Files
selfheal-lab-gitops/vm/harness/apply.sh
T
seon 7ce2dc68fe feat: AI VM stack (WP-12) and Alloy telemetry on k8s, legacy and DB VMs (WP-15)
WP-12(실험 설계서 6장) vm/ai-env: apply.sh(시크릿 4종을 Secret Manager에서 파일로, 미등록이면
성능 저하 모드로 기동), compose(agent 8080·hitl 8081·rag-db pgvector 0.8.7-pg16), ai.env(Discord
서버 Selfheal Lab 1557424985793101824, approvals 1557425140302872698, escalation 1557425282363691048,
OPENAI_MODEL gpt-6.1-sol 후보), 프롬프트 3종, 러너북 11종(조치별·토폴로지·3층 절차).

WP-15(실험 설계서 4.1·4.3): apps/alloy.yaml(Alloy Helm 1.13.0 DaemonSet, 클러스터링으로 KSM·Argo CD·
cadvisor 스크랩 분산, demo 등 파드 로그 → Loki), apps/kube-state-metrics.yaml(Helm 8.6.0).
legacy-api compose에 Alloy 사이드카(up{job="legacy-api"}, 컨테이너 로그). DB VM은
vm/postgres-common/alloy.sh로 apt 설치 + prometheus.exporter.postgres(pg_replication_lag_seconds)
+ custom query pg_is_wal_replay_paused + PostgreSQL 로그.

vm/harness/apply.sh: 준비 대기 루프의 curl에 || true(러너 재기동 순간 curl 56으로 중단되던 문제,
2026-10-08 harness-sync 실측).
2026-10-08 01:47:38 +09:00

62 lines
3.3 KiB
Bash
Executable File

#!/usr/bin/env bash
# Harness VM (10.20.0.11). Idempotent: first boot (startup script) and `make vm-sync`.
# Secrets come from Secret Manager through the VM service account (no key files, Terraform design 6.11):
# selfheal-k8s-harness-token, selfheal-k8s-ca-cert, selfheal-vm-ssh-private-key, selfheal-db-password, selfheal-harness-token
# Runner inputs (ALB DNS, AWS role ARN) come from instance metadata set by Terraform (20-compute).
set -euo pipefail
cd "$(dirname "$0")"
MD=http://metadata.google.internal/computeMetadata/v1
md() { curl -sf -H 'Metadata-Flavor: Google' "$MD/$1"; }
PROJECT="$(md project/project-id)"
ALB_DNS="$(md instance/attributes/alb-dns)"
AWS_ROLE_ARN="$(md instance/attributes/aws-role-arn)"
command -v jq >/dev/null || { apt-get update -qq && apt-get install -y -qq jq >/dev/null; }
TOKEN="$(md instance/service-accounts/default/token | jq -r .access_token)"
secret() { curl -sf -H "Authorization: Bearer ${TOKEN}" "https://secretmanager.googleapis.com/v1/projects/${PROJECT}/secrets/$1/versions/latest:access" | jq -r .payload.data | base64 -d; }
SEC=/opt/selfheal/harness/secrets
mkdir -p "$SEC"; chmod 700 /opt/selfheal/harness "$SEC"
umask 077
secret selfheal-k8s-harness-token > "$SEC/k8s-token"
secret selfheal-k8s-ca-cert > "$SEC/k8s-ca.crt"
secret selfheal-vm-ssh-private-key > "$SEC/vm-ssh-key"
secret selfheal-db-password > "$SEC/db-password"
secret selfheal-harness-token > "$SEC/harness-token"
unset TOKEN
for f in k8s-token k8s-ca.crt vm-ssh-key db-password harness-token; do [ -s "$SEC/$f" ] || { echo "empty secret file $f" >&2; exit 1; }; done
chown -R 10001:10001 "$SEC"; chmod 600 "$SEC"/* # runner runs as uid 10001
ENV_FILE=/opt/selfheal/harness.env
if [ ! -f "$ENV_FILE" ] || ! grep -q '^MEASURE_DB_PASSWORD=' "$ENV_FILE"; then
MDB_PW="$(head -c 24 /dev/urandom | base64 | tr -d '/+=')"
else
MDB_PW="$(sed -n 's/^MEASURE_DB_PASSWORD=//p' "$ENV_FILE")"
fi
HARNESS_TAG="$(cat image.tag)"
{
printf 'ALB_DNS=%s\n' "$ALB_DNS"
printf 'AWS_ROLE_ARN=%s\n' "$AWS_ROLE_ARN"
printf 'AWS_REGION=ap-northeast-1\n'
printf 'GCP_PROJECT=%s\n' "$PROJECT"
printf 'GCP_REGION=asia-northeast1\n'
printf 'LEGACY_MIG=selfheal-legacy-mig\n'
printf 'K8S_API=https://10.10.0.10:6443\n'
printf 'MIMIR_URL=http://10.20.0.10:9009/prometheus\n'
printf 'AI_DIAGNOSE_URL=http://10.20.0.12:8080/diagnose\n'
printf 'HARNESS_TAG=%s\n' "$HARNESS_TAG"
printf 'MEASURE_DB_PASSWORD=%s\n' "$MDB_PW"
} > "$ENV_FILE"
unset MDB_PW
docker compose --env-file "$ENV_FILE" -f compose.yaml up -d --pull always --remove-orphans
# runner re-reads secret files per call; recreate it anyway so a new image tag / env takes effect
docker compose --env-file "$ENV_FILE" -f compose.yaml up -d --force-recreate --no-deps runner
for i in $(seq 1 30); do
# `|| true`: a reset while the runner restarts (curl 56) must not abort the script under set -e (seen 2026-10-08 harness-sync)
h=$(curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:8080/healthz || true); b=$(curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:9115/-/healthy || true)
a=$(curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:12345/-/ready || true)
if [ "$h$b$a" = "200200200" ]; then break; fi; sleep 5
done
echo "ready: runner=$h blackbox=$b alloy=$a"
docker compose --env-file "$ENV_FILE" -f compose.yaml ps --format 'table {{.Name}}\t{{.Status}}'