FailedProxy/Varaverk
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: rename failover/HA → fallback across entire codebase

Browse Source 
Removes all references to "failover" and "HA" (high availability)
terminology from variable names, config keys, state values, rsync
profile names, directory paths, and user-visible strings.

Mapping:
  FAILOVER_*              → FALLBACK_*
  FAILOVER_HOST*_RUNS_FOR → FALLBACK_HOST*_COVERS
  critical-failover       → critical-fallback
  emby-failover           → emby-fallback
  appdata-Failover/       → appdata-Fallback/
  "FAILOVER" state value  → "FALLBACK"
  failover_start key      → fallback_start
  Failover/ directory     → Fallback/
  failover.sh             → fallback.sh
  failover_state.db       → fallback_state.db
  -Failover folder suffix → -Fallback

State machine: NORMAL | FALLBACK | DARK (unchanged)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Gmer4Lfe
2026-05-08 19:28:21 -04:00
co-authored by Claude Sonnet 4.6
parent 4e22f5d1f7
commit 009820e981
19 changed files with 517 additions and 416 deletions
Download Patch File Download Diff File Expand all files Collapse all files
master.conf
+35 -35
View File
@@ -49,7 +49,7 @@
#
# ── FAILOVER ───────────────────────────────────────────────────────────────────────────────
# FAILOVER Mutual container failover shared settings
# FAILOVER TEST Simulated outage settings for failover_test.sh
# FALLBACK TEST Simulated outage settings for fallback_test.sh
#
# ── DOCKER ESSENTIALS ──────────────────────────────────────────────────────────────────────
# DOWNLOADERS RESET Retention and thresholds for slskd, SABnzbd, qBittorrent
@@ -99,7 +99,7 @@
# DATA_DIR is the same path on all servers — persistent script state and statistics.
# Array share — survives reboots, no flash drive wear.
# Created automatically if it doesn't exist.
# Only truly critical files (failover state, watchdog reboot log) stay on /boot/config.
# Only truly critical files (fallback state, watchdog reboot log) stay on /boot/config.
DATA_DIR="/mnt/user/appdata/unraid_scripts/data"
# ── Version Parity ──
@@ -254,7 +254,7 @@
"Docker_Essentials/docker_network_connect.sh" # ensure networks exist + connect containers
"unRAID_Essentials/system_watchdog.sh" # system health monitor — continuous loop
"Docker_Essentials/docker_watchdog.sh" # container health monitor — continuous loop
# "Failover/failover.sh" # mutual failover — enable when HOST2 ready
# "Fallback/fallback.sh" # mutual failover — enable when HOST2 ready
)
# ━━━ Daily Sync Maintenance ━━━
@@ -352,14 +352,14 @@
# DAILY_RSYNC_ENABLED=false ← skip daily HDD syncs during rebuild
# WEEKLY_RSYNC_ENABLED=true ← Emby + Critical-Data still sync (NVMe)
# CRITICAL_RSYNC_ENABLED=true ← 15min auth stack sync still runs
# FAILOVER_RSYNC_ENABLED=true ← handback writeback still works
# FALLBACK_RSYNC_ENABLED=true ← handback writeback still works
# → Run individual: bash Rsync/rsync.sh /mnt/user/Movies
# → When ready: DAILY_RSYNC_ENABLED=true
RSYNC_ENABLED=true # Tier 1 — global gate, overrides everything below
DAILY_RSYNC_ENABLED=false # Tier 2 — HOST2 rebuild in progress, re-enable when ready
WEEKLY_RSYNC_ENABLED=true # Tier 2 — weekly_sync_maintenance.sh rsync section
CRITICAL_RSYNC_ENABLED=false # Tier 2 — disabled during HOST2 rebuild, re-enable when ready
