feat: watchdog architecture v2 — resource manager + single-pass orchestrator
Introduce a four-layer self-healing stack replacing the continuous-loop watchdogs: - resource_manager.sh (new): single-pass pressure reduction layer; throttles SABnzbd/qBit at level 1, docker-pauses background containers at level 2, docker-stops optional containers and signals docker_watchdog to defer at level 3; graduated recovery with hysteresis - watchdog_orchestrator.sh (new, Orchestrators/): runs resource_manager → docker_watchdog → system_watchdog in sequence; intended for per-minute cron via User Scripts; startup grace, acquire_lock to prevent pile-up, heartbeat - docker_watchdog.sh: de-looped to single-pass; daemon strikes persisted to state file across runs; cross-script coordination reads RM_STATE_FILE instead of SYS_WATCHDOG_STATE_FILE - system_watchdog.sh: de-looped to single-pass; stripped of all container management (shutdown_non_essential_containers removed); reboot-only last resort - master.conf: removed system_watchdog and docker_watchdog from ARRAY_START_SCRIPTS; added WATCHDOG ORCHESTRATOR and RESOURCE MANAGER sections - master_host1.conf: added RM_PAUSE_CONTAINERS and RM_STOP_CONTAINERS arrays - common.sh: aliased RM_PAUSE_CONTAINERS and RM_STOP_CONTAINERS via detect_hosts() - continuous_scripts_status.sh: moved to Tools/ (preserved for future use) - sunday_morning_coffee_report.sh: watchdog section updated to use state file mtime checks instead of is_running; added Resource Manager subsection; fixed mem_shutdown grep filter pointing to wrong state file Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Gmer4Lfe
