Merge pull request #438 from EdouardVanbelle/feat/cap-chunk-size-and-use-stream
This commit is contained in:
Dionisio Pozo
@@ -97,3 +97,6 @@ tests/e2e/test-results/
|
|||||||
tests/e2e/blob-report/
|
tests/e2e/blob-report/
|
||||||
tests/e2e/playwright/.cache/
|
tests/e2e/playwright/.cache/
|
||||||
tests/e2e/playwright/.auth/
|
tests/e2e/playwright/.auth/
|
||||||
|
|
||||||
|
# Test fixtures generated on-the-fly by tests/api/run.sh
|
||||||
|
tests/fixtures/chunk-over-cap-*.bin
|
||||||
|
|||||||
@@ -78,6 +78,7 @@ export default defineConfig({
|
|||||||
items: [
|
items: [
|
||||||
{ text: "Deployment & Docker", link: "/config/deployment" },
|
{ text: "Deployment & Docker", link: "/config/deployment" },
|
||||||
{ text: "Environment Variables", link: "/config/env" },
|
{ text: "Environment Variables", link: "/config/env" },
|
||||||
|
{ text: "Storage Fine Tuning", link: "/config/storage-fine-tuning" },
|
||||||
{ text: "Authentication", link: "/config/authentication" },
|
{ text: "Authentication", link: "/config/authentication" },
|
||||||
{ text: "OIDC / SSO", link: "/config/oidc" },
|
{ text: "OIDC / SSO", link: "/config/oidc" },
|
||||||
{ text: "OIDC Config Examples", link: "/config/oidc-config-examples" },
|
{ text: "OIDC Config Examples", link: "/config/oidc-config-examples" },
|
||||||
|
|||||||
+5
-1
@@ -11,7 +11,11 @@ Most runtime variables use the `OXICLOUD_` prefix. A few build-time or allocator
|
|||||||
| `OXICLOUD_SERVER_PORT` | `8086` | Server port |
|
| `OXICLOUD_SERVER_PORT` | `8086` | Server port |
|
||||||
| `OXICLOUD_SERVER_HOST` | `127.0.0.1` | Server bind address (IPv4 or IPv6 allowed) |
|
| `OXICLOUD_SERVER_HOST` | `127.0.0.1` | Server bind address (IPv4 or IPv6 allowed) |
|
||||||
| `OXICLOUD_BASE_URL` | (auto) | Public base URL for share links; defaults to `http://{host}:{port}` |
|
| `OXICLOUD_BASE_URL` | (auto) | Public base URL for share links; defaults to `http://{host}:{port}` |
|
||||||
| `OXICLOUD_MAX_UPLOAD_SIZE` | `10737418240` | Maximum upload size in bytes (10 GB on 64-bit, 1 GB on 32-bit) |
|
| `OXICLOUD_MAX_UPLOAD_SIZE` | `10737418240` | Whole-file size ceiling, in bytes (10 GB on 64-bit, 1 GB on 32-bit). Applies to BOTH direct PUTs (per-request body) and chunked uploads (declared `total_size`, checked upfront at session creation). |
|
||||||
|
| `OXICLOUD_DIRECT_PUT_MAX_BYTES` | `1073741824` | Per-request cap for non-chunked PUT bodies, in bytes (1 GiB). Set below `OXICLOUD_MAX_UPLOAD_SIZE` so larger files are pushed onto the chunked protocol (resumable on failure). See [Storage Fine Tuning](./storage-fine-tuning.md). |
|
||||||
|
| `OXICLOUD_CHUNK_MAX_BYTES` | `104857600` | Maximum size of a single chunked-upload PUT in bytes (100 MB). Per-chunk cap, independent of `OXICLOUD_MAX_UPLOAD_SIZE` (whole-file cap). See [Storage Fine Tuning](./storage-fine-tuning.md). |
|
||||||
|
| `OXICLOUD_UPLOAD_TMPDIR` | (OS temp dir) | Spool directory for non-chunked PUT bodies (`/api/files/upload`, WebDAV PUT). Point at a real-disk path on the same FS as `.blobs/` to avoid tmpfs OOMKill and make blob promotion an atomic rename. See [Storage Fine Tuning](./storage-fine-tuning.md). |
|
||||||
|
| `OXICLOUD_CHUNK_DIR` | `{STORAGE_PATH}/.uploads` | Root directory for chunked-upload sessions (REST + NextCloud). Same-FS / NVMe placement guidance: see [Storage Fine Tuning](./storage-fine-tuning.md). |
|
||||||
| `OXICLOUD_REUSE_PORT` | `false` | Enable `SO_REUSEPORT` so multiple processes can share the same port. **Disabled by default** — a second accidental instance will fail with "address already in use". Enable only for deliberate multi-worker setups (process supervisor, rolling restart). Not supported on Windows. |
|
| `OXICLOUD_REUSE_PORT` | `false` | Enable `SO_REUSEPORT` so multiple processes can share the same port. **Disabled by default** — a second accidental instance will fail with "address already in use". Enable only for deliberate multi-worker setups (process supervisor, rolling restart). Not supported on Windows. |
|
||||||
|
|
||||||
## Database
|
## Database
|
||||||
|
|||||||
@@ -6,6 +6,7 @@ OxiCloud is configured entirely via **environment variables** (no config files n
|
|||||||
|
|
||||||
- [Deployment & Docker](/config/deployment) — Docker Compose, Kubernetes Helm chart, image details
|
- [Deployment & Docker](/config/deployment) — Docker Compose, Kubernetes Helm chart, image details
|
||||||
- [Environment Variables](/config/env) — complete reference of all `OXICLOUD_*` variables
|
- [Environment Variables](/config/env) — complete reference of all `OXICLOUD_*` variables
|
||||||
|
- [Storage Fine Tuning](/config/storage-fine-tuning) — sizing the upload caps + spool directories; tmpfs vs real disk; NVMe split layouts
|
||||||
- [Authentication](/config/authentication) — JWT auth, login, refresh, password changes, and auth status
|
- [Authentication](/config/authentication) — JWT auth, login, refresh, password changes, and auth status
|
||||||
- [OIDC / SSO](/config/oidc) — single sign-on with Keycloak, Authentik, Authelia, Google, Azure AD
|
- [OIDC / SSO](/config/oidc) — single sign-on with Keycloak, Authentik, Authelia, Google, Azure AD
|
||||||
- [WOPI (Office Editing)](/config/wopi) — Collabora Online / OnlyOffice integration
|
- [WOPI (Office Editing)](/config/wopi) — Collabora Online / OnlyOffice integration
|
||||||
|
|||||||
@@ -0,0 +1,319 @@
|
|||||||
|
# Storage Fine Tuning
|
||||||
|
|
||||||
|
This page is for sysadmins who want to tune **where** OxiCloud spools
|
||||||
|
upload bodies and **why** the placement matters for throughput and
|
||||||
|
memory. The defaults work; the gains from a tuned layout are
|
||||||
|
significant on busy instances or constrained containers.
|
||||||
|
|
||||||
|
## The upload lifecycle in 30 seconds
|
||||||
|
|
||||||
|
Every upload moves through two stages:
|
||||||
|
|
||||||
|
```
|
||||||
|
┌─── direct (single-PUT) upload ────────┐
|
||||||
|
client ─┤ ├──► OxiCloud accepts the
|
||||||
|
└─── multi-chunk upload │ bytes into a SPOOL on
|
||||||
|
(`/api/uploads` / │ local disk.
