dtoro
35feada286
- Refactor executeCheck to return checkResult struct with metrics map - Add ping check kind (ICMP reachability via system ping, macOS+Linux) - Add ssh-script check kind (remote host exec via SSH, allowlisted scripts) - Add threshold evaluation (warn/crit per metric from check config JSONB) - Add inode tracking to disk check - All 4 existing checks now return structured metrics - 17 check scripts: cpu, memory, load, swap, disk_usage, disk_smart, updates, zfs, process, uptime, oom, journal, time, fd, docker_health, caddy_error_rate, backup_freshness - Auto-deploy via tools/setup-checks.sh -> checks/install.sh on git pull - Add ping to OpenAPI CheckKind enum and generated Go types
30 lines
849 B
Bash
30 lines
849 B
Bash
#!/usr/bin/env bash
|
|
# disk_smart_check.sh — SMART pre-failure indicators for physical disks.
|
|
set -euo pipefail
|
|
|
|
if ! command -v smartctl >/dev/null 2>&1; then
|
|
echo '{"health":"healthy"}'
|
|
exit 0
|
|
fi
|
|
|
|
DISKS=$(lsblk -ndo NAME,TYPE 2>/dev/null | awk '$2=="disk"{print "/dev/"$1}' || true)
|
|
if [ -z "$DISKS" ]; then
|
|
echo '{"health":"healthy"}'
|
|
exit 0
|
|
fi
|
|
|
|
FAILED=""
|
|
for dev in $DISKS; do
|
|
INFO=$(smartctl -H "$dev" 2>/dev/null || true)
|
|
if ! echo "$INFO" | grep -q "PASSED\|OK"; then
|
|
MODEL=$(smartctl -i "$dev" 2>/dev/null | awk -F': ' '/Device Model|Product/{print $2; exit}' || echo "$dev")
|
|
FAILED="$FAILED $MODEL"
|
|
fi
|
|
done
|
|
|
|
if [ -n "$FAILED" ]; then
|
|
echo "{\"health\":\"degraded\",\"signalKind\":\"disk-smart-fail\",\"evidence\":\"SMART check failed for:$(echo "$FAILED" | sed 's/ /, /g')\"}"
|
|
else
|
|
echo '{"health":"healthy"}'
|
|
fi
|