Benchmark-gated (equivalence + BEFORE/AFTER; results + reproduce commands in
benches/ROUND7.md):
- Photos timeline re-grouped + re-laid-out the whole accumulated library on
every 60-item page (both `groups` and `photoRows` were $derived over the
full list), Σ ≈ O(N²/60) main-thread work during a scroll. Pages arrive
newest-first so grouping is append-only: the new PhotoTimeline
(lib/utils/photoTimeline.ts) re-buckets only the fresh page and re-lays-out
only changed groups, reusing untouched groups' cached rows, falling back to
a full rebuild on any config/deletion/non-append change. The pure
buildPhotoRows is the verbatim reference the gate holds it equal to at every
page. 50×60 drain: 76 500 → 3 000 grouping ops (25.5x), 23.0 → 2.2 ms
(10.6x).
- Range downloads paid authz + access-notify twice: download_file_impl
resolves the file via get_file_with_perms, then the Range branch re-ran
require_file + notify_file_accessed per request. Media/PDF viewers fetch
exclusively via Range (one request per seek), so every seek in a scrub
re-authorized an already-cleared file. Now routed through the non-perms
get_file_range_preloaded (matching the share-landing + WebDAV range paths);
the unused _with_perms range method is removed. The request-level gate still
denies before the branch runs (bench asserts member granted, outsider
denied). Per seek removed: WARM 0.67 µs, COLD 1362.66 µs — a grant-cascade
drive-resolve query per seek for a shared-drive recipient on a cold cache.
- /api/folders/{id}/resources row→DTO mapping cloned row.name into the DTO
though the row is owned; folders move it (fixed icons), files compute the
name-derived icon/category classes first then move it. 500-row page:
10.004 → 9.004 allocs/row (500 clones removed), output identical.
Deferred with rationale in ROUND7.md: thumbnail ACL-before-304 (security
posture — needs a security review, not a perf tweak), batch_operations
Arc<str>→String widening, list-view O(N²) on smaller lists, and the serial→
join! pairs (decide-by-bench with injected latency, per the round-6 rejection).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017aJu9ghvuT8WqC31ZEGTBA
Benchmark-gated (equivalence + BEFORE/AFTER in examples/bench_*, results
and reproduce commands in benches/ROUND6.md):
- CardDAV whole-book REPORT + depth-1 PROPFIND stream through a PG
cursor (stream_contacts_by_book, 500-contact pages) instead of
materialising every vCard twice: 8 000 contacts TTFB 37.4 → 7.6 ms
(4.9x), peak heap 19.0 → 7.0 MiB (2.7x), wall -23%; REPORT and
PROPFIND byte-identical to the buffered writers.
- NC numeric-id chain fully borrowed: get_or_create_file_ids/folder_ids
take &[&str] and return HashMap<Uuid, i64>; batch_resolve_ids callers
(PROPFIND pages, REPORT, trashbin, OCS search) pass id slices and look
up via nc_id_of. 2.006 → 0.006 allocs/child (334x), 1.53x wall per
500-child page. batch_check_favorites binds &[&str] as text[].
- file_blob_read_repository listing SELECTs drop id::text/folder_id::text
server casts: rows decode binary Uuid (16 vs 36 bytes on the wire) and
render once in row_to_file. A/B on 500-row pages: 1.225 → 1.044 ms
mean (1.17x), p95 1.686 → 1.345 (bench_uuid_text_cast; single-row,
param and min() sites left as-is deliberately).
- IncrementalHasher::finalize_hex renders through common::fmt::hex_lower
instead of one format! per digest byte: 18 → 1 (md5) / 35 → 1 (sha256)
allocs per chunk finalize, 14-15x wall.
- Share landing overlaps the access-count UPDATE with the unlock fetch
via tokio::join! (one round-trip off every public link hit).
- REJECTED by benchmark and reverted: try_join_all fan-out of the
batch-favorites authz pre-check — 42.6 → 56.4 ms cold, 0.15 → 0.23 ms
warm against local-socket PG (bench_favorites_authz kept as evidence).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017aJu9ghvuT8WqC31ZEGTBA
Round 3 of benchmark-gated optimizations (benches/ROUND3.md; every change
gated by a before/after benchmark — an AFTER that did not beat its BEFORE
was to be rolled back; none needed it. Equivalence gates assert identical
row sequences / byte-identical output on every behavior-preserving rewrite):
DB hot paths (local PG16, EXPLAIN-verified):
- Web-UI listing (list_resources_paged): cursor pushed INSIDE the
folders/files UNION-ALL branches as sargable row-value comparisons with
per-branch ORDER/LIMIT + two partial expression indexes
(folder_id, LOWER(name), id). 20k-entry folder: 26.6 -> 1.3 ms/page
(19.5x); other sort modes at parity or better. New migration
20260918000000. [benches/LISTING-KEYSET.md section in ROUND3]
- Photos timeline (list_media_files): per-drive CROSS JOIN LATERAL top-N
on the timeline index, joins moved above the top-N. 50k-photo library:
97.4 -> 1.6 ms/page (55.7x). The old "LIMIT stops the scan early"
comment was refuted by EXPLAIN.
