Собрать наблюдаемый стенд, чтобы причину деградации API и worker было видно по метрикам, логам и трассам.

This commit is contained in:
2026-11-07 01:36:19 +03:00
parent 470d9d6f1e
commit 7d4e1237a3
56 changed files with 4419 additions and 53 deletions
+29
View File
@@ -0,0 +1,29 @@
#!/bin/sh
set -eu
cd "$(dirname "$0")/.."
wait_healthy() {
i=0
while [ "$i" -lt 40 ]; do
ok=1
for svc in "$@"; do
health=$(docker compose --env-file .env ps --format '{{.Service}} {{.Health}}' "$svc" | awk 'NR==1 {print $2}')
if [ "$health" != "healthy" ]; then
ok=0
fi
done
if [ "$ok" -eq 1 ]; then
return 0
fi
i=$((i + 1))
sleep 1
done
echo "timed out waiting for healthy: $*" >&2
return 1
}
docker compose --env-file .env restart -t 5 postgres s3 rabbitmq
wait_healthy postgres s3 rabbitmq
docker compose --env-file .env restart -t 5 api-1 api-2 worker
wait_healthy api-1 api-2 worker
docker compose --env-file .env restart -t 2 nginx