perf(blobs): batch chunk fsyncs into one durability sweep per upload

Storing a new file through CDC dedup issued sync_all + a parent-dir
fsync for every ~256 KB chunk (~8,200 fsyncs for a 1 GB upload), plus
one PG INSERT round-trip per chunk. The actual durability boundary is
the manifest INSERT: chunks only need to be durable before any PG row
references them, not one by one.

- BlobStorageBackend grows put_blob_from_bytes_unsynced + sync_blobs
  with conservative defaults (unsynced delegates to the synced write,
  sync_blobs is a no-op) so backends that don't opt in keep the
  per-write durability semantics. Remote stores are durable on PUT.
- LocalBlobBackend writes chunks without fsync and implements
  sync_blobs as a parallel sweep: every listed blob file (hard
  requirement) plus each distinct prefix directory exactly once
  (best-effort, same tier as fsync_parent_dir).
- DedupService::store_chunks writes new chunks unsynced, runs one
  sync_blobs sweep, then registers all new chunks in ONE batched
  UNNEST INSERT - durability before visibility, and the per-chunk PG
  round-trips collapse into one.
- Encrypted/Migration decorators forward both methods so the
  optimization survives encrypted-local and live-migration stacks.

https://claude.ai/code/session_013Bk4BMQEvR9QxCU7QXLRwv
This commit is contained in:
Claude
2026-06-10 09:55:02 +00:00
parent 2161292e2c
commit 9a181053bd
5 changed files with 367 additions and 69 deletions
@@ -53,6 +53,19 @@ impl EncryptedBlobBackend {
}
}
/// Encrypt `data` into the on-disk layout: `[12-byte nonce][ciphertext + tag]`.
fn encrypt_bytes(cipher: &Aes256Gcm, data: &[u8]) -> Result<Bytes, DomainError> {
let nonce = Aes256Gcm::generate_nonce(&mut OsRng);
let ciphertext = cipher
.encrypt(&nonce, data)
.map_err(|e| DomainError::internal_error("Encryption", format!("encrypt failed: {e}")))?;
let mut encrypted = Vec::with_capacity(NONCE_SIZE + ciphertext.len());
encrypted.extend_from_slice(nonce.as_slice());
encrypted.extend_from_slice(&ciphertext);
Ok(Bytes::from(encrypted))
}
impl BlobStorageBackend for EncryptedBlobBackend {
fn initialize(
&self,
@@ -113,22 +126,34 @@ impl BlobStorageBackend for EncryptedBlobBackend {
let hash = hash.to_string();
let cipher = self.cipher.clone();
Box::pin(async move {
// Encrypt in memory: nonce || ciphertext (includes GCM tag)
let nonce = Aes256Gcm::generate_nonce(&mut OsRng);
let ciphertext = cipher.encrypt(&nonce, data.as_ref()).map_err(|e| {
DomainError::internal_error("Encryption", format!("encrypt failed: {e}"))
})?;
let mut encrypted = Vec::with_capacity(NONCE_SIZE + ciphertext.len());
encrypted.extend_from_slice(nonce.as_slice());
encrypted.extend_from_slice(&ciphertext);
inner
.put_blob_from_bytes(&hash, Bytes::from(encrypted))
.await
let encrypted = encrypt_bytes(&cipher, data.as_ref())?;
inner.put_blob_from_bytes(&hash, encrypted).await
})
}
fn put_blob_from_bytes_unsynced(
&self,
hash: &str,
data: Bytes,
) -> Pin<Box<dyn std::future::Future<Output = Result<u64, DomainError>> + Send + '_>> {
let inner = self.inner.clone();
let hash = hash.to_string();
let cipher = self.cipher.clone();
Box::pin(async move {
let encrypted = encrypt_bytes(&cipher, data.as_ref())?;
inner.put_blob_from_bytes_unsynced(&hash, encrypted).await
})
}
fn sync_blobs(
&self,
hashes: &[String],
) -> Pin<Box<dyn std::future::Future<Output = Result<(), DomainError>> + Send + '_>> {
// Hashes key the *plaintext* content but address the same inner
// blobs, so the durability sweep forwards untouched.
self.inner.sync_blobs(hashes)
}
fn get_blob_stream(
&self,
hash: &str,