- PROPFIND sub-folders (both DAV surfaces): keyset list_folders_batch off
idx_folders_unique_name replaces COUNT(*) OVER() + LIMIT/OFFSET
(5k dirs: 79.7 -> 17.9 ms full walk, 4.5x).
Concurrency:
- Basic-auth cache single-flight (moka try_get_with): 8 concurrent DAV
connections at TTL expiry paid 8 Argon2id runs (2.6 s CPU + 8x64 MiB);
now 1 (300 ms). Failed verifications remain uncached.
- CachedBlobBackend per-hash single-flight + unique tmp names: 16
concurrent cold readers = 16 full remote downloads racing truncating
writes on ONE deterministic .tmp (corruptible cache); now 1 download
(16x less egress, 2.8x wall on a shared link) and torn files can never
be renamed into the cache.
I/O and allocations:
- Chunk-assembly reads 64K -> 512K buffers (2.3x, 8x fewer syscalls);
chunk-spool writes via BufWriter 512K (5.6x, 32x fewer syscalls).
- S3/Azure put_blob_from_bytes_unsynced overrides: dedup settle no longer
pays a HEAD probe per new chunk (2 RTT -> 1, 1.8x); Azure stops copying
every chunk (Bytes -> Body, -0.44 ms - 4 MiB alloc per 4 MiB chunk).
- Entity->DTO mapping: Arc<str> interning of closed-set display fields +
common MIMEs, 1-alloc etag/size formatting, FolderDto moves instead of
clones. File row: 11 -> 4 allocs; folder row: 11.8 -> 1 (2.1x faster).
- CardDAV REPORT: deleted dead per-contact vCard pre-generation and the
O(N^2) uid scan whose result was discarded (5k contacts: 55.7 -> 5.7 ms,
9.8x); byte-identical XML asserted.
- Search-results cache: byte weigher + 32 MiB budget
(OXICLOUD_SEARCH_CACHE_MAX_BYTES) replaces the 1000-ENTRY cap that let
~300 MiB of enriched rows sit in RSS; read latency parity.
- Dropped aws-config + aws-smithy-types (zero references; -82 dep-graph
nodes, three SDK stacks gone from every build). tokio "process" is now
an explicit feature (was enabled transitively by aws-config).
Frontend:
- Cached Intl.DateTimeFormat keyed by (locale, options) in formatDate and
4 sibling callsites: 20k dates 2612 -> 51 ms (51.6x); vitest gate
asserts output identity across locales and a 3x floor.
Validation: cargo fmt + clippy --all-features --all-targets -D warnings
clean; 518 unit + 548 integration-cfg tests green; new-shape endpoints
smoke-tested end-to-end over HTTP (all 5 listing sort modes with cursor
walks, WebDAV PROPFIND Depth-1, photos timeline, Basic-auth DAV login);
frontend npm run check clean, new vitest gates green.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EBsU2qEzny3A8WQUEuMNCr
Round 2 of benchmark-gated optimizations (benches/ROUND2.md; every change
gated by a before/after in examples/bench_round2.rs — an AFTER that did
not beat its BEFORE was to be rolled back; none needed it):
- Range requests (REST/DAV/shares) answered from the moka content cache
for sub-10MB files: PG resolve + open/seek/read -> Bytes::slice.
256KiB seeks: 1,730/s -> 3.7M/s (p50 552us -> 0.15us).
- Streaming folder/share ZIPs via tokio duplex: TTFB no longer scales
with archive size (326ms -> 0.4ms on 192MiB corpus; total also faster).
Content-Length dropped (size unknown up front).
- NC chunked-upload per-PUT gate: O(k) directory scan+stat -> in-RAM
per-session counter (lazy rebuild on cold start). 1,000-chunk upload
gate cost: 33.1s -> 0.09s cumulative.
- Delta download + commit-verify now use the CDC path's
buffered(read_prefetch) read-ahead: 64-chunk drain at 5ms open
latency 440ms -> 51ms; order preserved.
- CDC ingest settles batches on a spawned task (depth-1 pipeline) so
the source stream keeps flowing during PG pin + backend writes;
rollback ledger shared + lock-serialized so compensation stays exact
on cancellation. 512MiB paced ingest: 60-69 -> 74-75 MB/s.
OXICLOUD_INGEST_OVERLAP=0 restores inline settling (ops/bench hatch).
- Frontend: instant-upload BLAKE3 hashing moved off the main thread to
a bounded Web Worker pool (File handles by reference); vitest gate
asserts the pool beats sequential (first gate draft posting buffers
was 2.6x slower and was rewritten — copies dominated).
Validation: cargo fmt + clippy -D warnings clean; 514 unit + 544
integration tests green; 270 frontend tests green.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CBK1RdtzyP6759Muqe1K1w
Every change is benchmark-verified (harness + before/after numbers in
benches/, measured on this branch; reproduction commands in each doc):
DAV / sync-client hot paths
- PROPFIND dead-properties: one = ANY($1) query per 500-child page instead
of one sequential query per child, and indexable `=` predicates instead
of IS NOT DISTINCT FROM (seq scans). 2,000-child folder: 1.07-4.54 s of
DB chatter -> 4-6 ms (258-773x). Applied to native + NC PROPFIND and
both NC REPORT handlers. [benches/DEAD-PROPS.md]
- Folder paging: keyset cursor (name > $last) + new partial index
(folder_id, name) replaces LIMIT/OFFSET full-folder rescan per page.
