97cf6402e2
fix: resolve all clippy warnings and enforce cargo fmt
...
- display_helpers: convert module doc-comments to regular comments,
merge identical text/markdown + text/ branches
- search_service: replace needless range loops with slice-based pagination
- folder_repository, folder_db_repository: collapse nested if statements
- favorites_pg_repository: remove unnecessary borrow on generic arg
- file_blob_read_repository: collapse 6 nested if-let blocks
- file_blob_write_repository: collapse nested if for dedup ref decrement
- chunked_upload_service: use div_ceil(), collapse 2 nested if blocks
- folder_handler: collapse nested if-let for owner check
- webdav_handler: replace 7x io::Error::new(ErrorKind::Other, ..) with
io::Error::other(..)
- cargo fmt applied to all files
Passes: cargo clippy --all-targets --all-features -- -D warnings
2026-02-25 10:28:34 +01:00
71c2cb5edb
perf: Arc<AppState>, streaming PROPFIND, spawn_blocking SHA-256
...
- Issue #4 : Wrap AppState in Arc — eliminates 42 Arc::clone + 16 String::clone per request
- Issue #2 : Reject Depth:infinity with 403 + streaming XML with paginated DB queries
- Issue #5 : Move chunked upload assembly (SHA-256 hash-on-write) to spawn_blocking
- Remove ~270 lines dead code from di.rs (unused builders, Default impl, stubs)
- Clean up unused tokio imports in chunked_upload_service.rs
2026-02-24 15:11:56 +01:00
78ae145af5
perf(chunked-upload): hoist 512KB read buffer out of per-chunk loop
...
causing N × 512KB alloc+memset+dealloc cycles per upload. Moving it
before the loop reuses a single allocation across all chunks.
For a 100-chunk upload this eliminates 99 allocations totalling ~50 MB
of unnecessary memset work.
2026-02-24 13:03:18 +01:00
b5652b029d
perf: offload MD5 checksum to spawn_blocking in chunked uploads
...
md5::compute(&data) is CPU-bound (~1.2ms per 5MB chunk) and was
blocking the Tokio worker thread. Move it to the blocking thread-pool
via spawn_blocking so the async worker is freed in ~5µs. Bytes::clone
is O(1) (Arc increment) so no extra copy overhead.
2026-02-23 22:49:34 +01:00
1da284a841
perf: move 512KB I/O buffer from stack to heap in chunked upload assembly
...
- Async Future size drops from ~525KB to ~5KB
- Eliminates stack overflow risk and reduces work-stealing copy cost
2026-02-23 22:41:50 +01:00
41b5500b77
perf: move persist_progress disk I/O outside write lock in chunked uploads
...
- Write lock now held only for RAM updates (~microseconds instead of ~ms)
- Bitmask built under lock, written to disk after lock release
- Concurrent uploads across all sessions no longer blocked by disk I/O
- Under 10 concurrent sessions: lock wait drops from ~50ms to ~10µs
2026-02-23 22:32:14 +01:00
fd9e509648
perf: implement findings #2 , #3 , #17 from architecture audit
...
- Finding #2 : Replace Mutex<HashMap> with moka::sync::Cache in file_blob_read_repository (10K cap, 30s TTI)
- Finding #3 : Add chunked upload persistence with session.json + progress.bin bitmask for crash recovery
- Finding #17 : Remove manual gzip compression, delegate entirely to tower-http CompressionLayer
- Remove dead code: StubCompressionPort, GzipCompressionService re-export, duplicate response structs
- All 114 tests passing
2026-02-22 14:12:53 +01:00
1ed20f425f
perf: Phase 4+5 optimizations — uploads 10x, downloads 2x, concurrent 2x. moka cache, 512KB buffers, remove sync_all, hash-on-write, preloaded queries, bench.sh v3, gitignore storage/. 500MB upload 12.6s->1.3s (392MB/s). RSS 69-113MB, 0 swap.
2026-02-15 17:56:47 +01:00
4c98c5a657
style: apply cargo fmt to entire codebase
...
Standardize code formatting across all 173 Rust source files
using rustfmt. No functional changes - purely cosmetic.
This establishes a consistent code style baseline for the
project going forward.
2026-02-14 01:29:34 +01:00
67137a3ef2
refactor: apply clippy auto-fixes (162 warnings resolved)
...
- Fix needless borrows and references
- Collapse nested if statements
- Replace manual strip_prefix with str::strip_prefix()
- Remove redundant closures in map/unwrap_or_else
- Use Iterator::next_back() instead of rev().next()
- Simplify map_or patterns
- Use std::io::Error::other() instead of new(ErrorKind::Other, ..)
- Use div_ceil() instead of manual ceiling division
- Consolidate format! string arguments
- Various other idiomatic Rust improvements
39 files changed, 220 insertions(+), 320 deletions(-)
2026-02-14 01:26:02 +01:00
a82faa5eaf
refactoring hexagonal and clean architecture
2026-02-08 13:40:23 +01:00
8f2b0a354c
big refactoring
2026-02-03 17:59:04 +01:00
Dionisio