|
||||||
|
`/dav/uploads/...`) │
|
||||||
|
│ Direct upload → OXICLOUD_UPLOAD_TMPDIR
|
||||||
|
│ Chunked upload → OXICLOUD_CHUNK_DIR
|
||||||
|
│
|
||||||
|
▼
|
||||||
|
┌─────────────────────────┐
|
||||||
|
│ Once the upload is │
|
||||||
|
│ complete (and verified │
|
||||||
|
│ if a checksum was │
|
||||||
|
│ supplied), OxiCloud │
|
||||||
|
│ MOVES the assembled │
|
||||||
|
│ blob into the configured│
|
||||||
|
│ STORAGE BACKEND: │
|
||||||
|
│ │
|
||||||
|
│ • local FS (.blobs/) │
|
||||||
|
│ • S3-compatible │
|
||||||
|
│ • Azure Blob │
|
||||||
|
└─────────────────────────┘
|
||||||
|
```
|
||||||
|
|
||||||
|
Two practical consequences:
|
||||||
|
|
||||||
|
- **The spool/chunk directories see write-heavy churn** during uploads —
|
||||||
|
fast disk (NVMe) and sufficient free space matter more here than on
|
||||||
|
the final storage backend.
|
||||||
|
- **The promotion from spool → storage is a `rename(2)` whenever
|
||||||
|
source and destination share a filesystem** (i.e. when the backend
|
||||||
|
is `local` and the spool dir is on the same FS as `.blobs/`). On
|
||||||
|
remote backends (S3, Azure) the promotion is always a network
|
||||||
|
upload from the local spool; placement of the spool still matters
|
||||||
|
for intake throughput but the "same FS" rule doesn't apply.
|
||||||
|
|
||||||
|
## Upload size caps — what each one bounds
|
||||||
|
|
||||||
|
Three independent caps control how large an upload OxiCloud will
|
||||||
|
accept. Pick them with disk and tmpfs sizing in mind: the spool/chunk
|
||||||
|
directories must be able to hold the worst case (cap × concurrent
|
||||||
|
uploads).
|
||||||
|
|
||||||
|
| Variable | Default | What it caps | When it fires |
|
||||||
|
|---|---|---|---|
|
||||||
|
| `OXICLOUD_MAX_UPLOAD_SIZE` | 10 GB | **Whole-file ceiling.** Applies to both direct PUT (per-body) and chunked uploads (declared `total_size`). The absolute upper bound on any single file in OxiCloud. | Chunked: at `POST /api/uploads` against the JSON-declared `total_size`, before any chunk is uploaded. Direct PUT: indirectly via `OXICLOUD_DIRECT_PUT_MAX_BYTES`, which is expected to be ≤ `OXICLOUD_MAX_UPLOAD_SIZE`. |
|
||||||
|
| `OXICLOUD_DIRECT_PUT_MAX_BYTES` | 1 GiB | **Non-chunked PUT body.** Per-request cap for `POST /api/files/upload`, `PUT /webdav/...`, and `PUT /remote.php/dav/files/.../...`. Set below `OXICLOUD_MAX_UPLOAD_SIZE` so larger files are pushed onto the chunked protocol — which is resumable on failure. | During body streaming, as a per-frame accumulator. Excess → 413 with a "use chunked upload" hint. |
|
||||||
|
| `OXICLOUD_CHUNK_MAX_BYTES` | 100 MB | **Per-chunk body** in a chunked-upload session (`PATCH /api/uploads/{id}` or `PUT /remote.php/dav/uploads/.../chunk`). Independent of the whole-file cap — a 5 GB file in 100 MB chunks is 50 PATCHes each bounded by this. | During chunk-body streaming. Excess → 413. |
|
||||||
|
|
||||||
|
### Recommendation: prefer chunked uploads for large files
|
||||||
|
|
||||||
|
The defaults (`OXICLOUD_DIRECT_PUT_MAX_BYTES` = 1 GiB, well below
|
||||||
|
`OXICLOUD_MAX_UPLOAD_SIZE` = 10 GB) are deliberately asymmetric.
|
||||||
|
Files between those two caps can only succeed via the chunked
|
||||||
|
protocol. Three reasons to keep them that way:
|
||||||
|
|
||||||
|
- **Resilience.** A direct PUT at 95 % of 5 GB that drops loses
|
||||||
|
everything. The same drop on a chunked upload loses one ~5 MB
|
||||||
|
chunk; the client retries that chunk and continues.
|
||||||
|
- **Memory + disk pressure.** Direct PUT spools the full body to
|
||||||
|
disk per request. Ten concurrent 5 GB direct PUTs use up to 50 GB
|
||||||
|
of transient spool disk. Chunked spreads each upload across many
|
||||||
|
small PATCHes; per-request resource use stays bounded by
|
||||||
|
`OXICLOUD_CHUNK_MAX_BYTES`.
|
||||||
|
- **Convention.** NextCloud desktop and the OxiCloud web UI already
|
||||||
|
switch to chunked at ~10 MB (`CHUNKED_UPLOAD_THRESHOLD`).
|
||||||
|
|
||||||
|
### Why caps matter for tmpfs sizing
|
||||||
|
|
||||||
|
OxiCloud streams bodies frame-by-frame, so **RAM** is bounded to one
|
||||||
|
HTTP frame (~64 KB) per request regardless of the caps. **Disk space**,
|
||||||
|
however, scales with the caps:
|
||||||
|
|
||||||
|
- **Direct PUT**: each in-flight upload spools the full body to disk
|
||||||
|
under `OXICLOUD_UPLOAD_TMPDIR` until promotion. Worst case disk =
|
||||||
|
`OXICLOUD_DIRECT_PUT_MAX_BYTES × concurrent_direct_PUTs`.
|
||||||
|
- **Chunked upload**: each in-flight session accumulates chunks
|
||||||
|
under `OXICLOUD_CHUNK_DIR`, then assembles them into a single temp
|
||||||
|
file before promotion. Worst case disk per session = **2 ×
|
||||||
|
file_size** (chunks + assembled file); total disk =
|
||||||
|
`2 × OXICLOUD_MAX_UPLOAD_SIZE × concurrent_chunked_sessions`.
|
||||||
|
|
||||||
|
The chunked formula uses `OXICLOUD_MAX_UPLOAD_SIZE` because that's
|
||||||
|
what bounds the declared `total_size` at session creation. The
|
||||||
|
direct-PUT formula uses the smaller `OXICLOUD_DIRECT_PUT_MAX_BYTES`
|
||||||
|
since that's what bounds each direct PUT body.