Full 20k-file walk: 1266 ms -> 77 ms (16.5x). New migration
20260917000000. [benches/PROPFIND-PAGING.md]
- NC chroot / default-drive resolution: moka caches (30 s TTL, explicit
invalidation on drive mutations) for find_default_for_user and the
markerless chroot FolderDto. 2 uncached queries + 2 pool checkouts per
NC/WebDAV/WOPI request -> sub-us moka hit (p50 0.7-3.6 ms -> ~1 us).
[benches/CHROOT-CACHE.md]
- Quota: PROPFINDs whose prop list never names a quota prop skip the
2-query resolution entirely (wants_quota()); the remaining lookups read
2 columns instead of the full auth.users row with its <=512 KiB avatar
(11-16x, p50 3.4 ms -> 0.29 ms). Same narrow read now gates every
upload quota check. [benches/QUOTA-PATH.md]
CPU on the request path
- ZIP exports (folder download, share ZIP, batch download): entries whose
MIME says already-compressed (JPEG/MP4/zip/pdf/...) are Stored instead
of Deflate - deflate ran inline on the tokio writer task at ~41 MB/s
for ~0% size gain. Mixed media corpus: 4.31x wall and CPU, archive size
unchanged. Shared predicate in common::mime_detect. [benches/ZIP-MEDIA.md]
- Compression layers: tower-http's default maps to Brotli QUALITY 11
(verified in brotli-8.0.2 source and empirically: 90 ms per 64 KiB JSON
response, 1.3 s per 700 KiB bundle). Both layers pinned to Precise(4):
99x less CPU for ~15% more bytes. SPA assets are now precompressed at
build time (scripts/precompress.mjs, 77% smaller) and served via
ServeDir::precompressed_br/gzip: 2016x less per-request work, and
clients get the better q11 bytes. [benches/STATIC-PRECOMPRESSED.md]
Batched / cached backend paths [benches/NPLUS1-AND-CACHES.md]
- Content-search ReBAC re-verification: new
AuthorizationEngine::check_files_read_batch (default = old loop;
PgAclEngine override batches drive resolution + reuses role cache).
200 sequential point SELECTs per search -> 1-2 queries.
- Batch-ZIP subtree downloads: drop per-file re-authz + per-file Recent
recording (2 writes/file) for subtree entries already authorized at the
root - mirrors the native folder-download path. ~6,000 statements
removed from a 2,000-file archive.
- CDC chunk manifests: immutable by content address, now moka-cached
(weight-bounded 32 MiB, 60 s TTL, positive-only, invalidated on delete)
- removes one manifest query (p50 0.44-4.4 ms) from every stream,
range and full blob read.
- People tab: grouped COUNT + batched cover lookup instead of dragging
every face row with its 2 KiB embedding (10k faces: 30.4 ms & 21 MB ->
3.8 ms & 1.3 KB, 8.1x); merge() is one set-based UPDATE.
[benches/PEOPLE-LIST.md]
- Photos timeline cursor: raw timestamptz comparison instead of
EXTRACT(EPOCH ...) wrapper + IS NULL OR disjunction - cursor is an
index boundary again, deep scroll stops re-scanning skipped rows.
- Public share landing: one atomic UPDATE ... access_count + 1 (was
SELECT + full-row write-back: racy, lost updates, clobbered concurrent
owner edits) - 3 round-trips -> 2 per visit.
- move_to_trash: dead full-entity SELECT feeding a documented no-op
removed from both branches; dead fields dropped from TrashService.
- NFC normalization: is_nfc_quick fast path skips the decompose/recompose
state machine for the ~100% already-NFC case (every row loaded from PG).
Frontend
- Large folders paint after page one (~200 items) via fetchFolderListing's
new onPage hook instead of waiting for every sequential page.
- Tested-and-reverted (kept for the record): cached Intl.Collator for name
sorts - vitest showed it 2x SLOWER than V8's argument-less localeCompare
fast path (5.6 ms vs 12.1 ms / 5k names). Sort order untouched.
New bench harnesses under examples/ (bench feature): zip_media,
dead_props, chroot_cache, quota_path, people_list, propfind_paging,
static_precompress.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CBK1RdtzyP6759Muqe1K1w
- and protect amount of properties
- azure_core 0.21.0 is using quick-xml 0.31.0 which is Dos-able
azure_core is no more maintained, would migrte to official azure lib
later
lopdf <0.42.0 has an unbounded-recursion stack overflow on deeply
nested PDF objects (advisory 2026-06-21). The vector through OxiCloud
is the search-index text extractor — anyone who can upload a file can
ship a malicious PDF, and the existing catch_unwind in
text_extractor::extract_pdf does not save us: a stack overflow aborts
the process, it is not a panic.
pdf-extract 0.12.0 requires lopdf ^0.42 which adds the depth bound;
the only consumer call (`extract_text_from_mem`) is API-compatible,
no source changes needed.
