Structural reorganization: watchdog taxonomy + server_reboot integration
Watchdog renames and moves: system_watchdog.sh → stability_watchdog.sh (last line of defense — reboots) storage_watchdog.sh → Watchdogs/System/storage_watchdog.sh webgui_restart.sh → Watchdogs/System/webgui_watchdog.sh (renamed to match folder convention) New thin orchestrator: Watchdogs/system_watchdog.sh — runs SYSTEM_WATCHDOG_SCRIPTS from master.conf Sits between docker_watchdog and stability_watchdog in the orchestrator tier chain System/ subfolder is the growth seam for future system component watchdogs master.conf: WATCHDOG_ORCHESTRATOR_SCRIPTS updated — storage removed, system_watchdog added as tier SYSTEM_WATCHDOG_SCRIPTS array added — storage + webgui server_reboot.sh: Calls array_stopping.sh before VM shutdown for guaranteed safe array stop Removed raw rc.docker stop and exit trap — orchestrator owns container shutdown
This commit is contained in:
Gmer4Lfe
@@ -637,5 +637,5 @@ grep "system_watchdog" /var/log/syslog | tail -20
|
||||
Orchestrators/watchdog_orchestrator.sh --status
|
||||
|
||||
# Run the slow watchdog directly with --log to see where it's hanging:
|
||||
Watchdogs/system_watchdog.sh --log --dry-run
|
||||
Watchdogs/stability_watchdog.sh --log --dry-run
|
||||
```
|
||||
|
||||
@@ -140,7 +140,7 @@
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
|
||||
source "$SCRIPT_DIR/../load_config.sh"
|
||||
source "$SCRIPT_DIR/../../load_config.sh"
|
||||
|
||||
parse_args "$@"
|
||||
|
||||
@@ -0,0 +1,302 @@
|
||||
#!/bin/bash
|
||||
# ==============================================================================================
|
||||
# ================================= WebGUI Watchdog ============================================
|
||||
# ==============================================================================================
|
||||
#
|
||||
# PURPOSE
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
# Monitors the unRAID WebGUI and restarts services if unresponsive. Uses a
|
||||
# three-step escalating strategy — lightest fix first, heaviest last. Run
|
||||
# every 5–10 minutes via the User Scripts plugin. Silent when healthy.
|
||||
#
|
||||
# ==============================================================================================
|
||||
# OPERATIONAL MODEL
|
||||
# ==============================================================================================
|
||||
#
|
||||
# Escalation Path
|
||||
# WebGUI responding → log() + exit 0 (completely silent ✅)
|
||||
#
|
||||
# Not responding:
|
||||
# Step 1 — nginx restart
|
||||
# Lightest fix — handles most transient WebGUI failures:
|
||||
# nginx crash, worker stuck, connection timeout.
|
||||
# Wait WEBGUI_NGINX_WAIT seconds → recheck.
|
||||
#
|
||||
# Step 2 — php-fpm restart
|
||||
# WebGUI runs through PHP-FPM. Worker exhaustion causes silent
|
||||
# failure — requests queue and the WebGUI appears frozen.
|
||||
# Wait WEBGUI_PHP_WAIT seconds → recheck.
|
||||
#
|
||||
# Step 3 — emhttp restart
|
||||
# Heaviest fix. emhttp is the unRAID management daemon.
|
||||
# Array, Docker, and shares stay running — only WebGUI
|
||||
# management restarts. Takes longer — WEBGUI_EMHTTP_WAIT.
|
||||
# Wait WEBGUI_EMHTTP_WAIT seconds → recheck.
|
||||
#
|
||||
# All three failed → notify, manual intervention needed → exit 1.
|
||||
#
|
||||
# ==============================================================================================
|
||||
# OPERATIONAL SAFEGUARDS
|
||||
# ==============================================================================================
|
||||
#
|
||||
# Root Required
|
||||
# Service restart commands require root.
|
||||
#
|
||||
# Single Instance Lock
|
||||
# acquire_lock prevents concurrent runs double-restarting services.
|
||||
#
|
||||
# Process Verify After Each Restart
|
||||
# pgrep check after each rc.* command — errors if process not running.
|
||||
#
|
||||
# Silent When Healthy
|
||||
# Completely silent on healthy cycles. Only produces output when recovering.
|
||||
#
|
||||
# ==============================================================================================
|
||||
# CONFIGURATION
|
||||
# ==============================================================================================
|
||||
#
|
||||
# master.conf
|
||||
#
|
||||
# WEBGUI_URL
|
||||
# URL to check for WebGUI response. (default: http://localhost)
|
||||
#
|
||||
# WEBGUI_TIMEOUT
|
||||
# curl timeout in seconds. (default: 5)
|
||||
#
|
||||
# WEBGUI_NGINX_WAIT
|
||||
# Seconds after nginx restart before rechecking. (default: 15)
|
||||
#
|
||||
# WEBGUI_PHP_WAIT
|
||||
# Seconds after php-fpm restart before rechecking. (default: 10)
|
||||
#
|
||||
# WEBGUI_EMHTTP_WAIT
|
||||
# Seconds after emhttp restart before rechecking. (default: 30)
|
||||
#
|
||||
# ==============================================================================================
|
||||
# RUNTIME MODES
|
||||
# ==============================================================================================
|
||||
#
|
||||
# webgui_watchdog.sh
|
||||
# Check WebGUI. Escalate through nginx → php-fpm → emhttp if unresponsive.
|
||||
#
|
||||
# webgui_watchdog.sh --dry-run
|
||||
# Show which services would be restarted. No restarts, no waits.
|
||||
#
|
||||
# webgui_watchdog.sh --status
|
||||
# Show current WebGUI response state and nginx/php-fpm/emhttp process states.
|
||||
#
|
||||
# webgui_watchdog.sh --log
|
||||
# Verbose output — show each check, each restart attempt, each wait.
|
||||
#
|
||||
# ==============================================================================================
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
|
||||
source "$SCRIPT_DIR/../../load_config.sh"
|
||||
|
||||
parse_args "$@"
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Setup ━━━
|
||||
# ==============================================================================================
|
||||
if [[ "$EUID" -ne 0 ]]; then
|
||||
error "Must be run as root"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
validate_unraid_cmd \
|
||||
"/usr/local/emhttp/plugins/dynamix/scripts/notify" \
|
||||
"" "" \
|
||||
"unRAID notify script" || warn "unRAID notify script not found — native notifications disabled"
|
||||
|
||||
acquire_lock
|
||||
|
||||
detect_hosts
|
||||
|
||||
[[ "$DRY_RUN" == true ]] && warn "DRY RUN — no services will be restarted"
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Status ━━━
|
||||
# ==============================================================================================
|
||||
if [[ "$SHOW_STATUS" == true ]]; then
|
||||
echo ""
|
||||
echo "━━━━━ $ICON_SUMMARY WEBGUI WATCHDOG STATUS ━━━━━"
|
||||
echo "$ICON_HOST Identity: $MY_ID ($LOCAL_SERVER_NAME)"
|
||||
echo "$ICON_WEBGUI URL: $WEBGUI_URL"
|
||||
echo "$ICON_WEBGUI Timeouts: curl=${WEBGUI_TIMEOUT}s nginx=${WEBGUI_NGINX_WAIT}s php=${WEBGUI_PHP_WAIT:-10}s emhttp=${WEBGUI_EMHTTP_WAIT}s"
|
||||
echo ""
|
||||
|
||||
if curl -sf --max-time "$WEBGUI_TIMEOUT" "$WEBGUI_URL" >/dev/null 2>&1; then
|
||||
echo " $ICON_SUCCESS WebGUI: responding ✅"
|
||||
else
|
||||
echo " $ICON_ERROR WebGUI: NOT responding"
|
||||
fi
|
||||
|
||||
pgrep -x nginx >/dev/null 2>&1 && \
|
||||
echo " $ICON_SUCCESS nginx: running ✅" || \
|
||||
echo " $ICON_ERROR nginx: NOT running"
|
||||
|
||||
pgrep -f "php-fpm" >/dev/null 2>&1 && \
|
||||
FPM_COUNT=$(pgrep -fc "php-fpm" 2>/dev/null || echo "?") && \
|
||||
echo " $ICON_SUCCESS php-fpm: running ($FPM_COUNT workers) ✅" || \
|
||||
echo " $ICON_ERROR php-fpm: NOT running"
|
||||
|
||||
pgrep emhttpd >/dev/null 2>&1 && \
|
||||
echo " $ICON_SUCCESS emhttp: running ✅" || \
|
||||
echo " $ICON_ERROR emhttp: NOT running"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# ==============================================================================================
|
||||
# ── CHECK AND ESCALATE ────────────────────────────────────────────────────────────────────────
|
||||
# ==============================================================================================
|
||||
check_webgui() {
|
||||
curl -sf --max-time "$WEBGUI_TIMEOUT" "$WEBGUI_URL" >/dev/null 2>&1
|
||||
}
|
||||
|
||||
START=$(date +%s)
|
||||
RECOVERY_ACTION=""
|
||||
RECOVERY_OK=false
|
||||
|
||||
log "WebGUI check — $WEBGUI_URL"
|
||||
|
||||
# ── Healthy — completely silent ───────────────────────────────────────────────────────────────
|
||||
if check_webgui; then
|
||||
log "WebGUI responding — healthy ✅"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# ── Not responding — begin escalation ────────────────────────────────────────────────────────
|
||||
echo ""
|
||||
echo "━━━ $ICON_WEBGUI WebGUI Watchdog — $(date '+%Y-%m-%d %H:%M:%S') ━━━"
|
||||
echo "$ICON_HOST $MY_ID ($LOCAL_SERVER_NAME)"
|
||||
echo ""
|
||||
warn "WebGUI not responding at $WEBGUI_URL — beginning escalation"
|
||||
|
||||
# ── Step 1 — nginx restart ────────────────────────────────────────────────────────────────────
|
||||
echo ""
|
||||
echo "━━━ Step 1 — nginx Restart ━━━"
|
||||
|
||||
if [[ "$DRY_RUN" == true ]]; then
|
||||
warn "DRY RUN — would restart nginx"
|
||||
else
|
||||
warn "Restarting nginx..."
|
||||
if /etc/rc.d/rc.nginx restart >/dev/null 2>&1; then
|
||||
# Verify nginx actually running
|
||||
sleep 2
|
||||
if pgrep -x nginx >/dev/null 2>&1; then
|
||||
warn "nginx restarted ✅"
|
||||
else
|
||||
error "nginx not running after restart command"
|
||||
fi
|
||||
else
|
||||
error "nginx restart command failed"
|
||||
fi
|
||||
|
||||
log "Waiting ${WEBGUI_NGINX_WAIT}s for nginx to recover..."
|
||||
sleep "$WEBGUI_NGINX_WAIT"
|
||||
|
||||
if check_webgui; then
|
||||
RECOVERY_ACTION="nginx restart"
|
||||
RECOVERY_OK=true
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── Step 2 — php-fpm restart ──────────────────────────────────────────────────────────────────
|
||||
if [[ "$RECOVERY_OK" == false ]]; then
|
||||
echo ""
|
||||
echo "━━━ Step 2 — php-fpm Restart ━━━"
|
||||
warn "WebGUI still not responding — restarting php-fpm"
|
||||
warn "WebGUI may be frozen due to worker exhaustion (check system_tuning_monitor.sh)"
|
||||
|
||||
if [[ "$DRY_RUN" == true ]]; then
|
||||
warn "DRY RUN — would restart php-fpm"
|
||||
else
|
||||
if /etc/rc.d/rc.php-fpm restart >/dev/null 2>&1; then
|
||||
sleep 2
|
||||
if pgrep -f "php-fpm" >/dev/null 2>&1; then
|
||||
warn "php-fpm restarted ✅"
|
||||
else
|
||||
error "php-fpm not running after restart command"
|
||||
fi
|
||||
else
|
||||
error "php-fpm restart command failed"
|
||||
fi
|
||||
|
||||
log "Waiting ${WEBGUI_PHP_WAIT:-10}s for php-fpm to recover..."
|
||||
sleep "${WEBGUI_PHP_WAIT:-10}"
|
||||
|
||||
if check_webgui; then
|
||||
RECOVERY_ACTION="php-fpm restart"
|
||||
RECOVERY_OK=true
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── Step 3 — emhttp restart ───────────────────────────────────────────────────────────────────
|
||||
if [[ "$RECOVERY_OK" == false ]]; then
|
||||
echo ""
|
||||
echo "━━━ Step 3 — emhttp Restart ━━━"
|
||||
warn "WebGUI still not responding — restarting emhttp (unRAID management daemon)"
|
||||
warn "Array, Docker, and shares remain running — WebGUI management will briefly restart"
|
||||
|
||||
if [[ "$DRY_RUN" == true ]]; then
|
||||
warn "DRY RUN — would restart emhttp"
|
||||
else
|
||||
if /usr/local/sbin/emhttp stop >/dev/null 2>&1 && /usr/local/sbin/emhttp start >/dev/null 2>&1; then
|
||||
sleep 2
|
||||
if pgrep emhttpd >/dev/null 2>&1; then
|
||||
warn "emhttp restarted ✅"
|
||||
else
|
||||
error "emhttp not running after restart command"
|
||||
fi
|
||||
else
|
||||
error "emhttp restart command failed"
|
||||
fi
|
||||
|
||||
log "Waiting ${WEBGUI_EMHTTP_WAIT}s for emhttp to recover..."