co-authored by
Claude Sonnet 4.6
Claude Sonnet 4.6
parent
f16c962ac0
commit
309546e615
@@ -0,0 +1,501 @@
|
||||
#!/bin/bash
|
||||
# ==============================================================================================
|
||||
# ========================= Continuous Scripts Status ==========================================
|
||||
# ==============================================================================================
|
||||
# Live status dashboard for all continuously running scripts in the ecosystem.
|
||||
# Run manually anytime — no schedule, no cron.
|
||||
#
|
||||
# ── WHAT IT SHOWS ─────────────────────────────────────────────────────────────────────────────
|
||||
# For each continuous script (system_watchdog, docker_watchdog, failover):
|
||||
# Running state, PID, uptime, approximate cycle count
|
||||
# Active strikes and skip list
|
||||
# Recent restart history
|
||||
# Live health snapshot
|
||||
#
|
||||
# system_watchdog — rootfs, RAM, ZFS ARC, load, zombie count, CPU temp
|
||||
# docker_watchdog — running/stopped/unhealthy containers, required containers,
|
||||
# monitored memory containers, recent restart history
|
||||
# failover — current state, tier status, remote Tailscale visibility
|
||||
#
|
||||
# If a script is mid-cycle, state files are read as-is — reflects last completed cycle.
|
||||
#
|
||||
# ── HOST AWARENESS ────────────────────────────────────────────────────────────────────────────
|
||||
# detect_hosts() sets MY_ID and aliases all HOST*_WATCHDOG_* arrays.
|
||||
# Required containers and tier delays use MY_ID/REMOTE_ID correctly.
|
||||
#
|
||||
# ── USAGE ─────────────────────────────────────────────────────────────────────────────────────
|
||||
# continuous_scripts_status.sh — show dashboard
|
||||
# continuous_scripts_status.sh --log — verbose output
|
||||
# ==============================================================================================
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
|
||||
source "$SCRIPT_DIR/../load_config.sh"
|
||||
|
||||
# Dashboard script — output is the point
|
||||
SILENT_MODE=false
|
||||
|
||||
parse_args "$@"
|
||||
|
||||
DOCKER_TIMEOUT=15
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Setup ━━━
|
||||
# ==============================================================================================
|
||||
if [[ "$EUID" -ne 0 ]]; then
|
||||
error "Must be run as root"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# detect_hosts() sets MY_ID and aliases all HOST*_WATCHDOG_* arrays
|
||||
detect_hosts
|
||||
|
||||
# ==============================================================================================
|
||||
# ── HELPER FUNCTIONS ──────────────────────────────────────────────────────────────────────────
|
||||
# ==============================================================================================
|
