- 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
18 lines
673 B
Bash
18 lines
673 B
Bash
#!/usr/bin/env bash
|
|
# oom_check.sh — detect OOM kills since last boot.
|
|
set -euo pipefail
|
|
|
|
OOM_COUNT=0
|
|
|
|
if command -v dmesg >/dev/null 2>&1; then
|
|
OOM_COUNT=$(dmesg 2>/dev/null | grep -ci 'out of memory\|oom-killer\|Killed process' || echo 0)
|
|
elif command -v journalctl >/dev/null 2>&1; then
|
|
OOM_COUNT=$(journalctl -k --no-pager 2>/dev/null | grep -ci 'out of memory\|oom-killer\|Killed process' || echo 0)
|
|
fi
|
|
|
|
if [ "$OOM_COUNT" -gt 0 ]; then
|
|
echo "{\"health\":\"degraded\",\"signalKind\":\"oom-kills\",\"evidence\":\"$OOM_COUNT OOM events detected since boot\",\"metrics\":{\"oom_count\":$OOM_COUNT}}"
|
|
else
|
|
echo '{"health":"healthy","metrics":{"oom_count":0}}'
|
|
fi
|