fix(ci): distinguish unreachable from stale in /buildinfo verify step

The /buildinfo verify step (PR #2398) was treating "no /buildinfo response"
the same as "tenant returned wrong SHA" — both bumped MISMATCH_COUNT and
hard-failed the workflow. First post-merge run on staging caught a real
edge case: ephemeral E2E tenants (slug e2e-20260430-...) get torn down by
the E2E teardown trap between CP's healthz_ok snapshot and the verify step
running, so the verify step would dial into DNS that no longer resolves
and hard-fail on a benign condition.

The bug class we actually care about is STALE (tenant up + serving old
code, the #2395 root). UNREACHABLE post-redeploy is almost always a benign
teardown race; real "tenant up but unreachable" is caught by CP's own
healthz monitor + the alert pipeline, so double-counting it here was
making this workflow flaky on every staging push that overlapped E2E.

Wire:
  - Split MISMATCH_COUNT into STALE_COUNT + UNREACHABLE_COUNT.
  - STALE → hard-fail the workflow (the bug class we're guarding).
  - UNREACHABLE → :⚠️:, don't fail. Reachable-mismatch still hard-fails.
  - Job summary surfaces both lists separately so on-call can tell at a
    glance which class fired.

Mirror in redeploy-tenants-on-main.yml for shape parity (prod has fewer
ephemeral tenants but identical asymmetry would be a gratuitous fork).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Hongming Wang 2026-04-30 11:25:46 -07:00
parent c06e2fec5e
commit d45241cae7
2 changed files with 74 additions and 26 deletions

View File

@ -246,8 +246,15 @@ jobs:
echo "Verifying ${#SLUGS[@]} tenant(s) against EXPECTED_SHA=${EXPECTED_SHA:0:7}..."
MISMATCH_COUNT=0
MISMATCH_LINES=()
# Two distinct failure modes — STALE (the #2395 bug class, hard-fail)
# vs UNREACHABLE (teardown race, soft-warn). See the staging variant's
# comment for the full rationale; same logic applies on prod even
# though prod has fewer ephemeral tenants — the asymmetry would be a
# gratuitous fork.
STALE_COUNT=0
UNREACHABLE_COUNT=0
STALE_LINES=()
UNREACHABLE_LINES=()
for slug in "${SLUGS[@]}"; do
URL="https://${slug}.${TENANT_DOMAIN}/buildinfo"
# 30s total: tenant just SSM-restarted, may still be coming
@ -257,15 +264,15 @@ jobs:
BODY=$(curl -sS --max-time 30 --retry 3 --retry-delay 5 --retry-connrefused "$URL" || true)
ACTUAL_SHA=$(echo "$BODY" | jq -r '.git_sha // ""' 2>/dev/null || echo "")
if [ -z "$ACTUAL_SHA" ]; then
MISMATCH_COUNT=$((MISMATCH_COUNT + 1))
MISMATCH_LINES+=("| $slug | (no /buildinfo response) | ${EXPECTED_SHA:0:7} | ❌ unreachable |")
UNREACHABLE_COUNT=$((UNREACHABLE_COUNT + 1))
UNREACHABLE_LINES+=("| $slug | (no /buildinfo response) | ${EXPECTED_SHA:0:7} | ⚠ unreachable (likely teardown race) |")
continue
fi
if [ "$ACTUAL_SHA" = "$EXPECTED_SHA" ]; then
echo " $slug: ${ACTUAL_SHA:0:7} ✓"
else
MISMATCH_COUNT=$((MISMATCH_COUNT + 1))
MISMATCH_LINES+=("| $slug | ${ACTUAL_SHA:0:7} | ${EXPECTED_SHA:0:7} | ❌ stale |")
STALE_COUNT=$((STALE_COUNT + 1))
STALE_LINES+=("| $slug | ${ACTUAL_SHA:0:7} | ${EXPECTED_SHA:0:7} | ❌ stale |")
fi
done
@ -275,20 +282,33 @@ jobs:
echo ""
echo "Expected SHA: \`${EXPECTED_SHA:0:7}\`"
echo ""
if [ $MISMATCH_COUNT -gt 0 ]; then
echo "**${MISMATCH_COUNT} mismatch(es) — these tenants did NOT pick up the new image despite ssm_status=Success:**"
if [ $STALE_COUNT -gt 0 ]; then
echo "**${STALE_COUNT} STALE tenant(s) — these did NOT pick up the new image despite ssm_status=Success:**"
echo ""
echo "| Slug | Actual /buildinfo SHA | Expected | Status |"
echo "|------|----------------------|----------|--------|"
for line in "${MISMATCH_LINES[@]}"; do echo "$line"; done
else
for line in "${STALE_LINES[@]}"; do echo "$line"; done
echo ""
fi
if [ $UNREACHABLE_COUNT -gt 0 ]; then
echo "**${UNREACHABLE_COUNT} unreachable tenant(s) — likely teardown race (soft-warn, not failing):**"
echo ""
echo "| Slug | Actual /buildinfo SHA | Expected | Status |"
echo "|------|----------------------|----------|--------|"
for line in "${UNREACHABLE_LINES[@]}"; do echo "$line"; done
echo ""
fi
if [ $STALE_COUNT -eq 0 ] && [ $UNREACHABLE_COUNT -eq 0 ]; then
echo "All ${#SLUGS[@]} tenants returned matching SHA. ✓"
fi
} >> "$GITHUB_STEP_SUMMARY"
if [ $MISMATCH_COUNT -gt 0 ]; then
echo "::error::$MISMATCH_COUNT tenant(s) did not pick up the new image. ssm_status=Success was misleading — see job summary."
if [ $UNREACHABLE_COUNT -gt 0 ]; then
echo "::warning::$UNREACHABLE_COUNT tenant(s) unreachable post-redeploy. Likely benign teardown race — CP healthz monitor catches real outages."
fi
if [ $STALE_COUNT -gt 0 ]; then
echo "::error::$STALE_COUNT tenant(s) returned a stale SHA. ssm_status=Success was misleading — see job summary."
exit 1
fi
echo "::notice::Tenant fleet redeploy complete + verified — all tenants on ${EXPECTED_SHA:0:7}."
echo "::notice::Tenant fleet redeploy complete — all reachable tenants on ${EXPECTED_SHA:0:7} (${UNREACHABLE_COUNT} unreachable, soft-warned)."

