starred/orca
1
0
Fork 0
mirror of https://github.com/stablyai/orca.git synced 2026-09-22 16:02:32 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(relay-ops): retry transient admin-endpoint failures in same-cap verify and rehome jobs (#18769)

Browse Source
This commit is contained in:
Jinwoo Hong
2026-09-04 22:04:21 -04:00
committed by GitHub
parent df7b1028dd
commit e2b70a5eba
13 changed files with 496 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/cloud-deploy-relay-production-same-cap-job.yml
+38 -18
View File
@@ -275,10 +275,22 @@ jobs:
env:
ORCA_RELAY_ADMIN_ID_TOKEN: ${{ steps.deploy-auth.outputs.id_token }}
run: |
CURRENT_RUNTIME="$(curl --fail-with-body --max-time 30 \
--request POST "${CELL_ORIGIN}/v1/admin/runtime-status" \
--header "Authorization: Bearer ${ORCA_RELAY_ADMIN_ID_TOKEN}" \
--header 'Content-Type: application/json' --data '{"v":1}')"
# A single transient 5xx (LB warm-up behind a fresh instance) must not
# fail a canary; 4xx (auth, generation mismatch) still fails fast.
admin_post() {
local out="${RUNNER_TEMP}/$1.json"
if ! curl --fail-with-body --max-time 30 \
--retry 3 --retry-delay 2 --retry-connrefused --output "${out}" \
--request POST "$2" \
--header "Authorization: Bearer ${ORCA_RELAY_ADMIN_ID_TOKEN}" \
--header 'Content-Type: application/json' --data "$3"; then
cat "${out}" >&2
return 1
fi
cat "${out}"
}
CURRENT_RUNTIME="$(admin_post current-runtime \
"${CELL_ORIGIN}/v1/admin/runtime-status" '{"v":1}')"
# A rollback that failed between template apply and admission restore
# leaves the cell already on the rollback image; resume from that
# state instead of demanding the pre-rollback predecessor.
@@ -374,11 +386,9 @@ jobs:
if .regionalRehomeProtocol == null then "regionalRehomeProtocol" else empty end
] | if length > 0 then "runtime predecessor normalized legacy fields=" + join(",") else empty end' \
<<< "${CURRENT_RUNTIME}"
CURRENT_DIRECTOR_STATUS="$(curl --fail-with-body --max-time 30 \
--request POST "${DIRECTOR_ORIGIN}/v1/admin/cell-status" \
--header "Authorization: Bearer ${ORCA_RELAY_ADMIN_ID_TOKEN}" \
--header 'Content-Type: application/json' \
--data "$(jq -cn --arg cell "${TARGET_CELL_ID}" '{v:1,cellId:$cell}')")"
CURRENT_DIRECTOR_STATUS="$(admin_post current-cell-status \
"${DIRECTOR_ORIGIN}/v1/admin/cell-status" \
"$(jq -cn --arg cell "${TARGET_CELL_ID}" '{v:1,cellId:$cell}')")"
SOURCE_INCARNATION="$(jq -er '.status.runtime.cellIncarnation' \
<<< "${CURRENT_DIRECTOR_STATUS}")"
if test "${ROLLBACK_RESUME}" = true && ! jq -e \
@@ -536,6 +546,20 @@ jobs:
env:
ORCA_RELAY_ADMIN_ID_TOKEN: ${{ steps.post-auth.outputs.id_token }}
run: |
# A single transient 5xx (LB warm-up behind a fresh instance) must not
# fail a canary; 4xx (auth, generation mismatch) still fails fast.
admin_post() {
local out="${RUNNER_TEMP}/$1.json"
if ! curl --fail-with-body --max-time 30 \
--retry 3 --retry-delay 2 --retry-connrefused --output "${out}" \
--request POST "$2" \
--header "Authorization: Bearer ${ORCA_RELAY_ADMIN_ID_TOKEN}" \
--header 'Content-Type: application/json' --data "$3"; then
cat "${out}" >&2
return 1
fi
cat "${out}"
}
node dev/scripts/verify-relay-capacity-transition.mjs \
--director-origin "${DIRECTOR_ORIGIN}" --cell-origin "${CELL_ORIGIN}" \
--cell-id "${TARGET_CELL_ID}" --hard-cap "${EXPECTED_HARD_CAP}" \
@@ -543,19 +567,15 @@ jobs:
--heartbeat fresh --admission migration-only --draining forbidden \
--activity allowed --expected-image-digests "${DESIRED_IMAGE_DIGEST}" \
--regional-rehome-protocol "${DESIRED_REHOME_PROTOCOL}" --timeout-ms 900000
TARGET_RUNTIME="$(curl --fail-with-body --max-time 30 \
--request POST "${CELL_ORIGIN}/v1/admin/runtime-status" \
--header "Authorization: Bearer ${ORCA_RELAY_ADMIN_ID_TOKEN}" \
--header 'Content-Type: application/json' --data '{"v":1}')"
TARGET_RUNTIME="$(admin_post target-runtime \
"${CELL_ORIGIN}/v1/admin/runtime-status" '{"v":1}')"
jq -e --arg digest "${DESIRED_IMAGE_DIGEST}" \
--argjson protocol "${DESIRED_REHOME_PROTOCOL}" \
'.imageDigest == $digest and (.regionalRehomeProtocol // 0) == $protocol' \
<<< "${TARGET_RUNTIME}" >/dev/null
TARGET_DIRECTOR_STATUS="$(curl --fail-with-body --max-time 30 \
--request POST "${DIRECTOR_ORIGIN}/v1/admin/cell-status" \
--header "Authorization: Bearer ${ORCA_RELAY_ADMIN_ID_TOKEN}" \
--header 'Content-Type: application/json' \
--data "$(jq -cn --arg cell "${TARGET_CELL_ID}" '{v:1,cellId:$cell}')")"
TARGET_DIRECTOR_STATUS="$(admin_post target-cell-status \
"${DIRECTOR_ORIGIN}/v1/admin/cell-status" \
"$(jq -cn --arg cell "${TARGET_CELL_ID}" '{v:1,cellId:$cell}')")"
TARGET_INCARNATION="$(jq -er '.status.runtime.cellIncarnation' \
<<< "${TARGET_DIRECTOR_STATUS}")"
if test "${ROLLBACK_RESUME}" = true; then