Revert orchestrator + skip_list_manager to original folders
watchdog_orchestrator.sh stays in Orchestrators/ — it's an orchestrator, not a watchdog. watchdog_skip_list_manager.sh stays in Tools/ — it's a management utility. Only the 4 watchdog scripts belong in Watchdogs/: docker_watchdog.sh, resource_watchdog.sh, storage_watchdog.sh, system_watchdog.sh
This commit is contained in:
Gmer4Lfe
@@ -0,0 +1,286 @@
|
||||
#!/bin/bash
|
||||
# ==============================================================================================
|
||||
# =========================== Watchdog Skip List Manager =======================================
|
||||
# ==============================================================================================
|
||||
#
|
||||
# PURPOSE
|
||||
# ─────────────────────────────────────────────────────────────────────────────
|
||||
# View and manage the persistent container skip list used by docker_watchdog.sh.
|
||||
# docker_watchdog.sh adds a container to the skip list when it exceeds
|
||||
# WATCHDOG_CONTAINER_RESTART_LIMIT restarts within WATCHDOG_CONTAINER_RESTART_WINDOW
|
||||
# hours — prevents infinite restart loops on containers that keep crashing.
|
||||
#
|
||||
# Skip list persists on /boot/config (survives reboots). Auto-clears when
|
||||
# docker_watchdog.sh sees the container running on a later cycle. Use this
|
||||
# script to clear manually after fixing the underlying problem.
|
||||
#
|
||||
# ==============================================================================================
|
||||
# OPERATIONAL MODEL
|
||||
# ==============================================================================================
|
||||
#
|
||||
# Skip List Lifecycle
|
||||
# 1. Container crashes repeatedly → watchdog adds to skip list, notifies
|
||||
# 2. Watchdog stops restarting the container on subsequent cycles
|
||||
# 3a. If container recovers on its own (Docker restart policy), watchdog
|
||||
# sees it running, removes from skip list automatically
|
||||
# 3b. If stuck stopped → fix the root cause, clear via this script, then
|
||||
# docker start ContainerName manually
|
||||
# 4. Watchdog monitors normally on next cycle. If it crashes again → re-added.
|
||||
#
|
||||
# ==============================================================================================
|
||||
# OPERATIONAL SAFEGUARDS
|
||||
# ==============================================================================================
|
||||
#
|
||||
# Single Instance Lock
|
||||
# acquire_lock prevents concurrent access with docker_watchdog.sh writing
|
||||
# the same files.
|
||||
#
|
||||
# Active Watchdog Detection
|
||||
# Warns if docker_watchdog.sh is currently running when a clear is attempted
|
||||
# — the watchdog could re-add the container to the skip list within seconds.
|
||||
#
|
||||
# Docker Timeout
|
||||
# DOCKER_TIMEOUT caps docker inspect calls against a hung daemon.
|
||||
#
|
||||
# Confirmation Required
|
||||
# Interactive mode prompts for YES before clearing. Use --force for scripts.
|
||||
#
|
||||
# ==============================================================================================
|
||||
# STATE FILES
|
||||
# ==============================================================================================
|
||||
#
|
||||
# SYS_WATCHDOG_FAILED_FILE — persistent container skip list (on /boot/config)
|
||||
# WATCHDOG_CONTAINER_RESTART_LOG — restart history used for loop detection
|
||||
#
|
||||
# ==============================================================================================
|
||||
# RUNTIME MODES
|
||||
# ==============================================================================================
|
||||
#
|
||||
# watchdog_skip_list_manager.sh [--status]
|
||||
# Show skip list, container states, and recent restart history.
|
||||
#
|
||||
# watchdog_skip_list_manager.sh --clear ContainerName
|
||||
# Remove a specific container from the skip list and clear its restart history.
|
||||
# Prompts for YES unless --force is passed.
|
