cjw/Oxicloud
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

perf: round 21 — CalDAV/CardDAV row-mapper pre-size, dedup hash-bind & digest-key dedup, CardDAV etag/BDAY emit, NC trashbin content-type

Browse Source 
Round 21 of the benchmark-gated perf sweep. Six behaviour-preserving,
allocation-reducing changes, each with a BEFORE/AFTER counting-allocator
section in examples/bench_round21_micro.rs and a byte/-value equivalence
gate; all six pass their deterministic alloc gate (a non-winning AFTER
exits 1 = rollback).

- R1: pre-size the 16 CalDAV/CardDAV row-mapper Vecs (+1 HashMap) with
  Vec::with_capacity(rows.len()) — the ROUND20 §I1 file-side pattern
  extended to the calendar/contact repos it deferred. 7 → 1 allocs/op.
- R2: settle_batch binds a borrowed Vec<&str> instead of cloning every
  chunk hash into a Vec<String> (sqlx encodes &[&str] as text[]
  identically; favorites_pg_repository.rs:271 precedent). 33 → 1 allocs/op,
  39x wall.
- R3: store_loose_chunks keys its intra-request dedup set on the raw
  [u8;32] BLAKE3 digest and moves the hex on a duplicate (the ROUND17 §D2
  pattern applied to the delta-upload sibling). 401 → 209 allocs/op.
- R4: CardDAV getetag emits borrowed pre-escaped &quot; quotes via a shared
  write_quoted_etag helper (ROUND20 §C1 pattern, all 4 CardDAV etag sites).
  3 → 0 allocs/op.
- R5: BDAY stamped via the new fmt::compact_date stack renderer instead of
  chrono's strftime interpreter (chrono fallback out of the 4-digit-year
  range; byte-identical, unit-tested vs chrono). 2 → 0 allocs/op, 10.5x wall.
- R6: NC trashbin folder content-type via Cow::Borrowed instead of
  .to_string() on the constant (ROUND16 §M1 pattern). 1 → 0 allocs/op.

See benches/ROUND21.md for the full write-up and the deferred-items list
(HeaderMap-clone hot handlers, Query→typed-struct, WebDAV dead-props
HashSet, and others surfaced by the audit that want their own validated
pass). Validated: cargo fmt, cargo clippy --features bench --all-targets
-D warnings, cargo test --lib --features test_utils (529 passed).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015gHVq5Wy2TzdWeSqtEmK6m
This commit is contained in:
Claude
2026-07-20 08:48:42 +00:00
parent aec9b8f037
commit 77f13ac643
11 changed files with 910 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/infrastructure/repositories/pg/calendar_event_pg_repository.rs
+6 -6
View File
@@ -182,7 +182,7 @@ impl CalendarEventRepository for CalendarEventPgRepository {
DomainError::database_error(format!("Failed to get events in time range: {}", e))
})?;
let mut events = Vec::new();
let mut events = Vec::with_capacity(rows.len());
for row in rows {
let mut event = CalendarEvent::with_id(
row.get("id"),
@@ -288,7 +288,7 @@ impl CalendarEventRepository for CalendarEventPgRepository {
DomainError::database_error(format!("Failed to get events by calendar: {}", e))
})?;
let mut events = Vec::new();
let mut events = Vec::with_capacity(rows.len());
for row in rows {
let mut event = CalendarEvent::with_id(
row.get("id"),
@@ -341,7 +341,7 @@ impl CalendarEventRepository for CalendarEventPgRepository {
DomainError::database_error(format!("Failed to find events by summary: {}", e))
})?;
let mut events = Vec::new();
let mut events = Vec::with_capacity(rows.len());
for row in rows {
let mut event = CalendarEvent::with_id(
row.get("id"),
@@ -515,7 +515,7 @@ impl CalendarEventRepository for CalendarEventPgRepository {
DomainError::database_error(format!("Failed to get calendar events by UIDs: {}", e))
})?;
let mut events = Vec::new();
let mut events = Vec::with_capacity(rows.len());
for row in rows {
let mut event = CalendarEvent::with_id(
row.get("id"),
@@ -664,7 +664,7 @@ impl CalendarEventRepository for CalendarEventPgRepository {
))
})?;
let mut events = Vec::new();
let mut events = Vec::with_capacity(rows.len());
for row in rows {
let event = CalendarEvent::with_id(
row.get("id"),
@@ -719,7 +719,7 @@ impl CalendarEventRepository for CalendarEventPgRepository {