FAILOVER_RSYNC_ENABLED=true # Tier 2 — failover.sh writeback jobs on handback
FALLBACK_RSYNC_ENABLED=true # Tier 2 — fallback.sh writeback jobs on handback
# ━━━ Rsync Defaults ━━━
# Global fallback values used when no profile match is found.
@@ -395,53 +395,53 @@
# arrs_stack — arr databases — lower bandwidth, containers stopped for consistency
# critical-data — auth stack — full stop both sides, Authelia delayed start
# called by weekly_sync_maintenance.sh — full clean sync weekly
# critical-failover — dirty sync — auth stays running both sides, WAL excluded
# critical-fallback — dirty sync — auth stays running both sides, WAL excluded
# called by critical_sync_maintenance.sh every 15min
# host1-appdata — HOST1 server-specific appdata — defined in master_host1.conf
# host2-appdata — HOST2 server-specific appdata — defined in master_host2.conf
# important-data — NextCloud + Postgres — NextCloud delayed start after Postgres
# emby — weekly clean sync — both Emby stopped, full mirror
# called by weekly_sync_maintenance.sh only — do NOT schedule separately
# emby-failover — dirty sync — Emby stays running, WAL excluded
# emby-fallback — dirty sync — Emby stays running, WAL excluded
# called by critical_sync_maintenance.sh every 15min
declare -A PROFILE_RSYNC_OPTS=(
[arrs_stack]="-av --info=progress2 --human-readable --bwlimit=$BW_LIMIT --delete --inplace"
[critical-data]="-av --human-readable --bwlimit=$BW_LIMIT --delete"
[critical-failover]="-av --human-readable --bwlimit=$BW_LIMIT --delete --inplace --no-whole-file"
[critical-fallback]="-av --human-readable --bwlimit=$BW_LIMIT --delete --inplace --no-whole-file"
[important-data]="-av --human-readable --bwlimit=$BW_LIMIT"
[emby]="-av --human-readable --bwlimit=$BW_LIMIT --delete --inplace --no-whole-file"
[emby-failover]="-av --human-readable --bwlimit=$BW_LIMIT --delete --inplace --no-whole-file"
[emby-fallback]="-av --human-readable --bwlimit=$BW_LIMIT --delete --inplace --no-whole-file"
)
# Per-profile bandwidth limits in KB/s
declare -A PROFILE_BW_LIMIT=(
[arrs_stack]=5000 # lower — runs alongside other syncs
[critical-data]=9500 # high — small dataset, sync fast
[critical-failover]=9500 # high — small dataset, sync fast
[critical-fallback]=9500 # high — small dataset, sync fast
[important-data]=9500 # high — database sync
[emby]=8000 # medium — large full mirror
[emby-failover]=9500 # high — small critical dataset
[emby-fallback]=9500 # high — small critical dataset
)
# Retry attempts per profile
declare -A PROFILE_RETRY_COUNT=(
[arrs_stack]=3
[critical-data]=3
[critical-failover]=3
[critical-fallback]=3
[important-data]=3
[emby]=3
[emby-failover]=3
[emby-fallback]=3
)
# Seconds between retry attempts
declare -A PROFILE_SLEEP=(
[arrs_stack]=300
[critical-data]=300
[critical-failover]=120 # shorter — frequent dirty sync, retry faster
[critical-fallback]=120 # shorter — frequent dirty sync, retry faster
[important-data]=300
[emby]=300
[emby-failover]=120 # shorter — frequent dirty sync, retry faster
[emby-fallback]=120 # shorter — frequent dirty sync, retry faster
)
# Containers stopped on BOTH LOCAL and REMOTE before rsync.
@@ -451,10 +451,10 @@
declare -A PROFILE_CRITICAL_CONTAINER_NAMES=(
[arrs_stack]="Sonarr Lidarr Readarr Radarr Prowlarr Bazarr Pinchflat"
[critical-data]="Mariadb-Authelia Mariadb-Authelia-Secondary Redis-Authelia Redis-Authelia-Secondary Lldap-Gmer4Lfe NginxProxyManager Authelia Authelia-Secondary"
[critical-failover]="" # dirty sync — auth stays running both sides
[critical-fallback]="" # dirty sync — auth stays running both sides
[important-data]="Postgres-NextCloud NextCloud"
[emby]="Emby"
[emby-failover]="" # dirty sync — Emby stays running both sides
[emby-fallback]="" # dirty sync — Emby stays running both sides
)
# Containers needing a delay after rsync before starting.
@@ -462,20 +462,20 @@
declare -A PROFILE_DELAYED_CONTAINERS=(
[arrs_stack]=""
[critical-data]="Authelia Authelia-Secondary" # wait for Mariadb + Redis
[critical-failover]=""
[critical-fallback]=""
[important-data]="NextCloud" # wait for Postgres
[emby]=""
[emby-failover]=""
[emby-fallback]=""
)
# Seconds before starting delayed containers
declare -A PROFILE_CONTAINER_DELAY=(
[arrs_stack]=5
[critical-data]=15 # Mariadb + Redis need time to accept connections
[critical-failover]=5
[critical-fallback]=5
[important-data]=10 # Postgres needs time before NextCloud
[emby]=5
[emby-failover]=5
[emby-fallback]=5
)