|
||||
sleep "$WEBGUI_EMHTTP_WAIT"
|
||||
|
||||
if check_webgui; then
|
||||
RECOVERY_ACTION="emhttp restart"
|
||||
RECOVERY_OK=true
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
END=$(date +%s)
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Summary ━━━
|
||||
# ==============================================================================================
|
||||
echo ""
|
||||
echo "━━━━━ $ICON_SUMMARY WEBGUI WATCHDOG SUMMARY ━━━━━"
|
||||
echo "$ICON_HOST Identity: $MY_ID ($LOCAL_SERVER_NAME)"
|
||||
echo "$ICON_WEBGUI URL: $WEBGUI_URL"
|
||||
echo "$ICON_TIME Duration: $(format_duration $(( END - START )))"
|
||||
echo ""
|
||||
|
||||
if [[ "$DRY_RUN" == true ]]; then
|
||||
warn "DRY RUN — no services restarted"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
if [[ "$RECOVERY_OK" == true ]]; then
|
||||
warn "$ICON_SUCCESS WebGUI recovered via: $RECOVERY_ACTION"
|
||||
notify "WebGUI recovered on $(hostname) ($MY_ID) via $RECOVERY_ACTION — monitor for recurrence" \
|
||||
"WebGUI Watchdog" "warning"
|
||||
else
|
||||
echo "$ICON_ERROR Status: UNRECOVERED — all three restart steps failed"
|
||||
echo "$ICON_ERROR Manual intervention needed:"
|
||||
echo " 1. Check: pgrep nginx; pgrep emhttpd"
|
||||
echo " 2. Check: journalctl -u nginx --since '10 minutes ago'"
|
||||
echo " 3. Try: server_reboot.sh if nothing else works"
|
||||
notify "WebGUI UNRECOVERED on $(hostname) ($MY_ID) — nginx + php-fpm + emhttp restart all failed — manual intervention needed" \
|
||||
"WebGUI Watchdog" "warning"
|
||||
fi
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
[[ "$RECOVERY_OK" == false && "$DRY_RUN" == false ]] && exit 1
|
||||
exit 0
|
||||
@@ -52,9 +52,9 @@
|
||||
# Parity awareness — skips restart actions during parity check
|
||||
# Timeout protection — all docker commands wrapped in timeout
|
||||
# Docker daemon check — each cycle begins with daemon health check; hung daemon →
|
||||
# restart via rc.docker → system_watchdog.sh escalates if needed
|
||||
# restart via rc.docker → stability_watchdog.sh escalates if needed
|
||||
# RAM emergency defer — reads SYS_WATCHDOG_STATE_FILE; stands down while
|
||||
# system_watchdog.sh is managing a RAM emergency
|
||||
# stability_watchdog.sh is managing a RAM emergency
|
||||
#
|
||||
# ==============================================================================================
|
||||
# DESIGN PRINCIPLES
|
||||
@@ -113,13 +113,13 @@
|
||||
# Docker Daemon Health Check
|
||||
# First operation every cycle. Daemon not responding within DOCKER_TIMEOUT →
|
||||
# restart via /etc/rc.d/rc.docker → verify recovery. If still hung: log
|
||||
# critical, skip cycle. system_watchdog.sh handles further escalation.
|
||||
# critical, skip cycle. stability_watchdog.sh handles further escalation.
|
||||
#
|
||||
# RAM Emergency Deferral
|
||||
# Reads SYS_WATCHDOG_STATE_FILE each cycle. If system_watchdog.sh has set
|
||||
# Reads SYS_WATCHDOG_STATE_FILE each cycle. If stability_watchdog.sh has set
|
||||
# mem_shutdown_active=true, all restart logic defers until the flag clears.
|
||||
# Stale state guard: if file is >2 hours old with flag still set,
|
||||
# system_watchdog.sh has likely stopped — watchdog resumes normal operation.
|
||||
# stability_watchdog.sh has likely stopped — watchdog resumes normal operation.
|
||||
#
|
||||
# Timeout Protection
|
||||
# All docker commands wrapped in timeout. Daemon hangs cannot stall the
|
||||
@@ -465,7 +465,7 @@ is_parity_running() {
|
||||
# At WATCHDOG_DAEMON_STRIKE_LIMIT → attempt daemon restart via rc.docker
|
||||
# After restart → wait WATCHDOG_DAEMON_RESTART_WAIT seconds → verify
|
||||
# If verified → clear strikes, continue cycle ✅
|
||||
# If still hung → notify critical, skip cycle → system_watchdog.sh escalates from here
|
||||
# If still hung → notify critical, skip cycle → stability_watchdog.sh escalates from here
|
||||
#
|
||||
# Returns: 0 = daemon healthy | 1 = daemon down, skip this cycle
|
||||
|
||||
@@ -543,7 +543,7 @@ check_docker_daemon() {
|
||||
|
||||
if [[ "$WATCHDOG_DAEMON_RESTARTED" == true ]]; then
|
||||
error "Docker daemon still unresponsive after restart attempt"
|
||||
error "system_watchdog.sh will handle further escalation"
|
||||
error "stability_watchdog.sh will handle further escalation"
|
||||
queue_notify "Docker daemon hung on $(hostname) — restart failed — manual intervention needed" "critical"
|
||||
flush_notify
|
||||
return 1
|
||||
|
||||
Executable
+805
@@ -0,0 +1,805 @@
|
||||
#!/bin/bash
|
||||
# ==============================================================================================
|
||||
# ================================= System Watchdog ============================================
|
||||
# ==============================================================================================
|
||||
#
|
||||
# PURPOSE
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
# Last line of defense — reboots the system cleanly if it is about to become
|
||||
# unstable. Runs continuously as a background process started by
|
||||
# array_started.sh at array start. Works alongside docker_watchdog.sh which
|
||||
# handles container-level healing first. Only escalates to reboot when
|
||||
# docker_watchdog.sh cannot resolve the condition.
|
||||
#
|
||||
# ==============================================================================================
|
||||
# OPERATIONAL MODEL
|
||||
# ==============================================================================================
|
||||
#
|
||||
# Three-Tier Response System
|
||||
#
|
||||
# Tier 1 — CRITICAL (bypass all strikes, reboot immediately)
|
||||
# Docker daemon unresponsive — nothing can be healed; running it longer makes it worse
|
||||
# rootfs at 99%+ — writes failing; SSH may stop; no recovery options
|
||||
# Kernel oops/BUG in dmesg — kernel running with corrupted state
|
||||
# File descriptor exhaustion — new connections and processes failing silently
|
||||
# /boot read-only unexpectedly — state files and config writes silently failing
|
||||
#
|
||||
# Tier 2 — URGENT (bypass strikes when OOM confirms active crisis)
|
||||
# RAM < MEM_GB AND OOM kills >= OOM_LIMIT in this cycle.
|
||||
# OOM kills at this rate means the system is dying faster than watchdogs can heal.
|
||||
# Without OOM confirmation → standard strike system applies.
|
||||
#
|
||||
# Tier 3 — STANDARD (N consecutive failures → reboot)
|
||||
# RAM tiers, load, CPU temp, zombies, /var/log, /tmp, containers, NIC, mdstat.
|
||||
#
|
||||
# RAM Tiers
|
||||
# MEM_WARN_GB (10GB) — warn + notify only
|
||||
# MEM_SHUTDOWN_GB (6GB) — stop non-essential containers, wait for recovery
|
||||
# MEM_GB (4GB) — strike system → reboot (bypass with OOM confirmation)
|
||||
# MEM_RECOVER_GB (30GB) — RAM must reach this before stopped containers restart
|
||||
#
|
||||
# Container Shutdown Logic (at MEM_SHUTDOWN_GB)
|
||||
# Stops all containers not in SYS_WATCHDOG_MEM_SHUTDOWN_EXCLUDED.
|
||||
# Stopped containers tracked in shutdown list — won't restart until RAM recovers.
|
||||
# Strike system prevents flip-flopping — shutdown only once per degradation event.
|
||||
#
|
||||
# Abort Conditions (prevent reboot during sensitive operations)
|
||||
# ZFS pool unhealthy, parity running, mover running — each toggleable.
|
||||
# CRITICAL tier bypasses all abort conditions — imminent crash overrides data safety.
|
||||
#
|
||||
# Checks Run Every Cycle
|
||||
# rootfs usage, /var/log, /tmp, free RAM, ZFS ARC, CPU temp, load avg,
|
||||
# zombie processes, Docker daemon, OOM rate, /boot read-only, kernel oops,
|
||||
# file descriptor exhaustion, array disk errors, NIC state, required containers.
|
||||
#
|
||||
# ==============================================================================================
|
||||
# OPERATIONAL SAFEGUARDS
|
||||
# ==============================================================================================
|
||||
#
|
||||
# Root Required
|
||||
# Reboot and container stop require root.
|
||||
#
|
||||
# Single Instance Lock
|
||||
# acquire_lock prevents a second watchdog instance from starting.
|
||||
#
|
||||
# State File Verification
|
||||
# All state files verified writable at startup — errors if any cannot be created.
|
||||
#
|
||||
# ==============================================================================================
|
||||
# CONFIGURATION
|
||||
# ==============================================================================================
|
||||
#
|
||||
# master.conf — System Watchdog section
|
||||
# Full variable listing in master.conf. Key variables:
|
||||
#
|
||||
# SYS_WATCHDOG_REBOOT_WINDOW_HRS — reboot rate limit window (default: 2)
|
||||
# SYS_WATCHDOG_MAX_REBOOTS — max reboots in window before giving up (default: 3)
|
||||
# SYS_WATCHDOG_STRIKES — consecutive failures before reboot (default: 3)
|
||||
# SYS_WATCHDOG_OOM_LIMIT — OOM kills/cycle to trigger URGENT bypass (default: 3)
|
||||
# SYS_WATCHDOG_MEM_SHUTDOWN_EXCLUDED — containers exempt from memory shutdown
|
||||
#
|
||||
# ==============================================================================================
|
||||
# STATE FILES
|
||||
# ==============================================================================================
|
||||
#
|
||||
# SYS_WATCHDOG_STATE_FILE — strike counters and cycle state
|
||||
# SYS_WATCHDOG_REBOOT_LOG — reboot history for rate limiting
|
||||
# SYS_WATCHDOG_FAILED_FILE — containers confirmed down for skip list integration
|
||||
# SYS_WATCHDOG_OOM_FILE — OOM kill counter from previous cycle
|
||||
#
|
||||
# ==============================================================================================
|
||||
# RUNTIME MODES
|
||||
# ==============================================================================================
|
||||
#
|
||||
# stability_watchdog.sh
|
||||
# Start continuous monitoring loop. Runs until stopped or system reboots.
|
||||
#
|
||||
# stability_watchdog.sh --dry-run
|
||||
# Run detection logic without rebooting or stopping containers.
|
||||
#
|
||||
# stability_watchdog.sh --status
|
||||
# Show config, thresholds, current system state, and strike counts.
|
||||
#
|
||||
# stability_watchdog.sh --log
|
||||
# Verbose per-cycle output — show every check result and threshold comparison.
|
||||
#
|
||||
# ==============================================================================================
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
|
||||
source "$SCRIPT_DIR/../load_config.sh"
|
||||
|
||||
parse_args "$@"
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Setup — runs once at start ━━━
|
||||
# ==============================================================================================
|
||||
if [[ "$EUID" -ne 0 ]]; then
|
||||
error "Must be run as root"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
validate_unraid_cmd \
|
||||
"/usr/local/emhttp/plugins/dynamix/scripts/notify" \
|
||||
"" "" \
|
||||
"unRAID notify script" || warn "unRAID notify script not found — native notifications disabled"
|
||||
|
||||
acquire_lock
|
||||
|
||||
detect_hosts
|
||||
|
||||
TOTAL_CORES=$(nproc)
|
||||
DOCKER_TIMEOUT=10
|
||||
SYS_WATCHDOG_REBOOT_WINDOW=$(( SYS_WATCHDOG_REBOOT_WINDOW_HRS * 3600 ))
|
||||
|
||||
# Ensure state files exist
|
||||
for state_file in "$SYS_WATCHDOG_STATE_FILE" "$SYS_WATCHDOG_REBOOT_LOG" \
|
||||
"$SYS_WATCHDOG_FAILED_FILE" "$SYS_WATCHDOG_OOM_FILE"; do
|
||||
touch "$state_file" 2>/dev/null || {
|
||||
error "Cannot create state file: $state_file"
|
||||
exit 1
|
||||
}
|
||||
done
|
||||
|
||||
[[ "$DRY_RUN" == true ]] && warn "DRY RUN — no reboots or container shutdowns will occur"
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Status ━━━
|
||||
# ==============================================================================================
|
||||
if [[ "$SHOW_STATUS" == true ]]; then
|
||||
echo ""
|
||||
echo "━━━━━ $ICON_SUMMARY SYSTEM WATCHDOG STATUS ━━━━━"
|
||||
echo "$ICON_HOST Identity: $MY_ID ($LOCAL_SERVER_NAME)"
|
||||
echo ""
|
||||
echo "── Tier 1 — CRITICAL (bypass strikes immediately) ──"
|
||||
echo "$ICON_DISK rootfs critical: ${SYS_WATCHDOG_ROOTFS_CRITICAL_PCT}%"
|
||||
echo "$ICON_GEAR FD critical: ${SYS_WATCHDOG_FD_CRITICAL_PCT}%"
