Merge pull request #30 from openqj/monitor-autoscaler-check

monitor.sh: worker check accepts autoscaler (static worker retired)
This commit is contained in:
openqj authored and GitHub committed 2026-10-26 11:03:49 +08:00
commit b984171f27
1 file changed
+6 -2
+6 -2
View File
@@ -7,7 +7,10 @@
# #
# 检查项(全部不需要密码、不读 env 文件): # 检查项(全部不需要密码、不读 env 文件):
# server:systemctl is-active codex-cloud-server 为 active # server:systemctl is-active codex-cloud-server 为 active
# worker:systemctl is-active codex-cloud-worker 为 active # worker:codex-autoscaler 或 codex-cloud-worker 任一为 active
# (autoscaler 接管后静态 worker 故意停用,只查静态会误报:
# 2026-10-26 07:02:55 静态 worker 停用后每 5 分钟 worker fail,
# 实际 worker 正常、health 的 worker_ok 也一直 pass)
# health:curl health,要求 ok=true、backend=postgres、db_ok=true、 # health:curl health,要求 ok=true、backend=postgres、db_ok=true、
# worker_ok=true(worker 心跳 180 秒内,见 server.py) # worker_ok=true(worker 心跳 180 秒内,见 server.py)
# postgres:pg_isready -h 127.0.0.1 -p 5432(只测就绪,不连库查数据, # postgres:pg_isready -h 127.0.0.1 -p 5432(只测就绪,不连库查数据,
@@ -43,7 +46,8 @@ check_server() {
} }
check_worker() { check_worker() {
if systemctl is-active codex-cloud-worker >/dev/null 2>&1; then if systemctl is-active codex-autoscaler >/dev/null 2>&1 \
|| systemctl is-active codex-cloud-worker >/dev/null 2>&1; then
echo pass echo pass
else else
echo fail echo fail