This reverts ee51b32. The create_new change showed no measurable throughput
benefit — three 9-rep interleaved runs on the same ext4 device swung −12%..+21%
at the 256 KiB CDC size (a negative stat on a warm dentry cache is ~µs, below
the shared-disk noise floor). Applying the same "no change without a measured
win" bar used for the pool-sizing revert: the idiom/TOCTOU angle is real but the
race is already prevented upstream by the PG pin-or-classify serialisation, so
it's defence-in-depth only — not enough to keep an unmeasured change. Reverts
the production change, the bench, and its doc together.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JG5yYZ9s868mJwqT2Qz7ez
Replace the try_exists(stat) + File::create(O_CREAT|O_TRUNC) pair with a single
OpenOptions::create_new (O_CREAT|O_EXCL), treating AlreadyExists as the existing
idempotent skip. One metadata syscall per new chunk instead of two (each a
spawn_blocking round-trip), and O_EXCL closes the check-then-create TOCTOU the
old pair left open (a racing writer could be truncated).
Honest measurement caveat (benches/BLOB-WRITE.md): the wall-clock throughput
effect is BELOW the noise floor of the test environment — three 9-rep
interleaved runs on the same ext4 device swing −12%..+21% at the 256 KiB CDC
size, because a negative stat on a warm dentry cache is ~µs, dwarfed by the
chunk's create+write+flush. So this is justified as a code-quality / correctness
change (canonical idiom, strictly fewer syscalls, closes a TOCTOU, zero
downside), NOT as a benchmarked perf win.
The sibling idea — reusing the File handle for the fsync sweep — is deliberately
NOT done: sync_blobs is a single end-of-stream sweep over all the upload's new
hashes, so retaining handles would hold thousands of FDs open (>ulimit) on a
large upload. The re-open sweep is a deliberate FD-frugal design.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JG5yYZ9s868mJwqT2Qz7ez
bench_pool_concurrency drives the real service path (Semaphore(K) gating
spawn_blocking(bench_render_all)) with a gallery of concurrent callers and
sweeps the decode-permit count K, reporting throughput + p50/p99. Run under
taskset to model a CPU quota: it shows the effect of sizing the image pools to
effective_parallelism (K=cores) vs the host count (over-subscribed).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JG5yYZ9s868mJwqT2Qz7ez
bench_tokio_runtime (behind the bench feature) measures the two things
build_runtime changes vs the #[tokio::main] defaults:
A) worker over-subscription — throughput + p50/p99 of an async+CPU workload
with many workers vs core-sized, run under taskset to model a CPU quota.
B) blocking-pool RSS blast radius — peak RSS flooding the blocking pool with
memory-heavy spawn_blocking tasks, default 512 vs bounded.
No Postgres needed. Lets us verify the runtime change empirically before/after.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JG5yYZ9s868mJwqT2Qz7ez
Adds `bench_blob_prefetch` (behind the `bench` feature) to measure the
local backend's chunk read-ahead depth — the `buffered(N)` read-ahead in
DedupService::stream_chunks fed by BlobStorageBackend::read_prefetch().
The bench reproduces the exact production reassembly combinator over a
real LocalBlobBackend (chunk files scattered across the 256 hash-prefix
dirs) and sweeps the prefetch depth under the two axes that decide whether
read-ahead helps on local disk:
- consumer speed: unthrottled (disk-bound) vs throttled@MB/s (network-bound)
- page cache: warm vs cold (posix_fadvise DONTNEED, Linux best-effort)
N=1 is current production; higher N is the candidate change. Lets us
verify gains/regressions empirically before changing read_prefetch(),
since the trait doc deliberately defaults local to 1.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JG5yYZ9s868mJwqT2Qz7ez
read_blob_bytes read the same storage.chunk_manifests PK row twice per
full-blob read — blob_size (SELECT total_size) then read_blob_stream
(SELECT chunk_hashes) — even though both columns live in one row. Fold
them into a single `SELECT chunk_hashes, total_size` and share the chunk
stream builder via a new stream_chunks helper. The legacy (no-manifest)
path is unchanged. Output is identical; the read just costs one fewer DB
round-trip.
Benchmark (examples/bench_blob_manifest.rs, isolates the manifest lookup
against the real Postgres): ~1.9x throughput and p50/p99 roughly halved on
that sub-step; the win is the removed round-trip under pool pressure during
upload bursts. Note this is the manifest sub-step only — end-to-end
read_blob_bytes is dominated by the actual chunk reads, and it is a
background path (thumbnail generation / EXIF / indexing), not normal gallery
serving. Methodology + honest framing in benches/BLOB-MANIFEST.md.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Videos now get a thumbnail generated eagerly server-side on upload, through
the same WebP/blob-hash pipeline as photos — instead of the old browser path
that only ran when the Photos grid first rendered a video tile, re-downloaded
the whole video to seek a frame, and PUT 3 JPEGs back (and produced nothing at
all for HEVC/.mov, which a browser <video> cannot decode).
- New VideoFramePort (application) + FfmpegVideoFrameService / NoopVideoFrameService
(infrastructure): shell out to the system ffmpeg (no compile-time libav dep),
extract one representative frame as PNG, bounded by its own semaphore + a
per-process timeout + kill_on_drop. Noop when ffmpeg is absent/disabled, so
videos degrade gracefully to no thumbnail.
