Benchmark-gated, same rule as rounds 2–14: every change ships with a
BEFORE/AFTER benchmark and an equivalence/safety gate; an AFTER that doesn't
beat its BEFORE is rolled back. The rule is encoded per harness (GATE FAIL
non-zero exit in the Rust examples, threshold expect() in vitest).
F1 — Grouped listings (trash / recent / favorites / shared-with-me)
re-bucketed the WHOLE accumulated list on every infinite-scroll page.
ResourceSectionsBuilder (new, off the reactive graph) re-buckets only the
fresh page and hands VirtualList the same rows array reference for untouched
buckets. 50×50 (2 500-item) drain: 63 750 → 2 500 bucketOf calls (25.5×),
12.5 → 1.3 ms wall (9.9×); O(N²/page) → O(N). Deep-equal to the full-rebuild
reference at every page for both a contiguous (date) and a non-contiguous
(trash-by-drive) group-by; reference-stability + fallback gated.
B1 — exif Make/Model: the display String was thrown away to allocate the
trimmed copy; display_value_trimmed trims in place (drain + truncate), 2 → 1
alloc per field (8 → 4 allocs/op, 1.26×).
B2 — content-index worker: text_extractor::supports (lowercases MIME +
extension) was called twice per file per drain batch; classify once into a
Vec<bool> and thread it through both uses. 256-file batch: 704 → 353 allocs,
34.5 → 16.7 µs (2.07×).
B3 — tantivy: skip SnippetGenerator::create on a zero-hit content search
(return Ok(vec![]) once top_docs.is_empty()); the per-hit loop was empty.
400-doc index: 1 575.6 → 1 237.2 ns (1.27×), widens with index size.
Harnesses: examples/bench_round15_micro.rs, examples/bench_round15_tantivy.rs,
frontend resourceSections.bench.test.ts; writeup in benches/ROUND15.md. Also
normalizes two round14 bench examples that were committed unformatted
(cargo fmt --all).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012o47jSrtL7xuNGTHXmtiYL
Benchmark-gated (benches/ROUND14.md); every change ships a BEFORE/AFTER
benchmark with an equivalence gate and is rolled back on regression (the
rule is encoded as a GATE FAIL exit / threshold expect).
Backend
- Q1 faces_for_file → narrow face_boxes_for_file(id, person_id, bbox) with the
caller filter pushed into SQL: drops the 2 KiB embedding BYTEA + 6 unused
columns per face. 15-face lightbox open 0.312→0.219 ms, 32 KB→840 B/req.
- A1 cookie auth uses the borrow-only extract_cookie_str (already backs CSRF)
instead of extract_cookie_value's owned String: -1 alloc/cookie request.
- A2 compute_relevance ASCII case-fold fast path vs name.to_lowercase() per
result row (Unicode fallback preserved): 1.40x, 12→3 allocs/page.
- A3 sub pre-parsed to Uuid at decode time (TokenClaims.sub_id) vs re-parsing
the 36-char claim on every request incl. cache hits: 22.7→0.7 ns.
- A4 auth + NextCloud middlewares borrow request.headers() instead of taking
axum's HeaderMap extractor (a full map clone): 2→0 allocs/authed request.
- A5 CalDAV getlastmodified via the stack rfc2822_utc (byte-identical to
chrono) vs a per-event to_rfc2822() heap String: 5→0 allocs.
- A6 CalDAV per-event href + quoted etag written into reused page buffers vs a
fresh format! pair per event: 3.48x, 240→6 allocs/40-event page.
Frontend
- F1 t() shares one frozen EMPTY_PARAMS for the no-interpolation call forms vs
a throwaway {} per call: -1 alloc/call.
- F2 favorites favoriteIds is a persistent SvelteSet with per-page add (clear
on reset) vs a brand-new set over the whole accumulated list each page:
22.3x over a 40-page drain (O(N^2)→O(N)).
