash scripts/ci/step_timer_start.sh
@@ -542,6 +573,12 @@ jobs:
GITHUB_TOKEN: ${{ github.token }}
run: |
curl -sfH "Authorization: token $GITHUB_TOKEN" -o /tmp/_ci_checkout.sh "${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/raw/scripts/ci/step_checkout.sh?ref=${GITHUB_SHA}" && bash /tmp/_ci_checkout.sh
- name: Zombie run selfcheck
shell: sh
env:
GITHUB_TOKEN: ${{ github.token }}
GITHUB_RUN_ID: ${{ github.run_id }}
run: bash scripts/ci/ci_run_selfcheck.sh
- name: Record job start time
shell: sh
run: bash scripts/ci/step_timer_start.sh
@@ -604,6 +641,12 @@ jobs:
GITHUB_TOKEN: ${{ github.token }}
run: |
curl -sfH "Authorization: token $GITHUB_TOKEN" -o /tmp/_ci_checkout.sh "${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/raw/scripts/ci/step_checkout.sh?ref=${GITHUB_SHA}" && bash /tmp/_ci_checkout.sh
- name: Zombie run selfcheck
shell: sh
env:
GITHUB_TOKEN: ${{ github.token }}
GITHUB_RUN_ID: ${{ github.run_id }}
run: bash scripts/ci/ci_run_selfcheck.sh
- name: Record job start time
shell: sh
run: bash scripts/ci/step_timer_start.sh
@@ -695,6 +738,12 @@ jobs:
GITHUB_TOKEN: ${{ github.token }}
run: |
curl -sfH "Authorization: token $GITHUB_TOKEN" -o /tmp/_ci_checkout.sh "${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/raw/scripts/ci/step_checkout.sh?ref=${GITHUB_SHA}" && bash /tmp/_ci_checkout.sh
- name: Zombie run selfcheck
shell: sh
env:
GITHUB_TOKEN: ${{ github.token }}
GITHUB_RUN_ID: ${{ github.run_id }}
run: bash scripts/ci/ci_run_selfcheck.sh
- name: Record job start time
shell: sh
run: bash scripts/ci/step_timer_start.sh
@@ -873,6 +922,12 @@ jobs:
GITHUB_TOKEN: ${{ github.token }}
run: |
curl -sfH "Authorization: token $GITHUB_TOKEN" -o /tmp/_ci_checkout.sh "${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/raw/scripts/ci/step_checkout.sh?ref=${GITHUB_SHA}" && bash /tmp/_ci_checkout.sh
- name: Zombie run selfcheck
shell: sh
env:
GITHUB_TOKEN: ${{ github.token }}
GITHUB_RUN_ID: ${{ github.run_id }}
run: bash scripts/ci/ci_run_selfcheck.sh
- name: Record job start time
shell: sh
run: bash scripts/ci/step_timer_start.sh
@@ -1246,6 +1301,12 @@ jobs:
GITHUB_TOKEN: ${{ github.token }}
run: |
curl -sfH "Authorization: token $GITHUB_TOKEN" -o /tmp/_ci_checkout.sh "${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/raw/scripts/ci/step_checkout.sh?ref=${GITHUB_SHA}" && bash /tmp/_ci_checkout.sh
- name: Zombie run selfcheck
shell: sh
env:
GITHUB_TOKEN: ${{ github.token }}
GITHUB_RUN_ID: ${{ github.run_id }}
run: bash scripts/ci/ci_run_selfcheck.sh
- name: Record job start time
shell: sh
run: bash scripts/ci/step_timer_start.sh
@@ -1293,6 +1354,12 @@ jobs:
GITHUB_TOKEN: ${{ github.token }}
run: |
curl -sfH "Authorization: token $GITHUB_TOKEN" -o /tmp/_ci_checkout.sh "${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/raw/scripts/ci/step_checkout.sh?ref=${GITHUB_SHA}" && bash /tmp/_ci_checkout.sh
- name: Zombie run selfcheck
shell: sh
env:
GITHUB_TOKEN: ${{ github.token }}
GITHUB_RUN_ID: ${{ github.run_id }}
run: bash scripts/ci/ci_run_selfcheck.sh
- name: Record job start time
shell: sh
run: bash scripts/ci/step_timer_start.sh
@@ -1367,6 +1434,12 @@ jobs:
GITHUB_TOKEN: ${{ github.token }}
run: |
curl -sfH "Authorization: token $GITHUB_TOKEN" -o /tmp/_ci_checkout.sh "${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/raw/scripts/ci/step_checkout.sh?ref=${GITHUB_SHA}" && bash /tmp/_ci_checkout.sh
- name: Zombie run selfcheck
shell: sh
env:
GITHUB_TOKEN: ${{ github.token }}
GITHUB_RUN_ID: ${{ github.run_id }}
run: bash scripts/ci/ci_run_selfcheck.sh
- name: Record job start time
shell: sh
run: bash scripts/ci/step_timer_start.sh
+34
View File
@@ -0,0 +1,34 @@
#!/bin/bash
# CI job 运行前自检 —— 防 Gitea 1.26 调度 bug
# 被 concurrency cancel 的 run,其已派发的 job 可能在数小时后被调度器复活重跑
# 2026-08-30 实测:18:46 取消的 run21:46 复活 attempt=2,与正常流水线抢 runner 1.5 小时)。
# job 启动第一步先实时查本 run 状态,若已终结(cancelled/skipped),容器立即退出不烧资源。
#
# 用法:在重量级 jobValidate/Unit Tests/Integration/Frontend/Build/E2E 类)的
# 首个 step 中加入:bash scripts/ci/ci_run_selfcheck.sh
set -u
echo "▶ CI 运行前自检(僵尸 run 复活防护)..."
if [ -z "${GITHUB_API_URL:-}" ] || [ -z "${GITHUB_REPOSITORY:-}" ] || [ -z "${GITHUB_TOKEN:-}" ] || [ -z "${GITHUB_RUN_ID:-}" ]; then
echo "⚠️ 缺少 GITHUB_* 环境变量(GITHUB_RUN_ID/GITHUB_TOKEN),跳过自检(不阻断)"
exit 0
fi
CONCLUSION=$(curl -sf -H "Authorization: token ${GITHUB_TOKEN}" --max-time 10 \
"${GITHUB_API_URL}/repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}" 2>/dev/null \
| python3 -c "import json,sys; print(json.load(sys.stdin).get('conclusion') or 'running')" 2>/dev/null || echo "unknown")
case "${CONCLUSION}" in
cancelled|skipped)
echo "::error::本 run(${GITHUB_RUN_ID}) 状态已为 ${CONCLUSION},却仍被调度器派发执行——判定为 Gitea 复活的僵尸 job,立即退出,不再占用 runner"
exit 78 # EX_CONFIG:非零退出让调度器知晓该 job 终结(避免被当成功空跑)
;;
running|unknown|"")
# unknown 时不阻断(API 临时故障),正常执行
echo "✅ run ${GITHUB_RUN_ID} 状态正常(${CONCLUSION:-running}),继续执行"
;;
*)
echo "✅ run ${GITHUB_RUN_ID} 结论=${CONCLUSION}(已终结但非取消),继续执行"
;;
esac