Files
Gmer4Lfe d5cf3db2ec Close every orchestrator the same way, and make skipped work a visible outcome
A gated-off section left nothing failed, so the weekly could run for hours and report "all
complete" beside "0 shares synced"; skipped is now derived from what was expected rather than
self-reported, and the verdict degrades to PARTIAL instead of flattering.
2026-08-23 16:38:58 -04:00

196 lines
7.8 KiB
Bash
Executable File

#!/bin/bash
# ==============================================================================================
# ================================= Array Stop Orchestrator ====================================
# ==============================================================================================
#
# PURPOSE
# ─────────────────────────────────────────────────────────────────────────────
# Planned shutdown orchestrator — stops all active processes cleanly before
# array maintenance. Runs ARRAY_STOP_SCRIPTS from master.conf sequentially,
# each confirmed complete before the next starts.
#
# ==============================================================================================
# OPERATIONAL MODEL
# ==============================================================================================
#
# 1. user_scripts_stop.sh — kill background user scripts (prevents new operations)
# 2. rsync_stop.sh --rsync-only — kill rsync; skip container recovery (handled in step 4)
# 3. mover_stop.sh — stop mover after rsync (both write to same paths)
# 4. docker_container_stop.sh — stop all containers one-by-one with verification
#
# Unlike array_started.sh, all scripts run in the foreground. Each must complete
# (pass or fail) before the next starts — a failed stop is noted but does not
# prevent remaining steps from running.
#
# ==============================================================================================
# DESIGN PRINCIPLES
# ==============================================================================================
#
# Order Is Load-Bearing
# User scripts are stopped first — they can spawn new rsync or docker operations
# mid-shutdown. Rsync stops before mover — both write to the same paths and
# running together risks corruption. Containers stop last — apps should stay
# available as long as possible during shutdown prep.
#
# Non-Fatal Steps
# A failed stop step is logged and notified but does not abort the sequence.
# Remaining scripts still run — a partial stop is better than a halted one.
#
# ==============================================================================================
# OPERATIONAL SAFEGUARDS
# ==============================================================================================
#
# Root Enforcement
# Every stop script launched here requires root.
#
# Lock Acquisition
# acquire_lock prevents concurrent array stop runs. Two overlapping shutdown
# sequences would fight over the same containers.
#
# Host Detection
# detect_hosts() sets MY_ID for notifications and logs.
#
# Empty Job List Guard
# Exits with an error and a notification if ARRAY_STOP_SCRIPTS is empty. An empty
# list means the array stops without saving the conf cache or gracefully stopping
# containers — the failure would only be discovered at the next boot.
#
# Non-Fatal Steps
# A failing stop script is recorded and the remaining ones still run. Abandoning the
# shutdown sequence partway would leave more state unsaved than continuing does.
#
# Failure Notification
# Any failing stop script raises a notification. Shutdown is unattended and its
# failures are invisible until they cause a problem on the way back up.
#
# ==============================================================================================
# CONFIGURATION
# ==============================================================================================
#
# master.conf
#
# ARRAY_STOP_SCRIPTS — ordered list of stop scripts to run
#
# ==============================================================================================
# RUNTIME MODES
# ==============================================================================================
#
# array_stopping.sh
# Run full stop sequence.
#
# array_stopping.sh --dry-run
# Preview without stopping anything.
#
# array_stopping.sh --status
# Show configured scripts and exit.
#
# array_stopping.sh --log
# Verbose output.
#
# ==============================================================================================
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
ECOSYSTEM_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
source "$ECOSYSTEM_ROOT/load_config.sh"
parse_args "$@"
# ==============================================================================================
# ━━━ Setup ━━━
# ==============================================================================================
if [[ "$EUID" -ne 0 ]]; then
error "Must be run as root"
exit 1
fi
acquire_lock
if ! command -v docker &>/dev/null; then
error "Docker command not found"
exit 1
fi
detect_hosts
# An unconfigured job list would run nothing and still report "0/0 passed" — indistinguishable
# from a healthy run. Fail loudly instead of silently doing no work.
if [[ ${#ARRAY_STOP_SCRIPTS[@]} -eq 0 ]]; then
error "ARRAY_STOP_SCRIPTS is empty — no array stop scripts will run"
error "Check ARRAY_STOP_SCRIPTS in master.conf"
notify "array stop scripts skipped on $(hostname) ($MY_ID) — ARRAY_STOP_SCRIPTS is empty" \
"$(basename "$0" .sh)" "warning"
exit 1
fi
[[ "$DRY_RUN" == true ]] && warn "DRY RUN — no stop scripts will be executed"
# ==============================================================================================
# ━━━ Status ━━━
# ==============================================================================================
if [[ "$SHOW_STATUS" == true ]]; then
echo ""
echo "━━━━━ $ICON_SUMMARY ARRAY STOP STATUS ━━━━━"
echo "$ICON_HOST Identity: $MY_ID ($LOCAL_SERVER_NAME)"
echo "$ICON_GEAR Scripts: ${#ARRAY_STOP_SCRIPTS[@]} configured"
echo ""
for entry in "${ARRAY_STOP_SCRIPTS[@]}"; do
[[ -z "$entry" ]] && continue
read -r -a parts <<< "$entry"
script_path="$ECOSYSTEM_ROOT/${parts[0]}"
script_name=$(basename "${parts[0]}")
extra_args=("${parts[@]:1}")
if [[ ! -f "$script_path" ]]; then
echo " $ICON_ERROR $script_name — FILE NOT FOUND"
else
echo " $ICON_GEAR $script_name${extra_args:+ ${extra_args[*]}}"
fi
done
echo "━━━━━━━━━━━━━━━━━━━━━━━"
exit 0
fi
# ==============================================================================================
# ━━━ Stop Sequence ━━━
# ==============================================================================================
echo ""
echo "━━━ $ICON_STOP Array Stop — $MY_ID$(date '+%Y-%m-%d %H:%M:%S') ━━━"
echo "$ICON_GEAR Running ${#ARRAY_STOP_SCRIPTS[@]} stop script(s) sequentially..."
echo ""
START=$(date +%s)
JOB_PASS=()
JOB_FAIL=()
STEP=0
for entry in "${ARRAY_STOP_SCRIPTS[@]}"; do
[[ -z "$entry" ]] && continue
(( STEP++ ))
read -r -a parts <<< "$entry"
script_name=$(basename "${parts[0]}")
extra_args=("${parts[@]:1}")
echo "━━━ $ICON_GEAR Step $STEP: $script_name${extra_args:+ ${extra_args[*]}} ━━━"
run_orch_child "$entry"
echo ""
done
END=$(date +%s)
# ==============================================================================================
# ━━━ Summary ━━━
# ==============================================================================================
echo "━━━━━ $ICON_SUMMARY ARRAY STOP SUMMARY ━━━━━"
echo "$ICON_HOST Identity: $MY_ID ($LOCAL_SERVER_NAME)"
echo "$ICON_TIME Duration: $(format_duration $(( END - START )))"
[[ ${#JOB_PASS[@]} -gt 0 ]] && echo "$ICON_DONE Passed: ${JOB_PASS[*]}"
[[ ${#JOB_FAIL[@]} -gt 0 ]] && echo "$ICON_ERROR Failed: ${JOB_FAIL[*]}"
echo ""
JOB_COUNT="$STEP"
orchestrator_summary "ARRAY STOP" "$START" "Array Stop"
exit $?