Files
Oxicloud/static/js/features/files/deltaUpload.js
T
Claude 5d034b0d09 Delta-upload client: FastCDC in WASM + overlapped worker pipeline
Phase 2 — the client side of "upload only what changed", closing the
delta-sync plan.

WASM (wasm/oxicloud-hash): DeltaChunker adds incremental FastCDC with
the server's exact crate and parameters (64K/256K/1M) next to the BLAKE3
hasher. The incremental split is provably identical to a single pass:
every chunk except the last ends on a content/max-size condition whose
decision window was fully buffered, so only the tail is provisional and
re-examined as slices arrive. A mirror test — the client twin of the
server's stream≡slice test — chunks 4 MiB of xorshift noise with
adversarial slice sizes (7 B … 8 MiB) and requires boundary-for-boundary
equality with one FastCDC pass. Vendored artifacts rebuilt (55 KB wasm).

Worker (static/js/workers/deltaWorker.js): the full protocol off the
main thread with OVERLAPPED stages — 8 MiB file slices feed the chunker
while earlier batches (256 hashes) negotiate and their missing chunks
upload through a 2-deep PUT pool (≤8 MiB framed bodies, bytes re-sliced
from the File at send time, never hoarded). Commit handles 409
still_missing by uploading exactly the named hashes and retrying.

Orchestrator (features/files/deltaUpload.js): threshold (8 MiB),
worker lifecycle + size-scaled timeout, progress relay to the upload
bell, conclusive-outcome mapping (201/200, 507 quota, 409 name
conflict) and silent fallback to the byte upload for everything else.
Wired into uploadFiles and uploadFolderEntries, which now surface one
batch summary of the bytes dedup saved. This subsumes the whole-file
instant-upload module — a fully-known file negotiates to nothing
missing and the commit short-circuits on possession — so
instantUpload.js and hashWorker.js are removed (the /api/dedup/check
and /api/files/by-hash endpoints remain for API clients).

Verified end-to-end against PostgreSQL 16 — the cross-boundary proof
the whole design hangs on, in both directions: a 24 MB file byte-
uploaded (server-side CDC) then edited and delta-negotiated with
WASM-computed chunks reported missing 1/74 (boundaries bit-identical),
synced with 344 KB on the wire vs 24 MB (98.6% saved) and downloaded
byte-identical; inversely, a file created via delta then byte-uploaded
as identical content produced a server-side manifest DEDUP HIT with the
same content_hash. Insertion at the head of the file (the adversarial
CDC case) still negotiated missing 1/74. Chunk+hash throughput ≈275 MB/s
in V8 with SIMD128.

https://claude.ai/code/session_01WdNenpnujNR2sc32XVvwfS
2026-06-11 15:44:44 +00:00

