Oxicloud

cjw/Oxicloud

Fork 0

Commit Graph

Author	SHA1	Message	Date
Claude	fdf445d2b0	perf: round 9 — decorator PUT reactivation, session/search/dedup alloc purges, PROPFIND join!, folder-level cascade Benchmark-gated round (benches/ROUND9.md): every change carries a BEFORE/AFTER bench with equivalence/safety gates; verdicts below are from the committed harnesses on 4 cores / local PG 16. Backend: - Blob decorators (Retry/Cached) now forward put_blob_from_bytes_unsynced + sync_blobs — the trait default had silently reinstated HEAD-before-PUT per chunk on decorated remote stacks, undoing ROUND3 §8. Full production stack: 500 probes -> 0, 1.9x wall at 10 ms RTT (bench_s3_put §3). - NC PROPFIND per-page enrichment triple (favorites / oc:fileid / dead props) overlapped with tokio::join!: 2.07x local, 2.86x at 5 ms RTT (bench_nc_enrich_join, injected-latency decide-by-bench). - Search enrichment consumes its DTOs and carries the interned Arc<str> display fields end-to-end (SearchFileResultDto type change, OpenAPI shape preserved): enrich_file 2.0x, 11.6 -> 2.2 allocs/row; the NC REPORT conversion stops re-running all three classifiers per row (bench_search_enrich). - NC session Arc end-to-end: SharedNcSession extractor (8 -> 0 allocs), Arc<FolderDto> chroot cache (4 -> 0/hit), single shared Arc<CurrentUser> + lazy span render (11 -> 6/build) (bench_nc_session). - Storage micro-pack: atomic create_new chunk writes (2.1x fresh), stream_chunks over the manifest Arc (4097 -> 0 allocs/read incl. the Range path), manifest single-flight (herd 64 -> 1 loads), hex_lower for chunk Content-MD5 (18 -> 1 allocs) (bench_storage_micro). - OCS capabilities memoized into OnceLock<[Bytes;2]>: 237x, 102 -> 0 allocs/poll, byte-identical (bench_capabilities_static). - Drive::is_empty COUNT(*) sum -> EXISTS: 34.4x on a 100k-file drive (bench_drive_is_empty). - favorites/recents row-map ROUND7 port: path/name/blob_hash moved, -2.75 allocs/row (bench_resource_row_map §2). - Folder rows decode binary UUIDs (ROUND6 §10 port): 1.03-1.07x page fetch, honest verdict incl. one noise-band wash documented (bench_folder_uuid_decode). - Authz: file cascade decision decomposed into memoized folder-level decision + direct-grant lookup (ROUND8 deferred item). Cold shared-album first view 592 -> 418 µs/thumb; warm path unchanged; safety gates incl. new direct-grant sibling isolation, revoke-flush re-verified, full integration authz suite green (bench_thumbnail_cascade_cache). Frontend (vitest gates committed beside the code): - resolveLabel/resolveRecipient O(directory) scan -> id-keyed Map: 13.9x (recipients.bench.test.ts). - ResourceList selection-prune effect skips when nothing is selected (100 -> 0 Set builds per drain) and the photos timeline reads a listener-fed mobile flag instead of matchMedia per recompute (listDerives.bench.test.ts). Verification: cargo fmt + clippy --all-features --all-targets -D warnings clean; 524 unit + 554 integration (--cfg integration_tests) tests pass; frontend npm run check clean with 293 vitest tests green. Deferred with rationale in ROUND9.md: CalDAV authz-before-fetch reorder (maintainer sign-off), per-page batched parent resolution, JWT-claims Arc<str>, batch_operations signature widening. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01XDc9VtXvskJ6dnMRraSndn	2026-07-18 16:12:04 +00:00
Claude	63cf6646d0	perf: round 5 — CalDAV cursor streaming, SPA interning gaps, NC href prefix, per-request micro-allocs Seven benchmark-gated changes (benches/ROUND5.md; BEFORE/AFTER bench + equivalence gate each, rollback rule as ROUND2-4 — two intermediate CalDAV shapes measured worse and were themselves rolled back before shipping): - CalDAV whole-calendar responses (REPORT no-range/sync-collection, depth-1 collection PROPFIND, .ics GET): buffered double-residency → ONE window-ordered scan (MIN(start_time) OVER (PARTITION BY ical_uid)) streamed through a PG cursor, pages cut at UID boundaries. TTFB 23.3→11.0 ms (2.1x), peak heap 14.2→8.0 MiB at 4k events / 45→24 MiB at 12k, wall +9-15% (documented trade, ZIP-streaming class); both multistatus and ICS byte-identical to the buffered output. Rejected shapes kept in the doc: per-page GROUP-BY keyset (3-4x wall) and per-uid ANY hydration (~20 µs/index descent). - SPA listing interning gaps: folder/recent/favorites resources handlers (and the WebDAV pseudo-root) called raw Arc::from per row for the closed display set ROUND3 interned — now intern_display/intern_mime, 4→0 allocs/row, byte-identical Arc contents. - NC PROPFIND child hrefs: username + parent path encoded once per request instead of per child (543→165 ns/row, 13→4 allocs); native WebDAV href drops its intermediate encode String. - suggest enrichment: entity clone + field re-clones per keystroke row → consume + move (166.5→126.8 µs/200 rows, 20→7 allocs/row). - list_readable_by returns the cache's Arc (246→128 ns warm hit, 4→0 allocs) — deep Vec clone per DAV-selector request removed. - CardDAV REPORT: borrowed props, reused href buffer, exact-size etag quoting (3.04→2.34 ms per 5k-contact getetag poll). - Auth span records: user_id.to_string() per request ×3 → tracing::field::display. Checks: cargo fmt, clippy --all-features --all-targets -D warnings, cargo test --workspace (523 passed). Follow-ups (CardDAV streaming, &[&str] id batches, ::text UUID casts A/B, share-landing join) recorded in benches/ROUND5.md. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017aJu9ghvuT8WqC31ZEGTBA	2026-07-17 15:19:00 +00:00