View File

@ -219,22 +219,37 @@ jobs:
echo "Verifying ${#SLUGS[@]} staging tenant(s) against EXPECTED_SHA=${EXPECTED_SHA:0:7}..."
MISMATCH_COUNT=0
MISMATCH_LINES=()
# Two distinct failure modes here:
# STALE_COUNT — tenant returned a SHA that doesn't match. THIS is
# the #2395 bug class: tenant up + serving old code.
# Always hard-fail the workflow.
# UNREACHABLE_COUNT — tenant didn't respond. Almost always a benign
# teardown race: redeploy-fleet snapshot says
# healthz_ok=true, then the E2E suite tears the
# ephemeral tenant down before this step runs (the
# e2e-* fixtures churn 5-10/hour on staging). Soft-
# warn so we don't block staging→main on cleanup.
# Real "tenant up but unreachable" is caught by CP's
# own healthz monitor + the post-redeploy alert; we
# don't need to double-count it here.
STALE_COUNT=0
UNREACHABLE_COUNT=0
STALE_LINES=()
UNREACHABLE_LINES=()
for slug in "${SLUGS[@]}"; do
URL="https://${slug}.${TENANT_DOMAIN}/buildinfo"
BODY=$(curl -sS --max-time 30 --retry 3 --retry-delay 5 --retry-connrefused "$URL" || true)
ACTUAL_SHA=$(echo "$BODY" | jq -r '.git_sha // ""' 2>/dev/null || echo "")
if [ -z "$ACTUAL_SHA" ]; then
MISMATCH_COUNT=$((MISMATCH_COUNT + 1))
MISMATCH_LINES+=("| $slug | (no /buildinfo response) | ${EXPECTED_SHA:0:7} | ❌ unreachable |")
UNREACHABLE_COUNT=$((UNREACHABLE_COUNT + 1))
UNREACHABLE_LINES+=("| $slug | (no /buildinfo response) | ${EXPECTED_SHA:0:7} | ⚠ unreachable (likely teardown race) |")
continue
fi
if [ "$ACTUAL_SHA" = "$EXPECTED_SHA" ]; then
echo " $slug: ${ACTUAL_SHA:0:7} ✓"
else
MISMATCH_COUNT=$((MISMATCH_COUNT + 1))
MISMATCH_LINES+=("| $slug | ${ACTUAL_SHA:0:7} | ${EXPECTED_SHA:0:7} | ❌ stale |")
STALE_COUNT=$((STALE_COUNT + 1))
STALE_LINES+=("| $slug | ${ACTUAL_SHA:0:7} | ${EXPECTED_SHA:0:7} | ❌ stale |")
fi
done
@ -244,20 +259,33 @@ jobs:
echo ""
echo "Expected SHA: \`${EXPECTED_SHA:0:7}\`"
echo ""
if [ $MISMATCH_COUNT -gt 0 ]; then
echo "**${MISMATCH_COUNT} mismatch(es) — these staging tenants did NOT pick up the new image despite ssm_status=Success:**"
if [ $STALE_COUNT -gt 0 ]; then
echo "**${STALE_COUNT} STALE tenant(s) — these did NOT pick up the new image despite ssm_status=Success:**"
echo ""
echo "| Slug | Actual /buildinfo SHA | Expected | Status |"
echo "|------|----------------------|----------|--------|"
for line in "${MISMATCH_LINES[@]}"; do echo "$line"; done
else
for line in "${STALE_LINES[@]}"; do echo "$line"; done
echo ""
fi
if [ $UNREACHABLE_COUNT -gt 0 ]; then
echo "**${UNREACHABLE_COUNT} unreachable tenant(s) — likely E2E teardown race (soft-warn, not failing):**"
echo ""
echo "| Slug | Actual /buildinfo SHA | Expected | Status |"
echo "|------|----------------------|----------|--------|"
for line in "${UNREACHABLE_LINES[@]}"; do echo "$line"; done
echo ""
fi
if [ $STALE_COUNT -eq 0 ] && [ $UNREACHABLE_COUNT -eq 0 ]; then
echo "All ${#SLUGS[@]} staging tenants returned matching SHA. ✓"
fi
} >> "$GITHUB_STEP_SUMMARY"
if [ $MISMATCH_COUNT -gt 0 ]; then
echo "::error::$MISMATCH_COUNT staging tenant(s) did not pick up the new image. ssm_status=Success was misleading — see job summary."
if [ $UNREACHABLE_COUNT -gt 0 ]; then
echo "::warning::$UNREACHABLE_COUNT staging tenant(s) unreachable post-redeploy. Likely benign teardown race — CP healthz monitor catches real outages."
fi
if [ $STALE_COUNT -gt 0 ]; then
echo "::error::$STALE_COUNT staging tenant(s) returned a stale SHA. ssm_status=Success was misleading — see job summary."
exit 1
fi
echo "::notice::Staging tenant fleet redeploy complete + verified — all tenants on ${EXPECTED_SHA:0:7}."
echo "::notice::Staging tenant fleet redeploy complete — all reachable tenants on ${EXPECTED_SHA:0:7} (${UNREACHABLE_COUNT} unreachable, soft-warned)."