- 40-register.sh: idempotent — dopisuje lustro do topology.yaml + tworzy hosts/<node>/services.yaml, commituje na bieżącym branchu (bez push) - 50-verify.sh: 4 checki — node-agent running, eventy, observer restart + heartbeat poll, world/nodes.json; tabela pass/fail; exit 1 on failure - 40-deploy-node-agent.sh: usunięty (martwy scaffold; deploy w 30-node-agent.sh) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
161 lines
6.8 KiB
Bash
Executable file
161 lines
6.8 KiB
Bash
Executable file
#!/usr/bin/env bash
|
||
# scripts/onboard/steps/50-verify.sh — restart observera + smoke test węzła w panelu
|
||
#
|
||
# Uruchamiaj PO: merge task/node-onboarding → master + git pull na VPS.
|
||
#
|
||
# Sprawdzenia:
|
||
# 1. SSH <node>: node-agent container running
|
||
# 2. SSH <node>: eventy obecne w /opt/homelab/events/<node>/
|
||
# 3. SSH VPS: docker restart control-plane-observer + poll observer.heartbeat
|
||
# 4. SSH VPS: <node> widoczny w /opt/homelab/world/nodes.json
|
||
#
|
||
# Exit 0 — wszystkie OK | Exit 1 — co najmniej jedno FAIL (tabela podsumowująca)
|
||
|
||
set -euo pipefail
|
||
|
||
STEP_NAME="50-verify"
|
||
|
||
: "${REPO_ROOT:?REPO_ROOT is not set — run via onboard.sh}"
|
||
: "${NODE_YAML:?NODE_YAML is not set — run via onboard.sh}"
|
||
: "${DRY_RUN:=0}"
|
||
|
||
if ! declare -f log >/dev/null 2>&1; then
|
||
# shellcheck source=../lib/common.sh
|
||
source "${REPO_ROOT}/scripts/onboard/lib/common.sh"
|
||
fi
|
||
|
||
SSH_USER=$(yaml_get "${NODE_YAML}" "ssh_user")
|
||
TS_HOSTNAME=$(yaml_get "${NODE_YAML}" "tailscale.hostname")
|
||
[[ -z "${SSH_USER}" ]] && die "ssh_user not set in ${NODE_YAML}"
|
||
[[ -z "${TS_HOSTNAME}" ]] && die "tailscale.hostname not set in ${NODE_YAML}"
|
||
|
||
VPS_SSH_USER="oskar"
|
||
VPS_SSH_HOST="100.95.58.48"
|
||
VPS_REPO_PATH="/home/oskar/homelab-codex-ws"
|
||
|
||
_SSH_OPTS=(-o StrictHostKeyChecking=accept-new -o ConnectTimeout=10 -o BatchMode=yes)
|
||
|
||
_ssh_node() { ssh "${_SSH_OPTS[@]}" "${SSH_USER}@${TS_HOSTNAME}" -- "$@"; }
|
||
_ssh_vps() { ssh "${_SSH_OPTS[@]}" "${VPS_SSH_USER}@${VPS_SSH_HOST}" -- "$@"; }
|
||
|
||
declare -A RESULTS=()
|
||
|
||
# ── 1. node-agent running on <node> ──────────────────────────────────────────
|
||
step "[${STEP_NAME}] 1/4 ${TS_HOSTNAME}: node-agent container"
|
||
|
||
if [ "${DRY_RUN:-0}" = 1 ]; then
|
||
dryrun "ssh ${SSH_USER}@${TS_HOSTNAME} docker ps --filter name=^node-agent\$"
|
||
RESULTS["node-agent-running"]="skip"
|
||
elif _ssh_node "docker ps --filter name=^node-agent\$ --filter status=running --format '{{.Names}}'" 2>/dev/null \
|
||
| grep -q "node-agent"; then
|
||
log "OK: node-agent running"
|
||
_ssh_node "docker ps --filter name=node-agent --format 'table {{.Names}}\t{{.Status}}'" 2>/dev/null || true
|
||
RESULTS["node-agent-running"]="PASS"
|
||
else
|
||
warn "FAIL: node-agent nie działa na ${TS_HOSTNAME}"
|
||
RESULTS["node-agent-running"]="FAIL"
|
||
fi
|
||
|
||
# ── 2. eventy w /opt/homelab/events/<node>/ ───────────────────────────────────
|
||
step "[${STEP_NAME}] 2/4 ${TS_HOSTNAME}: eventy"
|
||
|
||
if [ "${DRY_RUN:-0}" = 1 ]; then
|
||
dryrun "ssh ${SSH_USER}@${TS_HOSTNAME} find /opt/homelab/events/${TS_HOSTNAME}/ -name '*.json'"
|
||
RESULTS["events-present"]="skip"
|
||
elif _ssh_node "find /opt/homelab/events/${TS_HOSTNAME}/ -name '*.json' 2>/dev/null | head -1" 2>/dev/null \
|
||
| grep -q ".json"; then
|
||
_latest=$(_ssh_node "ls -t /opt/homelab/events/${TS_HOSTNAME}/*.json 2>/dev/null | head -1" || echo "?")