||||
|
||||
get_lock_pid() {
|
||||
local script_name="$1"
|
||||
local lockfile="$LOCK_DIR/${script_name}.lock"
|
||||
if [[ -f "$lockfile" ]]; then
|
||||
local content
|
||||
content=$(cat "$lockfile" 2>/dev/null)
|
||||
echo "${content%%:*}"
|
||||
fi
|
||||
}
|
||||
|
||||
get_lock_name() {
|
||||
local script_name="$1"
|
||||
local lockfile="$LOCK_DIR/${script_name}.lock"
|
||||
if [[ -f "$lockfile" ]]; then
|
||||
local content
|
||||
content=$(cat "$lockfile" 2>/dev/null)
|
||||
echo "${content##*:}"
|
||||
fi
|
||||
}
|
||||
|
||||
is_script_running() {
|
||||
local script_name="$1"
|
||||
local pid locked_name
|
||||
pid=$(get_lock_pid "$script_name")
|
||||
locked_name=$(get_lock_name "$script_name")
|
||||
[[ -n "$pid" ]] && kill -0 "$pid" 2>/dev/null && [[ "$locked_name" == "$script_name" ]]
|
||||
}
|
||||
|
||||
get_lock_age() {
|
||||
local script_name="$1"
|
||||
local lockfile="$LOCK_DIR/${script_name}.lock"
|
||||
if [[ -f "$lockfile" ]]; then
|
||||
local mtime now
|
||||
mtime=$(stat -c %Y "$lockfile" 2>/dev/null || echo 0)
|
||||
now=$(date +%s)
|
||||
echo $(( now - mtime ))
|
||||
else
|
||||
echo 0
|
||||
fi
|
||||
}
|
||||
|
||||
# Human readable uptime — days/hours/mins
|
||||
format_uptime() {
|
||||
local seconds=$1
|
||||
local days=$(( seconds / 86400 ))
|
||||
local hours=$(( (seconds % 86400) / 3600 ))
|
||||
local mins=$(( (seconds % 3600) / 60 ))
|
||||
if (( days > 0 )); then
|
||||
echo "${days}d ${hours}h ${mins}m"
|
||||
elif (( hours > 0 )); then
|
||||
echo "${hours}h ${mins}m"
|
||||
else
|
||||
echo "${mins}m"
|
||||
fi
|
||||
}
|
||||
|
||||
divider() { printf '%.0s─' {1..57}; echo; }
|
||||
section() { echo ""; echo " $1"; divider; }
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Header ━━━
|
||||
# ==============================================================================================
|
||||
clear
|
||||
echo ""
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo " 🛡️ WATCHDOG STATUS — $(date '+%A, %B %-d at %-I:%M%p')"
|
||||
echo " $ICON_HOST $MY_ID — $LOCAL_SERVER_NAME"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ System Watchdog ━━━
|
||||
# ==============================================================================================
|
||||
section "⚙️ SYSTEM WATCHDOG"
|
||||
|
||||
SYS_PID=$(get_lock_pid "system_watchdog")
|
||||
SYS_RUNNING=false
|
||||
|
||||
if is_script_running "system_watchdog"; then
|
||||
SYS_RUNNING=true
|
||||
SYS_AGE=$(get_lock_age "system_watchdog")
|
||||
SYS_UPTIME=$(format_uptime "$SYS_AGE")
|
||||
SYS_CYCLE=$(( SYS_AGE / SYSTEM_WATCHDOG_INTERVAL ))
|
||||
echo " ✅ Running │ PID: $SYS_PID │ Uptime: $SYS_UPTIME │ ~Cycle: $SYS_CYCLE"
|
||||
echo " ⏱️ Interval: ${SYSTEM_WATCHDOG_INTERVAL}s │ Heartbeat every: ${SYSTEM_WATCHDOG_HEARTBEAT_HOURS}hr"
|
||||
else
|
||||
echo " ❌ NOT RUNNING — system_watchdog.sh is not active"
|
||||