- ThumbnailRefreshHook.on_file_created routes video/* to
generate_video_thumbnails_background: stream the (decrypted, reassembled) blob
to a size- and time-bounded temp file on the data volume, extract a frame, and
reuse the shared render_and_persist_all_webp helper — so video thumbnails are
WebP, blob-hash keyed (dedup'd) and content-negotiated, exactly like photos.
- GET thumbnail serves the video's WebP to every client (byte-sniffed
Content-Type); a genuine miss returns 204.
- Config: OXICLOUD_ENABLE_VIDEO_THUMBNAILS (default true, needs ffmpeg detected
at startup) + OXICLOUD_FFMPEG_PATH / _CONCURRENCY / _TIMEOUT_SECS / _MAX_MB.
- Dockerfile installs ffmpeg in the runtime image.
- Frontend: drop the client-side generateVideoThumb/frameFromVideo re-download
path; the server is now the source of truth.
Benchmark (examples/bench_video_thumbnails.rs, needs ffmpeg): 4/4 codecs incl.
HEVC/.mov produce a thumbnail server-side (was 0% for HEVC); ~50-70 ms/frame in
the background; ~3.9 KB preview WebP; up to ~23x less per-first-view transfer on
the test corpus (far more on real multi-MB clips). Methodology in
benches/VIDEO-THUMB.md.
Hardening from an adversarial review: video render holds the decode_semaphore
like the image path; the ffmpeg scale filter bounds both dimensions; the blob
stream has a timeout; the temp file lives on the data volume; the size cap uses
saturating_mul.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Thumbnails are now generated eagerly as lossy WebP (the primary codec) and
served to clients that advertise `Accept: image/webp`; JPEG is kept as a lazy
fallback for older clients and NextCloud, generated on first request and then
cached like WebP.
- ThumbnailFormat{Webp,Jpeg} enum threaded through encode/render/generate, the
on-disk path ({hash}.webp / {hash}.jpg), the moka cache key
(file_id, size, format), and cleanup (both formats removed).
- file_handler: parse Accept -> format, format-keyed ETag, `Vary: Accept` on
every response (incl. 304) so shared caches never serve the wrong codec;
Content-Type is byte-sniffed (infer) so it always matches the bytes.
- preview_handler (NextCloud) pins JPEG.
- webp = "0.3" (vendored libwebp via cc, no system dependency).
WEBP_QUALITY=82, chosen via a quality sweep (bench Table E1): SSIM within
~0.005 of JPEG q80 (imperceptible at thumbnail scale) for ~62% fewer bytes. On
the photo-realistic bench corpus the full set (3 sizes x 3 photos) drops 65.6%
(213->73 KB); real photos with edges/text land nearer ~25-40%. Encode is +5ms,
paid once in the eager background generator (off the request path).
The bench corpus is now photo-realistic (per-channel sums of low-frequency
sinusoids) instead of white noise, which had distorted codec byte ratios.
Methodology + numbers in benches/WEBP.md.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The owner short-circuit in PgAclEngine::check ran a PK query
(SELECT user_id FROM storage.folders/files WHERE id=$1) on every authorization
check of a folder/file — the common case, since users mostly act on their own
resources. Memoise it in an owner_cache (moka, TTL 300s, 100k cap). The owner
column is immutable, so this is safe: the cache maps resource -> real owner and
can never grant a non-owner access (a different caller's owner==uid test fails
against the cached owner and falls through to grants); a hard-deleted resource
that briefly resolves to its former owner simply fails later at execution with
NotFound. The per-check sql_queries counter now increments only on a miss.
Removes 1 DB query + 1 pool-connection acquisition per owner check. Magnitude is
deployment-specific (query latency x whether the pool is contended); see
benches/ACL-OWNER-CACHE.md.
Also adds two DB perf-investigation harnesses, gated behind the `bench` feature
(need the dev Postgres; zero prod impact):
- examples/bench_db_pool.rs + benches/DB-POOL.md — pool size vs tail latency
- examples/bench_owner_cache.rs + benches/ACL-OWNER-CACHE.md — owner query vs cache
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Replace the image crate's scalar resampler with fast_image_resize
(AVX2/SSE4.1/NEON) in a shared encode_thumbnail() helper. render_all now
converts to RGB8 once and SIMD-resizes the shared buffer per size. Lanczos3 for
downscaling, CatmullRom when upscaling (Lanczos rings on enlargement).
Also folds the duplicated path-variant generate_all_sizes_background into the
shared render path -- it had missed BOTH shrink-on-load and SIMD resizing -- so
every thumbnail path now goes through one optimised routine (no duplication).
Measured on 14 cores vs the post-1.5 state (benches/BASELINE.md):
- PNG 2.60x faster (33.6->12.9ms), GIF/WebP 1.25-1.6x: full-resolution decode
paths where the resize dominates, so SIMD helps most
- JPEG only ~7% (shrink-on-load already shrank the bitmap) but peak heap fell
another ~2.5x (17.6->7.1MB): tight RGB buffers, RGB conversion once
- quality SSIM 0.986-0.994 at identical dims (>=0.98 gate)
Thumbnails are now exactly max_dim on the long side (e.g. 400x266) vs the old
fit-within 399x266 -- a <=1px change, invisible under object-fit: cover.