||||
#
|
||||
# watchdog_skip_list_manager.sh --clear-all
|
||||
# Clear all skip lists and all restart history.
|
||||
# Prompts for YES unless --force is passed.
|
||||
#
|
||||
# All actions support --dry-run (show what would change) and --force (skip prompt).
|
||||
#
|
||||
# ==============================================================================================
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
|
||||
source "$SCRIPT_DIR/../load_config.sh"
|
||||
|
||||
DOCKER_TIMEOUT=15
|
||||
|
||||
# ── Parse action flags before parse_args ──────────────────────────────────────────────────────
|
||||
ACTION="status"
|
||||
TARGET_CONTAINER=""
|
||||
FORCE=false
|
||||
FILTERED_ARGS=()
|
||||
|
||||
for arg in "$@"; do
|
||||
case "$arg" in
|
||||
--clear-all) ACTION="clear-all" ;;
|
||||
--clear) ACTION="clear" ;;
|
||||
--status) ACTION="status" ;;
|
||||
--force) FORCE=true ;;
|
||||
*)
|
||||
if [[ "$ACTION" == "clear" && -z "$TARGET_CONTAINER" ]]; then
|
||||
TARGET_CONTAINER="$arg"
|
||||
else
|
||||
FILTERED_ARGS+=("$arg")
|
||||
fi
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
parse_args "${FILTERED_ARGS[@]}"
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Setup ━━━
|
||||
# ==============================================================================================
|
||||
if [[ "$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
|
||||
|
||||
if ! command -v docker &>/dev/null; then
|
||||
error "Docker command not found"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# detect_hosts() sets MY_ID — used in output
|
||||
detect_hosts
|
||||
|
||||
[[ "$DRY_RUN" == true ]] && warn "DRY RUN — no changes will be made"
|
||||
[[ "$FORCE" == true ]] && warn "FORCE mode — confirmation prompt skipped"
|
||||
|
||||
# Ensure state files exist
|
||||
touch "$SYS_WATCHDOG_FAILED_FILE" "$WATCHDOG_CONTAINER_RESTART_LOG" 2>/dev/null
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Status — always shown regardless of action ━━━
|
||||
# ==============================================================================================
|
||||
echo ""
|
||||
echo "━━━ $ICON_WATCHDOG Skip List Status — $MY_ID ━━━"
|
||||
|
||||
SKIP_COUNT=$(grep -c "." "$SYS_WATCHDOG_FAILED_FILE" 2>/dev/null || echo 0)
|
||||
SKIP_COUNT="${SKIP_COUNT//[^0-9]/}"; SKIP_COUNT="${SKIP_COUNT:-0}"
|
||||
RESTART_COUNT=$(wc -l < "$WATCHDOG_CONTAINER_RESTART_LOG" 2>/dev/null || echo 0)
|
||||
RESTART_COUNT="${RESTART_COUNT//[^0-9]/}"; RESTART_COUNT="${RESTART_COUNT:-0}"
|
||||
|
||||
# docker_watchdog.sh running check
|
||||
WATCHDOG_RUNNING=false
|
||||
if pgrep -f "docker_watchdog.sh" >/dev/null 2>&1; then
|
||||
WATCHDOG_RUNNING=true
|
||||
warn "docker_watchdog.sh is currently RUNNING"
|
||||
[[ "$ACTION" != "status" ]] && \
|
||||
warn "Clearing during an active cycle — watchdog may re-add container on next iteration"
|
||||
fi
|
||||
|
||||
echo ""
|
||||
if [[ "$SKIP_COUNT" -eq 0 ]]; then
|
||||
echo "Skip list: empty — all containers monitored normally ✅"
|
||||
else
|
||||
warn "$SKIP_COUNT container(s) on skip list — manual intervention needed:"
|
||||
echo ""
|
||||
while IFS= read -r container; do
|
||||
[[ -z "$container" ]] && continue
|
||||
STATUS=$(timeout "$DOCKER_TIMEOUT" docker inspect -f \
|
||||
'{{.State.Running}}' "$container" 2>/dev/null || echo "unknown")
|
||||
case "$STATUS" in
|
||||
true)
|
||||
echo " $ICON_RUNNING $container — RUNNING (watchdog will auto-clear next cycle)"
|
||||
;;
|
||||
false)
|
||||
echo " $ICON_NOT_RUNNING $container — STOPPED — fix and start manually"
|
||||
;;
|
||||
*)
|
||||
echo " $ICON_WARN $container — not found on this server"
|
||||
;;
|
||||
esac
|
||||
done < "$SYS_WATCHDOG_FAILED_FILE"
|
||||
fi
|
||||
|
||||
echo ""
|
||||
echo "━━━ $ICON_WATCHDOG Restart History ━━━"
|
||||
if [[ "$RESTART_COUNT" -eq 0 ]]; then
|
||||
echo "No restart history"
|
||||
else
|
||||
echo "$RESTART_COUNT restart entries (window: ${WATCHDOG_CONTAINER_RESTART_WINDOW}h)"
|
||||
echo ""
|
||||
awk -F'|' '{counts[$1]++} END {
|
||||