|
||||||
|
|
||||||
|
### Sizing examples
|
||||||
|
|
||||||
|
A 4 GB tmpfs serving a small team (5 concurrent direct PUTs OR 5
|
||||||
|
concurrent chunked sessions):
|
||||||
|
|
||||||
|
| Settings | Direct-PUT worst case | Chunked worst case | Safe on 4 GB tmpfs? |
|
||||||
|
|---|---|---|---|
|
||||||
|
| Defaults: `OXICLOUD_MAX_UPLOAD_SIZE`=10 GB, `OXICLOUD_DIRECT_PUT_MAX_BYTES`=1 GiB, `OXICLOUD_CHUNK_MAX_BYTES`=100 MB | 5 GiB (5 × 1 GiB) | 100 GB (5 × 2 × 10 GB) | ❌ chunked overflows |
|
||||||
|
| `OXICLOUD_MAX_UPLOAD_SIZE`=500 MB, `OXICLOUD_DIRECT_PUT_MAX_BYTES`=100 MB, `OXICLOUD_CHUNK_MAX_BYTES`=20 MB | 500 MB | 5 GB | ⚠ direct PUT fits, chunked still overflows |
|
||||||
|
| `OXICLOUD_MAX_UPLOAD_SIZE`=300 MB, `OXICLOUD_DIRECT_PUT_MAX_BYTES`=50 MB, `OXICLOUD_CHUNK_MAX_BYTES`=10 MB | 250 MB | 3 GB | ✅ both fit |
|
||||||
|
|
||||||
|
A real-disk volume (cheap, large):
|
||||||
|
|
||||||
|
| Settings | Direct-PUT worst case | Chunked worst case | Comment |
|
||||||
|
|---|---|---|---|
|
||||||
|
| Defaults (see row above) | 5 GiB | 100 GB | Fine on a 200+ GB volume; almost any real-disk setup |
|
||||||
|
| `OXICLOUD_MAX_UPLOAD_SIZE`=100 GB, `OXICLOUD_DIRECT_PUT_MAX_BYTES`=5 GiB, `OXICLOUD_CHUNK_MAX_BYTES`=500 MB | 25 GiB | 1 TB | Plausible for video archives; needs a dedicated upload volume |
|
||||||
|
|
||||||
|
### Choosing tmpfs vs real disk
|
||||||
|
|
||||||
|
| Constraint | Choice |
|
||||||
|
|---|---|
|
||||||
|
| `OXICLOUD_DIRECT_PUT_MAX_BYTES × concurrent_direct_PUTs + 2 × OXICLOUD_MAX_UPLOAD_SIZE × concurrent_chunked_sessions ≤ free RAM × 0.5` | tmpfs OK (fast, atomic with `.blobs/` if also tmpfs) |
|
||||||
|
| Worst case exceeds half free RAM | **real disk** — same filesystem as `.blobs/` ideal |
|
||||||
|
| Container with cgroup memory limit | **real disk** — tmpfs spool counts against the cgroup limit and triggers OOMKill |
|
||||||
|
| Multi-GB uploads expected | **real disk** — even small concurrency on tmpfs runs out of space |
|
||||||
|
| Small-file workload only (≤ 50 MB), high concurrency | tmpfs gives a noticeable intake speedup |
|
||||||
|
|
||||||
|
The defaults (`OXICLOUD_MAX_UPLOAD_SIZE`=10 GB,
|
||||||
|
`OXICLOUD_DIRECT_PUT_MAX_BYTES`=1 GiB,
|
||||||
|
`OXICLOUD_CHUNK_MAX_BYTES`=100 MB) assume **real disk**. Don't run
|
||||||
|
the defaults against tmpfs unless you've sized it for the worst case.
|
||||||
|
|
||||||
|
## TL;DR
|
||||||
|
|
||||||
|
| Variable | Default | Purpose |
|
||||||
|
|---|---|---|
|
||||||
|
| `OXICLOUD_STORAGE_PATH` | `./storage` | Where `.blobs/` lives (the canonical content store) |
|
||||||
|
| `OXICLOUD_UPLOAD_TMPDIR` | OS temp dir | Where non-chunked PUT bodies are spooled |
|
||||||
|
| `OXICLOUD_CHUNK_DIR` | `{STORAGE_PATH}/.uploads` | Where chunked-upload sessions accumulate |
|
||||||
|
|
||||||
|
The two rules that matter most:
|
||||||
|
|
||||||
|
1. **Put all three on the same filesystem.** Blob promotion is an
|
||||||
|
atomic `rename(2)` when source and destination share an FS — cheap
|
||||||
|
and crash-safe. Across filesystems it becomes a full `read + write +
|
||||||
|
unlink`, multiplying the IO and widening the durability window.
|
||||||
|
2. **Don't leave the spool dir on tmpfs** (the default in many
|
||||||
|
containers). Spool bodies count against the cgroup memory limit
|
||||||
|
and can trigger OOMKill on multi-GB uploads.
|
||||||
|
|
||||||
|
## Where each upload surface spools
|
||||||
|
|
||||||
|
OxiCloud has several entry points that accept request bodies. They
|
||||||
|
land in different places by default:
|
||||||
|
|
||||||
|
| Surface | Default destination | Configurable via |
|
||||||
|
|---|---|---|
|
||||||
|
| REST chunked PUT (`PATCH /api/uploads/{id}`) | `{STORAGE_PATH}/.uploads/{upload_id}/chunk_NNNNNN` | `OXICLOUD_CHUNK_DIR` |
|
||||||
|
| REST chunked assemble (during `/complete`) | `{STORAGE_PATH}/.uploads/{upload_id}/assembled` | `OXICLOUD_CHUNK_DIR` |
|
||||||
|
| NextCloud chunked PUT (`PUT /dav/uploads/.../chunk`) | `{STORAGE_PATH}/.uploads/nextcloud/{user}/{upload_id}/{chunk_name}` | `OXICLOUD_CHUNK_DIR` |
|
||||||
|
| NextCloud chunked assemble (during `MOVE`) | `{STORAGE_PATH}/.uploads/nextcloud/{user}/{upload_id}/.assembled` | `OXICLOUD_CHUNK_DIR` |
|
||||||
|
| Native WebDAV PUT (`PUT /webdav/{path}`) | OS temp dir (`/tmp`) | `OXICLOUD_UPLOAD_TMPDIR` |
|
||||||
|
| NextCloud single-file PUT (`PUT /dav/files/.../{path}`) | OS temp dir | `OXICLOUD_UPLOAD_TMPDIR` |
|
||||||
|
| REST multipart upload (`POST /api/files/upload`) | `{STORAGE_PATH}/.dedup_temp/upload-{uuid}` | `OXICLOUD_STORAGE_PATH` (subdir is hard-wired) |
|
||||||
|
| Final blob storage (after fsync + rename) | `{STORAGE_PATH}/.blobs/{ab}/{abc…}.blob` | `OXICLOUD_STORAGE_PATH` |
|
||||||
|
|
||||||
|
## Why placement matters
|
||||||
|
|
||||||
|
### 1. Same filesystem ⇒ promotion is a rename
|
||||||
|
|
||||||
|
OxiCloud uses **content-addressable storage**: the final blob path is
|
||||||
|
derived from the file's BLAKE3 hash, which can only be known after the
|
||||||
|
last byte arrives. So every upload writes to a temp location first,
|
||||||
|
then **promotes** the temp file to `.blobs/{ab}/{abc…}.blob` by way of
|
||||||
|
a `rename(2)` call.
|
||||||
|
|
||||||
|
- **Same FS:** `rename` is atomic, O(1), no data copy. Total upload
|
||||||
|
cost = body bytes received + one rename syscall. Crash-safe — the
|
||||||
|
blob either exists at the final path or doesn't.
|
||||||
|
- **Cross-FS:** the kernel can't `rename(2)` across filesystems. The
|
||||||
|
blob backend falls back to `fs::copy + fs::remove_file` (visible in
|
||||||
|
`local_blob_backend.rs` as the EXDEV handler). Total cost = body
|
||||||
|
bytes received + one full file copy. Doubles the IO bandwidth used
|
||||||
|
per upload and widens the durability window.
|
||||||
|
|
||||||
|
### 2. Spool off tmpfs
|
||||||
|
|
||||||
|
`tempfile::NamedTempFile::new()` (used when `OXICLOUD_UPLOAD_TMPDIR`
|
||||||
|
is unset) honors `$TMPDIR`, which in many container setups points at
|
||||||
|
**tmpfs** — RAM-backed storage. A 2 GB upload spool then consumes 2 GB
|
||||||
|
of memory until the rename promotes it to disk.