Author

SHA1

Message

Date

Claude

fdf445d2b0

perf: round 9 — decorator PUT reactivation, session/search/dedup alloc purges, PROPFIND join!, folder-level cascade

Benchmark-gated round (benches/ROUND9.md): every change carries a
BEFORE/AFTER bench with equivalence/safety gates; verdicts below are from
the committed harnesses on 4 cores / local PG 16.

Backend:
- Blob decorators (Retry/Cached) now forward put_blob_from_bytes_unsynced
  + sync_blobs — the trait default had silently reinstated HEAD-before-PUT
  per chunk on decorated remote stacks, undoing ROUND3 §8. Full production
  stack: 500 probes -> 0, 1.9x wall at 10 ms RTT (bench_s3_put §3).
- NC PROPFIND per-page enrichment triple (favorites / oc:fileid / dead
  props) overlapped with tokio::join!: 2.07x local, 2.86x at 5 ms RTT
  (bench_nc_enrich_join, injected-latency decide-by-bench).
- Search enrichment consumes its DTOs and carries the interned Arc<str>
  display fields end-to-end (SearchFileResultDto type change, OpenAPI
  shape preserved): enrich_file 2.0x, 11.6 -> 2.2 allocs/row; the NC
  REPORT conversion stops re-running all three classifiers per row
  (bench_search_enrich).
- NC session Arc end-to-end: SharedNcSession extractor (8 -> 0 allocs),
  Arc<FolderDto> chroot cache (4 -> 0/hit), single shared Arc<CurrentUser>
  + lazy span render (11 -> 6/build) (bench_nc_session).
- Storage micro-pack: atomic create_new chunk writes (2.1x fresh),
  stream_chunks over the manifest Arc (4097 -> 0 allocs/read incl. the
  Range path), manifest single-flight (herd 64 -> 1 loads), hex_lower for
  chunk Content-MD5 (18 -> 1 allocs) (bench_storage_micro).
- OCS capabilities memoized into OnceLock<[Bytes;2]>: 237x, 102 -> 0
  allocs/poll, byte-identical (bench_capabilities_static).
- Drive::is_empty COUNT(*) sum -> EXISTS: 34.4x on a 100k-file drive
  (bench_drive_is_empty).
- favorites/recents row-map ROUND7 port: path/name/blob_hash moved,
  -2.75 allocs/row (bench_resource_row_map §2).
- Folder rows decode binary UUIDs (ROUND6 §10 port): 1.03-1.07x page
  fetch, honest verdict incl. one noise-band wash documented
  (bench_folder_uuid_decode).
- Authz: file cascade decision decomposed into memoized folder-level
  decision + direct-grant lookup (ROUND8 deferred item). Cold shared-album
  first view 592 -> 418 µs/thumb; warm path unchanged; safety gates incl.
  new direct-grant sibling isolation, revoke-flush re-verified, full
  integration authz suite green (bench_thumbnail_cascade_cache).

