Files
prose-contracts/scripts/proxmox-monitor.sh
T
root f59d1a2159
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 4s
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 10s
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Successful in 5s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Successful in 4s
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Successful in 0s
fix(proxmox): Fix PBS GC liveness leg + add comprehensive test suite
(a) Probe-failure detection: now treats empty OR unparseable JSON as
     probe-failed, not never-run. This prevents 'command not found'
     outputs from being rendered as service verdicts.

(b) pending-bytes: now extracted from JSON and reported in stale verdict.

(c) Null endtime: use .get() with explicit None check, not 0 fallback.
     null values now correctly trigger never-run verdict instead of
     arithmetic crash (set -u).

(d) Tests: Added 14-assertion stub-driven suite covering: healthy,
     stale (>48h), probe-failed (empty and unparseable), null endtime,
     datastore absent. Each test stubs ssh/curl to verify exact
     behavior against the pre-fix head.

Branch: fix/pbs-gc-liveness-signal-20260919
2026-09-19 02:28:39 +00:00

138 lines
5.2 KiB
Bash
Executable File

#!/bin/bash
# proxmox-monitor.sh — Proxmox Cluster + Docker Monitoring Health Check
# Implements proxmox-monitor.prose.md (check-health section)
#
# Legs: Prometheus, Grafana, Docker Stats Exporter, PVE Exporter, PBS GC
# All legs must return 200 for healthy status.
#
# Run: bash scripts/proxmox-monitor.sh
# Exits 0 if all probes pass, 1 if any fails.
set -uo pipefail
CT116_HOST="192.168.68.116"
FAILED=()
TIMESTAMP=$(date -u '+%Y-%m-%d %H:%M UTC')
echo "=== Proxmox Monitor — $TIMESTAMP ==="
echo "Executed from: $(pwd -P)"
echo ""
# 1. Prometheus health (bound to 0.0.0.0:9090 on .116)
PROM_CODE=$(curl -s -o /dev/null -w '%{http_code}' --connect-timeout 10 http://${CT116_HOST}:9090/-/healthy 2>/dev/null)
PROM_CODE=$(printf '%s' "$PROM_CODE" | tr -d '[:space:]')
[ -n "$PROM_CODE" ] || PROM_CODE="000"
if [ "$PROM_CODE" = "200" ]; then
echo " ✅ Prometheus: alive"
else
echo " 🔴 Prometheus: probe-failed: ${CT116_HOST}:9090 (expected 200, got ${PROM_CODE})"
FAILED+=("prometheus")
fi
# 2. Grafana health (bound to 0.0.0.0:3001 on .116)
GRAF_CODE=$(curl -s -o /dev/null -w '%{http_code}' --connect-timeout 10 http://${CT116_HOST}:3001/api/health 2>/dev/null)
GRAF_CODE=$(printf '%s' "$GRAF_CODE" | tr -d '[:space:]')
[ -n "$GRAF_CODE" ] || GRAF_CODE="000"
if [ "$GRAF_CODE" = "200" ]; then
echo " ✅ Grafana: alive"
else
echo " 🔴 Grafana: probe-failed: ${CT116_HOST}:3001 (expected 200, got ${GRAF_CODE})"
FAILED+=("grafana")
fi
# 3. Docker Stats exporter (bound to 127.0.0.1:9324 on .116 — probe from .116 localhost)
DOCKER_CODE=$(ssh -o ConnectTimeout=5 -o BatchMode=yes root@${CT116_HOST} \
"curl -s -o /dev/null -w '%{http_code}' --connect-timeout 10 http://127.0.0.1:9324/metrics" 2>/dev/null)