|
||||||
|
|
||||||
|
In a Kubernetes pod with a 4 GB memory limit, the OOMKiller wakes up
|
||||||
|
long before the upload finishes. With `OXICLOUD_UPLOAD_TMPDIR` pointed
|
||||||
|
at a real-disk directory, the spool's memory footprint stays at ~one
|
||||||
|
HTTP frame regardless of file size.
|
||||||
|
|
||||||
|
### 3. NVMe for the hot path
|
||||||
|
|
||||||
|
The chunked-upload session directory sees a LOT of small writes —
|
||||||
|
each chunk PUT writes a file, the progress bitmap is rewritten after
|
||||||
|
each PUT, the assemble step reads them all back in order. Pointing
|
||||||
|
`OXICLOUD_CHUNK_DIR` at an NVMe device is a substantial win on
|
||||||
|
deployments that handle large file uploads, even if the final blob
|
||||||
|
storage is on slower disk.
|
||||||
|
|
||||||
|
The same applies to `OXICLOUD_UPLOAD_TMPDIR` (single-file PUTs).
|
||||||
|
|
||||||
|
A common high-throughput layout:
|
||||||
|
|
||||||
|
- **NVMe** (small, fast): `OXICLOUD_CHUNK_DIR`, `OXICLOUD_UPLOAD_TMPDIR`
|
||||||
|
- **HDD or NAS** (large, cheap): `OXICLOUD_STORAGE_PATH`/`.blobs/`
|
||||||
|
|
||||||
|
Trade-off: the rename optimization (rule 1) DOESN'T apply across
|
||||||
|
filesystems. If you split the hot path off the blob filesystem, every
|
||||||
|
upload pays a full file copy on promotion. You have to choose
|
||||||
|
between **fast intake** and **zero-copy promotion**.
|
||||||
|
|
||||||
|
| Goal | Layout | Cost per upload |
|
||||||
|
|---|---|---|
|
||||||
|
| Fastest possible intake | NVMe chunk dir + HDD blobs | 1× write to NVMe + 1× read NVMe + 1× write to HDD (copy) |
|
||||||
|
| Lowest IO + crash safety | NVMe everything OR HDD everything | 1× write to disk + 1 rename (~0 cost) |
|
||||||
|
| Default (do nothing) | Everything under `STORAGE_PATH` on whatever FS that is | Depends on `STORAGE_PATH` placement |
|
||||||
|
|
||||||
|
For most deployments **"same FS everywhere"** wins. The NVMe-split is
|
||||||
|
useful when intake latency dominates the user experience and you can
|
||||||
|
afford the doubled IO.
|
||||||
|
|
||||||
|
## Recommended layouts
|
||||||
|
|
||||||
|
### Single-disk box (most common)
|
||||||
|
|
||||||
|
Defaults are fine. Optionally set `OXICLOUD_UPLOAD_TMPDIR` to keep
|
||||||
|
the PUT spool off `/tmp`:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
OXICLOUD_STORAGE_PATH=/var/lib/oxicloud
|
||||||
|
OXICLOUD_UPLOAD_TMPDIR=/var/lib/oxicloud/.spool
|
||||||
|
# OXICLOUD_CHUNK_DIR unset → /var/lib/oxicloud/.uploads
|
||||||
|
```
|
||||||
|
|
||||||
|
All three on the same filesystem → rename promotion → atomic and fast.
|
||||||
|
|
||||||
|
### Container with constrained memory
|
||||||
|
|
||||||
|
Critical: make sure neither spool sits on tmpfs.
|
||||||
|
|
||||||
|
```bash
|
||||||
|
OXICLOUD_STORAGE_PATH=/data
|
||||||
|
OXICLOUD_UPLOAD_TMPDIR=/data/.spool
|
||||||
|
OXICLOUD_CHUNK_DIR=/data/.uploads
|
||||||
|
```
|
||||||
|
|
||||||
|
If you can't mount a writable `/data`, at minimum bind-mount a real
|
||||||
|
volume at the spool dirs.
|
||||||
|
|
||||||
|
### Split-disk (NVMe intake + HDD blobs)
|
||||||
|
|
||||||
|
```bash
|
||||||
|
OXICLOUD_STORAGE_PATH=/mnt/hdd/oxicloud # .blobs/ + .dedup_temp/
|
||||||
|
OXICLOUD_UPLOAD_TMPDIR=/mnt/nvme/oxi-spool
|
||||||
|
OXICLOUD_CHUNK_DIR=/mnt/nvme/oxi-chunks
|
||||||
|
```
|
||||||
|
|
||||||
|
Faster intake; pays a copy on promotion. Worth it when uploads are
|
||||||
|
many small files (NVMe IOPS dominates) or when intake latency directly
|
||||||
|
hits user-visible UX.
|
||||||
|
|
||||||
|
## Sharing the spool and chunk directories
|
||||||
|
|
||||||
|
Pointing `OXICLOUD_UPLOAD_TMPDIR` and `OXICLOUD_CHUNK_DIR` at the
|
||||||
|
**same directory** is supported by design. Each writer tags its
|
||||||
|
output so the surfaces never interfere with each other:
|
||||||
|
|
||||||
|
| Writer | On-disk name pattern |
|
||||||
|
|---|---|
|
||||||
|
| PUT spool (single-file uploads) | `.tmpXXXXXXXX` — files (not directories), random suffix |
|
||||||
|
| REST chunked sessions | `oxi-chunk-{uuid}/` — directories with a well-known prefix |
|
||||||
|
| NC chunked subtree | `nextcloud/{user}/{uuid}/` — under its own root subdir |
|
||||||
|
|
||||||
|
The 24-hour orphan-session cleanup loop filters strictly on the
|
||||||
|
`oxi-chunk-` prefix, so it can NEVER delete a non-OxiCloud directory
|
||||||
|
that happens to live alongside chunked sessions. The PUT spool's
|
||||||
|
`.tmpXXXX` files are files (not directories) and the NC subtree's
|
||||||
|
`nextcloud/` root has its own name — both are invisible to the
|
||||||
|
cleanup loop.
|
||||||
|
|
||||||
|
**Recommendation:** for new deployments, use separate directories
|
||||||
|
anyway (the defaults `.spool/` and `.uploads/` already do this) —
|
||||||
|
it makes disk-usage attribution clearer and keeps IOPS isolated when
|
||||||
|
both are busy. Shared directories are safe to use when disk layout
|
||||||
|
forces it.
|
||||||
|
|
||||||
|
## What's NOT yet configurable
|
||||||
|
|
||||||
|
- **REST multipart upload directory** (`POST /api/files/upload`) is
|
||||||
|
hard-wired to `{STORAGE_PATH}/.dedup_temp/`. It can't be moved
|
||||||
|
separately. Same-FS placement is automatic.
|
||||||
|
- **WOPI PutFile spool** (Office editor saves) uses the bare OS temp
|
||||||
|
dir without honoring `OXICLOUD_UPLOAD_TMPDIR`. This is a known
|
||||||
|
inconsistency and on the hardening backlog.
|
||||||
|
- **Per-user / per-drive spool directories** — all users share the
|
||||||
|
same `OXICLOUD_CHUNK_DIR` root today. Multi-tenant isolation
|
||||||
|
through separate spool dirs isn't supported.
