c51af68432
perf: round 10 — auth alloc purge, parent-herd batching, query-shape pack, NC 304s
...
Benchmark-gated (benches/ROUND10.md; every change carries a BEFORE/AFTER
harness with equivalence/safety gates — two designs were rejected or
rewritten by their own benches before adoption):
- Auth hot path: TokenClaims/CurrentUser display fields to Arc<str>, role
to inline SmolStr end-to-end (Bearer, cookie, Basic-auth cache) — 4→1
allocs per authenticated request, 3→0 per warm DAV request; JWT
Encoding/Decoding/Validation built once.
- Cold shared-album herd: leader-inline parent batching in PgAclEngine
(+ cascade try_get_with single-flight) — 100→2 parent queries per
100-thumb cold herd, herd wall 1.9x, sequential + warm paths unchanged,
all ROUND8/9 safety gates plus new herd-equivalence gates.
- Query-shape pack: share download double-fetch 2→1 (2.18x), contact-group
COUNT(*) 14.9x, save_faces UNNEST 3.9x, playlist reorder UNNEST 63.7x
(now atomic), search files∥folders join! 1.45x, move drive-lookup join!
2.14x, trash partial (drive_id, trashed_at) indexes, CalDAV event-gate
narrow read, favorites/recents binary-decode port, dead count_files
removed.
- NC surface: preview + avatar honour If-None-Match (e2e: 5 KB and 197 KB
→ 0 bytes per revalidation), avatar WebP→PNG transcode memoised,
PROPFIND/trashbin integer+date emits on stack formatters, folder-header
enrichment join!, chunk-PUT retry stat folded into create_new open.
- common::fmt integer rendering rewritten on the std 2-digit LUT after the
round's own bench caught the div-loop losing to to_string (16.1 ns vs
22.5; speeds every prior-round call site).
- Micro-pack: WebDAV scope probe borrow-only, ShareService base_url
snapshot, cookie_secure OnceLock, Arc'd AES-GCM cipher, stack request-id,
tantivy analyzer clone dropped.
- SPA: search stale-guard + AbortController (10→1 completed round-trips,
stale-clobber gone), getFolder in-flight dedup, gridColumns matchMedia
hoist (10k→0 style reads).
Backend: cargo fmt + clippy -D warnings clean, 524 tests green.
Frontend: npm run check clean, 301 vitest green.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
Claude-Session: https://claude.ai/code/session_018DdM7V7M3QPW7HEHg3gLov
2026-07-18 20:33:50 +00:00
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
Edouard Vanbelle