diff --git a/scripts/media-verify.py b/scripts/media-verify.py index 23cca6d..346177c 100755 --- a/scripts/media-verify.py +++ b/scripts/media-verify.py @@ -9,8 +9,13 @@ its destination, and NO row may still name its source — a source row is a scan that has not caught up, and it is the one signature of a library pointing at files that no longer exist. -Two doors, both read-only, both without a lock while the server runs -(`mode=ro&immutable=1`; there is no `sqlite3` binary on these hosts): +Two doors, both read-only, both without a lock while the server runs (there is +no `sqlite3` binary on these hosts). Open `mode=ro` PLAIN: both servers keep +their libraries in WAL mode, and `immutable=1` — which claims the file never +changes — makes sqlite skip the write-ahead log entirely, so every row the +server has committed but not yet checkpointed reads as MISSING, and a read +beside a running scanner can even fail as "database disk image is malformed". +`immutable=1` is only the fallback, for a database whose `-shm` cannot be read. jellyfin `BaseItems.Path`. The container binds the share at `/data`, so the database holds `/data//…` where the journal holds @@ -22,9 +27,14 @@ Two doors, both read-only, both without a lock while the server runs Neither server holds a row for everything the journal renames: a `.log`, `.cue` or cover image has no row to land in, so its absence is not a fault. The report -therefore breaks the missing rows down by extension, and `--ignore-ext` names -the extensions this server does not index, which are then counted separately and -kept out of the verdict. +therefore breaks the missing rows down by extension, and `--ignore-ext` names the +extensions this server does not index, which are then counted separately and kept +out of the verdict. What is left is split by what the filesystem says, because +the database alone cannot: a file still at its `src` is `REAL` (this pass's own +damage), a file at neither path is `gone` (a later pass or the server renamed it), +and a file sitting at its `dst` with no row naming it is simply something the +server does not index. A row that still names `src` is none of these: it is the +server's own stale pointer — a phantom — and it costs a re-scan, never a restore. Exit codes: 0 every move landed; 1 something is stale or missing (the details are printed); 2 the journal or the database is not usable at all. @@ -92,10 +102,18 @@ def read_moves(path): def server_paths(db, kind): """Every path the server holds, or a refusal that names what is missing.""" spec = KINDS[kind] - try: - con = sqlite3.connect(f"file:{db}?mode=ro&immutable=1", uri=True) - except sqlite3.Error as e: - die(f"cannot open {db}: {e}") + con = None + err = None + # Plain ro reads the WAL the server commits through; immutable is the last + # resort, because it cannot see a row the server has not checkpointed. + for opt in ("mode=ro", "mode=ro&immutable=1"): + try: + con = sqlite3.connect(f"file:{db}?{opt}", uri=True) + break + except sqlite3.Error as e: + err = e + if con is None: + die(f"cannot open {db}: {err}") with con: have = {r[1] for r in con.execute(f"pragma table_info({spec['table']})")} if not spec["columns"] <= have: @@ -161,20 +179,37 @@ def main(): if at_src: stale.append(src) if not at_dst: - missing.append(dst) + missing.append((src, dst)) + + # The database cannot tell a lost file from one it never indexes: both read + # as "no row at the destination". Stat both paths, so the report separates + # the classes the runbook names — `REAL` is the only one that is this pass's + # own damage, and `gone` is a later pass or the server's own rename. + on_disk, real, gone = [], [], [] + for src, dst in missing: + if os.path.exists(dst): + on_disk.append(dst) + elif os.path.exists(src): + real.append(src) + else: + gone.append(dst) print(f"{args.db_kind}: {len(moves)} moves checked") print(f"landed: {landed}") print(f"still