|
||||
echo "$ICON_GEAR /boot read-only: check=${SYS_WATCHDOG_CHECK_BOOT}"
|
||||
echo "$ICON_GEAR Kernel oops: check=${SYS_WATCHDOG_CHECK_KERNEL_OOPS}"
|
||||
echo "$ICON_CONTAINERS Docker daemon: check=${SYS_WATCHDOG_CHECK_DOCKER_DAEMON}"
|
||||
echo ""
|
||||
echo "── Tier 2 — URGENT (bypass strikes with OOM confirmation) ──"
|
||||
echo "$ICON_MEM RAM critical: < ${SYS_WATCHDOG_MEM_GB}GB"
|
||||
echo "$ICON_GEAR OOM limit: ${SYS_WATCHDOG_OOM_LIMIT} kills/cycle"
|
||||
echo ""
|
||||
echo "── Tier 3 — STANDARD (strike system) ──"
|
||||
echo "$ICON_DISK rootfs warn: ${SYS_WATCHDOG_ROOTFS_PCT}%"
|
||||
echo "$ICON_GEAR /var/log warn: ${SYS_WATCHDOG_LOG_PCT}%"
|
||||
echo "$ICON_GEAR /tmp warn: ${SYS_WATCHDOG_TMP_PCT}%"
|
||||
echo "$ICON_MEM RAM reboot: < ${SYS_WATCHDOG_MEM_GB}GB (+ strikes)"
|
||||
echo " (RAM warn/shutdown/recover managed by resource_watchdog.sh)"
|
||||
echo "$ICON_ZFS ARC pinned: ${SYS_WATCHDOG_ARC_PINNED_PCT}%"
|
||||
echo "$ICON_GEAR Load multiplier: ${SYS_WATCHDOG_LOAD_MULTIPLIER}x (= $(( TOTAL_CORES * SYS_WATCHDOG_LOAD_MULTIPLIER )) on $TOTAL_CORES cores)"
|
||||
echo "$ICON_GEAR Zombie limit: ${SYS_WATCHDOG_ZOMBIE_LIMIT}"
|
||||
echo "$ICON_GEAR CPU temp max: ${SYS_WATCHDOG_CPU_TEMP_MAX}°C"
|
||||
echo "$ICON_GEAR Strike limit: ${SYS_WATCHDOG_STRIKE_LIMIT} cycles"
|
||||
echo "$ICON_TIME Interval: ${SYSTEM_WATCHDOG_INTERVAL}s"
|
||||
echo "$ICON_REBOOT_SMART Reboot limit: ${SYS_WATCHDOG_REBOOT_LIMIT} in ${SYS_WATCHDOG_REBOOT_WINDOW_HRS}hr"
|
||||
echo ""
|
||||
echo ""
|
||||
echo "── Check Toggles ──"
|
||||
echo " rootfs=$SYS_WATCHDOG_CHECK_ROOTFS log=$SYS_WATCHDOG_CHECK_LOG ram=$SYS_WATCHDOG_CHECK_RAM"
|
||||
echo " arc=$SYS_WATCHDOG_CHECK_ARC cpu_temp=$SYS_WATCHDOG_CHECK_CPU_TEMP load=$SYS_WATCHDOG_CHECK_LOAD"
|
||||
echo " zombies=$SYS_WATCHDOG_CHECK_ZOMBIES docker=$SYS_WATCHDOG_CHECK_DOCKER_DAEMON"
|
||||
echo " containers=$SYS_WATCHDOG_CHECK_CONTAINERS oom=$SYS_WATCHDOG_CHECK_OOM"
|
||||
echo " tmp=$SYS_WATCHDOG_CHECK_TMP fd=$SYS_WATCHDOG_CHECK_FD boot=$SYS_WATCHDOG_CHECK_BOOT"
|
||||
echo " kernel_oops=$SYS_WATCHDOG_CHECK_KERNEL_OOPS sshd=$SYS_WATCHDOG_CHECK_SSHD"
|
||||
echo " network=$SYS_WATCHDOG_CHECK_NETWORK mdstat=$SYS_WATCHDOG_CHECK_MDSTAT"
|
||||
echo " runaway=$SYS_WATCHDOG_CHECK_RUNAWAY"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# ==============================================================================================
|
||||
# ── STATE HELPERS ─────────────────────────────────────────────────────────────────────────────
|
||||
# ==============================================================================================
|
||||
|
||||
get_strikes() {
|
||||
grep -E "^${1}:" "$SYS_WATCHDOG_STATE_FILE" 2>/dev/null | cut -d':' -f2
|
||||
}
|
||||
|
||||
set_strikes() {
|
||||
local key="$1" count="$2"
|
||||
grep -vE "^${key}:" "$SYS_WATCHDOG_STATE_FILE" 2>/dev/null > "${SYS_WATCHDOG_STATE_FILE}.tmp"
|
||||
echo "${key}:${count}" >> "${SYS_WATCHDOG_STATE_FILE}.tmp"
|
||||
mv "${SYS_WATCHDOG_STATE_FILE}.tmp" "$SYS_WATCHDOG_STATE_FILE"
|
||||
}
|
||||
|
||||
increment_strikes() {
|
||||
local key="$1"
|
||||
local current
|
||||
current=$(get_strikes "$key")
|
||||
[[ -z "$current" ]] && current=0
|
||||
(( current++ ))
|
||||
set_strikes "$key" "$current"
|
||||
echo "$current"
|
||||
}
|
||||
|
||||
reset_strikes() {
|
||||
set_strikes "$1" 0
|
||||
}
|
||||
|
||||
get_state_val() {
|
||||
grep -E "^${1}=" "$SYS_WATCHDOG_STATE_FILE" 2>/dev/null | cut -d'=' -f2
|
||||
}
|
||||
|
||||
set_state_val() {
|
||||
local key="$1" val="$2"
|
||||
grep -vE "^${key}=" "$SYS_WATCHDOG_STATE_FILE" 2>/dev/null > "${SYS_WATCHDOG_STATE_FILE}.tmp"
|
||||
echo "${key}=${val}" >> "${SYS_WATCHDOG_STATE_FILE}.tmp"
|
||||
mv "${SYS_WATCHDOG_STATE_FILE}.tmp" "$SYS_WATCHDOG_STATE_FILE"
|
||||
}
|
||||
|
||||
purge_old_reboots() {
|
||||
local now cutoff
|
||||
now=$(date +%s)
|
||||
cutoff=$(( now - SYS_WATCHDOG_REBOOT_WINDOW ))
|
||||
grep -v "^$" "$SYS_WATCHDOG_REBOOT_LOG" 2>/dev/null | while IFS= read -r ts; do
|
||||
[[ "$ts" -gt "$cutoff" ]] && echo "$ts"
|
||||
done > "${SYS_WATCHDOG_REBOOT_LOG}.tmp"
|
||||
mv "${SYS_WATCHDOG_REBOOT_LOG}.tmp" "$SYS_WATCHDOG_REBOOT_LOG"
|
||||
}
|
||||
|
||||
count_recent_reboots() {
|
||||
purge_old_reboots
|
||||
grep -c "." "$SYS_WATCHDOG_REBOOT_LOG" 2>/dev/null || echo 0
|
||||
}
|
||||
|
||||
log_reboot() {
|
||||
date +%s >> "$SYS_WATCHDOG_REBOOT_LOG"
|
||||
}
|
||||
|
||||
# ==============================================================================================
|
||||
# ── OOM TRACKING ──────────────────────────────────────────────────────────────────────────────
|
||||
# ==============================================================================================
|
||||
# Reads /proc/vmstat oom_kill counter — delta per cycle = rate of OOM kills
|
||||
# Used for Tier 2 bypass and diagnostic context in reboot messages
|
||||
|
||||
get_oom_delta() {
|
||||
local current_oom
|
||||
current_oom=$(grep "^oom_kill " /proc/vmstat 2>/dev/null | awk '{print $2}')
|
||||
[[ -z "$current_oom" ]] && echo 0 && return
|
||||
|
||||
local prev_oom
|
||||
prev_oom=$(cat "$SYS_WATCHDOG_OOM_FILE" 2>/dev/null || echo 0)
|
||||
echo "$current_oom" > "$SYS_WATCHDOG_OOM_FILE"
|
||||
|
||||
local delta=$(( current_oom - prev_oom ))
|
||||
[[ "$delta" -lt 0 ]] && delta=0 # counter reset on reboot
|
||||
echo "$delta"
|
||||
}
|
||||
|
||||
get_oom_victims() {
|
||||
# Get process names from dmesg that were OOM killed this boot
|
||||
dmesg -T 2>/dev/null | grep -i "Killed process" | \
|
||||
awk '{print $NF}' | sort | uniq -c | sort -rn | head -5 | \
|
||||
awk '{printf "%s×%d ", $2, $1}' | sed 's/ $//'
|
||||
}
|
||||
|
||||
# ==============================================================================================
|
||||
# ── ABORT CONDITIONS ──────────────────────────────────────────────────────────────────────────
|
||||
# ==============================================================================================
|
||||
# Returns 1 if reboot should be aborted, 0 if reboot should proceed
|
||||
# CRITICAL tier bypasses this function entirely
|
||||
|
||||
check_abort_conditions() {
|
||||
local should_abort=false
|
||||
|
||||
if command -v zpool >/dev/null 2>&1; then
|
||||
local unhealthy
|
||||
unhealthy=$(zpool list -H -o health 2>/dev/null | grep -v ONLINE || true)
|
||||
if [[ -n "$unhealthy" ]]; then
|
||||
if [[ "$SYS_WATCHDOG_ABORT_ON_ZFS_UNHEALTHY" == true ]]; then
|
||||
error "ZFS pool unhealthy — aborting reboot to prevent data loss"
|
||||
notify "System watchdog aborted reboot on $(hostname) ($MY_ID) — ZFS pool unhealthy" \
|
||||
"System Watchdog" "warning"
|
||||
should_abort=true
|
||||
else
|
||||
warn "ZFS pool unhealthy — continuing reboot (ABORT_ON_ZFS_UNHEALTHY=false)"
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
if grep -q "progress" /var/local/emhttp/parity-date.txt 2>/dev/null; then
|
||||
if [[ "$SYS_WATCHDOG_ABORT_ON_PARITY" == true ]]; then
|
||||
error "Parity check running — aborting reboot"
|
||||
notify "System watchdog aborted reboot on $(hostname) ($MY_ID) — parity running" \
|
||||
"System Watchdog" "warning"
|
||||
should_abort=true
|
||||
else
|
||||
warn "Parity check running — continuing reboot (ABORT_ON_PARITY=false)"
|
||||
fi
|
||||
fi
|
||||
|
||||
if pgrep -f "mover" >/dev/null 2>&1; then
|
||||
if [[ "$SYS_WATCHDOG_ABORT_ON_MOVER" == true ]]; then
|
||||
error "Mover running — aborting reboot"
|
||||
notify "System watchdog aborted reboot on $(hostname) ($MY_ID) — mover running" \
|
||||
"System Watchdog" "warning"
|
||||
should_abort=true
|
||||
else
|
||||
warn "Mover running — continuing reboot (ABORT_ON_MOVER=false)"
|
||||
fi
|
||||
fi
|
||||
|
||||
[[ "$should_abort" == true ]] && return 1
|
||||
return 0
|
||||
}
|
||||
|
||||
# ==============================================================================================
|
||||
# ── STANDARD STRIKE CHECK ─────────────────────────────────────────────────────────────────────
|
||||
# ==============================================================================================
|
||||
# Returns 0 = reboot now | 1 = not yet
|
||||
|
||||
run_strike_check() {
|
||||
local key="$1" triggered="$2" description="$3"
|
||||
if [[ "$triggered" == true ]]; then
|
||||
local strikes
|
||||
strikes=$(increment_strikes "$key")
|
||||
warn "$description — strike $strikes/$SYS_WATCHDOG_STRIKE_LIMIT"
|
||||
if (( strikes >= SYS_WATCHDOG_STRIKE_LIMIT )); then
|
||||
error "$description — strike limit hit, reboot triggered"
|
||||
reset_strikes "$key"
|
||||
return 0
|
||||
fi
|
||||
else
|
||||
local current
|
||||
current=$(get_strikes "$key")
|
||||
[[ -n "$current" && "$current" -gt 0 ]] && reset_strikes "$key"
|
||||
fi
|
||||
return 1
|
||||
}
|
||||
|
||||
# ── Exit Trap — restart containers stopped before an aborted reboot ───────────────────────────
|
||||
_SYS_REBOOT_STOPPED=()
|
||||
_trap_sys_reboot_restart() {
|
||||
[[ ${#_SYS_REBOOT_STOPPED[@]} -eq 0 ]] && return
|
||||
warn "Exit trap: restarting containers stopped before aborted reboot"
|
||||
for c in "${_SYS_REBOOT_STOPPED[@]}"; do
|
||||
[[ -z "$c" ]] && continue
|
||||
docker inspect "$c" >/dev/null 2>&1 && docker start "$c" >/dev/null 2>&1 || true
|
||||
done
|
||||
}
|
||||
|
||||
# ==============================================================================================
|
||||
# ── DO REBOOT ─────────────────────────────────────────────────────────────────────────────────
|
||||
# ==============================================================================================
|
||||
# tier: "critical" (bypass abort) | "urgent" | "standard"
|
||||
|
||||
do_reboot() {
|
||||
local tier="${1:-standard}"
|
||||
shift
|
||||
local triggers=("$@")
|
||||
|
||||
# Get OOM context for reboot message
|
||||
local oom_victims=""
|
||||
if [[ "$SYS_WATCHDOG_CHECK_OOM" == true ]]; then
|
||||
oom_victims=$(get_oom_victims)
|
||||
[[ -n "$oom_victims" ]] && triggers+=("oom_victims: $oom_victims")
|
||||
fi
|
||||
|
||||
# Abort check — CRITICAL bypasses this
|
||||
if [[ "$tier" != "critical" ]]; then
|
||||
if ! check_abort_conditions; then
|
||||
return
|
||||
fi
|
||||
else
|
||||
warn "CRITICAL tier — bypassing abort conditions"
|
||||
fi
|
||||
|
||||
RECENT_REBOOTS=$(count_recent_reboots)
|
||||
log "Recent reboots in ${SYS_WATCHDOG_REBOOT_WINDOW_HRS}hr window: $RECENT_REBOOTS / $SYS_WATCHDOG_REBOOT_LIMIT"
|
||||
|
||||
if [[ "$RECENT_REBOOTS" -ge "$SYS_WATCHDOG_REBOOT_LIMIT" ]]; then
|
||||
error "Reboot loop detected — shutting down instead of rebooting"
|
||||
notify "Reboot loop on $(hostname) ($MY_ID) — shutting down after $RECENT_REBOOTS reboots — ${triggers[*]}" \
|
||||
"System Watchdog" "warning"
|
||||
if [[ "$DRY_RUN" == true ]]; then
|
||||
warn "DRY RUN — would shutdown now"
|
||||
return
|
||||
fi
|
||||
sync
|
||||
/sbin/poweroff
|
||||
return
|
||||
fi
|
||||
|
||||
echo ""
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo " $ICON_REBOOT_SMART SYSTEM WATCHDOG — REBOOT TRIGGERED"
|
||||
echo " Tier: ${tier^^}"
|
||||
echo " Host: $MY_ID ($LOCAL_SERVER_NAME)"
|
||||
for t in "${triggers[@]}"; do
|
||||
echo " → $t"
|
||||
done
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
notify "System watchdog ${tier^^} reboot on $(hostname) ($MY_ID) — ${triggers[*]}" \
|
||||
"System Watchdog" "warning"
|
||||
|
||||
if [[ "$DRY_RUN" == true ]]; then
|
||||
warn "DRY RUN — reboot sequence would begin now"
|
||||
return
|
||||
fi
|
||||
|
||||
log_reboot
|
||||
|
||||
# Graceful shutdown sequence
|
||||
warn "Shutting down VMs..."
|
||||
if command -v virsh >/dev/null 2>&1; then
|
||||
for VM in $(virsh list --name 2>/dev/null); do
|
||||
[[ -z "$VM" ]] && continue
|
||||
virsh shutdown "$VM" >/dev/null 2>&1
|
||||
done
|
||||
sleep 30
|
||||
fi
|
||||
|
||||
warn "Stopping Docker containers..."
|
||||
if command -v docker >/dev/null 2>&1; then
|
||||
mapfile -t _SYS_REBOOT_STOPPED < <(docker ps --format '{{.Names}}' 2>/dev/null)
|
||||
trap _trap_sys_reboot_restart EXIT
|
||||
timeout 60 docker ps -q 2>/dev/null | xargs -r docker stop >/dev/null 2>&1
|
||||
fi
|
||||
|
||||
warn "Stopping User Scripts..."
|
||||
pkill -f "/tmp/user.scripts" 2>/dev/null || true
|
||||
|
||||
warn "Syncing disks..."