for (c in counts)
|
||||
printf " %-30s %d restart(s)\n", c, counts[c]
|
||||
}' "$WATCHDOG_CONTAINER_RESTART_LOG" 2>/dev/null | sort
|
||||
fi
|
||||
|
||||
[[ "$ACTION" == "status" ]] && exit 0
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Clear All ━━━
|
||||
# ==============================================================================================
|
||||
if [[ "$ACTION" == "clear-all" ]]; then
|
||||
echo ""
|
||||
echo "━━━ $ICON_TRASH Clear All Skip Lists ━━━"
|
||||
warn "This will clear the skip list and restart history for ALL containers"
|
||||
echo ""
|
||||
|
||||
if [[ "$DRY_RUN" == false ]]; then
|
||||
if [[ "$FORCE" == true ]]; then
|
||||
log "FORCE flag set — skipping confirmation"
|
||||
elif [[ -t 0 ]]; then
|
||||
read -r -p "Type YES to confirm: " CONFIRM
|
||||
if [[ "$CONFIRM" != "YES" ]]; then
|
||||
warn "Cancelled"
|
||||
exit 0
|
||||
fi
|
||||
else
|
||||
error "Non-interactive mode — use --force flag to skip confirmation"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
> "$SYS_WATCHDOG_FAILED_FILE"
|
||||
> "$WATCHDOG_CONTAINER_RESTART_LOG"
|
||||
warn "Skip list cleared ✅"
|
||||
warn "Restart history cleared ✅"
|
||||
[[ "$WATCHDOG_RUNNING" == true ]] && \
|
||||
warn "Note: watchdog is running — containers will be monitored on next cycle"
|
||||
notify "Watchdog skip list cleared on $(hostname) ($MY_ID) — all containers will be monitored normally" \
|
||||
"Watchdog Manager" "warning"
|
||||
else
|
||||
warn "DRY RUN — would clear: $SYS_WATCHDOG_FAILED_FILE"
|
||||
warn "DRY RUN — would clear: $WATCHDOG_CONTAINER_RESTART_LOG"
|
||||
fi
|
||||
fi
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Clear Specific Container ━━━
|
||||
# ==============================================================================================
|
||||
if [[ "$ACTION" == "clear" ]]; then
|
||||
echo ""
|
||||
echo "━━━ $ICON_TRASH Clear Container: $TARGET_CONTAINER ━━━"
|
||||
|
||||
if [[ -z "$TARGET_CONTAINER" ]]; then
|
||||
error "No container specified"
|
||||
error "Usage: watchdog_skip_list_manager.sh --clear ContainerName"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Remove from skip list
|
||||
if ! grep -q "^${TARGET_CONTAINER}$" "$SYS_WATCHDOG_FAILED_FILE" 2>/dev/null; then
|
||||
warn "$TARGET_CONTAINER is not on the skip list"
|
||||
else
|
||||
if [[ "$DRY_RUN" == false ]]; then
|
||||
sed -i "/^${TARGET_CONTAINER}$/d" "$SYS_WATCHDOG_FAILED_FILE"
|
||||
warn "$TARGET_CONTAINER removed from skip list ✅"
|
||||
else
|
||||
warn "DRY RUN — would remove $TARGET_CONTAINER from skip list"
|
||||
fi
|
||||
fi
|
||||
|
||||
# Clear restart history for this container
|
||||
HIST_COUNT=$(grep -c "^${TARGET_CONTAINER}|" \
|
||||
"$WATCHDOG_CONTAINER_RESTART_LOG" 2>/dev/null || echo 0)
|
||||
HIST_COUNT="${HIST_COUNT//[^0-9]/}"; HIST_COUNT="${HIST_COUNT:-0}"
|
||||
|
||||
if [[ "$HIST_COUNT" -gt 0 ]]; then
|
||||
if [[ "$DRY_RUN" == false ]]; then
|
||||
sed -i "/^${TARGET_CONTAINER}|/d" "$WATCHDOG_CONTAINER_RESTART_LOG"
|
||||
warn "Cleared $HIST_COUNT restart history entries for $TARGET_CONTAINER ✅"
|
||||
else
|
||||
warn "DRY RUN — would clear $HIST_COUNT restart history entries"
|
||||
fi
|
||||
else
|
||||
log "No restart history for $TARGET_CONTAINER"
|
||||
fi
|
||||
|
||||
[[ "$WATCHDOG_RUNNING" == true ]] && \
|
||||
warn "Note: watchdog is running — $TARGET_CONTAINER may be re-added if still failing"
|
||||
|
||||
if [[ "$DRY_RUN" == false ]]; then
|
||||
echo ""
|
||||
echo "━━━ $ICON_INFO Next Steps ━━━"
|
||||
echo " 1. Fix whatever was causing $TARGET_CONTAINER to fail"
|
||||
echo " 2. Start it manually: docker start $TARGET_CONTAINER"
|
||||
echo " 3. docker_watchdog.sh monitors it on the next cycle"
|
||||
echo " 4. If it crashes again → watchdog adds it back and notifies"
|
||||
notify "$TARGET_CONTAINER cleared from watchdog skip list on $(hostname) ($MY_ID)" \
|
||||
"Watchdog Manager" "warning"
|
||||
fi
|
||||
fi
|
||||
|
||||
echo ""
|
||||
echo "━━━━━ $ICON_SUMMARY DONE — $MY_ID ━━━━━"
|
||||
Reference in New Issue
Block a user