Bench example gains an exact-dims quality reference + semaphore throughput table.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Decode JPEGs at the smallest DCT scale (1/8·1/4·1/2·1/1) whose long axis is
still ≥ the largest needed thumbnail (800px), via jpeg-decoder, instead of a
full-resolution decode through the image crate. The full-res bitmap — the
dominant time and RAM cost — is never materialised. PNG/GIF/WebP and unusual
JPEG colour spaces (CMYK / 16-bit grey) fall back to a full decode.
Extracts the shared decode + EXIF-orientation logic into decode_oriented(),
removing the duplication that existed between render_thumbnail_from_data and
render_all_thumbnails_from_data.
Measured on 14 cores (see benches/BASELINE.md):
- render_all 1.8-2.0× faster (12MP 111->61ms, 48MP 398->203ms)
- peak heap 5.5-14.8× lower, now decoupled from source MP (~18-25MB regardless)
- saturated throughput 3-3.6× (parallel efficiency 4.9×->8.5×)
- quality SSIM 0.987-0.999 (>=0.98 gate), PSNR 47-55dB
Also adds the Phase 0 benchmark harness (gated behind the `bench` feature, zero
prod impact): deterministic image corpus (src/bench_support.rs), criterion
latency bench (benches/thumbnails.rs), and a peak-RAM/throughput/SSIM harness
(examples/bench_thumbnails_mem.rs). Baseline + before/after in benches/BASELINE.md.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The SvelteKit app under /frontend has fully superseded the legacy
vanilla-JS/CSS frontend in /static, which was only ever served by a
debug `cargo run` / `PROFILE=dev` and never shipped to production.
Remove it together with the whole subsystem that existed only to
support it (~54k lines).
Frontend & assets:
- Delete /static (js/, css/, *.html, sw.js, basemaps/, locales symlink).
- Relocate the brand/PWA assets (logo/, favicon.ico, manifest.webmanifest)
to frontend/static/ so they ship with the SPA. This also fixes the
favicon, which app.html referenced but was missing from the prod bundle.
- Migrate the Nextcloud login-flow redirects from /nextcloud-error.html
to the SvelteKit /nextcloud/error route.
Web layer:
- Simplify resolve_static_path: drop the PROFILE=dev branch; always prefer
the Vite static-dist/ build, fall back to the configured path.
- Resolve i18n locales from the served SPA dir with a frontend/static
fallback so `just dev` works without a prior build.
Build:
- Prune build.rs from 1262 to ~70 lines (git metadata only); the Rust asset
pipeline and the OXICLOUD_RUST_ASSETS rollback flag are gone.
- Drop the now-unused build-dependencies (oxc_*, lightningcss).
- Remove the COPY static lines from the Dockerfile (cacher + builder).
Tooling & docs:
- Delete biome.json, jsconfig.json, tools/check-*.py, identifier.sh.
- Remove the legacy front-* justfile recipes; repoint the design-system
scripts (locales, dead-tokens, brand-drift, token-docs) at the frontend,
and drop check-contrast/check-headings (coupled to the old token
taxonomy / multi-page HTML).
- Repoint docs/DESIGN-SYSTEM.md links; remove 5 superseded docs/plan/*.
Backend dead code:
- Remove the dead `folder_repo` field from FileBlobWriteRepository.
- Remove the deprecated GET /api/folders/{id}/listing endpoint
(superseded by /resources).
Verified: cargo clippy (all-features/all-targets) clean, cargo test
--workspace 448 passed, cargo fmt clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Implements the last Phase 2 piece: a working face detector/embedder behind
the new `faces-onnx` cargo feature (mirrors how `plugins` gates wasmtime).
Inert by default — the default build is unchanged and ships the no-op
analyzer.
Pipeline (InsightFace/immich pattern): SCRFD detection with 5-point
landmarks → least-squares similarity alignment to the canonical 112×112
template → ArcFace embedding → L2-normalized 512-d vector.
- face_geometry.rs (always compiled, unit-tested): SCRFD anchor/distance
decode, NMS, the closed-form (complex-number) similarity transform,
bilinear affine warp, NCHW normalization, L2-norm, Laplacian sharpness.
11 unit tests cover the error-prone math with no model needed.
- onnx_face_analyzer.rs (feature `faces-onnx`): wires the geometry to ONNX
Runtime via `ort` (load-dynamic, so libonnxruntime is dlopen'd at runtime
and the crate builds without it). Inference runs on spawn_blocking; each
session is serialized behind a Mutex. Loads via `ort::init_from` (fallible)
not ORT's lazy loader, which would panic under `panic = "abort"`.
- config: FacesConfig + OXICLOUD_FACES_{ORT_DYLIB,DETECTOR_MODEL,
EMBEDDER_MODEL,DET_SIZE,DET_THRESHOLD,NMS_THRESHOLD,INTRA_THREADS}.
- di: build_face_analyzer() loads the real analyzer when the feature is
compiled in and runtime+models are configured; any missing piece or load
failure degrades to the no-op analyzer (logged) so startup never fails.
- ort/ndarray added as optional deps; example.env documents the setup.