|
||||
sync
|
||||
|
||||
trap - EXIT # committed to reboot — containers should stay down
|
||||
sleep 5
|
||||
/sbin/reboot
|
||||
}
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Single-Pass Health Check ━━━
|
||||
# ==============================================================================================
|
||||
warn "System watchdog — $MY_ID — $(date '+%H:%M:%S')"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
TRIGGERS=()
|
||||
CRITICAL_TRIGGERS=()
|
||||
URGENT_OOM_CONFIRMED=false
|
||||
|
||||
# ── OOM Delta — read every cycle for bypass decisions ─────────────────────────────────────
|
||||
OOM_DELTA=0
|
||||
if [[ "$SYS_WATCHDOG_CHECK_OOM" == true ]]; then
|
||||
OOM_DELTA=$(get_oom_delta)
|
||||
[[ "$OOM_DELTA" -gt 0 ]] && \
|
||||
log "OOM kills this cycle: $OOM_DELTA (limit: ${SYS_WATCHDOG_OOM_LIMIT})"
|
||||
fi
|
||||
|
||||
# ==========================================================================================
|
||||
# ━━━ TIER 1 — CRITICAL CHECKS (bypass all strikes, reboot immediately) ━━━
|
||||
# ==========================================================================================
|
||||
|
||||
# ── Docker daemon — critical: nothing can heal without it ─────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_DOCKER_DAEMON" == true ]]; then
|
||||
if ! timeout "$DOCKER_TIMEOUT" docker info >/dev/null 2>&1; then
|
||||
error "Docker daemon unresponsive — CRITICAL"
|
||||
|
||||
# Attempt daemon restart before rebooting
|
||||
warn "Attempting Docker daemon restart..."
|
||||
if [[ "$DRY_RUN" == false ]]; then
|
||||
/etc/rc.d/rc.docker restart >/dev/null 2>&1
|
||||
sleep 15
|
||||
if timeout "$DOCKER_TIMEOUT" docker info >/dev/null 2>&1; then
|
||||
warn "Docker daemon restarted successfully — continuing monitoring"
|
||||
else
|
||||
error "Docker daemon restart failed — adding to CRITICAL triggers"
|
||||
CRITICAL_TRIGGERS+=("docker_daemon_unresponsive")
|
||||
fi
|
||||
else
|
||||
warn "DRY RUN — would attempt Docker daemon restart"
|
||||
CRITICAL_TRIGGERS+=("docker_daemon_unresponsive")
|
||||
fi
|
||||
else
|
||||
log "Docker daemon healthy ✅"
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── rootfs critical — at 99%+ writes are failing ─────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_ROOTFS" == true ]]; then
|
||||
ROOTFS_USED=$(df / --output=pcent 2>/dev/null | tail -1 | tr -d ' %')
|
||||
if [[ "$ROOTFS_USED" -ge "${SYS_WATCHDOG_ROOTFS_CRITICAL_PCT:-99}" ]]; then
|
||||
error "rootfs ${ROOTFS_USED}% — CRITICAL (writes failing)"
|
||||
CRITICAL_TRIGGERS+=("rootfs_full=${ROOTFS_USED}%")
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── Kernel oops/BUG — kernel running with corrupted state ────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_KERNEL_OOPS" == true ]]; then
|
||||
PREV_OOPS=$(get_state_val "kernel_oops_count")
|
||||
CURRENT_OOPS=$(dmesg 2>/dev/null | grep -cE "BUG:|kernel BUG|Oops:" || echo 0)
|
||||
CURRENT_OOPS="${CURRENT_OOPS//[^0-9]/}"; CURRENT_OOPS="${CURRENT_OOPS:-0}"
|
||||
set_state_val "kernel_oops_count" "$CURRENT_OOPS"
|
||||
|
||||
if [[ -n "$PREV_OOPS" && "$PREV_OOPS" =~ ^[0-9]+$ ]]; then
|
||||
OOPS_DELTA=$(( CURRENT_OOPS - PREV_OOPS ))
|
||||
if [[ "$OOPS_DELTA" -gt 0 ]]; then
|
||||
error "Kernel oops/BUG detected — $OOPS_DELTA new since last cycle — CRITICAL"
|
||||
CRITICAL_TRIGGERS+=("kernel_oops=${OOPS_DELTA}_new")
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── File descriptor exhaustion — new connections failing silently ─────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_FD" == true ]]; then
|
||||
FD_LINE=$(cat /proc/sys/fs/file-nr 2>/dev/null)
|
||||
FD_OPEN=$(echo "$FD_LINE" | awk '{print $1}')
|
||||
FD_MAX=$(echo "$FD_LINE" | awk '{print $3}')
|
||||
if [[ -n "$FD_OPEN" && -n "$FD_MAX" && "$FD_MAX" -gt 0 ]]; then
|
||||
FD_PCT=$(( FD_OPEN * 100 / FD_MAX ))
|
||||
if [[ "$FD_PCT" -ge "${SYS_WATCHDOG_FD_CRITICAL_PCT:-95}" ]]; then
|
||||
error "File descriptors ${FD_PCT}% exhausted (${FD_OPEN}/${FD_MAX}) — CRITICAL"
|
||||
CRITICAL_TRIGGERS+=("fd_exhaustion=${FD_PCT}%")
|
||||
else
|
||||
log "File descriptors: ${FD_PCT}% (${FD_OPEN}/${FD_MAX})"
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── /boot read-only — state and config writes failing silently ────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_BOOT" == true ]]; then
|
||||
BOOT_TEST="/boot/.watchdog_write_test"
|
||||
if ! touch "$BOOT_TEST" 2>/dev/null; then
|
||||
error "/boot is read-only — config writes failing silently — CRITICAL"
|
||||
CRITICAL_TRIGGERS+=("boot_read_only")
|
||||
else
|
||||
rm -f "$BOOT_TEST" 2>/dev/null
|
||||
log "/boot is writable ✅"
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── Act on CRITICAL triggers immediately ─────────────────────────────────────────────────
|
||||
if [[ ${#CRITICAL_TRIGGERS[@]} -gt 0 ]]; then
|
||||
echo ""
|
||||
echo "━━━ $ICON_ERROR CRITICAL — IMMEDIATE REBOOT ━━━"
|
||||
for t in "${CRITICAL_TRIGGERS[@]}"; do
|
||||
error " CRITICAL: $t"
|
||||
done
|
||||
do_reboot "critical" "${CRITICAL_TRIGGERS[@]}"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# ==========================================================================================
|
||||
# ━━━ TIER 3 — STANDARD CHECKS (strike system) ━━━
|
||||
# ==========================================================================================
|
||||
|
||||
# ── rootfs standard ──────────────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_ROOTFS" == true ]]; then
|
||||
ROOTFS_USED=$(df / --output=pcent 2>/dev/null | tail -1 | tr -d ' %')
|
||||
TRIGGERED=false
|
||||
[[ "$ROOTFS_USED" -ge "$SYS_WATCHDOG_ROOTFS_PCT" ]] && TRIGGERED=true
|
||||
run_strike_check "rootfs" "$TRIGGERED" "rootfs ${ROOTFS_USED}%" && \
|
||||
TRIGGERS+=("rootfs=${ROOTFS_USED}%")
|
||||
fi
|
||||
|
||||
# ── /var/log ─────────────────────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_LOG" == true ]]; then
|
||||
LOG_USED=$(df -P /var/log 2>/dev/null | awk 'NR==2 {print $5}' | tr -d '%')
|
||||
TRIGGERED=false
|
||||
[[ "${LOG_USED:-0}" -ge "$SYS_WATCHDOG_LOG_PCT" ]] && TRIGGERED=true
|
||||
run_strike_check "log" "$TRIGGERED" "/var/log ${LOG_USED}%" && \
|
||||
TRIGGERS+=("log=${LOG_USED}%")
|
||||
fi
|
||||
|
||||
# ── /tmp ─────────────────────────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_TMP" == true ]]; then
|
||||
TMP_USED=$(df -P /tmp 2>/dev/null | awk 'NR==2 {print $5}' | tr -d '%')
|
||||
if [[ "${TMP_USED:-0}" -ge "${SYS_WATCHDOG_TMP_CRITICAL_PCT:-98}" ]]; then
|
||||
# Try to clear before escalating
|
||||
warn "/tmp ${TMP_USED}% — attempting cleanup..."
|
||||
find /tmp -type f -mmin +60 -not -name "*.lock" -delete 2>/dev/null
|
||||
TMP_USED_AFTER=$(df -P /tmp 2>/dev/null | awk 'NR==2 {print $5}' | tr -d '%')
|
||||
if [[ "${TMP_USED_AFTER:-0}" -ge "${SYS_WATCHDOG_TMP_CRITICAL_PCT:-98}" ]]; then
|
||||
error "/tmp still ${TMP_USED_AFTER}% after cleanup — adding to triggers"
|
||||
TRIGGERED=true
|
||||
else
|
||||
warn "/tmp cleared to ${TMP_USED_AFTER}% ✅"
|
||||
TRIGGERED=false
|
||||
fi
|
||||
elif [[ "${TMP_USED:-0}" -ge "${SYS_WATCHDOG_TMP_PCT:-90}" ]]; then
|
||||
TRIGGERED=true
|
||||
else
|
||||
TRIGGERED=false
|
||||
fi
|
||||
run_strike_check "tmp" "$TRIGGERED" "/tmp ${TMP_USED}%" && \
|
||||
TRIGGERS+=("tmp=${TMP_USED}%")
|
||||
fi
|
||||
|
||||
# ── RAM — reboot tier only (warn/shutdown/recover handled by resource_watchdog.sh) ──────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_RAM" == true ]]; then
|
||||
MEM_KB=$(awk '/MemAvailable/ {print $2}' /proc/meminfo)
|
||||
MEM_GB=$(( MEM_KB / 1024 / 1024 ))
|
||||
|
||||
if [[ "$MEM_GB" -lt "$SYS_WATCHDOG_MEM_GB" ]]; then
|
||||
# Tier 2 — bypass strike system if OOM confirms active crisis
|
||||
if [[ "$SYS_WATCHDOG_CHECK_OOM" == true ]] && \
|
||||
[[ "$OOM_DELTA" -ge "$SYS_WATCHDOG_OOM_LIMIT" ]]; then
|
||||
error "RAM ${MEM_GB}GB + ${OOM_DELTA} OOM kills this run — URGENT bypass"
|
||||
OOM_VICTIMS=$(get_oom_victims)
|
||||
URGENT_TRIGGERS=("urgent_low_ram=${MEM_GB}GB" "oom_kills=${OOM_DELTA}")
|
||||
[[ -n "$OOM_VICTIMS" ]] && URGENT_TRIGGERS+=("oom_victims: $OOM_VICTIMS")
|
||||
do_reboot "urgent" "${URGENT_TRIGGERS[@]}"
|
||||
exit 0
|
||||
fi
|
||||
# Standard strike path
|
||||
run_strike_check "ram" true "RAM ${MEM_GB}GB free" && \
|
||||
TRIGGERS+=("low_ram=${MEM_GB}GB")
|
||||
else
|
||||
reset_strikes "ram"
|
||||
log "RAM ${MEM_GB}GB free ✅"
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── ZFS ARC ──────────────────────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_ARC" == true ]] && [[ -f /proc/spl/kstat/zfs/arcstats ]]; then
|
||||
ARC_SIZE=$(awk '/^size / {print $3}' /proc/spl/kstat/zfs/arcstats)
|
||||
ARC_MAX=$(awk '/^c_max / {print $3}' /proc/spl/kstat/zfs/arcstats)
|
||||
ARC_PCT=$(( ARC_SIZE * 100 / ARC_MAX ))
|
||||
TRIGGERED=false
|
||||
if [[ "$ARC_PCT" -ge "$SYS_WATCHDOG_ARC_PINNED_PCT" ]]; then
|
||||
sync; echo 3 > /proc/sys/vm/drop_caches; sleep 5
|
||||
ARC_AFTER=$(awk '/^size / {print $3}' /proc/spl/kstat/zfs/arcstats)
|
||||
ARC_AFTER_PCT=$(( ARC_AFTER * 100 / ARC_MAX ))
|
||||
[[ "$ARC_AFTER_PCT" -ge "$SYS_WATCHDOG_ARC_RELEASE_PCT" ]] && TRIGGERED=true
|
||||
fi
|
||||
run_strike_check "arc" "$TRIGGERED" "ZFS ARC pinned ${ARC_PCT}%" && \
|
||||
TRIGGERS+=("arc_pinned=${ARC_PCT}%")
|
||||
fi
|
||||
|
||||
# ── CPU temperature ───────────────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_CPU_TEMP" == true ]]; then
|
||||
CPU_TEMP=""
|
||||
if command -v sensors >/dev/null 2>&1; then
|
||||
CPU_TEMP=$(sensors 2>/dev/null | \
|
||||
grep -i "Package id 0\|Tctl\|CPU Temp" | \
|
||||
awk '{print $NF}' | tr -d '+°C' | head -1)
|
||||
fi
|
||||
if [[ -n "$CPU_TEMP" ]]; then
|
||||
CPU_TEMP_INT=$(printf "%.0f" "$CPU_TEMP")
|
||||
TRIGGERED=false
|
||||
[[ "$CPU_TEMP_INT" -ge "$SYS_WATCHDOG_CPU_TEMP_MAX" ]] && TRIGGERED=true
|
||||
run_strike_check "cpu_temp" "$TRIGGERED" "CPU temp ${CPU_TEMP_INT}°C" && \
|
||||
TRIGGERS+=("cpu_temp=${CPU_TEMP_INT}C")
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── Load average ─────────────────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_LOAD" == true ]]; then
|
||||
LOAD=$(awk '{print $1}' /proc/loadavg)
|
||||
LOAD_INT=$(printf "%.0f" "$LOAD")
|
||||
LOAD_THRESHOLD=$(( TOTAL_CORES * SYS_WATCHDOG_LOAD_MULTIPLIER ))
|
||||
TRIGGERED=false
|
||||
[[ "$LOAD_INT" -ge "$LOAD_THRESHOLD" ]] && TRIGGERED=true
|
||||
run_strike_check "load" "$TRIGGERED" "load avg ${LOAD}" && \
|
||||
TRIGGERS+=("load=${LOAD}")
|
||||
fi
|
||||
|
||||
# ── Zombie processes ─────────────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_ZOMBIES" == true ]]; then
|
||||
ZOMBIE_COUNT=$(ps aux 2>/dev/null | awk '{print $8}' | grep -c "^Z$" || echo 0)
|
||||
ZOMBIE_COUNT="${ZOMBIE_COUNT//[^0-9]/}"; ZOMBIE_COUNT="${ZOMBIE_COUNT:-0}"
|
||||
TRIGGERED=false
|
||||
[[ "$ZOMBIE_COUNT" -ge "$SYS_WATCHDOG_ZOMBIE_LIMIT" ]] && TRIGGERED=true
|
||||
run_strike_check "zombies" "$TRIGGERED" "zombies ${ZOMBIE_COUNT}" && \
|
||||
TRIGGERS+=("zombies=${ZOMBIE_COUNT}")
|
||||
fi
|
||||
|
||||
# ── Array disk errors — accumulating mdstat errors ────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_MDSTAT" == true ]]; then
|
||||
PREV_MD_ERRORS=$(get_state_val "mdstat_errors")
|
||||
CURRENT_MD_ERRORS=$(grep -oP "(?<=\[)[^\]]*[U_][^\]]*(?=\])" \
|
||||
/proc/mdstat 2>/dev/null | grep -o "_" | wc -l || echo 0)
|
||||
CURRENT_MD_ERRORS="${CURRENT_MD_ERRORS//[^0-9]/}"; CURRENT_MD_ERRORS="${CURRENT_MD_ERRORS:-0}"
|
||||
set_state_val "mdstat_errors" "$CURRENT_MD_ERRORS"
|
||||
|
||||
if [[ -n "$PREV_MD_ERRORS" && "$PREV_MD_ERRORS" =~ ^[0-9]+$ ]]; then
|
||||
MD_DELTA=$(( CURRENT_MD_ERRORS - PREV_MD_ERRORS ))
|
||||
if [[ "$MD_DELTA" -ge "${SYS_WATCHDOG_MDSTAT_ERROR_LIMIT:-5}" ]]; then
|
||||
TRIGGERED=true
|
||||
run_strike_check "mdstat" "$TRIGGERED" \
|
||||
"mdstat errors +${MD_DELTA} (total: ${CURRENT_MD_ERRORS})" && \
|
||||
TRIGGERS+=("mdstat_errors=+${MD_DELTA}")
|
||||
else
|
||||
run_strike_check "mdstat" false "mdstat" > /dev/null
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── Network interface state ───────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_NETWORK" == true ]]; then
|
||||
NIC="${SYS_WATCHDOG_NIC:-eth0}"
|
||||
NIC_STATE=$(cat "/sys/class/net/${NIC}/operstate" 2>/dev/null || echo "unknown")
|
||||
TRIGGERED=false
|
||||
[[ "$NIC_STATE" != "up" ]] && TRIGGERED=true
|
||||
run_strike_check "network" "$TRIGGERED" "${NIC} state: ${NIC_STATE}" && \
|
||||
TRIGGERS+=("nic_down=${NIC}")
|
||||
fi
|
||||
|
||||
# ── sshd — try restart before escalating ─────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_SSHD" == true ]]; then
|
||||
if ! pgrep -x sshd >/dev/null 2>&1; then
|
||||
warn "sshd not running — attempting restart..."
