Files
selfheal-lab-gitops/vm/postgres-common/alloy.sh
T
seon a500c3d40c fix: Alloy block syntax, dpkg lock wait, hitl local bind, ai-reader nodes RBAC, harness image f30af2a
- Alloy 설정 3종: rule 블록을 한 줄 쉼표 나열에서 줄바꿈 속성으로 수정(실측: k8s DaemonSet
  CrashLoopBackOff, db-replica alloy.service "expected TERMINATOR, got ,"). alloy fmt로 3종 파싱 확인.
- vm/postgres-common/alloy.sh: apt에 DPkg::Lock::Timeout=600(db-primary에서 unattended-upgrades 잠금으로 100 종료).
- vm/ai-env/compose.yaml: hitl 8081을 127.0.0.1에만 바인딩(agent는 compose 네트워크로 접근).
- workloads/rbac/ai-reader.yaml: nodes get/list/watch ClusterRole 추가(agent get_k8s(nodes) selfcheck 거부 해소).
- vm/harness/image.tag: f30af2a(POST /proposals/{token}/approve·reject 포함 러너).
2026-10-08 01:53:06 +09:00

43 lines
2.6 KiB
Bash
Executable File

#!/usr/bin/env bash
# Alloy on the PostgreSQL VMs (WP-15, experiment design 4.1 / 4.3). Called by vm/postgres-{primary,replica}/apply.sh.
# The harness role password is read from Secret Manager (selfheal-db-password) through the VM service account. Installs Alloy from the Grafana apt repository (systemd service `alloy`,
# config /etc/alloy/config.alloy, environment /etc/default/alloy; https://grafana.com/docs/alloy/latest/configure/linux/),
# exposes the built-in postgres exporter (pg_replication_lag_seconds) plus a custom query for pg_is_wal_replay_paused
# (not in the upstream replication collector), and ships /var/log/postgresql to Loki. Idempotent.
set -euo pipefail
HERE="$(cd "$(dirname "$0")" && pwd)"
if ! command -v alloy >/dev/null; then
mkdir -p /etc/apt/keyrings
wget -qO /etc/apt/keyrings/grafana.asc https://apt.grafana.com/gpg-full.key
chmod 644 /etc/apt/keyrings/grafana.asc
echo "deb [signed-by=/etc/apt/keyrings/grafana.asc] https://apt.grafana.com stable main" > /etc/apt/sources.list.d/grafana.list
# wait for unattended-upgrades instead of failing on the dpkg lock (db-primary 2026-10-08: "Could not get lock /var/lib/dpkg/lock-frontend")
apt-get -o DPkg::Lock::Timeout=600 update -qq
apt-get -o DPkg::Lock::Timeout=600 install -y -qq alloy >/dev/null
fi
usermod -aG adm alloy # /var/log/postgresql/*.log is postgres:adm 0640
install -d -m 755 /etc/alloy
install -m 644 "$HERE/config.alloy" /etc/alloy/config.alloy
install -m 644 "$HERE/queries.yaml" /etc/alloy/queries.yaml
PROJECT="$(curl -sf -H 'Metadata-Flavor: Google' http://metadata.google.internal/computeMetadata/v1/project/project-id)"
TOKEN="$(curl -sf -H 'Metadata-Flavor: Google' 'http://metadata.google.internal/computeMetadata/v1/instance/service-accounts/default/token' | jq -r .access_token)"
PGPASSWORD="$(curl -sf -H "Authorization: Bearer ${TOKEN}" "https://secretmanager.googleapis.com/v1/projects/${PROJECT}/secrets/selfheal-db-password/versions/latest:access" | jq -r .payload.data | base64 -d)"
unset TOKEN
[ -n "$PGPASSWORD" ] || { echo "empty DB password" >&2; exit 1; }
IP="$(hostname -I | awk '{print $1}')"
umask 077
cat > /etc/default/alloy <<ENV
CONFIG_FILE="/etc/alloy/config.alloy"
CUSTOM_ARGS="--server.http.listen-addr=127.0.0.1:12345 --storage.path=/var/lib/alloy/data"
INSTANCE="$(hostname)"
PG_DSN="postgresql://harness:${PGPASSWORD}@${IP}:5432/app?sslmode=require"
ENV
unset PGPASSWORD
systemctl enable alloy >/dev/null 2>&1 || true
systemctl restart alloy
for i in $(seq 1 20); do
c=$(curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:12345/-/ready || true)
[ "$c" = "200" ] && break; sleep 3
done
echo "alloy ready=$c"