Models and the ONNX Runtime dylib are operator-provided at runtime and are
never committed. Cannot be exercised in CI (no models/dylib); the geometry
is unit-tested and the ONNX seam is isolated.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JW6ghFMDtnRYuYNzZhb47M
Backend — Photos timeline now groups by real capture date instead of upload time. New MediaMetadataService (FileLifecycleHook) extracts EXIF DateTimeOriginal from images and container creation_time from videos (mov/mp4/mkv) via nom-exif, timezone-correct (OffsetTimeOriginal), persisting captured_at so the existing media_sort_date trigger takes over. Adds POST /admin/photos/metadata/reextract to backfill existing media. Falls back to upload date when no embedded date exists.
Frontend — premium grid cards: combined metadata line (relative date · size, owner avatar when shared), custom selection checkbox with a clear checked state, uniform full-width 4:3 thumbnail tiles independent of filename length, centered file-type icons, and a hit-test fix so checkbox/star/kebab clicks reach the controls (the decorative thumbnail no longer captures pointer events). Notification messages internationalised across all 16 locales. Broader polish: design tokens, a11y/focus-visible states, brand + PWA assets.
Chore — bump semver-compatible dependencies (cargo upgrade); add nom-exif 3.6.1.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Both sides added a parameter to create_application_services and a
setup step before it: this branch's storage-usage/quota service (for
the instant-upload path) and main's Tantivy content index (for
SearchService). The resolution keeps both — the signature takes both
arguments and the build runs storage usage as step 3c and the content
index as 3d.
https://claude.ai/code/session_01WdNenpnujNR2sc32XVvwfS
/api/search now finds files by CONTENT as well as by name: BM25-ranked
matches over extracted text (PDF, Office OOXML/ODF, plain text/code)
with typo-tolerant fuzzy terms and search-as-you-type prefix matching,
served from an embedded Tantivy index at {storage}/.search-index.
Pipeline (all off the request path, mirroring tree-etag + thumbnails):
- statement triggers on storage.files append to a durable dirty queue
(storage.search_index_dirty) - every write surface (REST, WebDAV,
NextCloud, WOPI, trash) is covered, crash-safe by construction
- ContentIndexWorker drains the queue on the maintenance pool, extracts
text once per unique BLAKE3 blob (storage.blob_extracted_text cache:
N copies = 1 extraction, renames/moves = 0 re-extraction) and applies
batched single-writer Tantivy commits; queue rows are deleted only
after the commit succeeds (at-least-once, idempotent upserts)
- the index is a derived artifact: a version-marker mismatch wipes and
reseeds it from Postgres, which remains the single source of truth
SearchService merges content hits into the existing name search: hits
are hydrated through ONE SQL round-trip that re-applies user scope,
trash state and every active filter (a stale index id can never leak),
scored below name matches, and returned with a plain-text snippet and
a match_source field. Index failure or
OXICLOUD_ENABLE_CONTENT_SEARCH=false degrades to name-only search; a
discard-only janitor keeps the trigger-fed queue bounded while disabled.
The frontend renders the snippet under the file name in list view.
New dependencies: tantivy 0.26, zip 8.6 (deflate only), pdf-extract 0.10.
https://claude.ai/code/session_01Sc7F4xbo83YbFAQ4xEeDrX
Every upload surface previously wrote each byte to disk twice: the HTTP
body was spooled to a temp file (or assembled from chunk parts), then
mmap-re-read for FastCDC analysis, and finally the new chunks were
written to the blob backend. CDC could not start until the last byte
arrived, so large uploads paid receive + reread + rewrite latency.
The dedup engine now chunks, hashes and settles the stream WHILE it
arrives (fastcdc AsyncStreamCDC + incremental BLAKE3):
- Each batch of distinct chunks is pinned-or-classified by ONE
`UPDATE … RETURNING` (no check-then-bump TOCTOU; pinned chunks can't
be reclaimed mid-upload), and only chunks the store doesn't have are
written — a full dedup hit performs zero content writes.
- Durability before visibility is preserved: one batched fsync sweep,
then one batched INSERT, then the manifest. Identical concurrent
uploads are resolved at the manifest INSERT via ON CONFLICT (the
loser releases its references and becomes a dedup hit).
- A drop guard rolls back pins and surfaces written-but-unregistered
chunks to GC if the request future is cancelled mid-stream.
- MIME sniffing now peeks the first bytes in-flight; client-requested
MD5/SHA-256 checksums are computed by a stream tee — the post-upload
re-read of the assembled file is gone.
All surfaces converge on the new interfaces::upload_ingest helper:
REST multipart, WebDAV PUT, NextCloud PUT, WOPI PutFile, the dedup
endpoint, and both chunked-upload completions (which now stream their
ordered parts straight into the store instead of writing an assembled
file — chunk parts persist until finalize, so completion is genuinely
retryable). The legacy blob re-chunk migration streams from the
backend with no spool file either.
Legacy removed: store_from_file + mmap CDC analysers + temp-path
plumbing through every port (pre_computed_hash, save_file_from_temp,
update_file_content_from_temp), upload_spool + assembled-file
assembly in both chunked services, create_file/update_file byte-slice
variants (no callers), common::temp, the OXICLOUD_UPLOAD_TMPDIR
config, and the memmap2 dependency.