|
||||
if [[ "$DRY_RUN" == false ]]; then
|
||||
/etc/rc.d/rc.sshd start >/dev/null 2>&1
|
||||
sleep 3
|
||||
if pgrep -x sshd >/dev/null 2>&1; then
|
||||
warn "sshd restarted successfully ✅"
|
||||
reset_strikes "sshd"
|
||||
notify "sshd was down on $(hostname) ($MY_ID) — restarted automatically" \
|
||||
"System Watchdog" "warning"
|
||||
else
|
||||
error "sshd restart failed — remote access unavailable"
|
||||
run_strike_check "sshd" true "sshd not running" && \
|
||||
TRIGGERS+=("sshd_down")
|
||||
fi
|
||||
else
|
||||
warn "DRY RUN — would restart sshd"
|
||||
fi
|
||||
else
|
||||
reset_strikes "sshd"
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── Runaway process ───────────────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_RUNAWAY" == true ]]; then
|
||||
RUNAWAY_PCT="${SYS_WATCHDOG_RUNAWAY_CPU_PCT:-90}"
|
||||
TOP_CPU_PCT=$(ps aux 2>/dev/null | awk 'NR>1{print $3}' | sort -rn | head -1)
|
||||
TOP_CPU_INT=$(printf "%.0f" "${TOP_CPU_PCT:-0}")
|
||||
TOP_CPU_NAME=$(ps aux 2>/dev/null | sort -k3 -rn | awk 'NR==2{print $11}')
|
||||
TRIGGERED=false
|
||||
[[ "$TOP_CPU_INT" -ge "$RUNAWAY_PCT" ]] && TRIGGERED=true
|
||||
# Runaway uses SYS_WATCHDOG_RUNAWAY_STRIKES not global strike limit
|
||||
if [[ "$TRIGGERED" == true ]]; then
|
||||
RAWAY_S=$(increment_strikes "runaway")
|
||||
RLIMIT="${SYS_WATCHDOG_RUNAWAY_STRIKES:-3}"
|
||||
warn "Runaway ${TOP_CPU_NAME} ${TOP_CPU_PCT}% CPU -- strike $RAWAY_S/$RLIMIT"
|
||||
if (( RAWAY_S >= RLIMIT )); then
|
||||
error "Runaway process ${TOP_CPU_NAME} -- strike limit hit"
|
||||
reset_strikes "runaway"
|
||||
TRIGGERS+=("runaway=${TOP_CPU_NAME}@${TOP_CPU_PCT}%")
|
||||
fi
|
||||
else
|
||||
RAWAY_CUR=$(get_strikes "runaway")
|
||||
[[ "${RAWAY_CUR:-0}" -gt 0 ]] && reset_strikes "runaway"
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── Required containers from docker_watchdog skip list ────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_CONTAINERS" == true ]] && [[ -s "$SYS_WATCHDOG_FAILED_FILE" ]]; then
|
||||
FAILED_CONTAINERS=()
|
||||
while IFS= read -r container; do
|
||||
[[ -z "$container" ]] && continue
|
||||
STATUS=$(timeout "$DOCKER_TIMEOUT" docker inspect -f \
|
||||
'{{.State.Running}}' "$container" 2>/dev/null || echo "unknown")
|
||||
[[ "$STATUS" != "true" ]] && FAILED_CONTAINERS+=("$container")
|
||||
done < "$SYS_WATCHDOG_FAILED_FILE"
|
||||
|
||||
TRIGGERED=false
|
||||
[[ ${#FAILED_CONTAINERS[@]} -gt 0 ]] && TRIGGERED=true
|
||||
run_strike_check "failed_containers" "$TRIGGERED" \
|
||||
"required containers stopped: ${FAILED_CONTAINERS[*]:-}" && \
|
||||
TRIGGERS+=("containers=${FAILED_CONTAINERS[*]:-}")
|
||||
fi
|
||||
|
||||
# ==========================================================================================
|
||||
# ━━━ Evaluate Standard Triggers ━━━
|
||||
# ==========================================================================================
|
||||
if [[ ${#TRIGGERS[@]} -gt 0 ]]; then
|
||||
echo ""
|
||||
echo "━━━ $ICON_REBOOT_SMART System Watchdog — $(date '+%Y-%m-%d %H:%M:%S') ━━━"
|
||||
for t in "${TRIGGERS[@]}"; do
|
||||
echo " $ICON_REBOOT_SMART $t"
|
||||
done
|
||||
[[ "$OOM_DELTA" -gt 0 ]] && echo " OOM kills this run: $OOM_DELTA"
|
||||
echo ""
|
||||
do_reboot "standard" "${TRIGGERS[@]}"
|
||||
exit 0
|
||||
else
|
||||
echo "System healthy ✅ ($(date '+%H:%M:%S'))"
|
||||
fi
|
||||
|
||||
# Keep state file mtime fresh — docker_watchdog stale guard checks this
|
||||
set_state_val "watchdog_cycle" "$(date +%s)"