DomainError::database_error(format!("Failed to find recurring events in range: {}", e))
})?;
let mut events = Vec::new();
let mut events = Vec::with_capacity(rows.len());
for row in rows {
let event = CalendarEvent::with_id(
row.get("id"),
src/infrastructure/repositories/pg/calendar_pg_repository.rs
+3 -3
View File
@@ -211,7 +211,7 @@ impl CalendarRepository for CalendarPgRepository {
DomainError::database_error(format!("Failed to get calendars by owner: {}", e))
})?;
let mut calendars = Vec::new();
let mut calendars = Vec::with_capacity(rows.len());
for row in rows {
let calendar = Calendar::with_id(
row.get("id"),
@@ -292,7 +292,7 @@ impl CalendarRepository for CalendarPgRepository {
DomainError::database_error(format!("Failed to get public calendars: {}", e))
})?;
let mut calendars = Vec::new();
let mut calendars = Vec::with_capacity(rows.len());
for row in rows {
let calendar = Calendar::with_id(
row.get("id"),
@@ -400,7 +400,7 @@ impl CalendarRepository for CalendarPgRepository {
DomainError::database_error(format!("Failed to get calendar properties: {}", e))
})?;
let mut properties = std::collections::HashMap::new();
let mut properties = std::collections::HashMap::with_capacity(rows.len());
for row in rows {
properties.insert(row.get("name"), row.get("value"));
}
src/infrastructure/repositories/pg/contact_group_pg_repository.rs
+1 -1
View File
@@ -218,7 +218,7 @@ impl ContactGroupRepository for ContactGroupPgRepository {
)
})?;
let mut contacts = Vec::new();
let mut contacts = Vec::with_capacity(rows.len());
for row in &rows {
let email_json: JsonValue = row.get("email");
let phone_json: JsonValue = row.get("phone");
src/infrastructure/repositories/pg/contact_pg_repository.rs
+6 -6
View File
@@ -271,7 +271,7 @@ impl ContactRepository for ContactPgRepository {
DomainError::database_error(format!("Failed to get contacts by uids: {}", e))
})?;
let mut contacts = Vec::new();
let mut contacts = Vec::with_capacity(rows.len());
for row in &rows {
contacts.push(Self::row_to_contact(row)?);
}
@@ -339,7 +339,7 @@ impl ContactRepository for ContactPgRepository {
DomainError::database_error(format!("Failed to get contacts by address book: {}", e))
})?;
let mut contacts = Vec::new();
let mut contacts = Vec::with_capacity(rows.len());
for row in &rows {
contacts.push(Self::row_to_contact(row)?);
}
@@ -376,7 +376,7 @@ impl ContactRepository for ContactPgRepository {
))
})?;
let mut contacts = Vec::new();
let mut contacts = Vec::with_capacity(rows.len());
for row in &rows {
contacts.push(Self::row_to_contact(row)?);
}
@@ -404,7 +404,7 @@ impl ContactRepository for ContactPgRepository {
DomainError::database_error(format!("Failed to get contacts by email: {}", e))
})?;
let mut contacts = Vec::new();
let mut contacts = Vec::with_capacity(rows.len());
for row in &rows {
contacts.push(Self::row_to_contact(row)?);
}
@@ -434,7 +434,7 @@ impl ContactRepository for ContactPgRepository {
DomainError::database_error(format!("Failed to get contacts by group: {}", e))
})?;
let mut contacts = Vec::new();
let mut contacts = Vec::with_capacity(rows.len());
for row in &rows {
contacts.push(Self::row_to_contact(row)?);
}
@@ -474,7 +474,7 @@ impl ContactRepository for ContactPgRepository {
.await
.map_err(|e| DomainError::database_error(format!("Failed to search contacts: {}", e)))?;
let mut contacts = Vec::new();
let mut contacts = Vec::with_capacity(rows.len());
for row in &rows {
contacts.push(Self::row_to_contact(row)?);
}
src/infrastructure/services/dedup_service.rs
+39 -21
View File
@@ -860,7 +860,12 @@ impl DedupService {
let mut received: Vec<(String, u64)> = Vec::new();
let mut new_rows: Vec<(String, i64)> = Vec::new();
let mut seen: HashSet<String> = HashSet::new();
// Intra-request dedup set keyed on the raw 32-byte BLAKE3 digest
// (`[u8; 32]`, `Copy` — no per-distinct-chunk 64-byte `String` heap
// key), mirroring the streaming ingest loop (benches/ROUND17.md §D2).
