Files
Varaverk/Tools/fallback_state_reset.sh
Gmer4Lfe e8b114094a Bring script headers onto the template and close safeguard gaps
Headers claimed protections the code never had, and several destructive paths had no
guard against a collapsed config value.
2026-08-01 20:37:59 -04:00

287 lines
12 KiB
Bash
Executable File

#!/bin/bash
# ==============================================================================================
# ============================= fallback State Reset ===========================================
# ==============================================================================================
#
# PURPOSE
# ─────────────────────────────────────────────────────────────────────────────
# Resets the fallback state file to NORMAL and clears all tier flags. Use when
# the state file is stuck after fallback testing, a failed handback, manual
# intervention, or fallback.sh being killed mid-cycle.
#
# Writes a fresh state file with:
# state=NORMAL / fallback_start=0 / handback_strikes=0
# tier2_started=false / tier3_started=false / tier4_started=false
#
# Does NOT start or stop containers — state file only. After reset, fallback.sh
# resumes from NORMAL on its next cycle.
#
# WARNING: Only run when you have verified the stack is actually in a normal
# state — right containers on the right server, DDNS correct, no active fallback
# in progress. Resetting state during a real fallback causes fallback.sh to stop
# covering the remote server until the next detection cycle.
#
# ==============================================================================================
# OPERATIONAL MODEL
# ==============================================================================================
#
# 1. Read and display the current state file so the operator sees what is being discarded
# 2. Write a fresh state file:
# state=NORMAL, fallback_start=0, handback_strikes=0
# tier2_started=false, tier3_started=false, tier4_started=false
# 3. Report the new state
#
# Nothing else is touched. No container is started or stopped, no DDNS is moved, no rsync
# is run. fallback.sh picks the new state up on its next cycle and proceeds from NORMAL.
#
# ==============================================================================================
# DESIGN PRINCIPLES
# ==============================================================================================
#
# State File Only, Never Containers
# This tool changes what fallback.sh believes, not what is actually running. That
# separation is the point: reconciling the real stack is an operator judgement call,
# and a tool that tried to do both could act on a belief that was already wrong.
#
# The Operator Asserts Reality
# Resetting to NORMAL is a claim that the stack really is normal — right containers on
# the right host, DDNS pointing the right way. The script cannot verify that, so it
# shows the current state before overwriting it and leaves the check to the human. If
# the assertion is wrong, fallback.sh will act on a false NORMAL.
#
# Full Reset, Not Partial Edit
# Every field is rewritten rather than patching individual keys. A partially-reset file
# — NORMAL state with tier flags still true — is a state fallback.sh has no handling
# for and would be worse than either extreme.
#
# ==============================================================================================
# CONFIGURATION
# ==============================================================================================
#
# master.conf
#
# FALLBACK_STATE_FILE
# Path to the fallback state file this tool rewrites. Shared with fallback.sh —
# both must agree or the reset writes somewhere fallback.sh never reads.
#
# ==============================================================================================
# OPERATIONAL SAFEGUARDS
# ==============================================================================================
#
# Active Fallback Detection
# Checks whether fallback.sh is currently running and warns if so. A reset
# during an active cycle causes fallback.sh to lose its state on the next read.
#
# Single Instance Lock
# acquire_lock prevents concurrent resets.
#
# flock on State Write
# The state file write is protected with flock — prevents a race condition
# with fallback.sh reading the file mid-cycle.
#
# Confirmation Required
# Interactive mode prompts for YES before writing. Use --force to bypass in
# non-interactive contexts (cron, scripts).
#
# ==============================================================================================
# RUNTIME MODES
# ==============================================================================================
#
# fallback_state_reset.sh
# Show current state and prompt for YES before resetting.
#
# fallback_state_reset.sh --dry-run
# Show current state and what the new state file would contain. No write.
#
# fallback_state_reset.sh --status
# Show current state file contents and exit.
#
# fallback_state_reset.sh --force
# Reset without interactive confirmation. Safe for scripted use.
#
# fallback_state_reset.sh --force --dry-run
# Dry run without the confirmation prompt.
#
# ==============================================================================================
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
source "$SCRIPT_DIR/../load_config.sh"
# ── Handle --force flag before parse_args ─────────────────────────────────────────────────────
FORCE=false
FILTERED_ARGS=()
for arg in "$@"; do
case "$arg" in
--force) FORCE=true ;;
*) FILTERED_ARGS+=("$arg") ;;
esac
done
parse_args "${FILTERED_ARGS[@]}"