|
||||
+78
-746
@@ -2,117 +2,43 @@
|
||||
# ==============================================================================================
|
||||
# ================================= System Watchdog ============================================
|
||||
# ==============================================================================================
|
||||
# Thin orchestrator — runs SYSTEM_WATCHDOG_SCRIPTS from master.conf sequentially.
|
||||
# Called by watchdog_orchestrator.sh each cycle. Covers system component health:
|
||||
# storage pool growth, runaway logs, and WebGUI availability.
|
||||
#
|
||||
# PURPOSE
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
# Last line of defense — reboots the system cleanly if it is about to become
|
||||
# unstable. Runs continuously as a background process started by
|
||||
# array_started.sh at array start. Works alongside docker_watchdog.sh which
|
||||
# handles container-level healing first. Only escalates to reboot when
|
||||
# docker_watchdog.sh cannot resolve the condition.
|
||||
# ── EXECUTION ORDER ───────────────────────────────────────────────────────────────────────────
|
||||
# Driven by SYSTEM_WATCHDOG_SCRIPTS in master.conf — add, remove, or reorder there.
|
||||
# Default: storage_watchdog → webgui_watchdog
|
||||
#
|
||||
# ==============================================================================================
|
||||
# OPERATIONAL MODEL
|
||||
# ==============================================================================================
|
||||
# ── SEQUENTIAL EXECUTION ─────────────────────────────────────────────────────────────────────
|
||||
# All scripts run in the foreground. Each must complete before the next starts.
|
||||
# A failed script is logged but does not prevent remaining scripts from running.
|
||||
#
|
||||
# Three-Tier Response System
|
||||
# ── SAFEGUARDS ────────────────────────────────────────────────────────────────────────────────
|
||||
# Root check — child scripts require root
|
||||
# acquire_lock — prevents concurrent system watchdog runs
|
||||
# detect_hosts() — MY_ID in notifications and logs
|
||||
# Non-fatal steps — a failed step is logged; remaining steps still run
|
||||
#
|
||||
# Tier 1 — CRITICAL (bypass all strikes, reboot immediately)
|
||||
# Docker daemon unresponsive — nothing can be healed; running it longer makes it worse
|
||||
# rootfs at 99%+ — writes failing; SSH may stop; no recovery options
|
||||
# Kernel oops/BUG in dmesg — kernel running with corrupted state
|
||||
# File descriptor exhaustion — new connections and processes failing silently
|
||||
# /boot read-only unexpectedly — state files and config writes silently failing
|
||||
#
|
||||
# Tier 2 — URGENT (bypass strikes when OOM confirms active crisis)
|
||||
# RAM < MEM_GB AND OOM kills >= OOM_LIMIT in this cycle.
|
||||
# OOM kills at this rate means the system is dying faster than watchdogs can heal.
|
||||
# Without OOM confirmation → standard strike system applies.
|
||||
#
|
||||
# Tier 3 — STANDARD (N consecutive failures → reboot)
|
||||
# RAM tiers, load, CPU temp, zombies, /var/log, /tmp, containers, NIC, mdstat.
|
||||
#
|
||||
# RAM Tiers
|
||||
# MEM_WARN_GB (10GB) — warn + notify only
|
||||
# MEM_SHUTDOWN_GB (6GB) — stop non-essential containers, wait for recovery
|
||||
# MEM_GB (4GB) — strike system → reboot (bypass with OOM confirmation)
|
||||
# MEM_RECOVER_GB (30GB) — RAM must reach this before stopped containers restart
|
||||
#
|
||||
# Container Shutdown Logic (at MEM_SHUTDOWN_GB)
|
||||
# Stops all containers not in SYS_WATCHDOG_MEM_SHUTDOWN_EXCLUDED.
|
||||
# Stopped containers tracked in shutdown list — won't restart until RAM recovers.
|
||||
# Strike system prevents flip-flopping — shutdown only once per degradation event.
|
||||
#
|
||||
# Abort Conditions (prevent reboot during sensitive operations)
|
||||
# ZFS pool unhealthy, parity running, mover running — each toggleable.
|
||||
# CRITICAL tier bypasses all abort conditions — imminent crash overrides data safety.
|
||||
#
|
||||
# Checks Run Every Cycle
|
||||
# rootfs usage, /var/log, /tmp, free RAM, ZFS ARC, CPU temp, load avg,
|
||||
# zombie processes, Docker daemon, OOM rate, /boot read-only, kernel oops,
|
||||
# file descriptor exhaustion, array disk errors, NIC state, required containers.
|
||||
#
|
||||
# ==============================================================================================
|
||||
# OPERATIONAL SAFEGUARDS
|
||||
# ==============================================================================================
|
||||
#
|
||||
# Root Required
|
||||
# Reboot and container stop require root.
|
||||
#
|
||||
# Single Instance Lock
|
||||
# acquire_lock prevents a second watchdog instance from starting.
|
||||
#
|
||||
# State File Verification
|
||||
# All state files verified writable at startup — errors if any cannot be created.
|
||||
#
|
||||
# ==============================================================================================
|
||||
# CONFIGURATION
|
||||
# ==============================================================================================
|
||||
#
|
||||
# master.conf — System Watchdog section
|
||||
# Full variable listing in master.conf. Key variables:
|
||||
#
|
||||
# SYS_WATCHDOG_REBOOT_WINDOW_HRS — reboot rate limit window (default: 2)
|
||||
# SYS_WATCHDOG_MAX_REBOOTS — max reboots in window before giving up (default: 3)
|
||||
# SYS_WATCHDOG_STRIKES — consecutive failures before reboot (default: 3)
|
||||
# SYS_WATCHDOG_OOM_LIMIT — OOM kills/cycle to trigger URGENT bypass (default: 3)
|
||||
# SYS_WATCHDOG_MEM_SHUTDOWN_EXCLUDED — containers exempt from memory shutdown
|
||||
#
|
||||
# ==============================================================================================
|
||||
# STATE FILES
|
||||
# ==============================================================================================
|
||||
#
|
||||
# SYS_WATCHDOG_STATE_FILE — strike counters and cycle state
|
||||
# SYS_WATCHDOG_REBOOT_LOG — reboot history for rate limiting
|
||||
# SYS_WATCHDOG_FAILED_FILE — containers confirmed down for skip list integration
|
||||
# SYS_WATCHDOG_OOM_FILE — OOM kill counter from previous cycle
|
||||
#
|
||||
# ==============================================================================================
|
||||
# RUNTIME MODES
|
||||
# ==============================================================================================
|
||||
#
|
||||
# system_watchdog.sh
|
||||
# Start continuous monitoring loop. Runs until stopped or system reboots.
|
||||
#
|
||||
# system_watchdog.sh --dry-run
|
||||
# Run detection logic without rebooting or stopping containers.
|
||||
#
|
||||
# system_watchdog.sh --status
|
||||
# Show config, thresholds, current system state, and strike counts.
|
||||
#
|
||||
# system_watchdog.sh --log
|
||||
# Verbose per-cycle output — show every check result and threshold comparison.
|
||||
# ── CONFIGURATION (master.conf) ───────────────────────────────────────────────────────────────
|
||||
# SYSTEM_WATCHDOG_SCRIPTS — ordered list of system component watchdog scripts to run
|
||||
#
|
||||
# ── USAGE ─────────────────────────────────────────────────────────────────────────────────────
|
||||
# system_watchdog.sh — run all system component watchdogs
|
||||
# system_watchdog.sh --dry-run — preview without running anything
|
||||
# system_watchdog.sh --status — show configured scripts and exit
|
||||
# system_watchdog.sh --log — verbose output
|
||||
# ==============================================================================================
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
ECOSYSTEM_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
|
||||
|
||||
source "$SCRIPT_DIR/../load_config.sh"
|
||||
source "$ECOSYSTEM_ROOT/load_config.sh"
|
||||
|
||||
parse_args "$@"
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Setup — runs once at start ━━━
|
||||
# ━━━ Setup ━━━
|
||||
# ==============================================================================================
|
||||
if [[ "$EUID" -ne 0 ]]; then
|
||||
error "Must be run as root"
|
||||
@@ -128,20 +54,7 @@ acquire_lock
|
||||
|
||||
detect_hosts
|
||||
|
||||
TOTAL_CORES=$(nproc)
|
||||
DOCKER_TIMEOUT=10
|
||||
SYS_WATCHDOG_REBOOT_WINDOW=$(( SYS_WATCHDOG_REBOOT_WINDOW_HRS * 3600 ))
|
||||
|
||||
# Ensure state files exist
|
||||
for state_file in "$SYS_WATCHDOG_STATE_FILE" "$SYS_WATCHDOG_REBOOT_LOG" \
|
||||
"$SYS_WATCHDOG_FAILED_FILE" "$SYS_WATCHDOG_OOM_FILE"; do
|
||||
touch "$state_file" 2>/dev/null || {
|
||||
error "Cannot create state file: $state_file"
|
||||
exit 1
|
||||
}
|
||||
done
|
||||
|
||||
[[ "$DRY_RUN" == true ]] && warn "DRY RUN — no reboots or container shutdowns will occur"
|
||||
[[ "$DRY_RUN" == true ]] && warn "DRY RUN — no watchdog scripts will be executed"
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Status ━━━
|
||||
@@ -149,657 +62,76 @@ done
|
||||
if [[ "$SHOW_STATUS" == true ]]; then
|
||||
echo ""
|
||||
echo "━━━━━ $ICON_SUMMARY SYSTEM WATCHDOG STATUS ━━━━━"
|
||||
echo "$ICON_HOST Identity: $MY_ID ($LOCAL_SERVER_NAME)"
|
||||
echo "$ICON_HOST Identity: $MY_ID ($LOCAL_SERVER_NAME)"
|
||||
echo "$ICON_GEAR Scripts: ${#SYSTEM_WATCHDOG_SCRIPTS[@]} configured"
|
||||
echo ""
|
||||
echo "── Tier 1 — CRITICAL (bypass strikes immediately) ──"
|
||||
echo "$ICON_DISK rootfs critical: ${SYS_WATCHDOG_ROOTFS_CRITICAL_PCT}%"
|
||||
echo "$ICON_GEAR FD critical: ${SYS_WATCHDOG_FD_CRITICAL_PCT}%"
|
||||
echo "$ICON_GEAR /boot read-only: check=${SYS_WATCHDOG_CHECK_BOOT}"
|
||||
echo "$ICON_GEAR Kernel oops: check=${SYS_WATCHDOG_CHECK_KERNEL_OOPS}"
|
||||
echo "$ICON_CONTAINERS Docker daemon: check=${SYS_WATCHDOG_CHECK_DOCKER_DAEMON}"
|
||||
echo ""
|
||||
echo "── Tier 2 — URGENT (bypass strikes with OOM confirmation) ──"
|
||||
echo "$ICON_MEM RAM critical: < ${SYS_WATCHDOG_MEM_GB}GB"
|
||||
echo "$ICON_GEAR OOM limit: ${SYS_WATCHDOG_OOM_LIMIT} kills/cycle"
|
||||
echo ""
|
||||
echo "── Tier 3 — STANDARD (strike system) ──"
|
||||
echo "$ICON_DISK rootfs warn: ${SYS_WATCHDOG_ROOTFS_PCT}%"
|
||||
echo "$ICON_GEAR /var/log warn: ${SYS_WATCHDOG_LOG_PCT}%"
|
||||
echo "$ICON_GEAR /tmp warn: ${SYS_WATCHDOG_TMP_PCT}%"
|
||||
echo "$ICON_MEM RAM reboot: < ${SYS_WATCHDOG_MEM_GB}GB (+ strikes)"
|
||||
echo " (RAM warn/shutdown/recover managed by resource_watchdog.sh)"
|
||||
echo "$ICON_ZFS ARC pinned: ${SYS_WATCHDOG_ARC_PINNED_PCT}%"
|
||||
echo "$ICON_GEAR Load multiplier: ${SYS_WATCHDOG_LOAD_MULTIPLIER}x (= $(( TOTAL_CORES * SYS_WATCHDOG_LOAD_MULTIPLIER )) on $TOTAL_CORES cores)"
|
||||
echo "$ICON_GEAR Zombie limit: ${SYS_WATCHDOG_ZOMBIE_LIMIT}"
|
||||
echo "$ICON_GEAR CPU temp max: ${SYS_WATCHDOG_CPU_TEMP_MAX}°C"
|
||||
echo "$ICON_GEAR Strike limit: ${SYS_WATCHDOG_STRIKE_LIMIT} cycles"
|
||||
echo "$ICON_TIME Interval: ${SYSTEM_WATCHDOG_INTERVAL}s"
|
||||
echo "$ICON_REBOOT_SMART Reboot limit: ${SYS_WATCHDOG_REBOOT_LIMIT} in ${SYS_WATCHDOG_REBOOT_WINDOW_HRS}hr"
|
||||
echo ""
|
||||
echo ""
|
||||
echo "── Check Toggles ──"
|
||||
echo " rootfs=$SYS_WATCHDOG_CHECK_ROOTFS log=$SYS_WATCHDOG_CHECK_LOG ram=$SYS_WATCHDOG_CHECK_RAM"
|
||||
echo " arc=$SYS_WATCHDOG_CHECK_ARC cpu_temp=$SYS_WATCHDOG_CHECK_CPU_TEMP load=$SYS_WATCHDOG_CHECK_LOAD"
|
||||
echo " zombies=$SYS_WATCHDOG_CHECK_ZOMBIES docker=$SYS_WATCHDOG_CHECK_DOCKER_DAEMON"
|
||||
echo " containers=$SYS_WATCHDOG_CHECK_CONTAINERS oom=$SYS_WATCHDOG_CHECK_OOM"
|
||||
echo " tmp=$SYS_WATCHDOG_CHECK_TMP fd=$SYS_WATCHDOG_CHECK_FD boot=$SYS_WATCHDOG_CHECK_BOOT"
|
||||
echo " kernel_oops=$SYS_WATCHDOG_CHECK_KERNEL_OOPS sshd=$SYS_WATCHDOG_CHECK_SSHD"
|
||||
echo " network=$SYS_WATCHDOG_CHECK_NETWORK mdstat=$SYS_WATCHDOG_CHECK_MDSTAT"
|
||||
echo " runaway=$SYS_WATCHDOG_CHECK_RUNAWAY"
|
||||
|
||||
for entry in "${SYSTEM_WATCHDOG_SCRIPTS[@]}"; do
|
||||
[[ -z "$entry" ]] && continue
|
||||
read -r -a parts <<< "$entry"
|
||||
script_path="$ECOSYSTEM_ROOT/${parts[0]}"
|
||||
script_name=$(basename "${parts[0]}")
|
||||
if [[ ! -f "$script_path" ]]; then
|
||||
echo " $ICON_ERROR $script_name — FILE NOT FOUND"
|
||||
else
|
||||
echo " $ICON_GEAR $script_name"
|
||||
fi
|
||||
done
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# ==============================================================================================
|
||||
# ── STATE HELPERS ─────────────────────────────────────────────────────────────────────────────
|
||||
# ━━━ Run Sequence ━━━
|
||||
# ==============================================================================================
|
||||
START=$(date +%s)
|
||||
PASSED=()
|
||||
FAILED=()
|
||||
STEP=0
|
||||
|
||||
get_strikes() {
|
||||
grep -E "^${1}:" "$SYS_WATCHDOG_STATE_FILE" 2>/dev/null | cut -d':' -f2
|
||||
}
|
||||
for entry in "${SYSTEM_WATCHDOG_SCRIPTS[@]}"; do
|
||||
[[ -z "$entry" ]] && continue
|
||||
(( STEP++ ))
|
||||
|
||||
set_strikes() {
|
||||
local key="$1" count="$2"
|
||||
grep -vE "^${key}:" "$SYS_WATCHDOG_STATE_FILE" 2>/dev/null > "${SYS_WATCHDOG_STATE_FILE}.tmp"
|
||||
echo "${key}:${count}" >> "${SYS_WATCHDOG_STATE_FILE}.tmp"
|
||||
mv "${SYS_WATCHDOG_STATE_FILE}.tmp" "$SYS_WATCHDOG_STATE_FILE"
|
||||
}
|
||||
read -r -a parts <<< "$entry"
|
||||
script_path="$ECOSYSTEM_ROOT/${parts[0]}"
|
||||
script_name=$(basename "${parts[0]}")
|
||||
|
||||
increment_strikes() {
|
||||
local key="$1"
|
||||
local current
|
||||
current=$(get_strikes "$key")
|
||||
[[ -z "$current" ]] && current=0
|
||||
(( current++ ))
|
||||
set_strikes "$key" "$current"
|
||||
echo "$current"
|
||||
}
|
||||
|
||||
reset_strikes() {
|
||||
set_strikes "$1" 0
|
||||
}
|
||||
|
||||
get_state_val() {
|
||||
grep -E "^${1}=" "$SYS_WATCHDOG_STATE_FILE" 2>/dev/null | cut -d'=' -f2
|
||||
}
|
||||
|
||||
set_state_val() {
|
||||
local key="$1" val="$2"
|
||||
grep -vE "^${key}=" "$SYS_WATCHDOG_STATE_FILE" 2>/dev/null > "${SYS_WATCHDOG_STATE_FILE}.tmp"
|
||||
echo "${key}=${val}" >> "${SYS_WATCHDOG_STATE_FILE}.tmp"
|
||||
mv "${SYS_WATCHDOG_STATE_FILE}.tmp" "$SYS_WATCHDOG_STATE_FILE"
|
||||
}
|
||||
|
||||
purge_old_reboots() {
|
||||
local now cutoff
|
||||
now=$(date +%s)
|
||||
cutoff=$(( now - SYS_WATCHDOG_REBOOT_WINDOW ))
|
||||
grep -v "^$" "$SYS_WATCHDOG_REBOOT_LOG" 2>/dev/null | while IFS= read -r ts; do
|
||||
[[ "$ts" -gt "$cutoff" ]] && echo "$ts"
|
||||
done > "${SYS_WATCHDOG_REBOOT_LOG}.tmp"
|
||||
mv "${SYS_WATCHDOG_REBOOT_LOG}.tmp" "$SYS_WATCHDOG_REBOOT_LOG"
|
||||
}
|
||||
|
||||
count_recent_reboots() {
|
||||
purge_old_reboots
|
||||
grep -c "." "$SYS_WATCHDOG_REBOOT_LOG" 2>/dev/null || echo 0
|
||||
}
|
||||
|
||||
log_reboot() {
|
||||
date +%s >> "$SYS_WATCHDOG_REBOOT_LOG"
|
||||
}
|
||||
|
||||
# ==============================================================================================
|