Verified: cargo check --all-targets, cargo clippy -D warnings, both bench
packs (GATE PASS), frontend npm run check + vitest (4/4). ROUND14.md also
records the investigated-but-deferred backlog (music N+1, contact vcard
over-fetch, CachedBlobBackend syscalls, ResourceList.sections builder, etc.).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PymgCdK78NzUF3oRAQCJfN
Benchmark-gated round (benches/ROUND12.md; every change ships with a
BEFORE/AFTER harness + equivalence gates, one candidate rejected by its
own bench):
DB / query shapes (bench_round12_queries):
- NC sharee search: username-only projection instead of the 21-column row
(incl. the <=512 KiB avatar) per match, + gin_trgm_ops indexes on
auth.users for the leading-wildcard ILIKE (4.98x; 54.7x with index).
- Password login: delete the redundant full-row update_user — create_session
already stamps last_login_at in its own txn (4.45x per login).
- Email-verified stamp: narrow conditional UPDATE (8.9x); OIDC repeat login
now compares profile state in memory and issues ZERO queries when nothing
changed (was: full 17-column rewrite per login).
- Refresh rotation: revoke+insert+stamp fused into one transaction via new
rotate_session port method (1.18x).
- WOPI CheckFileInfo / authorize_wopi_access: require(Read) + get_file +
check(Update) overlapped with tokio::join!, original result precedence
(cold 1.34x).
- Upload quota gate: user-envelope + drive-cap checks fused into ONE
round-trip (check_upload_quotas) — the NC chunked PUT pays this per
chunk (1.81x, 2 -> 1 queries/chunk); shared verdict evaluators keep
error shapes byte-identical.
CPU / allocs (bench_round12_micro):
- sized_json: pre-sized listing serialization replacing axum Json's 128 B
seed + doubling-realloc chain on files/folder-resources/photos/search
responses (1.40x, 13 -> 2 allocs per 500-row page; byte-identical).
- Security headers: 4 SetResponseHeaderLayer folded into the CSP middleware
pass (5 layers -> 1; 1.43x per request, -26 allocs; header set gated
byte-identical incl. 304s).
- Media capture-metadata: single-read extraction — nom-exif now parses the
buffer kamadak already read (zero-copy Bytes) and videos open once with a
kind() dispatch; per-image opens 2-3 -> 1 (1.44x warm geomean, 1.6-3.2x
cold cache; extraction outputs gated identical incl. the MIME-mislabel
track fallback).
- Chunked-upload session ops: owner gate folded into the operation's own
DashMap lookup + stack-encoded uuid compare (5 -> 3 lookups, -2 allocs,
1.28x per chunk).
Blob cache (bench_blob_cache_index + round-3 regression guard):
- CachedBlobBackend index: tokio::sync::Mutex<LruCache> -> moka::sync::Cache
with byte weigher. The mutex serialized every cached chunk read and scaled
NEGATIVELY (2.08 -> 1.07 Mops/s from 1 -> 2 readers); moka probes are
lock-free (2.17x at K=2). Byte budget now enforced by moka (manual
current_size + collect_evictions machinery deleted); eviction listener
unlinks size-evicted files only (Replaced entries keep their file —
gated). Single-flight miss gate unchanged (16 concurrent misses -> 1
fetch re-verified via the round-3 harness).
- put_blob now populates the cache BEFORE the inner backend consumes the
source file (the old order failed 100% of the time — local renames,
S3/Azure delete the source — so the first read after a whole-file put
re-downloaded from the remote); inner-put failure invalidates the entry.
Frontend (vitest gates):
- List-view thumbnails request the 150px icon rendition instead of 400px
preview into a 40px slot (~7.1x fewer pixels, ~4-5x fewer bytes per
thumbnail across list views); grid keeps preview.
Rejected by its own bench (kept as evidence in bench_round12_micro §2):
- Single-pass compression predicate: the monomorphized And-chain already
costs ~4.6 ns / 0 allocs total; the fused node measured within noise.
New migration: 20260719000000_users_search_trgm.sql (trgm indexes).