echo " Start via: bash Orchestrators/array_started.sh"
|
||||
fi
|
||||
|
||||
echo ""
|
||||
|
||||
# System strikes
|
||||
if [[ -f "$SYS_WATCHDOG_STATE_FILE" ]]; then
|
||||
ACTIVE_STRIKES=$(grep -v ":0$" "$SYS_WATCHDOG_STATE_FILE" 2>/dev/null | grep -v "^$")
|
||||
if [[ -n "$ACTIVE_STRIKES" ]]; then
|
||||
echo " ⚠️ Active strikes:"
|
||||
while IFS=: read -r key count; do
|
||||
[[ -z "$key" ]] && continue
|
||||
echo " → $key: $count/$SYS_WATCHDOG_STRIKE_LIMIT"
|
||||
done <<< "$ACTIVE_STRIKES"
|
||||
else
|
||||
echo " ✅ Strikes: none"
|
||||
fi
|
||||
else
|
||||
echo " ℹ️ Strike state file not found (watchdog may not have run yet)"
|
||||
fi
|
||||
|
||||
# Reboot log
|
||||
if [[ -f "$SYS_WATCHDOG_REBOOT_LOG" ]]; then
|
||||
TOTAL_REBOOTS=$(grep -c "." "$SYS_WATCHDOG_REBOOT_LOG" 2>/dev/null || echo 0)
|
||||
TOTAL_REBOOTS="${TOTAL_REBOOTS//[^0-9]/}"
|
||||
TOTAL_REBOOTS="${TOTAL_REBOOTS:-0}"
|
||||
WEEK_CUTOFF=$(date -d "7 days ago" '+%Y-%m-%d %H:%M:%S')
|
||||
WEEK_REBOOTS=$(awk -v cutoff="$WEEK_CUTOFF" '$0 >= cutoff' \
|
||||
"$SYS_WATCHDOG_REBOOT_LOG" 2>/dev/null | wc -l)
|
||||
echo " 🔄 Watchdog reboots: $WEEK_REBOOTS this week / $TOTAL_REBOOTS total"
|
||||
fi
|
||||
|
||||
# Container skip list
|
||||
if [[ -f "$SYS_WATCHDOG_FAILED_FILE" ]] && [[ -s "$SYS_WATCHDOG_FAILED_FILE" ]]; then
|
||||
SKIP_COUNT=$(wc -l < "$SYS_WATCHDOG_FAILED_FILE")
|
||||
echo ""
|
||||
echo " ⛔ Skip list ($SKIP_COUNT — manual intervention needed):"
|
||||
while IFS= read -r container; do
|
||||
[[ -z "$container" ]] && continue
|
||||
echo " → $container"
|
||||
done < "$SYS_WATCHDOG_FAILED_FILE"
|
||||
else
|
||||
echo " ✅ Skip list: empty"
|
||||
fi
|
||||
|
||||
# Live system health snapshot
|
||||
echo ""
|
||||
echo " 📊 Current system state:"
|
||||
|
||||
ROOTFS_PCT=$(df / --output=pcent 2>/dev/null | tail -1 | tr -d ' %')
|
||||
[[ "${ROOTFS_PCT:-0}" -ge "${SYS_WATCHDOG_ROOTFS_PCT:-95}" ]] && \
|
||||
ROOTFS_ICON="⚠️ " || ROOTFS_ICON="✅"
|
||||
echo " ${ROOTFS_ICON} rootfs: ${ROOTFS_PCT}% (threshold: ${SYS_WATCHDOG_ROOTFS_PCT}%)"
|
||||
|
||||
MEM_AVAIL_KB=$(awk '/MemAvailable/ {print $2}' /proc/meminfo)
|
||||
MEM_FREE_GB=$(awk "BEGIN {printf \"%.1f\", $MEM_AVAIL_KB / 1048576}")
|
||||
MEM_TOTAL_GB=$(awk '/MemTotal/ {printf "%.0f", $2/1048576}' /proc/meminfo)
|
||||
[[ $(printf "%.0f" "$MEM_FREE_GB") -lt "${SYS_WATCHDOG_MEM_GB:-4}" ]] && \
|
||||
MEM_ICON="⚠️ " || MEM_ICON="✅"
|
||||
echo " ${MEM_ICON} RAM: ${MEM_FREE_GB}GB free / ${MEM_TOTAL_GB}GB total (threshold: ${SYS_WATCHDOG_MEM_GB}GB free)"
|
||||
|
||||
if [[ -f /proc/spl/kstat/zfs/arcstats ]]; then
|
||||
ARC_SIZE=$(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 ))
|
||||
ARC_GB=$(awk "BEGIN {printf \"%.1f\", $ARC_SIZE / 1073741824}")
|
||||
[[ "$ARC_PCT" -ge "${SYS_WATCHDOG_ARC_PINNED_PCT:-98}" ]] && \
|
||||
ARC_ICON="⚠️ " || ARC_ICON="✅"
|
||||