# ==============================================================================================
# ━━━ Setup ━━━
# ==============================================================================================
if [[ "$EUID" -ne 0 ]]; then
error "Must be run as root"
exit 1
fi
acquire_lock
# detect_hosts() sets MY_ID — used in summary and notification
detect_hosts
log "$ICON_GEAR Config: state-file=${FALLBACK_STATE_FILE}"
[[ "$DRY_RUN" == true ]] && warn "DRY RUN — no changes will be made"
[[ "$FORCE" == true ]] && warn "FORCE mode — confirmation prompt skipped"
# ==============================================================================================
# ━━━ Current State ━━━
# ==============================================================================================
echo ""
echo "━━━ $ICON_FALLBACK Current Fallback State ━━━"
echo "$ICON_HOST My ID: $MY_ID ($LOCAL_SERVER_NAME)"
echo ""
if [[ ! -f "$FALLBACK_STATE_FILE" ]]; then
warn "State file not found: $FALLBACK_STATE_FILE"
warn "Will be created fresh on reset"
CURRENT_STATE="NOT FOUND"
else
log "State file: $FALLBACK_STATE_FILE"
echo ""
while IFS='=' read -r key value; do
[[ -z "$key" ]] && continue
echo " $ICON_INFO $key = $value"
done < "$FALLBACK_STATE_FILE"
CURRENT_STATE=$(grep "^state=" "$FALLBACK_STATE_FILE" 2>/dev/null | cut -d= -f2)
fi
if [[ "$SHOW_STATUS" == true ]]; then
echo ""
# Check if fallback.sh is running — informational in status mode
if pgrep -f "fallback.sh" >/dev/null 2>&1; then
warn "fallback.sh is currently RUNNING — any reset would race with active cycle"
else
echo "fallback.sh is not running ✅"
fi
exit 0
fi
# ==============================================================================================
# ━━━ Safety Checks ━━━
# ==============================================================================================
echo ""
echo "━━━ $ICON_SHIELD Safety Checks ━━━"
# Check if fallback.sh is actively running
FALLBACK_RUNNING=false
if pgrep -f "fallback.sh" >/dev/null 2>&1; then
FALLBACK_RUNNING=true
warn "⚠️ fallback.sh is currently RUNNING"
warn "Resetting state mid-cycle may cause incorrect decisions on the next iteration"
warn "Consider stopping fallback.sh first: kill \$(pgrep -f fallback.sh)"
warn "Then reset state, then restart: bash Fallback/fallback.sh &"
echo ""
warn "If you are sure you want to proceed anyway, confirm below"
else
echo "fallback.sh is not running — safe to reset ✅"
fi
# Check current state — if already NORMAL warn user
if [[ "$CURRENT_STATE" == "NORMAL" ]]; then
warn "State is already NORMAL — reset may not be necessary"
warn "Proceeding anyway (will refresh the state file)"
fi
# ==============================================================================================
# ━━━ Confirmation ━━━
# ==============================================================================================
echo ""
warn "This will reset fallback state to NORMAL on $MY_ID ($LOCAL_SERVER_NAME)"
warn "Verify before proceeding:"
warn " ✓ Right containers running on the right server"
warn " ✓ DDNS pointing at correct server"
warn " ✓ No real fallback actually in progress"
warn " ✓ Both servers can reach each other"
echo ""
if [[ "$DRY_RUN" == false ]]; then
if [[ "$FORCE" == true ]]; then
log "FORCE flag set — skipping confirmation prompt"
elif [[ -t 0 ]]; then
# Interactive terminal — prompt for confirmation
read -r -p "Type YES to confirm reset: " CONFIRM
if [[ "$CONFIRM" != "YES" ]]; then
warn "Reset cancelled"
exit 0
fi
else
# Non-interactive — no terminal, cannot prompt
error "Non-interactive mode — use --force flag to skip confirmation"
error "Usage: fallback_state_reset.sh --force"
exit 1
fi
fi
# ==============================================================================================
# ━━━ Reset State File ━━━
# ==============================================================================================
echo ""
echo "━━━ $ICON_FALLBACK Resetting State File ━━━"
NEW_STATE_CONTENT="state=NORMAL
fallback_start=0
handback_strikes=0
tier2_started=false
tier3_started=false
tier4_started=false
last_reset=$(date '+%Y-%m-%d %H:%M:%S')
reset_by=$MY_ID"
if [[ "$DRY_RUN" == true ]]; then
warn "DRY RUN — would write to $FALLBACK_STATE_FILE:"
echo ""
echo "$NEW_STATE_CONTENT" | while IFS= read -r line; do
echo " $line"
done
else
mkdir -p "$(dirname "$FALLBACK_STATE_FILE")"
# flock prevents race with fallback.sh mid-cycle read/write
(
flock -x 200
echo "$NEW_STATE_CONTENT" > "$FALLBACK_STATE_FILE"
) 200>"${FALLBACK_STATE_FILE}.lock"
warn "State file reset to NORMAL ✅"
log "Written to: $FALLBACK_STATE_FILE"
fi
# ==============================================================================================
# ━━━ Summary ━━━
# ==============================================================================================
echo ""
echo "━━━━━ $ICON_SUMMARY FALLBACK STATE RESET SUMMARY ━━━━━"
echo "$ICON_HOST Identity: $MY_ID ($LOCAL_SERVER_NAME)"
echo "$ICON_FALLBACK File: $FALLBACK_STATE_FILE"
echo "$ICON_TIME Reset at: $(date '+%Y-%m-%d %H:%M:%S')"
echo ""
if [[ "$DRY_RUN" == true ]]; then
warn "DRY RUN — no changes made"
else
warn "$ICON_DONE State reset to NORMAL"
echo "fallback.sh will resume from NORMAL on next cycle"
echo "No containers were started or stopped"
echo ""
[[ "$FALLBACK_RUNNING" == true ]] && \
warn "⚠️ fallback.sh was running during reset — monitor next cycle carefully"
notify "Fallback state manually reset to NORMAL on $(hostname) ($MY_ID)" \
"Fallback State Reset" "warning"
fi
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
exit 0