Deferred with prepared design: grouped file/grid view virtualization
(single-VirtualRows flatten, the photos pattern) — next round's headline.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BfidAJD5AHw23jtvBUNamB
Backend (each change benchmark-gated with BEFORE replicas + equivalence
gates; see examples/bench_round11_micro.rs, bench_round11_queries.rs,
bench_log_writer.rs and benches/ROUND11.md — final numbers land in the
follow-up doc commit):
- StoragePath re-representation: single canonical joined String, segments
derived on demand; File/Folder drop the duplicated path_string field
(4000→1000 allocs per 500-row listing page)
- Display classifier fusion: classify_display shares one stack-lowered
extension across the three decision trees; call sites in FileDto,
folder/favorites/recent handlers, trash, path-resolver (+ interning
where Arc::from was still used)
- /status.php and /openapi.json memoized into OnceLock<Bytes> (openapi
rebuilt a 171 KiB spec per request: 2.8 ms → 18 ns)
- NC upload-session PROPFIND: write! + pre-sized body + stack RFC2822
dates (2.3-2.6x, 2582→772 allocs at 256 chunks)
- REST download: dead FileDto clone removed (capture mime/size + move)
- CalendarEventDto/TrashedItem into_parts moves (11 KiB ical_data memcpy
gone per CalDAV row); CardDAV getlastmodified stack render
- 4xx path: borrowed ErrorResponse serialize, ErrorKind::as_str,
not_found/already_exists clone kill
- vCard emit via write!; search page moved out with into_iter skip/take;
content-hit UUIDs parsed once; group last-user check via HashSet
- RateLimiter: lock-free get + insert (and_upsert_with variant REJECTED
by benchmark); CSRF token borrow-compare + borrowed cookie extraction
- Thumbnail/preview ETags built from as_str (Debug-identical bytes)
- Encrypted backend: encrypt_in_place_detached single-buffer write path,
chunk-sized reserve in collect_stream; retry labels made lazy
- PG: deferred upload registration 3→1 round-trips (persist_file CTE
template); direct_grant_cache for Calendar/AddressBook/Playlist authz
(single-flight + set_role/clear_role invalidation); expand_user
tokio::join!; geo clusters min(uuid)::text; recluster face assignment
batched into one UNNEST update
- People recluster cosine: norms precomputed once (bit-identical gate)
- NC capabilities poll logs demoted to debug; tracing-appender dep added
for the log-writer benchmark
Frontend:
- ResourceList.selectedEntries O(N)-per-toggle → id-index projection
O(k log k); favorites/recent consume the batchToolbar snippet param and
drop their duplicate filter + dead selectedIds mirror
- Recent: star state via new favoriteIds prop — a star click no longer
rebuilds all N entries
- admin timeAgo >30d fallback uses the cached Intl.DateTimeFormat
- vitest gates in src/lib/components/round11.bench.test.ts
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ABhTEHuGujvwoodh67Kga7
get_thumbnail_impl runs require_permission(Read) on every request. For a drive
member that's a drive_role_cache hit, but a shared-album recipient — granted a
folder (the album), not drive membership — fails the drive-role precheck and
falls through to file_cascade_grant_exists (a role_grants ⋈ folders lpath
ancestor query), once per file. Browsers revalidate immutable thumbnails
constantly, so the same (recipient, file, Read) decision was recomputed on
every thumbnail of every view — ~100 grant queries per 100-photo album per
navigate-away-and-back.
New cascade_grant_cache ((Subject, Resource, Permission) → bool, 30 s TTL)
memoises that decision. The check is NEVER skipped — the ordering is unchanged,
authz still runs on every request; only the result is cached, and only after
the drive-role precheck fails (so a later drive grant can't be shadowed by a
stale entry). Invalidation mirrors drive_role_cache's convention: explicit
invalidate_all on every File/Folder set_role/clear_role (immediate revoke on
the direct share path), 30 s TTL for the indirect paths (group membership,
moves, expiry) "rather than a deep invalidation tree".
Bench (bench_thumbnail_cascade_cache) with hard safety gates — recipient
allowed, outsider denied, and a clear_role revoke denies the very next check
(proving the grant-write flush): 100-photo album revalidation 2576 → 2.70
µs/thumb (~950x), 257.6 → 0.27 ms/view. Validated against the full
--cfg integration_tests authz suite (554 tests) + 524 workspace tests, clippy
-D warnings clean.
Deliberately not done: moving authz after the 304/cache short-circuit (a
security-posture change — a revoked user could serve cached thumbnails). With
the decision cached, the authz on the 304 path is now a memory hit, so the
"zero DB work on a 304" intent is restored without weakening the check.
