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
20 lines
759 B
Bash
20 lines
759 B
Bash
#!/usr/bin/env bash
|
|
# docker_health_check.sh — detect unhealthy Docker containers.
|
|
set -euo pipefail
|
|
|
|
if ! command -v docker >/dev/null 2>&1; then
|
|
echo '{"health":"healthy"}'
|
|
exit 0
|
|
fi
|
|
|
|
UNHEALTHY=$(docker ps --filter "health=unhealthy" --format "{{.Names}}" 2>/dev/null || true)
|
|
|
|
if [ -n "$UNHEALTHY" ]; then
|
|
COUNT=$(echo "$UNHEALTHY" | wc -l | tr -d ' ')
|
|
NAMES=$(echo "$UNHEALTHY" | tr '\n' ',' | sed 's/,$//')
|
|
echo "{\"health\":\"degraded\",\"signalKind\":\"docker-unhealthy\",\"evidence\":\"$COUNT unhealthy container(s): $NAMES\",\"metrics\":{\"docker_unhealthy\":$COUNT}}"
|
|
else
|
|
TOTAL=$(docker ps -q 2>/dev/null | wc -l | tr -d ' ' || echo 0)
|
|
echo "{\"health\":\"healthy\",\"metrics\":{\"docker_unhealthy\":0,\"docker_total\":$TOTAL}}"
|
|
fi
|