Verified end-to-end against PostgreSQL 16: 8 MB upload (26 chunks),
identical re-upload (dedup hit, zero writes), 3-byte edit re-upload
(26 chunks, 1 written), byte-identical downloads, Range across chunk
boundaries, concurrent identical-upload race (manifest ref 2), and
trash-empty reclaiming exactly the unshared chunk while the shared 25
survive for the edited file. The empty/sub-8KB multipart path found a
post-EOF re-poll panic in the MIME peek (fixed with fuse + regression
test).
https://claude.ai/code/session_01WdNenpnujNR2sc32XVvwfS
TL;DR:
fix duplicate filename via:
```
docker exec <container> migrate-nfc-filenames --dry-run # preview
docker exec <container> migrate-nfc-filenames # execute
```
== issue ==
Last week I uploaded Capture d'écran 2026-06-03 à 20.04.24.png from the web. It synced down to Nextcloud on my Mac. Two minutes later, the Web UI was showing the file twice.
Both rows had:
- the same name
- the same size
- the same content hash
So why two rows? Because to PostgreSQL, the names weren't the same.
Web upload (browser → Postgres):
"é" stored as 1 codepoint (U+00E9) bytes: c3 a9 ← NFC
NiextCloud client (macOS → Postgres):
"é" stored as 2 codepoints (e + U+0301) bytes: 65 cc 81 ← NFD
macOS's APFS keeps filenames in NFD (decomposed); browsers send NFC (composed). Visually é and é are identical. To WHERE name = $1 they're two different keys. Our UNIQUE index on (folder_id, name, user_id) never fired — and the row count quietly drifted every time a Mac user touched an accented
filename.
== The fix is two halves ==
1. No new duplicates — every name-receiving boundary (file upload, NC PUT, rename, MOVE, path lookup) now NFC-normalizes before touching the database. The storage invariant becomes "every stored name is NFC".
2. Clean up existing data — one-shot migrate-nfc-filenames binary walks storage.files, NFC-normalizes any non-NFC row, and resolves the collisions we've accumulated. Same-content duplicates go to trash (recoverable); different-content collisions get renamed with a .duplicate suffix.
== use of the clean up ==
example of use (do not forget to define env **DATABASE_URL**)
either
`cargo run --bin migrate-nfc-filenames -- --dry-run`
or
`cargo build --bin migrate-nfc-filenames`
`./target/debug/migrate-nfc-filenames --dry-run`
example:
```
% ./target/debug/migrate-nfc-filenames --dry-run
=== NFC filename migration (DRY RUN — no writes) ===
Loaded 543 non-trashed file rows
NORMALIZE 163451b5-5e6c-404b-9b1e-f4b01a2b7269 user=42433185-4717-416d-9a15-4580fff171ec 'Capture d’écran 2026-03-20 à 14.44.50.png' → 'Capture d’écran 2026-03-20 à 14.44.50.png'
NORMALIZE 827dddec-4dd5-48c2-a120-dec5289f7d29 user=969deca6-7935-4f12-a430-4d636b62fa3e 'Capture d’écran 2026-04-03 à 15.43.38.png' → 'Capture d’écran 2026-04-03 à 15.43.38.png'
NORMALIZE 09559934-a620-472d-9ba8-fc3cfeb6dc6f user=a0643a21-0092-4a84-9dde-7ac4e76bc1a5 'Capture d’écran 2026-06-03 à 20.05.38.png' → 'Capture d’écran 2026-06-03 à 20.05.38.png'
NORMALIZE 5ce6dbf9-0562-4758-8783-671aa9069590 user=a0643a21-0092-4a84-9dde-7ac4e76bc1a5 'Capture d’écran 2026-06-05 à 11.07.25.png' → 'Capture d’écran 2026-06-05 à 11.07.25.png'
DEDUP newer=26bcf82b-99cc-45c8-9d69-dd7e5c4484ff (trash, same blob) older=df3adc67-a778-424d-a817-b930c75f3b06 user=a0643a21-0092-4a84-9dde-7ac4e76bc1a5 hash=0d2cc7b0ffce2850
=== Summary ===
scanned : 543
already in NFC : 538
normalized in place (no collision) : 4
dedup-trashed (same content) : 1
renamed to .duplicate : 0
DRY RUN — no rows were written. Re-run without --dry-run to apply.
```
once valid remove --dry-run
- remove the hardcoded list of locales in favor of a discovry on start time
- server will stop on badly formatted locale .json
- add server.* entries for serer side translation
server side translation will be used for templating and email
note: no json in some embded html (like in /magic), amount of work was similar
- SMTP has a mock to enable end to end test and validate the whole path
(via OXICLOUD_SMTP_MOCK)
- add email normalisation ( including punicode)
- api to share to external user
Azure SDK crates (azure_core, azure_storage, azure_storage_blobs) were
enabling reqwest/default-tls → native-tls → openssl-sys via their
default 'enable_reqwest' feature. This breaks the Alpine musl Docker
build which lacks libssl.a/libcrypto.a.
- Set default-features = false on all 3 Azure crates
- Enable 'enable_reqwest_rustls' + 'hmac_rust' (pure Rust, no OpenSSL)
- Pin reqwest to ^0.12 (azure_core 0.21 requires reqwest ^0.12)
- openssl-sys is now fully eliminated from the dependency tree
Claude