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
add env variable `OXICLOUD_WEBDAV_DRIVE_LISTING_PREFIX`
which is by default:
`OXICLOUD_WEBDAV_DRIVE_LISTING_PREFIX="@drive"`
so `/webdav/` -> points to user's personal drive (**backward compatibilit**y)
`/web/dav/@drive/{uuid|drive name}/` points to the respective drive
if admins want directly `/webdav/` pointing to list of drives they need to:
`OXICLOUD_WEBDAV_DRIVE_LISTING_PREFIX=""`
+ ensure lock is per user (RFC 4918 §9.11)
fix: #554
strip_chroot_prefix replaces the hardcoded "Personal/" strip
in NC trashbin PROPFIND, OCS unified search, and REPORT
(favorites + search). Handles composed chroots, drops
cross-chroot items instead of surfacing malformed paths, and
fixes the leading-slash mismatch (FolderDto path has '/', DB
paths don't) that silently dropped every NC trashbin item
post-D3. OCS keeps a first-segment fallback (results
legitimately span drives, no single chroot).
uploads_handler switches to nc_to_internal_path(chroot, …)
for the two remaining hardcoded "Personal/" sites, closing
the D1 TODO markers.
RecentService::record_item_access is split from a new
record_item_access_internal (no authz) used by
RecentRecordingHook. Round 1's authz.require widened the
tokio::spawn race past tests/api/recent.hurl step 7; the
internal path skips the redundant Read gate — upstream
_with_perms already enforced it.
Tests: 8 unit tests pin strip_chroot_prefix (leading slash,
composed chroots, sibling-leak rejection, partial-prefix,
empty-chroot). drives_membership.hurl step 21b/22b cover
Editor upload → 201 / Viewer upload → 404 fresh + overwrite
with fixture cleanup at 30c. test_nc_move_copy_delete_trash
K1 pins the actual original-location value.
- 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
plan:
```
What step 5 is actually doing
Goal: stop writing to storage.files.user_id / storage.folders.user_id on new INSERTs. This is a prerequisite for step 6 (dropping the column entirely). The column has existed since the pre-D0 single-owner era; every read that used to key on it has already been migrated to drive-membership grants over the last N days.
What has to change together for this to be safe:
┌──────────────┬─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┬───────────────────────────────────────────────────────────────────────────────────────────────────────┐
│ Piece │ What changes │ Why │
├──────────────┼─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┼───────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ Migration │ Swap storage.files uniqueness indexes from (folder_id, name, user_id) to (drive_id, folder_id, name) │ Otherwise, two new rows with user_id = NULL would both be allowed (PG treats NULLs as distinct) — │
│ (a) │ │ uniqueness silently breaks │
├──────────────┼─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┼───────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ Migration │ ALTER user_id DROP NOT NULL on both tables │ Otherwise, dropping the INSERT bind violates NOT NULL and every write 500s │
│ (b) │ │ │
├──────────────┼─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┼───────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ Migration │ Drop dead user_id-leading indexes │ Cheap cleanup — nothing scans them anymore │
│ (c) │ │ │
├──────────────┼─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┼───────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ PL/pgSQL (d) │ Rewrite storage.copy_folder_tree without user_id in the INSERT column list │ Cross-drive copy runs entirely in SQL, needs the same treatment │
├──────────────┼─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┼───────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ Rust (e) │ ~12 INSERT column-list drops across folder_db_repository, file_blob_write_repository, drive_pg_repository, dedup_service, │ Actual write path │
│ │ folder_service, load-seed.rs │ │
├──────────────┼─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┼───────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ Rust (f) │ Simplify folder_db_repository::create_folder's parent lookup to only fetch drive_id (was fetching (user_id, drive_id)) │ It's fetching a value it no longer needs │
└──────────────┴─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┴───────────────────────────────────────────────────────────────────────────────────────────────────────┘
```
Add an in-memory DeadPropertyStore backed by RwLock<HashMap> that
stores arbitrary client-supplied XML properties per resource path.