at src: {len(stale)}") print(f"missing from the DB: {len(missing)}") + print(f" on disk at dst, no row names it: {len(on_disk)}") + print(f" REAL — file still at src: {len(real)}") + print(f" gone — at neither path: {len(gone)}") if ignored: print(f"not indexed (extension ignored): {ignored}") if missing: exts = Counter(os.path.splitext(d)[1].lower() or "(no extension)" - for d in missing) + for _, d in missing) print("missing by extension: " + ", ".join(f"{e} {n}" for e, n in sorted(exts.items()))) - for label, items in (("stale", stale), ("missing", missing)): + for label, items in (("real", real), ("gone", gone), ("missing", on_disk), + ("stale", stale)): for path in items[:args.show]: print(f" {label}: {path}") if len(items) > args.show: diff --git a/serverAppConfigs-docs/Dankserver/Plex.md b/serverAppConfigs-docs/Dankserver/Plex.md index 9cc843e..9b2c683 100644 --- a/serverAppConfigs-docs/Dankserver/Plex.md +++ b/serverAppConfigs-docs/Dankserver/Plex.md @@ -27,7 +27,7 @@ public traffic can be fronted by Caddy like every other vhost. | Runtime | podman quadlet, `plex.service` (user manager) — migrated from the native `plexmediaserver.service` OS-package unit (2026-09) | | Image | `lscr.io/linuxserver/plex:1.43.5.11029-6bf8af3f0-ls329` (pinned; verified == the registry's `latest` manifest digest at pin time: `sha256:8f655bad…e9e2334`) | | Data root | `/var/lib/plexmediaserver` bind-mounted **in place** as `/config` (RW) — the migration moved zero bytes | -| Media | git: `/var/lib/media-meta/view` (the [[Media Metadata View]] overlay) bound at the same absolute path `/mnt/entropy` **read-only**; live today: `/mnt/entropy` itself, read-only — the view has never been installed. Either way every library path in the PMS database stays valid, zero re-scan | +| Media | `/var/lib/media-meta/view` (the [[Media Metadata View]] overlay) bound at the same absolute path `/mnt/entropy` **read-only** — live since the 2026-10-31 cutover, so the PMS database's recorded paths keep resolving with zero re-scan | | Identity | fleet rootless model — container root maps to the `dank` user (1000:1000); the deployer chowns the data root on first cutover | | Port | `32400/tcp` published on `0.0.0.0` — zero client reconfiguration | | Network | `dankserver_appnet`, alias `plex`; Tautulli reaches it at `http://plex:32400` | @@ -40,7 +40,7 @@ public traffic can be fronted by Caddy like every other vhost. The migration moved zero bytes: the container bind-mounts the native data root where it already lived, and the media archive re-mounts at `/mnt/entropy` inside the container — only the HOST side of that bind has moved -(the array today; the overlay view in git has never been deployed), so every +(the array until the 2026-10-31 view cutover, the overlay since), so every absolute library path in the PMS database keeps resolving. The one metadata change: rootless podman cannot map the real host uid 997, so the fleet model applies — container @@ -87,6 +87,16 @@ root runs as the `dank` user, and the deployer adopts the data root with while the HTTP layer finishes loading; the first boot of a years-old library took ~10 minutes (2026-09 cutover). The deployer gate now allows 600 s before failing; later boots are much faster (warm page cache). +5. **`32400` answers TLS only to remote clients.** PMS requires secure + connections, so `curl http://192.168.0.235:32400/identity` from any other + machine closes without a single byte (curl exit 52) — that reads as a dead + server beside a healthy one, and it is how a post-cutover health check gets + misread. Probe with `curl -k https://192.168.0.235:32400/identity`. Two + consequences: `plex.franksdank.cloud` works **only** because its `transport + http` block carries `tls_insecure_skip_verify` (that option makes Caddy speak + TLS to PMS's self-signed cert — delete it and the vhost 502s), and the scan + block below rides `http://127.0.0.1` **inside** the container, where insecure + connections are allowed. ## Triggering a scan diff --git a/tests/media_verify.bats b/tests/media_verify.bats index 1d9f8e1..340e32a 100755 --- a/tests/media_verify.bats +++ b/tests/media_verify.bats @@ -195,7 +195,7 @@ setup() { --share "$SHARE" --container /data [ "$status" -eq 1 ] [ "${lines[3]}" = "missing from the DB: 2" ] - [ "${lines[4]}" = "missing by extension: .log 1, .mkv 1" ] + [[ "$output" == *"missing by extension: .log 1, .mkv 1"* ]] } @test "--ignore-ext keeps a file the server never indexes out of the verdict" { @@ -208,5 +208,75 @@ setup() { [ "$status" -eq 0 ] [ "${lines[1]}" = "landed: 1" ] [ "${lines[3]}" = "missing from the DB: 0" ] - [ "${lines[4]}" = "not indexed (extension ignored): 1" ] + [[ "$output" == *"not indexed (extension ignored): 1"* ]] +} + +# wal_case — a Jellyfin database whose NEW row lives only in the +# write-ahead log: the server has committed the rename but not checkpointed it, +# which is the normal state of a library a scan is writing. The holder +# connection keeps the WAL from folding into the main file, and the verifier +# runs as a real subprocess so it faces the same files Plex and Jellyfin leave. +wal_case() { + python3 - "$JFDB" "$JOURNAL" "$SHARE" "$VERIFY" <<'PY' +import sqlite3, subprocess, sys +db, journal, share, verify = sys.argv[1:5] +w = sqlite3.connect(db) +w.execute("pragma journal_mode=wal") +w.execute("pragma wal_autocheckpoint=0") +w.execute("insert into BaseItems (Path, Type) values ('/data/Movies/Old.mkv', 'x')") +w.commit() +w.execute("pragma wal_checkpoint(truncate)") +holder = sqlite3.connect(db) # last-connection close would checkpoint +w.execute("update BaseItems set Path='/data/Movies/Old/Old.mkv'") +w.commit() +r = subprocess.run([sys.executable, verify, "--journal", journal, + "--db-kind", "jellyfin", "--db", db, + "--share", share, "--container", "/data"], + capture_output=True, text=True) +print(r.stdout, end="") +sys.exit(r.returncode) +PY +} + +@test "a row the server committed but has not checkpointed is proof, not a miss" { + move_row "$SHARE/Movies/Old.mkv" "$SHARE/Movies/Old/Old.mkv" + run wal_case + [ "$status" -eq 0 ] + [ "${lines[1]}" = "landed: 1" ] + [ "${lines[3]}" = "missing from the DB: 0" ] +} + +# The DB alone cannot tell a lost file from a sidecar: both are "no row at the +# destination". The tool therefore stats the two paths and separates the classes +# the runbook names, so an operator never reads a `.pdf` as a lost film or, +# worse, reads a real loss as a sidecar. +@test "a file the database does not name that still sits at src is the pass's own damage" { + mkdir -p "$SHARE/Movies" + echo film > "$SHARE/Movies/Old.mkv" + move_row "$SHARE/Movies/Old.mkv" "$SHARE/Movies/Old/Old.mkv" + + run python3 "$VERIFY" --journal "$JOURNAL" --db-kind jellyfin --db "$JFDB" \ + --share "$SHARE" --container /data + [ "$status" -eq 1 ] + [ "${lines[3]}" = "missing from the DB: 1" ] + [ "${lines[4]}" = " on disk at dst, no row names it: 0" ] + [ "${lines[5]}" = " REAL — file still at src: 1" ] + [ "${lines[6]}" = " gone — at neither path: 0" ] + [[ "$output" == *"real: $SHARE/Movies/Old.mkv"* ]] +} + +@test "a file at neither path is gone, and a file at dst the server ignores is not a loss" { + move_row "$SHARE/Movies/Gone.mkv" "$SHARE/Movies/Gone/Gone.mkv" + mkdir -p "$SHARE/Movies/Sidecar" + echo cover > "$SHARE/Movies/Sidecar/cover.jpg" + move_row "$SHARE/Movies/Album/cover.jpg" "$SHARE/Movies/Sidecar/cover.jpg" + + run python3 "$VERIFY" --journal "$JOURNAL" --db-kind jellyfin --db "$JFDB" \ + --share "$SHARE" --container /data + [ "$status" -eq 1 ] + [ "${lines[3]}" = "missing from the DB: 2" ] + [ "${lines[4]}" = " on disk at dst, no row names it: 1" ] + [ "${lines[5]}" = " REAL — file still at src: 0" ] + [ "${lines[6]}" = " gone — at neither path: 1" ] + [[ "$output" == *"gone: $SHARE/Movies/Gone/Gone.mkv"* ]] }