||||
# ── OOM TRACKING ──────────────────────────────────────────────────────────────────────────────
|
||||
# ==============================================================================================
|
||||
# Reads /proc/vmstat oom_kill counter — delta per cycle = rate of OOM kills
|
||||
# Used for Tier 2 bypass and diagnostic context in reboot messages
|
||||
|
||||
get_oom_delta() {
|
||||
local current_oom
|
||||
current_oom=$(grep "^oom_kill " /proc/vmstat 2>/dev/null | awk '{print $2}')
|
||||
[[ -z "$current_oom" ]] && echo 0 && return
|
||||
|
||||
local prev_oom
|
||||
prev_oom=$(cat "$SYS_WATCHDOG_OOM_FILE" 2>/dev/null || echo 0)
|
||||
echo "$current_oom" > "$SYS_WATCHDOG_OOM_FILE"
|
||||
|
||||
local delta=$(( current_oom - prev_oom ))
|
||||
[[ "$delta" -lt 0 ]] && delta=0 # counter reset on reboot
|
||||
echo "$delta"
|
||||
}
|
||||
|
||||
get_oom_victims() {
|
||||
# Get process names from dmesg that were OOM killed this boot
|
||||
dmesg -T 2>/dev/null | grep -i "Killed process" | \
|
||||
awk '{print $NF}' | sort | uniq -c | sort -rn | head -5 | \
|
||||
awk '{printf "%s×%d ", $2, $1}' | sed 's/ $//'
|
||||
}
|
||||
|
||||
# ==============================================================================================
|
||||
# ── ABORT CONDITIONS ──────────────────────────────────────────────────────────────────────────
|
||||
# ==============================================================================================
|
||||
# Returns 1 if reboot should be aborted, 0 if reboot should proceed
|
||||
# CRITICAL tier bypasses this function entirely
|
||||
|
||||
check_abort_conditions() {
|
||||
local should_abort=false
|
||||
|
||||
if command -v zpool >/dev/null 2>&1; then
|
||||
local unhealthy
|
||||
unhealthy=$(zpool list -H -o health 2>/dev/null | grep -v ONLINE || true)
|
||||
if [[ -n "$unhealthy" ]]; then
|
||||
if [[ "$SYS_WATCHDOG_ABORT_ON_ZFS_UNHEALTHY" == true ]]; then
|
||||
error "ZFS pool unhealthy — aborting reboot to prevent data loss"
|
||||
notify "System watchdog aborted reboot on $(hostname) ($MY_ID) — ZFS pool unhealthy" \
|
||||
"System Watchdog" "warning"
|
||||
should_abort=true
|
||||
else
|
||||
warn "ZFS pool unhealthy — continuing reboot (ABORT_ON_ZFS_UNHEALTHY=false)"
|
||||
fi
|
||||
fi
|
||||
if [[ ! -f "$script_path" ]]; then
|
||||
error "$script_name — not found at $script_path"
|
||||
FAILED+=("$script_name")
|
||||
continue
|
||||
fi
|
||||
|
||||
if grep -q "progress" /var/local/emhttp/parity-date.txt 2>/dev/null; then
|
||||
if [[ "$SYS_WATCHDOG_ABORT_ON_PARITY" == true ]]; then
|
||||
error "Parity check running — aborting reboot"
|
||||
notify "System watchdog aborted reboot on $(hostname) ($MY_ID) — parity running" \
|
||||
"System Watchdog" "warning"
|
||||
should_abort=true
|
||||
else
|
||||
warn "Parity check running — continuing reboot (ABORT_ON_PARITY=false)"
|
||||
fi
|
||||
if [[ ! -x "$script_path" ]]; then
|
||||
chmod +x "$script_path" || {
|
||||
error "$script_name — chmod +x failed"
|
||||
FAILED+=("$script_name")
|
||||
continue
|
||||
}
|
||||
fi
|
||||
|
||||
if pgrep -f "mover" >/dev/null 2>&1; then
|
||||
if [[ "$SYS_WATCHDOG_ABORT_ON_MOVER" == true ]]; then
|
||||
error "Mover running — aborting reboot"
|
||||
notify "System watchdog aborted reboot on $(hostname) ($MY_ID) — mover running" \
|
||||
"System Watchdog" "warning"
|
||||
should_abort=true
|
||||
else
|
||||
warn "Mover running — continuing reboot (ABORT_ON_MOVER=false)"
|
||||
fi
|
||||
fi
|
||||
|
||||
[[ "$should_abort" == true ]] && return 1
|
||||
return 0
|
||||
}
|
||||
|
||||
# ==============================================================================================
|
||||
# ── STANDARD STRIKE CHECK ─────────────────────────────────────────────────────────────────────
|
||||
# ==============================================================================================
|
||||
# Returns 0 = reboot now | 1 = not yet
|
||||
|
||||
run_strike_check() {
|
||||
local key="$1" triggered="$2" description="$3"
|
||||
if [[ "$triggered" == true ]]; then
|
||||
local strikes
|
||||
strikes=$(increment_strikes "$key")
|
||||
warn "$description — strike $strikes/$SYS_WATCHDOG_STRIKE_LIMIT"
|
||||
if (( strikes >= SYS_WATCHDOG_STRIKE_LIMIT )); then
|
||||
error "$description — strike limit hit, reboot triggered"
|
||||
reset_strikes "$key"
|
||||
return 0
|
||||
fi
|
||||
else
|
||||
local current
|
||||
current=$(get_strikes "$key")
|
||||
[[ -n "$current" && "$current" -gt 0 ]] && reset_strikes "$key"
|
||||
fi
|
||||
return 1
|
||||
}
|
||||
|
||||
# ── Exit Trap — restart containers stopped before an aborted reboot ───────────────────────────
|
||||
_SYS_REBOOT_STOPPED=()
|
||||
_trap_sys_reboot_restart() {
|
||||
[[ ${#_SYS_REBOOT_STOPPED[@]} -eq 0 ]] && return
|
||||
warn "Exit trap: restarting containers stopped before aborted reboot"
|
||||
for c in "${_SYS_REBOOT_STOPPED[@]}"; do
|
||||
[[ -z "$c" ]] && continue
|
||||
docker inspect "$c" >/dev/null 2>&1 && docker start "$c" >/dev/null 2>&1 || true
|
||||
done
|
||||
}
|
||||
|
||||
# ==============================================================================================
|
||||
# ── DO REBOOT ─────────────────────────────────────────────────────────────────────────────────
|
||||
# ==============================================================================================
|
||||
# tier: "critical" (bypass abort) | "urgent" | "standard"
|
||||
|
||||
do_reboot() {
|
||||
local tier="${1:-standard}"
|
||||
shift
|
||||
local triggers=("$@")
|
||||
|
||||
# Get OOM context for reboot message
|
||||
local oom_victims=""
|
||||
if [[ "$SYS_WATCHDOG_CHECK_OOM" == true ]]; then
|
||||
oom_victims=$(get_oom_victims)
|
||||
[[ -n "$oom_victims" ]] && triggers+=("oom_victims: $oom_victims")
|
||||
fi
|
||||
|
||||
# Abort check — CRITICAL bypasses this
|
||||
if [[ "$tier" != "critical" ]]; then
|
||||
if ! check_abort_conditions; then
|
||||
return
|
||||
fi
|
||||
else
|
||||
warn "CRITICAL tier — bypassing abort conditions"
|
||||
fi
|
||||
|
||||
RECENT_REBOOTS=$(count_recent_reboots)
|
||||
log "Recent reboots in ${SYS_WATCHDOG_REBOOT_WINDOW_HRS}hr window: $RECENT_REBOOTS / $SYS_WATCHDOG_REBOOT_LIMIT"
|
||||
|
||||
if [[ "$RECENT_REBOOTS" -ge "$SYS_WATCHDOG_REBOOT_LIMIT" ]]; then
|
||||
error "Reboot loop detected — shutting down instead of rebooting"
|
||||
notify "Reboot loop on $(hostname) ($MY_ID) — shutting down after $RECENT_REBOOTS reboots — ${triggers[*]}" \
|
||||
"System Watchdog" "warning"
|
||||
if [[ "$DRY_RUN" == true ]]; then
|
||||
warn "DRY RUN — would shutdown now"
|
||||
return
|
||||
fi
|
||||
sync
|
||||
/sbin/poweroff
|
||||
return
|
||||
fi
|
||||
|
||||
echo ""
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo " $ICON_REBOOT_SMART SYSTEM WATCHDOG — REBOOT TRIGGERED"
|
||||
echo " Tier: ${tier^^}"
|
||||
echo " Host: $MY_ID ($LOCAL_SERVER_NAME)"
|
||||
for t in "${triggers[@]}"; do
|
||||
echo " → $t"
|
||||
done
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
notify "System watchdog ${tier^^} reboot on $(hostname) ($MY_ID) — ${triggers[*]}" \
|
||||
"System Watchdog" "warning"
|
||||
|
||||
if [[ "$DRY_RUN" == true ]]; then
|
||||
warn "DRY RUN — reboot sequence would begin now"
|
||||
return
|
||||
warn "DRY RUN — would run: $script_name"
|
||||
PASSED+=("$script_name")
|
||||
continue
|
||||
fi
|
||||
|
||||
log_reboot
|
||||
|
||||
# Graceful shutdown sequence
|
||||
warn "Shutting down VMs..."
|
||||
if command -v virsh >/dev/null 2>&1; then
|
||||
for VM in $(virsh list --name 2>/dev/null); do
|
||||
[[ -z "$VM" ]] && continue
|
||||
virsh shutdown "$VM" >/dev/null 2>&1
|
||||
done
|
||||
sleep 30
|
||||
fi
|
||||
|
||||
warn "Stopping Docker containers..."
|
||||
if command -v docker >/dev/null 2>&1; then
|
||||
mapfile -t _SYS_REBOOT_STOPPED < <(docker ps --format '{{.Names}}' 2>/dev/null)
|
||||
trap _trap_sys_reboot_restart EXIT
|
||||
timeout 60 docker ps -q 2>/dev/null | xargs -r docker stop >/dev/null 2>&1
|
||||
fi
|
||||
|
||||
warn "Stopping User Scripts..."
|
||||
pkill -f "/tmp/user.scripts" 2>/dev/null || true
|
||||
|
||||
warn "Syncing disks..."
|
||||
sync
|
||||
|
||||
trap - EXIT # committed to reboot — containers should stay down
|
||||
sleep 5
|
||||
/sbin/reboot
|
||||
}
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Single-Pass Health Check ━━━
|
||||
# ==============================================================================================
|
||||
warn "System watchdog — $MY_ID — $(date '+%H:%M:%S')"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
TRIGGERS=()
|
||||
CRITICAL_TRIGGERS=()
|
||||
URGENT_OOM_CONFIRMED=false
|
||||
|
||||
# ── OOM Delta — read every cycle for bypass decisions ─────────────────────────────────────
|
||||
OOM_DELTA=0
|
||||
if [[ "$SYS_WATCHDOG_CHECK_OOM" == true ]]; then
|
||||
OOM_DELTA=$(get_oom_delta)
|
||||
[[ "$OOM_DELTA" -gt 0 ]] && \
|
||||
log "OOM kills this cycle: $OOM_DELTA (limit: ${SYS_WATCHDOG_OOM_LIMIT})"
|
||||
fi
|
||||
|
||||
# ==========================================================================================
|
||||
# ━━━ TIER 1 — CRITICAL CHECKS (bypass all strikes, reboot immediately) ━━━
|
||||
# ==========================================================================================
|
||||
|
||||
# ── Docker daemon — critical: nothing can heal without it ─────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_DOCKER_DAEMON" == true ]]; then
|
||||
if ! timeout "$DOCKER_TIMEOUT" docker info >/dev/null 2>&1; then
|
||||
error "Docker daemon unresponsive — CRITICAL"
|
||||
|
||||
# Attempt daemon restart before rebooting
|
||||
warn "Attempting Docker daemon restart..."
|
||||
if [[ "$DRY_RUN" == false ]]; then
|
||||
/etc/rc.d/rc.docker restart >/dev/null 2>&1
|
||||
sleep 15
|
||||
if timeout "$DOCKER_TIMEOUT" docker info >/dev/null 2>&1; then
|
||||
warn "Docker daemon restarted successfully — continuing monitoring"
|
||||
else
|
||||
error "Docker daemon restart failed — adding to CRITICAL triggers"
|
||||
CRITICAL_TRIGGERS+=("docker_daemon_unresponsive")
|
||||
fi
|
||||
else
|
||||
warn "DRY RUN — would attempt Docker daemon restart"
|
||||
CRITICAL_TRIGGERS+=("docker_daemon_unresponsive")
|
||||
fi
|
||||
else
|
||||
log "Docker daemon healthy ✅"
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── rootfs critical — at 99%+ writes are failing ─────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_ROOTFS" == true ]]; then
|
||||
ROOTFS_USED=$(df / --output=pcent 2>/dev/null | tail -1 | tr -d ' %')
|
||||
if [[ "$ROOTFS_USED" -ge "${SYS_WATCHDOG_ROOTFS_CRITICAL_PCT:-99}" ]]; then
|
||||
error "rootfs ${ROOTFS_USED}% — CRITICAL (writes failing)"
|
||||
CRITICAL_TRIGGERS+=("rootfs_full=${ROOTFS_USED}%")
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── Kernel oops/BUG — kernel running with corrupted state ────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_KERNEL_OOPS" == true ]]; then
|
||||
PREV_OOPS=$(get_state_val "kernel_oops_count")
|
||||
CURRENT_OOPS=$(dmesg 2>/dev/null | grep -cE "BUG:|kernel BUG|Oops:" || echo 0)
|
||||
CURRENT_OOPS="${CURRENT_OOPS//[^0-9]/}"; CURRENT_OOPS="${CURRENT_OOPS:-0}"
|
||||
set_state_val "kernel_oops_count" "$CURRENT_OOPS"
|
||||
|
||||
if [[ -n "$PREV_OOPS" && "$PREV_OOPS" =~ ^[0-9]+$ ]]; then
|
||||
OOPS_DELTA=$(( CURRENT_OOPS - PREV_OOPS ))
|
||||
if [[ "$OOPS_DELTA" -gt 0 ]]; then
|
||||
error "Kernel oops/BUG detected — $OOPS_DELTA new since last cycle — CRITICAL"
|
||||
CRITICAL_TRIGGERS+=("kernel_oops=${OOPS_DELTA}_new")
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── File descriptor exhaustion — new connections failing silently ─────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_FD" == true ]]; then
|
||||
FD_LINE=$(cat /proc/sys/fs/file-nr 2>/dev/null)
|
||||
FD_OPEN=$(echo "$FD_LINE" | awk '{print $1}')
|
||||
FD_MAX=$(echo "$FD_LINE" | awk '{print $3}')
|
||||
if [[ -n "$FD_OPEN" && -n "$FD_MAX" && "$FD_MAX" -gt 0 ]]; then
|
||||
FD_PCT=$(( FD_OPEN * 100 / FD_MAX ))
|
||||
if [[ "$FD_PCT" -ge "${SYS_WATCHDOG_FD_CRITICAL_PCT:-95}" ]]; then
|
||||
error "File descriptors ${FD_PCT}% exhausted (${FD_OPEN}/${FD_MAX}) — CRITICAL"
|
||||
CRITICAL_TRIGGERS+=("fd_exhaustion=${FD_PCT}%")
|
||||
else
|
||||
log "File descriptors: ${FD_PCT}% (${FD_OPEN}/${FD_MAX})"
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── /boot read-only — state and config writes failing silently ────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_BOOT" == true ]]; then
|
||||
BOOT_TEST="/boot/.watchdog_write_test"
|
||||
if ! touch "$BOOT_TEST" 2>/dev/null; then
|
||||
error "/boot is read-only — config writes failing silently — CRITICAL"
|
||||
CRITICAL_TRIGGERS+=("boot_read_only")
|
||||
else
|
||||
rm -f "$BOOT_TEST" 2>/dev/null
|
||||
log "/boot is writable ✅"
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── Act on CRITICAL triggers immediately ─────────────────────────────────────────────────
|
||||
if [[ ${#CRITICAL_TRIGGERS[@]} -gt 0 ]]; then
|
||||
echo ""
|
||||
echo "━━━ $ICON_ERROR CRITICAL — IMMEDIATE REBOOT ━━━"
|
||||
for t in "${CRITICAL_TRIGGERS[@]}"; do
|
||||
error " CRITICAL: $t"
|
||||
done
|
||||
do_reboot "critical" "${CRITICAL_TRIGGERS[@]}"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# ==========================================================================================
|
||||
# ━━━ TIER 3 — STANDARD CHECKS (strike system) ━━━
|
||||
# ==========================================================================================
|
||||
|
||||
# ── rootfs standard ──────────────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_ROOTFS" == true ]]; then
|
||||
ROOTFS_USED=$(df / --output=pcent 2>/dev/null | tail -1 | tr -d ' %')
|
||||
TRIGGERED=false
|
||||
[[ "$ROOTFS_USED" -ge "$SYS_WATCHDOG_ROOTFS_PCT" ]] && TRIGGERED=true
|
||||
run_strike_check "rootfs" "$TRIGGERED" "rootfs ${ROOTFS_USED}%" && \
|
||||
TRIGGERS+=("rootfs=${ROOTFS_USED}%")
|
||||
fi
|
||||
|
||||
# ── /var/log ─────────────────────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_LOG" == true ]]; then
|
||||
LOG_USED=$(df -P /var/log 2>/dev/null | awk 'NR==2 {print $5}' | tr -d '%')
|
||||
TRIGGERED=false
|
||||
[[ "${LOG_USED:-0}" -ge "$SYS_WATCHDOG_LOG_PCT" ]] && TRIGGERED=true
|
||||
run_strike_check "log" "$TRIGGERED" "/var/log ${LOG_USED}%" && \
|
||||
TRIGGERS+=("log=${LOG_USED}%")
|
||||
fi
|
||||
|
||||
# ── /tmp ─────────────────────────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_TMP" == true ]]; then
|
||||
TMP_USED=$(df -P /tmp 2>/dev/null | awk 'NR==2 {print $5}' | tr -d '%')
|
||||
if [[ "${TMP_USED:-0}" -ge "${SYS_WATCHDOG_TMP_CRITICAL_PCT:-98}" ]]; then
|
||||
# Try to clear before escalating
|
||||
warn "/tmp ${TMP_USED}% — attempting cleanup..."