Wire it into AppState so PROPPATCH can persist dead props and PROPFIND
can retrieve them across requests.
initially the recent was done client side
recent files are now directly updated on serverside when accessing a file
note: nextcloud and webdav voluntary not included
Stamp `orphaned_at = now()` on the ref-0 row so it sits inside the
GC grace window for the duration of this test. Without it,
`orphaned_at IS NULL` is treated by `garbage_collect` as
"pre-migration, immediately reapable" — and any sibling test in
the shared pool that calls `garbage_collect()` (e.g.
`garbage_collect_respects_grace_and_cross_checks`) would race
with the pin below and delete the row first.
call fire_blob_hooks to respect lifecycle
dedup_service::garbage_collect_with_grac must call fire_blob_hooks() once blob are dropped
so other services like thumbnail can proceed to their cleanup
renable thumbnail test, ensure that blob lifecycle correctly
trigger thumbnail cleanup on blob deletion
need to call `/api/admin/internal/trigger-gc?force=true`
- permit shared drive creation from oxicloud admin (for now)
- prepare other personal drive creation (Not implemented), need to validate
quota policies and strategy first
- add hurl test to verify permissions
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
This reverts the image-pool migration (commit 5629ba6). The bench
(bench_pool_concurrency / POOL-CONCURRENCY.md) measured the one pool it could
isolate — the thumbnail decode semaphore — and found flat throughput, p99 AND
peak RSS (137 MiB) from K=1..16: shrink-on-load already makes each decode
RAM-cheap, so sizing it to the CFS quota gains nothing measurable. Adding code
without a measured benefit isn't worth it.
Kept: the effective_parallelism() helper (it has a *measured* win in the Tokio
runtime — benches/RUNTIME.md) and the benchmark itself (reusable). The ffmpeg
video fan-out has a plausible a-priori case (one OS process per permit) but is
left as a future, deliberately-measured change rather than shipped on
speculation. Doc updated to record the decision.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JG5yYZ9s868mJwqT2Qz7ez
The thumbnail decode semaphore, the transcode rayon pool, and the ffmpeg
video-thumbnail fan-out all sized from std::thread::available_parallelism(),
which honours CPU affinity but ignores the CFS bandwidth quota (--cpus /
cgroup cpu.max). Under a container quota they therefore permit one CPU-heavy
task per *host* core onto cores the scheduler can't grant — the same
over-subscription the runtime worker pool had.
Switch all three to common::runtime::effective_parallelism() (= min(affinity,
CFS quota)), and fix the doc comments that wrongly claimed available_parallelism
respects cgroup quotas. No change off-quota (effective == available there); the
env overrides (OXICLOUD_THUMBNAIL_DECODE_CONCURRENCY,
OXICLOUD_VIDEO_THUMBNAIL_CONCURRENCY) are unchanged.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JG5yYZ9s868mJwqT2Qz7ez
The local backend inherited the trait's conservative read_prefetch() = 1
(strictly sequential chunk reassembly), while S3/Azure already use 8. The
prior rationale was that concurrent opens over scattered content-addressed
chunk files turn one sequential read into competing random I/O ("slower
cold"). Benchmarked that assumption with examples/bench_blob_prefetch
(sweeps the buffered(N) depth over a real LocalBlobBackend under disk-bound
vs network-bound consumers and warm vs cold page cache).
Result on SSD-class storage (median MB/s vs N=1):
warm disk-bound N=2 +11.8% N=8 +3.9% N=16 -4.4%
cold disk-bound N=2 +7.2% (no cold regression on SSD)
network-bound (throttled) ~0% at any N — the socket, not the disk, caps it
So N=8 is wrong for local (leaves gain on the table, risks HDD seek thrash)
and the network-bound win the analysis assumed doesn't materialize: buffered()
here overlaps the per-chunk File::open (cheap on local disk), not the data
read. N=2 captures most of the disk-bound gain — which covers localhost/LAN
downloads AND the internal blob reads that drain as fast as the disk delivers
(thumbnail render, transcode, ZIP export, content extraction) — at the lowest
fan-out. Env-tunable via OXICLOUD_LOCAL_READ_PREFETCH (set 1 on seek-bound
HDDs to restore the old behaviour; raise on fast NVMe). Signature unchanged,
so all ~16 LocalBlobBackend::new call sites are untouched.
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>
Claude