|
||||||
|
|
||||||
|
## Quick verification
|
||||||
|
|
||||||
|
Boot the server with `RUST_LOG=info` and the first lines after the
|
||||||
|
banner include:
|
||||||
|
|
||||||
|
```
|
||||||
|
oxicloud: Upload limits loaded from config max_upload_size_mb=10240 chunk_max_bytes_mb=100
|
||||||
|
```
|
||||||
|
|
||||||
|
That confirms the upload-cap env vars were read. To confirm
|
||||||
|
directory placement, watch for chunk file creation under your
|
||||||
|
`OXICLOUD_CHUNK_DIR` (or its default `{STORAGE_PATH}/.uploads/`)
|
||||||
|
during a chunked upload — `ls` while a sync is in progress shows the
|
||||||
|
`{uuid}/chunk_NNNNNN` files appearing in real time.
|
||||||
+38
-8
@@ -31,18 +31,48 @@ OXICLOUD_SERVER_HOST=127.0.0.1
|
|||||||
# Example: https://cloud.example.com
|
# Example: https://cloud.example.com
|
||||||
#OXICLOUD_BASE_URL=https://cloud.example.com
|
#OXICLOUD_BASE_URL=https://cloud.example.com
|
||||||
|
|
||||||
# Maximum upload size in bytes (default: 10 GB on 64-bit)
|
# ── Upload size caps ──────────────────────────────────────────────────
|
||||||
|
# See docs/config/storage-fine-tuning.md for sizing guidance.
|
||||||
|
|
||||||
|
# Whole-file size ceiling. Applies to BOTH direct PUTs (per-request body)
|
||||||
|
# and chunked uploads (declared `total_size` at session creation — checked
|
||||||
|
# upfront so oversized requests never accumulate chunks on disk).
|
||||||
|
# Default: 10 GB on 64-bit, 1 GB on 32-bit.
|
||||||
#OXICLOUD_MAX_UPLOAD_SIZE=10737418240
|
#OXICLOUD_MAX_UPLOAD_SIZE=10737418240
|
||||||
|
|
||||||
# Directory for upload spool temp files. Uploads are streamed to a temp file
|
# Per-request cap for non-chunked PUT bodies (`POST /api/files/upload`,
|
||||||
# before deduplication. By default this uses the OS temp dir ($TMPDIR / /tmp),
|
# `PUT /webdav/...`, `PUT /remote.php/dav/files/...`). Set below
|
||||||
# which in many containers is tmpfs (RAM) — writing a large upload there fills
|
# MAX_UPLOAD_SIZE so files larger than this are pushed onto the chunked
|
||||||
# page-cache that counts against the cgroup memory limit and can OOMKill the
|
# protocol (resumable on failure, bounded per-request by CHUNK_MAX_BYTES).
|
||||||
# process. Point this at a real-disk path (same filesystem as the storage
|
# Default: 1 GiB.
|
||||||
# backend is ideal) to keep the upload footprint off RAM. Leave unset to use
|
#OXICLOUD_DIRECT_PUT_MAX_BYTES=1073741824
|
||||||
# the OS default.
|
|
||||||
|
# Per-chunk cap for a single chunked-upload PUT (PATCH /api/uploads/{id}
|
||||||
|
# or PUT /dav/uploads/.../chunk). NC desktop and the OxiCloud frontend
|
||||||
|
# split large files into chunks of this size or smaller, so this knob
|
||||||
|
# tightly bounds the worst-case per-request memory/disk footprint
|
||||||
|
# independently of the whole-file cap. Default: 100 MB.
|
||||||
|
#OXICLOUD_CHUNK_MAX_BYTES=104857600
|
||||||
|
|
||||||
|
# ── Upload spool directories ─────────────────────────────────────────
|
||||||
|
# Where in-flight uploads land BEFORE being promoted into final blob
|
||||||
|
# storage. Same-filesystem placement (with `.blobs/`) makes the
|
||||||
|
# promotion an atomic rename(2); NVMe placement speeds up intake.
|
||||||
|
# See docs/config/storage-fine-tuning.md for layout examples.
|
||||||
|
|
||||||
|
# Directory for non-chunked PUT spool tempfiles. Default: OS temp dir
|
||||||
|
# ($TMPDIR / /tmp), often tmpfs (RAM) in containers — writing a large
|
||||||
|
# upload there fills page-cache that counts against the cgroup memory
|
||||||
|
# limit and can OOMKill the process. Point this at a real-disk path
|
||||||
|
# (same FS as the storage backend is ideal).
|
||||||
#OXICLOUD_UPLOAD_TMPDIR=/var/lib/oxicloud/tmp
|
#OXICLOUD_UPLOAD_TMPDIR=/var/lib/oxicloud/tmp
|
||||||
|
|
||||||
|
# Root directory for chunked-upload sessions (REST + NextCloud chunked
|
||||||
|
# share this root). Default: {STORAGE_PATH}/.uploads. Pointing this at
|
||||||
|
# NVMe accelerates the chunk-write + assembly loop; pointing it at the
|
||||||
|
# same FS as `.blobs/` makes blob promotion atomic.
|
||||||
|
#OXICLOUD_CHUNK_DIR=/var/lib/oxicloud/.uploads
|
||||||
|
|
||||||
# How often (seconds) the background sweep reconciles each user's cached
|
# How often (seconds) the background sweep reconciles each user's cached
|
||||||
# storage usage with the real sum of their files (default: 600 = 10 min).
|
# storage usage with the real sum of their files (default: 600 = 10 min).
|
||||||
# GET /api/auth/me serves the cached value instead of recomputing per request;
|
# GET /api/auth/me serves the cached value instead of recomputing per request;
|
||||||
|
|||||||
@@ -17,6 +17,55 @@ pub const DEFAULT_CHUNK_SIZE: usize = 5 * 1024 * 1024;
|
|||||||
/// Minimum file size to use chunked upload (10 MB).
|
/// Minimum file size to use chunked upload (10 MB).
|
||||||
pub const CHUNKED_UPLOAD_THRESHOLD: usize = 10 * 1024 * 1024;
|
pub const CHUNKED_UPLOAD_THRESHOLD: usize = 10 * 1024 * 1024;
|
||||||
|
|
||||||
|
/// Algorithm used by the client-side chunk checksum.
|
||||||
|
///
|
||||||
|
/// The wire format is `?checksum=<hex>&checksumalg=<name>` (or the
|
||||||
|
/// equivalent header pair for older clients that send only `Content-MD5`).
|
||||||
|
/// Clients that omit `checksumalg` are assumed to mean MD5 — that's the
|
||||||
|
/// algorithm baked into the legacy `Content-MD5` header (RFC 1864), TUS-
|
||||||
|
/// like upload protocols, and S3 multipart ETags.
|
||||||
|
///
|
||||||
|
/// Three supported variants, all from already-declared dependencies:
|
||||||
|
/// - `Md5` — legacy default; weak cryptographically but fine for
|
||||||
|
/// transport-integrity checks under TLS.
|
||||||
|
/// - `Sha256` — industry-standard, FIPS-compliant, widely supported by
|
||||||
|
/// sync clients (AWS S3 also accepts SHA-256 trailers).
|
||||||
|
/// - `Blake3` — fastest of the three; already used by the blob-storage
|
||||||
|
/// layer, so the chunk-level integrity check and the assembled-file
|
||||||
|
/// dedup hash use the same algorithm when clients opt in.