# Directories excluded from rsync per profile.
@@ -483,19 +483,19 @@
declare -A PROFILE_EXCLUDE_DIRS=(
[arrs_stack]="logs *.tmp"
[critical-data]="logs *.tmp *.log nginx/temp nginx/cache __pycache__ notification.txt"
[critical-failover]="logs *.tmp *.log nginx/temp nginx/cache __pycache__ notification.txt *.db-wal *.db-shm"
[critical-fallback]="logs *.tmp *.log nginx/temp nginx/cache __pycache__ notification.txt *.db-wal *.db-shm"
[important-data]="logs *.tmp"
[emby]="logs transcodes cache crash*"
[emby-failover]="logs transcodes cache metadata *.db-wal *.db-shm crash* plugins root"
[emby-fallback]="logs transcodes cache metadata *.db-wal *.db-shm crash* plugins root"
)
# Remote restart after dirty sync — restart these on remote IF they were running before sync.
# Same logic as stop/start — was stopped = stays stopped, was running = gets restarted.
# Used by dirty sync profiles (critical-failover, emby-failover) so remote picks up changes.
# Used by dirty sync profiles (critical-fallback, emby-fallback) so remote picks up changes.
# SPACE-SEPARATED STRINGS — converted to array at runtime
declare -A PROFILE_REMOTE_RESTART_CONTAINERS=(
[critical-failover]="NginxProxyManager Authelia Authelia-Secondary Lldap-Gmer4Lfe Mariadb-Authelia Mariadb-Authelia-Secondary Redis-Authelia Redis-Authelia-Secondary"
[emby-failover]="Emby"
[critical-fallback]="NginxProxyManager Authelia Authelia-Secondary Lldap-Gmer4Lfe Mariadb-Authelia Mariadb-Authelia-Secondary Redis-Authelia Redis-Authelia-Secondary"
[emby-fallback]="Emby"
)
# Note: disk check is auto-detected from disks.ini — no PROFILE_SKIP_DISK_CHECK needed.
@@ -505,7 +505,7 @@
# ── FAILOVER ──────────────────────────────────────────────────────────────────────────────────
# ==============================================================================================
# Mutual container failover between two unRAID servers.
# Each server runs Failover/failover.sh independently via array_start.sh.
# Each server runs Fallback/fallback.sh independently via array_start.sh.
# All decisions based on two pings: remote reachable + internet reachable.
#
# States: NORMAL | FAILOVER | NO_INTERNET | DARK
@@ -519,16 +519,16 @@
# Shared settings (intervals, state file, thresholds) live here.
EXTERNAL_IP="8.8.8.8"
FAILOVER_CHECK_INTERVAL=120 # seconds between failover state checks
FAILOVER_HANDBACK_STRIKES=2 # consecutive healthy checks before initiating handback
FAILOVER_STATE_FILE="/boot/config/failover_state.db"
FAILOVER_ENABLED=false # HOST2 being rebuilt — set true when back online and tested
FALLBACK_CHECK_INTERVAL=120 # seconds between fallback state checks
FALLBACK_HANDBACK_STRIKES=2 # consecutive healthy checks before initiating handback
FALLBACK_STATE_FILE="/boot/config/fallback_state.db"
FALLBACK_ENABLED=false # HOST2 being rebuilt — set true when back online and tested
# false = suppresses "not running" warnings in status scripts
# ━━━ Failover Test ━━━
# Controlled simulation of a failover event — run manually via failover_test.sh.
FAILOVER_TEST_BLOCK_WAIT=150 # seconds to wait after blocking connectivity
FAILOVER_TEST_HANDBACK_WAIT=360 # seconds to wait before initiating handback
# Controlled simulation of a failover event — run manually via fallback_test.sh.
FALLBACK_TEST_BLOCK_WAIT=150 # seconds to wait after blocking connectivity
FALLBACK_TEST_HANDBACK_WAIT=360 # seconds to wait before initiating handback
# ==============================================================================================
# ── DOCKER ESSENTIALS ─────────────────────────────────────────────────────────────────────────
@@ -1046,7 +1046,7 @@
DIGEST_PROFILE="weekly" # always | smart | weekly
DIGEST_DAY="Sunday"
DIGEST_SMART_ON_WATCHDOG=true # send if any watchdog strikes are active
DIGEST_SMART_ON_FAILOVER=true # send if failover state is not NORMAL
DIGEST_SMART_ON_FALLBACK=true # send if fallback state is not NORMAL
DIGEST_SMART_ON_CERT_WARN=true # send if any cert is under CERT_WARN_DAYS
DIGEST_SMART_ON_BANDWIDTH=true # send if any transfer exceeded BANDWIDTH_WARN_GB