scheduler: add ping + ssh-script check kinds, metrics refactor, 17 host check scripts
- 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
This commit is contained in:
20
checks/cpu_check.sh
Normal file
20
checks/cpu_check.sh
Normal file
@@ -0,0 +1,20 @@
|
||||
#!/usr/bin/env bash
|
||||
# cpu_check.sh — CPU usage % and thermal temperature.
|
||||
set -euo pipefail
|
||||
|
||||
USAGE=$(top -bn1 2>/dev/null | awk '/^%Cpu/ {print 100 - $8}' || true)
|
||||
if [ -z "$USAGE" ]; then
|
||||
CORES=$(nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 1)
|
||||
USAGE=$(awk -v cores="$CORES" '{print ($1+$2+$3)*100/cores}' /proc/loadavg 2>/dev/null || echo "0")
|
||||
fi
|
||||
|
||||
TEMP=""
|
||||
if [ -f /sys/class/thermal/thermal_zone0/temp ]; then
|
||||
TEMP=$(awk '{printf "%.1f", $1/1000}' /sys/class/thermal/thermal_zone0/temp 2>/dev/null || true)
|
||||
fi
|
||||
|
||||
if [ -n "$TEMP" ]; then
|
||||
echo "{\"health\":\"healthy\",\"metrics\":{\"cpu_pct\":$USAGE,\"cpu_temp\":$TEMP}}"
|
||||
else
|
||||
echo "{\"health\":\"healthy\",\"metrics\":{\"cpu_pct\":$USAGE}}"
|
||||
fi
|
||||
Reference in New Issue
Block a user