echo " ${ARC_ICON} ZFS ARC: ${ARC_GB}GB (${ARC_PCT}% of max, threshold: ${SYS_WATCHDOG_ARC_PINNED_PCT}%)"
|
||||
fi
|
||||
|
||||
LOAD=$(awk '{print $1}' /proc/loadavg)
|
||||
CORES=$(nproc)
|
||||
LOAD_THRESH=$(( CORES * ${SYS_WATCHDOG_LOAD_MULTIPLIER:-3} ))
|
||||
LOAD_INT=$(printf "%.0f" "$LOAD")
|
||||
[[ "$LOAD_INT" -ge "$LOAD_THRESH" ]] && LOAD_ICON="⚠️ " || LOAD_ICON="✅"
|
||||
echo " ${LOAD_ICON} Load avg: $LOAD (threshold: ${LOAD_THRESH} = ${SYS_WATCHDOG_LOAD_MULTIPLIER}x ${CORES} cores)"
|
||||
|
||||
ZOMBIE_COUNT=$(ps aux | awk '{print $8}' | grep -c "^Z$" 2>/dev/null || echo 0)
|
||||
ZOMBIE_COUNT="${ZOMBIE_COUNT//[^0-9]/}"
|
||||
ZOMBIE_COUNT="${ZOMBIE_COUNT:-0}"
|
||||
[[ "$ZOMBIE_COUNT" -ge "${SYS_WATCHDOG_ZOMBIE_LIMIT:-50}" ]] && \
|
||||
ZOMBIE_ICON="⚠️ " || ZOMBIE_ICON="✅"
|
||||
echo " ${ZOMBIE_ICON} Zombies: $ZOMBIE_COUNT (threshold: ${SYS_WATCHDOG_ZOMBIE_LIMIT})"
|
||||
|
||||
if command -v sensors >/dev/null 2>&1; then
|
||||
CPU_TEMP=$(sensors 2>/dev/null | \
|
||||
grep -i "Package id 0\|Tctl\|CPU Temp" | \
|
||||
awk '{print $NF}' | tr -d '+°C' | head -1)
|
||||
if [[ -n "$CPU_TEMP" ]]; then
|
||||
CPU_TEMP_INT=$(printf "%.0f" "$CPU_TEMP")
|
||||
[[ "$CPU_TEMP_INT" -ge "${SYS_WATCHDOG_CPU_TEMP_MAX:-95}" ]] && \
|
||||
TEMP_ICON="⚠️ " || TEMP_ICON="✅"
|
||||
echo " ${TEMP_ICON} CPU temp: ${CPU_TEMP_INT}°C (threshold: ${SYS_WATCHDOG_CPU_TEMP_MAX}°C)"
|
||||
fi
|
||||
fi
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Docker Watchdog ━━━
|
||||
# ==============================================================================================
|
||||
section "🐳 DOCKER WATCHDOG"
|
||||
|
||||
DOCKER_PID=$(get_lock_pid "docker_watchdog")
|
||||
DOCKER_RUNNING=false
|
||||
|
||||
if is_script_running "docker_watchdog"; then
|
||||
DOCKER_RUNNING=true
|
||||
DOCKER_AGE=$(get_lock_age "docker_watchdog")
|
||||
DOCKER_UPTIME=$(format_uptime "$DOCKER_AGE")
|
||||
DOCKER_CYCLE=$(( DOCKER_AGE / DOCKER_WATCHDOG_INTERVAL ))
|
||||
echo " ✅ Running │ PID: $DOCKER_PID │ Uptime: $DOCKER_UPTIME │ ~Cycle: $DOCKER_CYCLE"
|
||||
echo " ⏱️ Interval: ${DOCKER_WATCHDOG_INTERVAL}s │ Heartbeat every: ${DOCKER_WATCHDOG_HEARTBEAT_HOURS}hr"
|
||||
else
|
||||
echo " ❌ NOT RUNNING — docker_watchdog.sh is not active"
|
||||
echo " Start via: bash Orchestrators/array_started.sh"
|
||||
fi
|
||||
|
||||
echo ""
|
||||
|
||||
# Container strikes
|
||||
if [[ -f "$WATCHDOG_STATE_FILE" ]]; then
|
||||
ACTIVE_CONTAINER_STRIKES=$(grep -v ":0$" "$WATCHDOG_STATE_FILE" 2>/dev/null | grep -v "^$")
|
||||
if [[ -n "$ACTIVE_CONTAINER_STRIKES" ]]; then
|
||||
echo " ⚠️ Active container strikes:"
|
||||
while IFS=: read -r key count; do
|
||||
[[ -z "$key" ]] && continue
|
||||
echo " → $key: $count"
|
||||
done <<< "$ACTIVE_CONTAINER_STRIKES"
|
||||
else
|
||||
echo " ✅ Container strikes: none"
|
||||
fi
|
||||
fi
|
||||
|
||||
# Container restart history
|
||||