|
||||||
|
///
|
||||||
|
/// Skipped intentionally: SHA-1 (deprecated, broken), CRC32 (too weak for
|
||||||
|
/// integrity claims). Both can be added if a real client need appears.
|
||||||
|
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||||
|
pub enum ChecksumAlg {
|
||||||
|
Md5,
|
||||||
|
Sha256,
|
||||||
|
Blake3,
|
||||||
|
}
|
||||||
|
|
||||||
|
impl ChecksumAlg {
|
||||||
|
/// Parse a client-supplied algorithm name. Case-insensitive. Accepts
|
||||||
|
/// `sha-256` as a synonym for `sha256` since both forms are common
|
||||||
|
/// in HTTP headers. Unknown names return `None` so the handler can
|
||||||
|
/// 400 with the offending value.
|
||||||
|
pub fn parse(s: &str) -> Option<Self> {
|
||||||
|
match s.trim().to_ascii_lowercase().as_str() {
|
||||||
|
"md5" => Some(Self::Md5),
|
||||||
|
"sha256" | "sha-256" => Some(Self::Sha256),
|
||||||
|
"blake3" => Some(Self::Blake3),
|
||||||
|
_ => None,
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn as_str(self) -> &'static str {
|
||||||
|
match self {
|
||||||
|
Self::Md5 => "md5",
|
||||||
|
Self::Sha256 => "sha256",
|
||||||
|
Self::Blake3 => "blake3",
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
/// Response returned when a new upload session is created.
|
/// Response returned when a new upload session is created.
|
||||||
#[derive(Debug, Clone, Serialize, ToSchema)]
|
#[derive(Debug, Clone, Serialize, ToSchema)]
|
||||||
pub struct CreateUploadResponseDto {
|
pub struct CreateUploadResponseDto {
|
||||||
|
|||||||
@@ -211,12 +211,38 @@ pub struct StorageConfig {
|
|||||||
/// Maximum upload file size in bytes (default: 10 GB).
|
/// Maximum upload file size in bytes (default: 10 GB).
|
||||||
/// Applied as a hard limit to WebDAV PUT and streaming uploads.
|
/// Applied as a hard limit to WebDAV PUT and streaming uploads.
|
||||||
pub max_upload_size: usize,
|
pub max_upload_size: usize,
|
||||||
|
/// Maximum size of a single chunk in a chunked-upload session, in bytes
|
||||||
|
/// (default: 100 MB). Distinct from [`max_upload_size`] (which bounds the
|
||||||
|
/// total file size): NC desktop and other clients split large files into
|
||||||
|
/// many smaller PUTs against `/dav/uploads/…`, so the per-chunk cap can
|
||||||
|
/// be far tighter than the whole-file cap and prevents one HTTP request
|
||||||
|
/// from monopolising server memory or disk. Env: `OXICLOUD_CHUNK_MAX_BYTES`.
|
||||||
|
pub chunk_max_bytes: usize,
|
||||||
|
/// Maximum size of a single non-chunked PUT body, in bytes (default:
|
||||||
|
/// 1 GiB). Set below `max_upload_size` so files larger than this are
|
||||||
|
/// pushed onto the chunked-upload protocol (`/api/uploads/…` or
|
||||||
|
/// `/dav/uploads/…`) — which is resilient to mid-transfer failures,
|
||||||
|
/// resumable, and bounded per-request by `chunk_max_bytes`. Without
|
||||||
|
/// this cap a 10 GB direct PUT spools 10 GB to disk in a single
|
||||||
|
/// request; a connection drop at 95 % loses everything. The server
|
||||||
|
/// returns 413 with a "use chunked upload" hint when a direct PUT
|
||||||
|
/// exceeds this cap. Env: `OXICLOUD_DIRECT_PUT_MAX_BYTES`.
|
||||||
|
pub direct_put_max_bytes: usize,
|
||||||
/// Directory for upload spool temp files. When `Some`, large uploads are
|
/// Directory for upload spool temp files. When `Some`, large uploads are
|
||||||
/// spooled here instead of the OS default temp dir (often tmpfs/RAM in
|
/// spooled here instead of the OS default temp dir (often tmpfs/RAM in
|
||||||
/// containers, where the spool's page-cache counts against the cgroup
|
/// containers, where the spool's page-cache counts against the cgroup
|
||||||
/// memory limit and can trigger OOMKill on large files). Env:
|
/// memory limit and can trigger OOMKill on large files). Env:
|
||||||
/// `OXICLOUD_UPLOAD_TMPDIR`.
|
/// `OXICLOUD_UPLOAD_TMPDIR`.
|
||||||
pub upload_temp_dir: Option<PathBuf>,
|
pub upload_temp_dir: Option<PathBuf>,
|
||||||
|
/// Root directory for chunked-upload sessions. When `Some`, chunks land
|
||||||
|
/// under `{chunk_dir}/{upload_id}/` (REST) and
|
||||||
|
/// `{chunk_dir}/nextcloud/{user}/{upload_id}/` (NC). When `None`, falls
|
||||||
|
/// back to `{root_dir}/.uploads/`. Pointing this at the **same
|
||||||
|
/// filesystem** as `.blobs/` keeps the final assembled-to-blob promotion
|
||||||
|
/// an atomic `rename(2)` rather than a full cross-FS copy; pointing it
|
||||||
|
/// at fast storage (NVMe) accelerates the chunk-write + assembly loop
|
||||||
|
/// independently of where final blobs live. Env: `OXICLOUD_CHUNK_DIR`.
|
||||||
|
pub chunk_dir: Option<PathBuf>,
|
||||||
/// Interval (seconds) of the background sweep that reconciles every user's
|
/// Interval (seconds) of the background sweep that reconciles every user's
|
||||||
/// cached `storage_used_bytes` with the real sum of their files. Keeps the
|
/// cached `storage_used_bytes` with the real sum of their files. Keeps the
|
||||||
/// quota fresh for all mutations without recomputing on the request path.
|
/// quota fresh for all mutations without recomputing on the request path.
|
||||||
@@ -359,7 +385,10 @@ impl Default for StorageConfig {
|
|||||||
parallel_threshold: 100 * 1024 * 1024, // 100 MB
|
parallel_threshold: 100 * 1024 * 1024, // 100 MB
|
||||||
trash_retention_days: 30, // 30 days
|
trash_retention_days: 30, // 30 days
|
||||||
max_upload_size: MAX_UPLOAD_SIZE,
|
max_upload_size: MAX_UPLOAD_SIZE,
|
||||||
|
chunk_max_bytes: 100 * 1024 * 1024, // 100 MB — sane upper bound for a single chunked-upload PUT
|
||||||
|
direct_put_max_bytes: 1024 * 1024 * 1024, // 1 GiB — pushes larger uploads onto the chunked protocol
|
||||||
upload_temp_dir: None,
|
upload_temp_dir: None,
|
||||||
|
chunk_dir: None,
|
||||||
usage_reconcile_secs: 600, // 10 minutes
|
usage_reconcile_secs: 600, // 10 minutes
|
||||||
backend: StorageBackendType::Local,
|
backend: StorageBackendType::Local,
|
||||||
s3: None,
|
s3: None,
|
||||||
@@ -1224,6 +1253,17 @@ impl AppConfig {
|
|||||||
{
|
{
|
||||||
config.storage.max_upload_size = val;
|
config.storage.max_upload_size = val;
|
||||||
}
|
}
|
||||||
|
if let Ok(chunk_max) = env::var("OXICLOUD_CHUNK_MAX_BYTES").map(|v| v.parse::<usize>())
|
||||||
|
&& let Ok(val) = chunk_max
|
||||||
|
{
|
||||||
|
config.storage.chunk_max_bytes = val;
|
||||||
|
}
|
||||||
|
if let Ok(direct_max) =
|
||||||
|
env::var("OXICLOUD_DIRECT_PUT_MAX_BYTES").map(|v| v.parse::<usize>())
|
||||||
|
&& let Ok(val) = direct_max
|
||||||
|
{
|
||||||
|
config.storage.direct_put_max_bytes = val;
|
||||||
|
}
|
||||||
|
|
||||||
// Upload spool directory — keep large upload temp files off tmpfs/RAM
|
// Upload spool directory — keep large upload temp files off tmpfs/RAM
|
||||||
// (otherwise their page-cache counts against the cgroup memory limit).