|
||||
find /tmp -type f -mmin +60 -not -name "*.lock" -delete 2>/dev/null
|
||||
TMP_USED_AFTER=$(df -P /tmp 2>/dev/null | awk 'NR==2 {print $5}' | tr -d '%')
|
||||
if [[ "${TMP_USED_AFTER:-0}" -ge "${SYS_WATCHDOG_TMP_CRITICAL_PCT:-98}" ]]; then
|
||||
error "/tmp still ${TMP_USED_AFTER}% after cleanup — adding to triggers"
|
||||
TRIGGERED=true
|
||||
else
|
||||
warn "/tmp cleared to ${TMP_USED_AFTER}% ✅"
|
||||
TRIGGERED=false
|
||||
fi
|
||||
elif [[ "${TMP_USED:-0}" -ge "${SYS_WATCHDOG_TMP_PCT:-90}" ]]; then
|
||||
TRIGGERED=true
|
||||
else
|
||||
TRIGGERED=false
|
||||
fi
|
||||
run_strike_check "tmp" "$TRIGGERED" "/tmp ${TMP_USED}%" && \
|
||||
TRIGGERS+=("tmp=${TMP_USED}%")
|
||||
fi
|
||||
|
||||
# ── RAM — reboot tier only (warn/shutdown/recover handled by resource_watchdog.sh) ──────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_RAM" == true ]]; then
|
||||
MEM_KB=$(awk '/MemAvailable/ {print $2}' /proc/meminfo)
|
||||
MEM_GB=$(( MEM_KB / 1024 / 1024 ))
|
||||
|
||||
if [[ "$MEM_GB" -lt "$SYS_WATCHDOG_MEM_GB" ]]; then
|
||||
# Tier 2 — bypass strike system if OOM confirms active crisis
|
||||
if [[ "$SYS_WATCHDOG_CHECK_OOM" == true ]] && \
|
||||
[[ "$OOM_DELTA" -ge "$SYS_WATCHDOG_OOM_LIMIT" ]]; then
|
||||
error "RAM ${MEM_GB}GB + ${OOM_DELTA} OOM kills this run — URGENT bypass"
|
||||
OOM_VICTIMS=$(get_oom_victims)
|
||||
URGENT_TRIGGERS=("urgent_low_ram=${MEM_GB}GB" "oom_kills=${OOM_DELTA}")
|
||||
[[ -n "$OOM_VICTIMS" ]] && URGENT_TRIGGERS+=("oom_victims: $OOM_VICTIMS")
|
||||
do_reboot "urgent" "${URGENT_TRIGGERS[@]}"
|
||||
exit 0
|
||||
fi
|
||||
# Standard strike path
|
||||
run_strike_check "ram" true "RAM ${MEM_GB}GB free" && \
|
||||
TRIGGERS+=("low_ram=${MEM_GB}GB")
|
||||
else
|
||||
reset_strikes "ram"
|
||||
log "RAM ${MEM_GB}GB free ✅"
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── ZFS ARC ──────────────────────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_ARC" == true ]] && [[ -f /proc/spl/kstat/zfs/arcstats ]]; then
|
||||
ARC_SIZE=$(awk '/^size / {print $3}' /proc/spl/kstat/zfs/arcstats)
|
||||
ARC_MAX=$(awk '/^c_max / {print $3}' /proc/spl/kstat/zfs/arcstats)
|
||||
ARC_PCT=$(( ARC_SIZE * 100 / ARC_MAX ))
|
||||
TRIGGERED=false
|
||||
if [[ "$ARC_PCT" -ge "$SYS_WATCHDOG_ARC_PINNED_PCT" ]]; then
|
||||
sync; echo 3 > /proc/sys/vm/drop_caches; sleep 5
|
||||
ARC_AFTER=$(awk '/^size / {print $3}' /proc/spl/kstat/zfs/arcstats)
|
||||
ARC_AFTER_PCT=$(( ARC_AFTER * 100 / ARC_MAX ))
|
||||
[[ "$ARC_AFTER_PCT" -ge "$SYS_WATCHDOG_ARC_RELEASE_PCT" ]] && TRIGGERED=true
|
||||
fi
|
||||
run_strike_check "arc" "$TRIGGERED" "ZFS ARC pinned ${ARC_PCT}%" && \
|
||||
TRIGGERS+=("arc_pinned=${ARC_PCT}%")
|
||||
fi
|
||||
|
||||
# ── CPU temperature ───────────────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_CPU_TEMP" == true ]]; then
|
||||
CPU_TEMP=""
|
||||
if command -v sensors >/dev/null 2>&1; then
|
||||
CPU_TEMP=$(sensors 2>/dev/null | \
|
||||
grep -i "Package id 0\|Tctl\|CPU Temp" | \
|
||||
awk '{print $NF}' | tr -d '+°C' | head -1)
|
||||
fi
|
||||
if [[ -n "$CPU_TEMP" ]]; then
|
||||
CPU_TEMP_INT=$(printf "%.0f" "$CPU_TEMP")
|
||||
TRIGGERED=false
|
||||
[[ "$CPU_TEMP_INT" -ge "$SYS_WATCHDOG_CPU_TEMP_MAX" ]] && TRIGGERED=true
|
||||
run_strike_check "cpu_temp" "$TRIGGERED" "CPU temp ${CPU_TEMP_INT}°C" && \
|
||||
TRIGGERS+=("cpu_temp=${CPU_TEMP_INT}C")
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── Load average ─────────────────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_LOAD" == true ]]; then
|
||||
LOAD=$(awk '{print $1}' /proc/loadavg)
|
||||
LOAD_INT=$(printf "%.0f" "$LOAD")
|
||||
LOAD_THRESHOLD=$(( TOTAL_CORES * SYS_WATCHDOG_LOAD_MULTIPLIER ))
|
||||
TRIGGERED=false
|
||||
[[ "$LOAD_INT" -ge "$LOAD_THRESHOLD" ]] && TRIGGERED=true
|
||||
run_strike_check "load" "$TRIGGERED" "load avg ${LOAD}" && \
|
||||
TRIGGERS+=("load=${LOAD}")
|
||||
fi
|
||||
|
||||
# ── Zombie processes ─────────────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_ZOMBIES" == true ]]; then
|
||||
ZOMBIE_COUNT=$(ps aux 2>/dev/null | awk '{print $8}' | grep -c "^Z$" || echo 0)
|
||||
ZOMBIE_COUNT="${ZOMBIE_COUNT//[^0-9]/}"; ZOMBIE_COUNT="${ZOMBIE_COUNT:-0}"
|
||||
TRIGGERED=false
|
||||
[[ "$ZOMBIE_COUNT" -ge "$SYS_WATCHDOG_ZOMBIE_LIMIT" ]] && TRIGGERED=true
|
||||
run_strike_check "zombies" "$TRIGGERED" "zombies ${ZOMBIE_COUNT}" && \
|
||||
TRIGGERS+=("zombies=${ZOMBIE_COUNT}")
|
||||
fi
|
||||
|
||||
# ── Array disk errors — accumulating mdstat errors ────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_MDSTAT" == true ]]; then
|
||||
PREV_MD_ERRORS=$(get_state_val "mdstat_errors")
|
||||
CURRENT_MD_ERRORS=$(grep -oP "(?<=\[)[^\]]*[U_][^\]]*(?=\])" \
|
||||
/proc/mdstat 2>/dev/null | grep -o "_" | wc -l || echo 0)
|
||||
CURRENT_MD_ERRORS="${CURRENT_MD_ERRORS//[^0-9]/}"; CURRENT_MD_ERRORS="${CURRENT_MD_ERRORS:-0}"
|
||||
set_state_val "mdstat_errors" "$CURRENT_MD_ERRORS"
|
||||
|
||||
if [[ -n "$PREV_MD_ERRORS" && "$PREV_MD_ERRORS" =~ ^[0-9]+$ ]]; then
|
||||
MD_DELTA=$(( CURRENT_MD_ERRORS - PREV_MD_ERRORS ))
|
||||
if [[ "$MD_DELTA" -ge "${SYS_WATCHDOG_MDSTAT_ERROR_LIMIT:-5}" ]]; then
|
||||
TRIGGERED=true
|
||||
run_strike_check "mdstat" "$TRIGGERED" \
|
||||
"mdstat errors +${MD_DELTA} (total: ${CURRENT_MD_ERRORS})" && \
|
||||
TRIGGERS+=("mdstat_errors=+${MD_DELTA}")
|
||||
else
|
||||
run_strike_check "mdstat" false "mdstat" > /dev/null
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── Network interface state ───────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_NETWORK" == true ]]; then
|
||||
NIC="${SYS_WATCHDOG_NIC:-eth0}"
|
||||
NIC_STATE=$(cat "/sys/class/net/${NIC}/operstate" 2>/dev/null || echo "unknown")
|
||||
TRIGGERED=false
|
||||
[[ "$NIC_STATE" != "up" ]] && TRIGGERED=true
|
||||
run_strike_check "network" "$TRIGGERED" "${NIC} state: ${NIC_STATE}" && \
|
||||
TRIGGERS+=("nic_down=${NIC}")
|
||||
fi
|
||||
|
||||
# ── sshd — try restart before escalating ─────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_SSHD" == true ]]; then
|
||||
if ! pgrep -x sshd >/dev/null 2>&1; then
|
||||
warn "sshd not running — attempting restart..."
|
||||
if [[ "$DRY_RUN" == false ]]; then
|
||||
/etc/rc.d/rc.sshd start >/dev/null 2>&1
|
||||
sleep 3
|
||||
if pgrep -x sshd >/dev/null 2>&1; then
|
||||
warn "sshd restarted successfully ✅"
|
||||
reset_strikes "sshd"
|
||||
notify "sshd was down on $(hostname) ($MY_ID) — restarted automatically" \
|
||||
"System Watchdog" "warning"
|
||||
else
|
||||
error "sshd restart failed — remote access unavailable"
|
||||
run_strike_check "sshd" true "sshd not running" && \
|
||||
TRIGGERS+=("sshd_down")
|
||||
fi
|
||||
else
|
||||
warn "DRY RUN — would restart sshd"
|
||||
fi
|
||||
else
|
||||
reset_strikes "sshd"
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── Runaway process ───────────────────────────────────────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_RUNAWAY" == true ]]; then
|
||||
RUNAWAY_PCT="${SYS_WATCHDOG_RUNAWAY_CPU_PCT:-90}"
|
||||
TOP_CPU_PCT=$(ps aux 2>/dev/null | awk 'NR>1{print $3}' | sort -rn | head -1)
|
||||
TOP_CPU_INT=$(printf "%.0f" "${TOP_CPU_PCT:-0}")
|
||||
TOP_CPU_NAME=$(ps aux 2>/dev/null | sort -k3 -rn | awk 'NR==2{print $11}')
|
||||
TRIGGERED=false
|
||||
[[ "$TOP_CPU_INT" -ge "$RUNAWAY_PCT" ]] && TRIGGERED=true
|
||||
# Runaway uses SYS_WATCHDOG_RUNAWAY_STRIKES not global strike limit
|
||||
if [[ "$TRIGGERED" == true ]]; then
|
||||
RAWAY_S=$(increment_strikes "runaway")
|
||||
RLIMIT="${SYS_WATCHDOG_RUNAWAY_STRIKES:-3}"
|
||||
warn "Runaway ${TOP_CPU_NAME} ${TOP_CPU_PCT}% CPU -- strike $RAWAY_S/$RLIMIT"
|
||||
if (( RAWAY_S >= RLIMIT )); then
|
||||
error "Runaway process ${TOP_CPU_NAME} -- strike limit hit"
|
||||
reset_strikes "runaway"
|
||||
TRIGGERS+=("runaway=${TOP_CPU_NAME}@${TOP_CPU_PCT}%")
|
||||
fi
|
||||
else
|
||||
RAWAY_CUR=$(get_strikes "runaway")
|
||||
[[ "${RAWAY_CUR:-0}" -gt 0 ]] && reset_strikes "runaway"
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── Required containers from docker_watchdog skip list ────────────────────────────────────
|
||||
if [[ "$SYS_WATCHDOG_CHECK_CONTAINERS" == true ]] && [[ -s "$SYS_WATCHDOG_FAILED_FILE" ]]; then
|
||||
FAILED_CONTAINERS=()
|
||||
while IFS= read -r container; do
|
||||
[[ -z "$container" ]] && continue
|
||||
STATUS=$(timeout "$DOCKER_TIMEOUT" docker inspect -f \
|
||||
'{{.State.Running}}' "$container" 2>/dev/null || echo "unknown")
|
||||
[[ "$STATUS" != "true" ]] && FAILED_CONTAINERS+=("$container")
|
||||
done < "$SYS_WATCHDOG_FAILED_FILE"
|
||||
|
||||
TRIGGERED=false
|
||||
[[ ${#FAILED_CONTAINERS[@]} -gt 0 ]] && TRIGGERED=true
|
||||
run_strike_check "failed_containers" "$TRIGGERED" \
|
||||
"required containers stopped: ${FAILED_CONTAINERS[*]:-}" && \
|
||||
TRIGGERS+=("containers=${FAILED_CONTAINERS[*]:-}")
|
||||
fi
|
||||
|
||||
# ==========================================================================================
|
||||
# ━━━ Evaluate Standard Triggers ━━━
|
||||
# ==========================================================================================
|
||||
if [[ ${#TRIGGERS[@]} -gt 0 ]]; then
|
||||
echo ""
|
||||
echo "━━━ $ICON_REBOOT_SMART System Watchdog — $(date '+%Y-%m-%d %H:%M:%S') ━━━"
|
||||
for t in "${TRIGGERS[@]}"; do
|
||||
echo " $ICON_REBOOT_SMART $t"
|
||||
done
|
||||
[[ "$OOM_DELTA" -gt 0 ]] && echo " OOM kills this run: $OOM_DELTA"
|
||||
echo ""
|
||||
do_reboot "standard" "${TRIGGERS[@]}"
|
||||
exit 0
|
||||
if bash "$script_path"; then
|
||||
log "$script_name — done ✅"
|
||||
PASSED+=("$script_name")
|
||||
else
|
||||
echo "System healthy ✅ ($(date '+%H:%M:%S'))"
|
||||
warn "$script_name — exit non-zero (issues found or fixed) — continuing"
|
||||
FAILED+=("$script_name")
|
||||
fi
|
||||
done
|
||||
|
||||
# Keep state file mtime fresh — docker_watchdog stale guard checks this
|
||||
set_state_val "watchdog_cycle" "$(date +%s)"
|
||||
END=$(date +%s)
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Summary ━━━
|
||||
# ==============================================================================================
|
||||
log "System watchdog — $STEP script(s) — $(format_duration $(( END - START )))"
|
||||
|
||||
[[ ${#FAILED[@]} -gt 0 ]] && exit 1
|
||||
exit 0
|
||||
|
||||
Reference in New Issue
Block a user