if [[ -f "$WATCHDOG_CONTAINER_RESTART_LOG" ]]; then
|
||||
WEEK_CUTOFF=$(date -d "7 days ago" '+%Y-%m-%d %H:%M:%S')
|
||||
WEEK_RESTARTS=$(awk -F'|' -v cutoff="$WEEK_CUTOFF" \
|
||||
'$2 >= cutoff' "$WATCHDOG_CONTAINER_RESTART_LOG" 2>/dev/null | wc -l)
|
||||
if [[ "${WEEK_RESTARTS:-0}" -gt 0 ]]; then
|
||||
echo ""
|
||||
echo " 🔄 Container restarts this week: $WEEK_RESTARTS"
|
||||
awk -F'|' -v cutoff="$WEEK_CUTOFF" \
|
||||
'$2 >= cutoff {print $1}' "$WATCHDOG_CONTAINER_RESTART_LOG" 2>/dev/null | \
|
||||
sort | uniq -c | sort -rn | head -5 | \
|
||||
while read -r count name; do
|
||||
echo " → $name: $count restart(s)"
|
||||
done
|
||||
else
|
||||
echo " ✅ Container restarts this week: none"
|
||||
fi
|
||||
fi
|
||||
|
||||
# Container overview
|
||||
echo ""
|
||||
echo " 📦 Container overview:"
|
||||
|
||||
if command -v docker >/dev/null 2>&1; then
|
||||
RUNNING=$(timeout "$DOCKER_TIMEOUT" docker ps -q 2>/dev/null | wc -l)
|
||||
TOTAL=$(timeout "$DOCKER_TIMEOUT" docker ps -aq 2>/dev/null | wc -l)
|
||||
UNHEALTHY=$(timeout "$DOCKER_TIMEOUT" docker ps \
|
||||
--filter health=unhealthy -q 2>/dev/null | wc -l)
|
||||
|
||||
# Stopped containers — bucket into clean vs unexpected, skip SCAN_IGNORE entirely
|
||||
CLEAN_STOPPED=()
|
||||
UNEXPECTED_STOPPED=()
|
||||
while IFS= read -r name; do
|
||||
[[ -z "$name" ]] && continue
|
||||
SKIP=false
|
||||
for ignore in "${WATCHDOG_SCAN_IGNORE[@]}"; do
|
||||
[[ "$name" == "$ignore" ]] && SKIP=true && break
|
||||
done
|
||||
[[ "$SKIP" == true ]] && continue
|
||||
exit_code=$(docker inspect --format '{{.State.ExitCode}}' "$name" 2>/dev/null)
|
||||
if [[ "$exit_code" == "0" || "$exit_code" == "143" ]]; then
|
||||
CLEAN_STOPPED+=("$name")
|
||||
else
|
||||
UNEXPECTED_STOPPED+=("$name")
|
||||
fi
|
||||
done < <(timeout "$DOCKER_TIMEOUT" docker ps -af "status=exited" \
|
||||
--format "{{.Names}}" 2>/dev/null)
|
||||
|
||||
echo " Running: $RUNNING / $TOTAL total"
|
||||
[[ "$UNHEALTHY" -gt 0 ]] && echo " ⚠️ Unhealthy: $UNHEALTHY"
|
||||
|
||||
if [[ "${#UNEXPECTED_STOPPED[@]}" -gt 0 ]]; then
|
||||
echo " ⚠️ Stopped (unexpected):"
|
||||
for name in "${UNEXPECTED_STOPPED[@]}"; do
|
||||
echo " → $name"
|
||||
done
|
||||
fi
|
||||
|
||||
if [[ "${#CLEAN_STOPPED[@]}" -gt 0 ]]; then
|
||||
echo " ⏸️ Stopped (clean):"
|
||||
for name in "${CLEAN_STOPPED[@]}"; do
|
||||
echo " → $name"
|
||||
done
|
||||
fi
|
||||
|
||||
if [[ "${#UNEXPECTED_STOPPED[@]}" -eq 0 && "${#CLEAN_STOPPED[@]}" -eq 0 ]]; then
|
||||
echo " ✅ All containers running"
|
||||
fi
|
||||
|
||||
# Required containers — aliased by detect_hosts() → WATCHDOG_REQUIRED_CONTAINERS
|
||||
REQUIRED_ISSUES=0
|
||||
if [[ ${#WATCHDOG_REQUIRED_CONTAINERS[@]} -gt 0 ]]; then
|
||||
echo ""
|
||||
echo " 🔐 Required containers:"
|
||||
for container in "${WATCHDOG_REQUIRED_CONTAINERS[@]}"; do
|
||||
[[ -z "$container" ]] && continue
|
||||