// hex ↔ digest is bijective, so membership is identical to the old
// `HashSet<String>`.
let mut seen: HashSet<[u8; 32]> = HashSet::new();
while let Some(frame) = frames.next().await {
let data = frame?;
@@ -870,14 +875,21 @@ impl DedupService {
data.len()
)));
}
let hash = blake3::hash(&data).to_hex().to_string();
received.push((hash.clone(), data.len() as u64));
if seen.insert(hash.clone()) {
let len = data.len() as i64;
let digest = blake3::hash(&data);
let hash = digest.to_hex().to_string();
let len = data.len();
if seen.insert(*digest.as_bytes()) {
self.backend
.put_blob_from_bytes_unsynced(&hash, data)
.await?;
new_rows.push((hash, len));
// First occurrence: `received` needs a copy, `new_rows` moves it.
received.push((hash.clone(), len as u64));
new_rows.push((hash, len as i64));
} else {
// Duplicate within this request — move the hex into `received`
// (no clone; the blob is already registered by its first
// occurrence). Same `received` sequence, input order preserved.
received.push((hash, len as u64));
}
}
@@ -1216,24 +1228,30 @@ impl DedupService {
return Ok(());
}
let mut guard = state.lock().await;
let hashes: Vec<String> = batch.iter().map(|(h, _)| h.clone()).collect();
// Pin-or-classify in one statement: rows that exist take this
// session's reference NOW; hashes not returned don't exist and are
// ours to write.
let pinned: HashSet<String> = sqlx::query_scalar::<_, String>(
"UPDATE storage.blobs SET ref_count = ref_count + 1, orphaned_at = NULL
WHERE hash = ANY($1)
RETURNING hash",
)
.bind(&hashes)
.fetch_all(pool.as_ref())
.await
.map_err(|e| {
DomainError::internal_error("Dedup", format!("Failed to pin existing chunks: {e}"))
})?
.into_iter()
.collect();
// ours to write. Bind borrowed `&str`s — sqlx encodes `&[&str]` to
// `text[]` identically to the owned Strings the old `.clone()` built,
// so no per-chunk hash String is allocated just to run the query
// (the pattern favorites_pg_repository.rs:271 already uses). The
// borrow is scoped so it ends before `batch` is moved below.
let pinned: HashSet<String> = {
let hashes: Vec<&str> = batch.iter().map(|(h, _)| h.as_str()).collect();
sqlx::query_scalar::<_, String>(
"UPDATE storage.blobs SET ref_count = ref_count + 1, orphaned_at = NULL
WHERE hash = ANY($1)
RETURNING hash",
)
.bind(&hashes)
.fetch_all(pool.as_ref())
.await
.map_err(|e| {
DomainError::internal_error("Dedup", format!("Failed to pin existing chunks: {e}"))
})?
.into_iter()
.collect()
};
let mut to_write: Vec<(String, Bytes)> = Vec::with_capacity(batch.len());
for (hash, data) in batch {