|
||
log "OK: eventy obecne (ostatni: ${_latest})"
|
||
RESULTS["events-present"]="PASS"
|
||
else
|
||
warn "FAIL: brak eventów w /opt/homelab/events/${TS_HOSTNAME}/"
|
||
RESULTS["events-present"]="FAIL"
|
||
fi
|
||
|
||
# ── 3. restart observera + healthcheck ────────────────────────────────────────
|
||
step "[${STEP_NAME}] 3/4 VPS: restart control-plane-observer"
|
||
|
||
if [ "${DRY_RUN:-0}" = 1 ]; then
|
||
dryrun "ssh ${VPS_SSH_USER}@${VPS_SSH_HOST} docker restart control-plane-observer"
|
||
dryrun "poll /opt/homelab/state/observer.heartbeat (max 30s)"
|
||
RESULTS["observer-healthy"]="skip"
|
||
else
|
||
log "Restarting control-plane-observer na VPS..."
|
||
_ssh_vps "docker restart control-plane-observer"
|
||
|
||
log "Polling observer.heartbeat (max 30s)..."
|
||
_ok=0
|
||
for _i in $(seq 1 6); do
|
||
sleep 5
|
||
_age=$(_ssh_vps "python3 -c \
|
||
\"import os,time; s=os.stat('/opt/homelab/state/observer.heartbeat'); \
|
||
print(int(time.time()-s.st_mtime))\" 2>/dev/null" || echo "999")
|
||
if [[ "${_age}" -lt 20 ]]; then
|
||
log "OK: observer.heartbeat fresh (${_age}s temu)"
|
||
_ok=1
|
||
break
|
||
fi
|
||
log " ... ${_i}×5s, heartbeat ${_age}s old..."
|
||
done
|
||
|
||
if [[ "${_ok}" -eq 1 ]]; then
|
||
RESULTS["observer-healthy"]="PASS"
|
||
else
|
||
warn "FAIL: observer.heartbeat nie odświeżony po 30s"
|
||
warn "Sprawdź: ssh ${VPS_SSH_USER}@${VPS_SSH_HOST} docker logs control-plane-observer --tail 30"
|
||
RESULTS["observer-healthy"]="FAIL"
|
||
fi
|
||
fi
|
||
|
||
# ── 4. <node> widoczny w world/nodes.json ─────────────────────────────────────
|
||
step "[${STEP_NAME}] 4/4 VPS: ${TS_HOSTNAME} w world/nodes.json"
|
||
|
||
if [ "${DRY_RUN:-0}" = 1 ]; then
|
||
dryrun "ssh ${VPS_SSH_USER}@${VPS_SSH_HOST} python3 -c \"json.load(.../world/nodes.json)['${TS_HOSTNAME}']\""
|
||
RESULTS["world-state"]="skip"
|
||
else
|
||
_node_status=$(_ssh_vps "python3 -c \"
|
||
import json, sys
|
||
try:
|
||
d = json.load(open('/opt/homelab/world/nodes.json'))
|
||
node = d.get('${TS_HOSTNAME}', {})
|
||
print(node.get('status', 'missing'))
|
||
except Exception as e:
|
||
print('error:' + str(e))
|
||
\"" 2>/dev/null || echo "ssh-error")
|
||
|
||
case "${_node_status}" in
|
||
online|offline)
|
||
log "OK: ${TS_HOSTNAME} w world/nodes.json (status=${_node_status})"
|
||
RESULTS["world-state"]="PASS"
|
||
;;
|
||
missing)
|
||
warn "FAIL: ${TS_HOSTNAME} nie ma wpisu w world/nodes.json"
|
||
warn "Możliwa przyczyna: observer nie przetworzyл jeszcze eventów (poczekaj 60s i spróbuj ponownie)"
|
||
RESULTS["world-state"]="FAIL"
|
||
;;
|
||
*)
|
||
warn "FAIL: nieoczekiwana odpowiedź: ${_node_status}"
|
||
RESULTS["world-state"]="FAIL"
|
||
;;
|
||
esac
|
||
fi
|
||
|
||
# ── tabela podsumowująca ──────────────────────────────────────────────────────
|
||
echo ""
|
||
printf '%s\n' "══════════════════════════════════════════"
|
||
printf " %-30s %s\n" "CHECK" "RESULT"
|
||
printf '%s\n' "──────────────────────────────────────────"
|
||
for _key in "node-agent-running" "events-present" "observer-healthy" "world-state"; do
|
||
_val="${RESULTS[${_key}]:-???}"
|
||
printf " %-30s %s\n" "${_key}" "${_val}"
|
||
done
|
||
printf '%s\n' "══════════════════════════════════════════"
|
||
echo ""
|
||
|
||
for _val in "${RESULTS[@]}"; do
|
||
[[ "${_val}" == "FAIL" ]] && { warn "Verify: co najmniej jeden check nie przeszedł"; exit 1; }
|
||
done
|
||
|
||
log "[${STEP_NAME}] Verify OK — ${TS_HOSTNAME} zarejestrowany i widoczny w panelu"
|