STATUS=$(timeout "$DOCKER_TIMEOUT" docker inspect -f \
|
||||
'{{.State.Running}}' "$container" 2>/dev/null || echo "not found")
|
||||
if [[ "$STATUS" == "true" ]]; then
|
||||
echo " ✅ $container"
|
||||
else
|
||||
echo " ❌ $container — $STATUS"
|
||||
(( REQUIRED_ISSUES++ ))
|
||||
fi
|
||||
done
|
||||
fi
|
||||
|
||||
# Memory-monitored containers — aliased by detect_hosts() → WATCHDOG_CONTAINERS
|
||||
if [[ ${#WATCHDOG_CONTAINERS[@]} -gt 0 ]]; then
|
||||
echo ""
|
||||
echo " 📊 Monitored containers (memory):"
|
||||
for container in "${!WATCHDOG_CONTAINERS[@]}"; do
|
||||
LIMIT_MB="${WATCHDOG_CONTAINERS[$container]}"
|
||||
LIMIT_GB=$(awk "BEGIN {printf \"%.0f\", $LIMIT_MB / 1024}")
|
||||
USAGE=$(timeout "$DOCKER_TIMEOUT" docker stats --no-stream \
|
||||
--format "{{.MemUsage}}" "$container" 2>/dev/null | awk '{print $1}')
|
||||
STATUS=$(timeout "$DOCKER_TIMEOUT" docker inspect -f \
|
||||
'{{.State.Running}}' "$container" 2>/dev/null || echo "not found")
|
||||
if [[ "$STATUS" == "true" ]]; then
|
||||
echo " ✅ $container: ${USAGE:-?} (limit: ${LIMIT_GB}GB)"
|
||||
else
|
||||
echo " ❌ $container: not running (limit: ${LIMIT_GB}GB)"
|
||||
fi
|
||||
done
|
||||
fi
|
||||
else
|
||||
echo " Docker not available"
|
||||
fi
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Failover ━━━
|
||||
# ==============================================================================================
|
||||
section "🔀 FALLBACK"
|
||||
|
||||
FALLBACK_PID=$(get_lock_pid "fallback")
|
||||
FALLBACK_RUNNING=false
|
||||
|
||||
if is_script_running "fallback"; then
|
||||
FALLBACK_RUNNING=true
|
||||
FALLBACK_AGE=$(get_lock_age "fallback")
|
||||
FALLBACK_UPTIME=$(format_uptime "$FALLBACK_AGE")
|
||||
echo " ✅ Running │ PID: $FALLBACK_PID │ Uptime: $FALLBACK_UPTIME"
|
||||
else
|
||||
if [[ "${FALLBACK_ENABLED:-true}" == false ]]; then
|
||||
echo " ⏸️ Disabled — FALLBACK_ENABLED=false in master.conf"
|
||||
else
|
||||
echo " ❌ NOT RUNNING — fallback.sh is not active"
|
||||
echo " Start via: bash Orchestrators/array_started.sh"
|
||||
fi
|
||||
fi
|
||||
|
||||
echo ""
|
||||
|
||||
# Fallback state
|
||||
FALLBACK_STATE="UNKNOWN"
|
||||
FALLBACK_STATE_SECONDS=0
|
||||
|
||||
if [[ -f "$FALLBACK_STATE_FILE" ]]; then
|
||||
FALLBACK_STATE=$(grep "^state=" "$FALLBACK_STATE_FILE" 2>/dev/null | cut -d= -f2)
|
||||
FALLBACK_LAST_EPOCH=$(grep "^fallback_start=" "$FALLBACK_STATE_FILE" \
|
||||
2>/dev/null | cut -d= -f2)
|
||||
if [[ -n "$FALLBACK_LAST_EPOCH" && "$FALLBACK_LAST_EPOCH" -gt 0 ]]; then
|
||||
FALLBACK_STATE_SECONDS=$(( $(date +%s) - FALLBACK_LAST_EPOCH ))
|
||||
fi
|
||||
fi
|
||||
|
||||
STATE_DURATION=$(format_uptime "${FALLBACK_STATE_SECONDS:-0}")
|
||||
|
||||
# Tier delays via REMOTE_ID — same logic as fallback.sh
|
||||
REMOTE_TIER2_VAR="${REMOTE_ID}_TIER2_DELAY"
|
||||
REMOTE_TIER3_VAR="${REMOTE_ID}_TIER3_DELAY"
|
||||