Frontend (vitest gates committed beside the code):
- resolveLabel/resolveRecipient O(directory) scan -> id-keyed Map: 13.9x
  (recipients.bench.test.ts).
- ResourceList selection-prune effect skips when nothing is selected
  (100 -> 0 Set builds per drain) and the photos timeline reads a
  listener-fed mobile flag instead of matchMedia per recompute
  (listDerives.bench.test.ts).

Verification: cargo fmt + clippy --all-features --all-targets -D warnings
clean; 524 unit + 554 integration (--cfg integration_tests) tests pass;
frontend npm run check clean with 293 vitest tests green.

Deferred with rationale in ROUND9.md: CalDAV authz-before-fetch reorder
(maintainer sign-off), per-page batched parent resolution, JWT-claims
Arc<str>, batch_operations signature widening.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XDc9VtXvskJ6dnMRraSndn

2026-07-18 16:12:04 +00:00

Claude

63cf6646d0

perf: round 5 — CalDAV cursor streaming, SPA interning gaps, NC href prefix, per-request micro-allocs

Seven benchmark-gated changes (benches/ROUND5.md; BEFORE/AFTER bench +
equivalence gate each, rollback rule as ROUND2-4 — two intermediate
CalDAV shapes measured worse and were themselves rolled back before
shipping):

- CalDAV whole-calendar responses (REPORT no-range/sync-collection,
  depth-1 collection PROPFIND, .ics GET): buffered double-residency →
  ONE window-ordered scan (MIN(start_time) OVER (PARTITION BY ical_uid))
  streamed through a PG cursor, pages cut at UID boundaries. TTFB
  23.3→11.0 ms (2.1x), peak heap 14.2→8.0 MiB at 4k events / 45→24 MiB
  at 12k, wall +9-15% (documented trade, ZIP-streaming class); both
  multistatus and ICS byte-identical to the buffered output. Rejected
  shapes kept in the doc: per-page GROUP-BY keyset (3-4x wall) and
  per-uid ANY hydration (~20 µs/index descent).
- SPA listing interning gaps: folder/recent/favorites resources handlers
  (and the WebDAV pseudo-root) called raw Arc::from per row for the
  closed display set ROUND3 interned — now intern_display/intern_mime,
  4→0 allocs/row, byte-identical Arc contents.
- NC PROPFIND child hrefs: username + parent path encoded once per
  request instead of per child (543→165 ns/row, 13→4 allocs); native
  WebDAV href drops its intermediate encode String.
- suggest enrichment: entity clone + field re-clones per keystroke row →
  consume + move (166.5→126.8 µs/200 rows, 20→7 allocs/row).
- list_readable_by returns the cache's Arc (246→128 ns warm hit, 4→0
  allocs) — deep Vec clone per DAV-selector request removed.
- CardDAV REPORT: borrowed props, reused href buffer, exact-size etag
  quoting (3.04→2.34 ms per 5k-contact getetag poll).
- Auth span records: user_id.to_string() per request ×3 →
  tracing::field::display.

Checks: cargo fmt, clippy --all-features --all-targets -D warnings,
cargo test --workspace (523 passed). Follow-ups (CardDAV streaming,
&[&str] id batches, ::text UUID casts A/B, share-landing join) recorded
in benches/ROUND5.md.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017aJu9ghvuT8WqC31ZEGTBA

2026-07-17 15:19:00 +00:00

2 Commits