|
// (otherwise their page-cache counts against the cgroup memory limit).
|
||||||
@@ -1232,6 +1272,16 @@ impl AppConfig {
|
|||||||
{
|
{
|
||||||
config.storage.upload_temp_dir = Some(PathBuf::from(dir.trim()));
|
config.storage.upload_temp_dir = Some(PathBuf::from(dir.trim()));
|
||||||
}
|
}
|
||||||
|
// Chunked-upload session root — separate from the PUT spool because
|
||||||
|
// chunked sessions accumulate disk on long uploads (multi-chunk
|
||||||
|
// resumable transfers) while PUT spool is short-lived. Sysadmins
|
||||||
|
// commonly want one of them on fast/local storage (NVMe) and the
|
||||||
|
// other on bulk storage; this knob lets that be expressed.
|
||||||
|
if let Ok(dir) = env::var("OXICLOUD_CHUNK_DIR")
|
||||||
|
&& !dir.trim().is_empty()
|
||||||
|
{
|
||||||
|
config.storage.chunk_dir = Some(PathBuf::from(dir.trim()));
|
||||||
|
}
|
||||||
|
|
||||||
// Background storage-usage reconciliation interval
|
// Background storage-usage reconciliation interval
|
||||||
if let Ok(secs) =
|
if let Ok(secs) =
|
||||||
|
|||||||
+27
-4
@@ -171,11 +171,23 @@ impl AppServiceFactory {
|
|||||||
// Initialize thumbnail directories
|
// Initialize thumbnail directories
|
||||||
thumbnail_service.initialize().await?;
|
thumbnail_service.initialize().await?;
|
||||||
|
|
||||||
// Chunked upload service for large files (>10MB)
|
// Chunked upload service for large files (>10MB).
|
||||||
let chunked_temp_dir = std::path::PathBuf::from(&self.storage_path).join(".uploads");
|
// Root for both REST (`/api/uploads/...`) and NC (`/dav/uploads/...`)
|
||||||
|
// chunked sessions: honour `OXICLOUD_CHUNK_DIR` when set so sysadmins
|
||||||
|
// can put session directories on fast storage (NVMe) or on the same
|
||||||
|
// filesystem as `.blobs/` (turns the final blob promotion into an
|
||||||
|
// atomic rename instead of a cross-FS copy). Falls back to
|
||||||
|
// `{storage_path}/.uploads/` when unset — backwards-compatible with
|
||||||
|
// every existing deployment.
|
||||||
|
let chunk_root = self
|
||||||
|
.config
|
||||||
|
.storage
|
||||||
|
.chunk_dir
|
||||||
|
.clone()
|
||||||
|
.unwrap_or_else(|| std::path::PathBuf::from(&self.storage_path).join(".uploads"));
|
||||||
let chunked_upload_service = Arc::new(
|
let chunked_upload_service = Arc::new(
|
||||||
crate::infrastructure::services::chunked_upload_service::ChunkedUploadService::new(
|
crate::infrastructure::services::chunked_upload_service::ChunkedUploadService::new(
|
||||||
chunked_temp_dir,
|
chunk_root.clone(),
|
||||||
)
|
)
|
||||||
.await,
|
.await,
|
||||||
);
|
);
|
||||||
@@ -870,7 +882,18 @@ impl AppServiceFactory {
|
|||||||
);
|
);
|
||||||
}
|
}
|
||||||
|
|
||||||
let chunk_base = self.storage_path.join(".uploads/nextcloud");
|
// NC chunked-upload sessions root. Honour `OXICLOUD_CHUNK_DIR`
|
||||||
|
// (same env var that the REST chunked service uses) so a single
|
||||||
|
// value covers both surfaces and they stay co-located on one
|
||||||
|
// filesystem; fall back to `{storage_path}/.uploads/` to match
|
||||||
|
// the legacy layout.
|
||||||
|
let chunk_root = self
|
||||||
|
.config
|
||||||
|
.storage
|
||||||
|
.chunk_dir
|
||||||
|
.clone()
|
||||||
|
.unwrap_or_else(|| self.storage_path.join(".uploads"));
|
||||||
|
let chunk_base = chunk_root.join("nextcloud");
|
||||||
let chunked_uploads = Arc::new(NextcloudChunkedUploadService::new(chunk_base));
|
let chunked_uploads = Arc::new(NextcloudChunkedUploadService::new(chunk_base));
|
||||||
|
|
||||||
let file_id_repo = Arc::new(
|
let file_id_repo = Arc::new(
|
||||||
|
|||||||
@@ -44,10 +44,32 @@ pub const MAX_PARALLEL_CHUNKS: usize = 6;
|
|||||||
/// Upload session expiration time (24 h)
|
/// Upload session expiration time (24 h)
|
||||||
const SESSION_EXPIRATION: Duration = Duration::from_secs(24 * 60 * 60);
|
const SESSION_EXPIRATION: Duration = Duration::from_secs(24 * 60 * 60);
|
||||||
|
|
||||||
|
/// Prefix every session directory name with this string so the cleanup
|
||||||
|
/// loop can be safely co-located with unrelated writers (PUT spool
|
||||||
|
/// tempfiles, the NC chunked subtree, anything else a sysadmin places
|
||||||
|
/// under the same `OXICLOUD_CHUNK_DIR`). The orphan-cleanup scan
|
||||||
|
/// filters by this prefix, so non-OxiCloud directories sharing the
|
||||||
|
/// root are never touched.
|
||||||
|
const SESSION_DIR_PREFIX: &str = "oxi-chunk-";
|
||||||
|
|
||||||
/// Sentinel file names inside each session directory
|
/// Sentinel file names inside each session directory
|
||||||
const SESSION_META_FILE: &str = "session.json";
|
const SESSION_META_FILE: &str = "session.json";
|
||||||
const PROGRESS_FILE: &str = "progress.bin";
|
const PROGRESS_FILE: &str = "progress.bin";
|
||||||
|
|
||||||
|
/// Build a session directory name from an upload_id by attaching the
|
||||||
|
/// well-known prefix. Symmetric with [`strip_session_prefix`].
|
||||||
|
fn session_dir_name(upload_id: &str) -> String {
|
||||||
|
format!("{}{}", SESSION_DIR_PREFIX, upload_id)
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Extract the upload_id from a session directory name. Returns
|
||||||
|
/// `None` when the directory wasn't created by this service (no
|
||||||
|
/// `oxi-chunk-` prefix) — the recovery and cleanup paths use this to
|
||||||
|
/// skip foreign directories cohabiting under `OXICLOUD_CHUNK_DIR`.