REMOTE_TIER4_VAR="${REMOTE_ID}_TIER4_DELAY"
|
||||
TIER2_DELAY="${!REMOTE_TIER2_VAR:-240}"
|
||||
TIER3_DELAY="${!REMOTE_TIER3_VAR:-720}"
|
||||
TIER4_DELAY="${!REMOTE_TIER4_VAR:-1440}"
|
||||
|
||||
case "$FALLBACK_STATE" in
|
||||
NORMAL)
|
||||
echo " ✅ State: NORMAL"
|
||||
;;
|
||||
FALLBACK)
|
||||
echo " ⚠️ State: FALLBACK — $REMOTE_SERVER_NAME is down"
|
||||
echo " ⏱️ Duration: $STATE_DURATION"
|
||||
FALLBACK_MINS=$(( FALLBACK_STATE_SECONDS / 60 ))
|
||||
echo ""
|
||||
echo " 🔄 Tier status:"
|
||||
echo " Tier 1 (immediate): ✅ active"
|
||||
if (( FALLBACK_MINS >= TIER2_DELAY )); then
|
||||
echo " Tier 2 (${TIER2_DELAY}min): ✅ active"
|
||||
else
|
||||
REMAINING=$(( TIER2_DELAY - FALLBACK_MINS ))
|
||||
echo " Tier 2 (${TIER2_DELAY}min): ⏳ in ${REMAINING}min"
|
||||
fi
|
||||
if (( FALLBACK_MINS >= TIER3_DELAY )); then
|
||||
echo " Tier 3 (${TIER3_DELAY}min): ✅ active"
|
||||
else
|
||||
REMAINING=$(( TIER3_DELAY - FALLBACK_MINS ))
|
||||
echo " Tier 3 (${TIER3_DELAY}min): ⏳ in ${REMAINING}min"
|
||||
fi
|
||||
if (( FALLBACK_MINS >= TIER4_DELAY )); then
|
||||
echo " Tier 4 (${TIER4_DELAY}min): ✅ active"
|
||||
else
|
||||
REMAINING=$(( TIER4_DELAY - FALLBACK_MINS ))
|
||||
echo " Tier 4 (${TIER4_DELAY}min): ⏳ in ${REMAINING}min"
|
||||
fi
|
||||
;;
|
||||
NO_INTERNET)
|
||||
echo " ❌ State: NO_INTERNET — DDNS stopped"
|
||||
echo " ⏱️ Down for: $STATE_DURATION"
|
||||
;;
|
||||
DARK)
|
||||
echo " ❌ State: DARK — $REMOTE_SERVER_NAME down AND no internet"
|
||||
echo " ⏱️ Duration: $STATE_DURATION"
|
||||
;;
|
||||
*)
|
||||
echo " ❓ State: ${FALLBACK_STATE:-unknown}"
|
||||
;;
|
||||
esac
|
||||
|
||||
|
||||
echo " 📡 Check interval: ${FALLBACK_CHECK_INTERVAL}s │ Handback strikes: ${FALLBACK_HANDBACK_STRIKES}"
|
||||
|
||||
# ==============================================================================================
|
||||
# ━━━ Footer ━━━
|
||||
# ==============================================================================================
|
||||
echo ""
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
ISSUES=0
|
||||
[[ "$SYS_RUNNING" == false ]] && (( ISSUES++ ))
|
||||
[[ "$DOCKER_RUNNING" == false ]] && (( ISSUES++ ))
|
||||
[[ "$FALLBACK_RUNNING" == false && "${FALLBACK_ENABLED:-true}" != false ]] && (( ISSUES++ ))
|
||||
[[ -n "$ACTIVE_STRIKES" ]] && (( ISSUES++ ))
|
||||
[[ -n "$ACTIVE_CONTAINER_STRIKES" ]] && (( ISSUES++ ))
|
||||
[[ "${REQUIRED_ISSUES:-0}" -gt 0 ]] && (( ISSUES++ ))
|
||||
[[ "$FALLBACK_STATE" != "NORMAL" && "$FALLBACK_STATE" != "UNKNOWN" ]] && (( ISSUES++ ))
|
||||
|
||||
if [[ "$ISSUES" -eq 0 ]]; then
|
||||
echo " ✅ $MY_ID — all continuous scripts healthy"
|
||||
else
|
||||
echo " ⚠️ $ISSUES issue(s) detected — review above"
|
||||
fi
|
||||
|
||||
echo " 🕐 Checked: $(date '+%H:%M:%S')"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo ""
|
||||
Reference in New Issue
Block a user