161 lines
6.0 KiB
JavaScript

/**
* OxiCloud - Delta upload ("upload only what changed").
*
* Main-thread orchestrator for `workers/deltaWorker.js`, which runs the
* whole client side of the delta protocol off the UI thread: FastCDC
* chunking + BLAKE3 (the same WASM crate and parameters as the server,
* so boundaries match bit for bit), per-batch negotiation, upload of
* only the missing chunks, and the commit.
*
* This SUBSUMES the previous whole-file instant upload: a fully known
* file negotiates to "nothing missing" and the commit short-circuits on
* possession of the file hash — same zero-byte outcome, one pipeline.
*
* Performance posture:
* - Stages overlap inside the worker (hash ‖ negotiate ‖ upload), so
* wall-clock approaches max(hash, upload) instead of their sum.
* - RAM stays flat: 8 MiB read slices; chunk bytes are re-sliced from
* the File at upload time, never hoarded.
* - Files below {@link DELTA_UPLOAD_MIN_SIZE} skip the pipeline: the
* round-trips cost more than the bytes.
* - Any failure falls back silently to the normal byte upload — delta
* is an optimization, never a gate.
*/
import { getCsrfToken } from '../../core/csrf.js';
/**
* Files smaller than this upload normally: hashing + negotiation
* round-trips outweigh the transfer.
*/
export const DELTA_UPLOAD_MIN_SIZE = 8 * 1024 * 1024;
// Absolute URL on purpose — works in dev and in the release IIFE bundle
// (same pattern as the pdf.js loader in thumbnail.js).
const DELTA_WORKER_URL = '/js/workers/deltaWorker.js';
/** Budget: 120 s base + 90 s per GB (hashing + uploading the delta). */
const DELTA_TIMEOUT_BASE_MS = 120000;
const DELTA_TIMEOUT_PER_GB_MS = 90000;
/**
* `false` once the environment proved unable to run the worker/WASM —
* later files skip straight to the byte upload. `null` = not yet known.
* @type {boolean | null}
*/
let _deltaUploadUsable = null;
/**
* Result contract shared with the uploaders' `UploadAnswer`, plus the
* bandwidth accounting the UI surfaces.
* @typedef {Object} DeltaUploadAnswer
* @property {boolean} ok
* @property {any} [data] FileDto on success
* @property {string} [errorMsg]
* @property {boolean} [isQuotaError]
* @property {number} [savedBytes] bytes NOT transferred thanks to dedup
*/
/**
* Try to upload `file` through the delta protocol.
*
* Resolves `null` whenever the plain byte upload should proceed (file too
* small, environment unusable, any transport/protocol failure). Resolves
* a {@link DeltaUploadAnswer} when the outcome is conclusive — success,
* quota exceeded, or a name conflict a byte upload would also hit.
*
* @param {File} file
* @param {string | null | undefined} folderId
* @param {(pct: number) => void} [onProgress] 0-99 while transferring
* @returns {Promise<DeltaUploadAnswer | null>}
*/
export function tryDeltaUpload(file, folderId, onProgress) {
if (!folderId || file.size < DELTA_UPLOAD_MIN_SIZE || _deltaUploadUsable === false || typeof Worker === 'undefined') {
return Promise.resolve(null);
}
return new Promise((resolve) => {
/** @type {Worker} */
let worker;
try {
worker = new Worker(DELTA_WORKER_URL, { type: 'module' });
} catch (_) {
_deltaUploadUsable = false;
resolve(null);
return;
}
const sizeGB = file.size / (1024 * 1024 * 1024);
const timeoutMs = DELTA_TIMEOUT_BASE_MS + Math.ceil(sizeGB) * DELTA_TIMEOUT_PER_GB_MS;
let savedBytes = 0;
/** @param {DeltaUploadAnswer | null} answer */
const settle = (answer) => {
clearTimeout(timer);
worker.terminate();
resolve(answer);
};
const timer = setTimeout(() => settle(null), timeoutMs);
worker.onmessage = (event) => {
const msg = /** @type {any} */ (event.data);
if (msg.type === 'progress') {
savedBytes = msg.reusedBytes;
if (onProgress && msg.totalBytes > 0) {
const pct = Math.min(99, Math.round((100 * (msg.reusedBytes + msg.uploadedBytes)) / msg.totalBytes));
onProgress(pct);
}
return;
}
if (msg.type === 'fallback') {
settle(null);
return;
}
if (msg.type === 'done') {
if (msg.status === 201 || msg.status === 200) {
settle({ ok: true, data: msg.body, savedBytes });
return;
}
/** @type {string} */
const errorMsg = msg.body?.message || msg.body?.error || `Delta upload failed (HTTP ${msg.status})`;
if (msg.status === 507) {
settle({ ok: false, isQuotaError: true, errorMsg });
return;
}
if (msg.status === 409 && !msg.body?.still_missing) {
// Duplicate name — a byte upload would hit the same wall.
settle({ ok: false, errorMsg });
return;
}
// still_missing exhausted, 4xx/5xx oddities: byte upload is
// the safe road (the server dedups it on write anyway).
settle(null);
}
};
worker.onerror = () => {
// Worker script failed to load/parse — permanent environment trait.
_deltaUploadUsable = false;
settle(null);
};
worker.postMessage({
file,
folderId,
name: file.name,
csrfToken: getCsrfToken() || ''
});
});
}
/**
* Bilingual one-line summary for the bandwidth saved by a batch.
* @param {number} savedBytes
* @param {string} locale
* @returns {string}
*/
export function formatSavedSummary(savedBytes, locale) {
const mb = (savedBytes / (1024 * 1024)).toFixed(1);
return locale.startsWith('es') ? `Deduplicación: ${mb} MB no necesitaron subirse` : `Deduplication: ${mb} MB didn't need uploading`;
}