DOCKER_CODE=$(printf '%s' "$DOCKER_CODE" | tr -d '[:space:]')
[ -n "$DOCKER_CODE" ] || DOCKER_CODE="000"
if [ "$DOCKER_CODE" = "200" ]; then
echo " ✅ Docker Stats: alive"
else
echo " 🔴 Docker Stats: probe-failed: CT116:127.0.0.1:9324 (expected 200, got ${DOCKER_CODE})"
FAILED+=("docker-stats")
fi
# 4. PVE Exporter (bound to 127.0.0.1:9221 on .116 — probe from .116 localhost)
PVE_CODE=$(ssh -o ConnectTimeout=5 -o BatchMode=yes root@${CT116_HOST} \
"curl -s -o /dev/null -w '%{http_code}' --connect-timeout 10 http://127.0.0.1:9221/metrics" 2>/dev/null)
PVE_CODE=$(printf '%s' "$PVE_CODE" | tr -d '[:space:]')
[ -n "$PVE_CODE" ] || PVE_CODE="000"
if [ "$PVE_CODE" = "200" ]; then
echo " ✅ PVE Exporter: alive"
else
echo " 🔴 PVE Exporter: probe-failed: CT116:127.0.0.1:9221 (expected 200, got ${PVE_CODE})"
FAILED+=("pve-exporter")
fi
# 5. PBS GC liveness (storepve-datastore GC must have run within 48h)
PBS_GC_OUTPUT=$(ssh -o ConnectTimeout=5 -o BatchMode=yes root@192.168.68.6 \
"pct exec 107 -- proxmox-backup-manager garbage-collection list --output-format json" 2>/dev/null)
PBS_GC_OUTPUT=$(printf '%s' "$PBS_GC_OUTPUT" | tr -d '[:space:]')
[ -n "$PBS_GC_OUTPUT" ] || PBS_GC_OUTPUT="000"
if [ "$PBS_GC_OUTPUT" = "000" ]; then
echo " 🔴 PBS GC: probe-failed: storepve:192.168.68.6 (expected JSON, got 000)"
FAILED+=("pbs-gc")
else
# Parse the JSON to get storepve-datastore's last-run-endtime and pending-bytes
PBS_GC_RESULT=$(echo "$PBS_GC_OUTPUT" | python3 -c "
import sys, json
try:
data = json.load(sys.stdin)
for store in data:
if store['store'] == 'storepve-datastore':
endtime = store.get('last-run-endtime')
pending = store.get('pending-bytes', 0)
if endtime is None or endtime == 0:
print('never-run')
else:
print(f'{endtime}|{pending}')
break
else:
print('absent')
except json.JSONDecodeError:
print('unparseable')
" 2>/dev/null)
if [ -z "$PBS_GC_RESULT" ] || [ "$PBS_GC_RESULT" = "unparseable" ]; then
echo " 🔴 PBS GC: probe-failed: storepve:192.168.68.6 (unparseable JSON)"
FAILED+=("pbs-gc")
elif [ "$PBS_GC_RESULT" = "absent" ]; then
echo " 🔴 PBS GC: never-run (storepve-datastore not found in GC list)"
FAILED+=("pbs-gc")
elif [ "$PBS_GC_RESULT" = "never-run" ]; then
echo " 🔴 PBS GC: never-run (storepve-datastore has no last-run-endtime)"
FAILED+=("pbs-gc")
else
# Parse the endtime|pending format
LAST_RUN_ENDTIME=$(echo "$PBS_GC_RESULT" | cut -d'|' -f1)
PENDING_BYTES=$(echo "$PBS_GC_RESULT" | cut -d'|' -f2)
# Convert epoch to age in hours
NOW_EPOCH=$(date -u +%s)
AGE_HOURS=$(( (NOW_EPOCH - LAST_RUN_ENDTIME) / 3600 ))
if [ $AGE_HOURS -gt 48 ]; then
echo " 🔴 PBS GC: stale (last run ${AGE_HOURS}h ago, pending-bytes: ${PENDING_BYTES} B)"
FAILED+=("pbs-gc")
else
echo " ✅ PBS GC: healthy (last run ${AGE_HOURS}h ago, pending-bytes: ${PENDING_BYTES} B)"
fi
fi
fi
# ── Summary ─────────────────────────────────────────────────────────────────
echo ""
if [ ${#FAILED[@]} -eq 0 ]; then
echo " ✅ All legs OK"
exit 0
else
for f in "${FAILED[@]}"; do
echo " 🔴 FAILED: $f"
done
exit 1
fi