Guard arr cache writes against in-flight rescans, add rescan monitor tool

A direct arr_cache_write() call mid-rescan wrote a partial snapshot that looked like real data loss to every consumer of the cache. The guard now lives in arr_cache_write() itself so every caller is protected, not just arr_get_tracked_data(). arr_rescan_monitor.sh closes the resulting gap for rescans triggered outside arr_full_rescan.sh's own trigger-and-wait path.
2026-07-16 22:57:54 -04:00
parent fb13958881
commit 2c3f0b9cb1
5 changed files with 215 additions and 2 deletions
@@ -0,0 +1,97 @@
+#!/bin/bash
+# ==============================================================================================
+# ========================= Arr Rescan Monitor ==================================================
+# ==============================================================================================
+#
+# PURPOSE
+# ─────────────────────────────────────────────────────────────────────────────
+# Waits for an already-active rescan-type command (RescanFolders/RescanSeries/RescanMovie,
+# DownloadedXScan, RefreshX — see ARR_RESCAN_COMMANDS in common.sh) on the given arr to finish,
+# then refreshes the shared tracked-data cache (arr_cache_write) with the real post-scan
+# numbers. Triggers nothing itself — for watching a rescan that was already started some
+# other way (manual API call, arr's own UI, another script).
+#
+# Exists because arr_cache_write() now refuses to write while a rescan is active for that arr
+# (2026-07-17 — a direct cache write mid-scan read as real data loss to every consumer of the
+# cache, e.g. check_tracked_count_floor, instead of what it was: an in-flight scan). That
+# guard protects the cache, but it also means nothing writes the real number through once the
+# scan finishes unless something is watching for completion — arr_full_rescan.sh already does
+# this for scans it triggers itself; this tool covers everything else.
+#
+# ==============================================================================================
+# RUNTIME MODES
+# ==============================================================================================
+#
+# arr_rescan_monitor.sh lidarr
+#     Wait for lidarr's active rescan (if any) to finish, then refresh its cache.
+#     Exits immediately if no rescan is currently active — nothing to wait for.
+#
+# arr_rescan_monitor.sh lidarr 3600
+#     Override the default 2-hour wait ceiling (second positional arg, seconds).
+#
+# arr_rescan_monitor.sh lidarr --status
+#     Show whether a rescan is currently active and the cache's current age, no waiting.
+#
+# arr_rescan_monitor.sh lidarr --dry-run
+#     Show what would be waited on without actually waiting or writing the cache.
+#
+# ==============================================================================================
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+source "$SCRIPT_DIR/../load_config.sh"
+parse_args "$@"
+detect_hosts
+
+ARR_TYPE="${PARSED_ARGS[0]:-}"
+TIMEOUT="${PARSED_ARGS[1]:-7200}"
+
+case "$ARR_TYPE" in
+    lidarr|sonarr|radarr) ;;
+    *) error "Usage: arr_rescan_monitor.sh lidarr|sonarr|radarr [timeout_seconds] [--status] [--dry-run]"; exit 1 ;;
+esac
+
+url_var="${ARR_TYPE^^}_URL"; key_var="${ARR_TYPE^^}_API_KEY"
+URL="${!url_var:-}"; KEY="${!key_var:-}"
+VER="${ARR_API_VERSION[$ARR_TYPE]}"
+
+require_var "$url_var"
+require_var "$key_var"
+
+ACTIVE=$(arr_active_rescan_command "$ARR_TYPE" "$URL" "$KEY" "$VER")
+CACHE_AGE=$(arr_cache_age_seconds "$ARR_TYPE")
+
+if [[ "$SHOW_STATUS" == true ]]; then
+    info "${ARR_TYPE^} active rescan: ${ACTIVE:-none}"
+    info "${ARR_TYPE^} cache age: $(( CACHE_AGE / 60 )) minutes"
+    exit 0
+fi
+
+if [[ -z "$ACTIVE" ]]; then
+    info "No active rescan on ${ARR_TYPE^} — nothing to wait for."
+    exit 0
+fi
+
+if [[ "$DRY_RUN" == true ]]; then
+    warn "DRY RUN — would wait for ${ARR_TYPE^}'s active $ACTIVE (timeout ${TIMEOUT}s), then refresh its cache"
+    exit 0
+fi
+
+info "Waiting for ${ARR_TYPE^}'s active $ACTIVE to finish (timeout ${TIMEOUT}s)..."
+if ! arr_wait_for_active_rescan "$ARR_TYPE" "$URL" "$KEY" "$VER" "$TIMEOUT"; then
+    error "Timed out after ${TIMEOUT}s waiting for ${ARR_TYPE^}'s rescan — cache not refreshed. Re-run once it finishes, or it'll pick up naturally next time something calls arr_get_tracked_data()."
+    exit 1
+fi
+
+ENDPOINT="${ARR_LIBRARY_ENDPOINT[$ARR_TYPE]}"
+EXPR="${ARR_TRACKED_COUNT_EXPR[$ARR_TYPE]}"
+ITEMS=$(curl -sf --max-time 60 -H "X-Api-Key: $KEY" "${URL}/api/${VER}/${ENDPOINT}" 2>/dev/null)
+TOTAL=$(echo "$ITEMS" | jq "$EXPR" 2>/dev/null)
+
+if [[ -z "$ITEMS" || -z "$TOTAL" || "$TOTAL" == "null" ]]; then
+    error "${ARR_TYPE^} rescan finished but couldn't fetch fresh library data — cache not refreshed"
+    exit 1
+fi
+
+arr_cache_write "$ARR_TYPE" "$ITEMS"
+success "${ARR_TYPE^} rescan finished — cache refreshed, tracked: ${TOTAL}"
+notify "${ARR_TYPE^} rescan finished on $(hostname) — cache refreshed, tracked: ${TOTAL}" "Arr Rescan Monitor" "normal"