|
||||||
|
fn strip_session_prefix(dir_name: &str) -> Option<&str> {
|
||||||
|
dir_name.strip_prefix(SESSION_DIR_PREFIX)
|
||||||
|
}
|
||||||
|
|
||||||
// ─── Serialisable types ──────────────────────────────────────────────────────
|
// ─── Serialisable types ──────────────────────────────────────────────────────
|
||||||
|
|
||||||
/// Chunk status
|
/// Chunk status
|
||||||
@@ -203,6 +225,15 @@ impl ChunkedUploadService {
|
|||||||
// Ensure the base directory exists
|
// Ensure the base directory exists
|
||||||
let _ = fs::create_dir_all(&temp_base_dir).await;
|
let _ = fs::create_dir_all(&temp_base_dir).await;
|
||||||
|
|
||||||
|
// One-shot migration of pre-prefix session directories to the
|
||||||
|
// `oxi-chunk-{uuid}/` layout. Without this, any chunked upload
|
||||||
|
// in flight at the moment an admin upgrades from a pre-prefix
|
||||||
|
// build to this one would be orphaned — the recovery scan
|
||||||
|
// filters strictly on the `oxi-chunk-` prefix and would skip
|
||||||
|
// legacy `{uuid}/` directories. Idempotent: subsequent boots
|
||||||
|
// find no legacy dirs left to rename and do nothing.
|
||||||
|
Self::migrate_pre_prefix_sessions(&temp_base_dir).await;
|
||||||
|
|
||||||
// Recover sessions that survived a restart
|
// Recover sessions that survived a restart
|
||||||
let recovered = Self::recover_sessions(&temp_base_dir).await;
|
let recovered = Self::recover_sessions(&temp_base_dir).await;
|
||||||
let recovered_count = recovered.len();
|
let recovered_count = recovered.len();
|
||||||
@@ -235,6 +266,84 @@ impl ChunkedUploadService {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// ── Upgrade migration ────────────────────────────────────────────────
|
||||||
|
|
||||||
|
/// One-shot upgrade migration: rename any pre-prefix session
|
||||||
|
/// directory to the new `oxi-chunk-{uuid}/` layout so the recovery
|
||||||
|
/// scan picks it up.
|
||||||
|
///
|
||||||
|
/// A pre-prefix session is identified by: a directory under
|
||||||
|
/// `temp_base_dir` whose name does NOT start with
|
||||||
|
/// `SESSION_DIR_PREFIX` but whose contents include `session.json`.
|
||||||
|
/// That signature can only come from a chunked upload created by
|
||||||
|
/// a pre-prefix OxiCloud build — admins don't normally drop
|
||||||
|
/// session.json files into the chunk dir.
|
||||||
|
///
|
||||||
|
/// Idempotent: on a fresh boot all dirs are already prefixed, the
|
||||||
|
/// scan finds nothing to rename, no-op. Safe against concurrent
|
||||||
|
/// boots: `fs::rename` is atomic, so a racing migration sees the
|
||||||
|
/// source disappear and proceeds.
|
||||||
|
async fn migrate_pre_prefix_sessions(base: &Path) {
|
||||||
|
let mut entries = match fs::read_dir(base).await {
|
||||||
|
Ok(e) => e,
|
||||||
|
Err(_) => return,
|
||||||
|
};
|
||||||
|
|
||||||
|
let mut migrated_count = 0usize;
|
||||||
|
|
||||||
|
while let Ok(Some(entry)) = entries.next_entry().await {
|
||||||
|
let path = entry.path();
|
||||||
|
if !path.is_dir() {
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
let dir_name = match path.file_name().and_then(|n| n.to_str()) {
|
||||||
|
Some(n) => n.to_string(),
|
||||||
|
None => continue,
|
||||||
|
};
|
||||||
|
if dir_name.starts_with(SESSION_DIR_PREFIX) {
|
||||||
|
continue; // already migrated
|
||||||
|
}
|
||||||
|
// Identify pre-prefix sessions by `session.json` presence.
|
||||||
|
// Avoids touching the NC subtree (`nextcloud/` — no
|
||||||
|
// session.json at that level) and any operator-placed
|
||||||
|
// sibling directories without the marker.
|
||||||
|
if !fs::try_exists(path.join(SESSION_META_FILE))
|
||||||
|
.await
|
||||||
|
.unwrap_or(false)
|
||||||
|
{
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
|
||||||
|
let new_path = base.join(session_dir_name(&dir_name));
|
||||||
|
match fs::rename(&path, &new_path).await {
|
||||||
|
Ok(()) => {
|
||||||
|
migrated_count += 1;
|
||||||
|
tracing::info!(
|
||||||
|
old = %path.display(),
|
||||||
|
new = %new_path.display(),
|
||||||
|
"Migrated pre-prefix chunked-upload session to new layout"
|
||||||
|
);
|
||||||
|
}
|
||||||
|
Err(e) => {
|
||||||
|
tracing::warn!(
|
||||||
|
error = %e,
|
||||||
|
old = %path.display(),
|
||||||
|
"Failed to migrate pre-prefix session — left orphaned on disk; \
|
||||||
|
next chunk PATCH from the client will 404 and the client should \
|
||||||
|
restart its upload session. Manual rm safe."
|
||||||
|
);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
if migrated_count > 0 {
|
||||||
|
tracing::info!(
|
||||||
|
count = migrated_count,
|
||||||
|
"🔧 Upgraded chunked-upload session layout (one-shot migration)"
|
||||||
|
);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
// ── Recovery ─────────────────────────────────────────────────────────
|
// ── Recovery ─────────────────────────────────────────────────────────
|
||||||
|
|
||||||
/// Scan `temp_base_dir` for directories containing `session.json`,
|
/// Scan `temp_base_dir` for directories containing `session.json`,
|
||||||
@@ -252,6 +361,17 @@ impl ChunkedUploadService {
|
|||||||
if !dir.is_dir() {
|
if !dir.is_dir() {
|
||||||
continue;
|
continue;
|
||||||
}
|
}
|
||||||
|
// Only consider directories WE created — anything without the
|
||||||
|
// `oxi-chunk-` prefix belongs to a sibling writer (NC subtree,
|
||||||
|
// PUT spool tempfiles, sysadmin-placed dirs) and must be left
|
||||||
|
// strictly alone. See `SESSION_DIR_PREFIX`.
|
||||||
|
let dir_name = match dir.file_name().and_then(|n| n.to_str()) {
|
||||||
|
Some(n) => n,
|
||||||
|
None => continue,
|
||||||
|
};
|
||||||
|
if strip_session_prefix(dir_name).is_none() {
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
|
||||||
let meta_path = dir.join(SESSION_META_FILE);
|
let meta_path = dir.join(SESSION_META_FILE);
|
||||||
let meta_bytes = match fs::read(&meta_path).await {
|
let meta_bytes = match fs::read(&meta_path).await {
|
||||||
@@ -346,14 +466,26 @@ impl ChunkedUploadService {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// Also clean orphaned temp directories (no session.json or very old)
|
// Also clean orphaned temp directories (no session.json or very old).
|
||||||
|
// Filter strictly on the `oxi-chunk-` prefix so we never touch
|
||||||
|
// sibling directories sharing `OXICLOUD_CHUNK_DIR` (NC subtree
|
||||||
|
// `nextcloud/`, PUT spool tempfiles which are files anyway,
|
||||||
|
// operator-placed dirs). Without the prefix filter this loop
|
||||||
|
// would silently delete anything older than 24 h sitting at the
|
||||||
|
// root of the chunked-upload dir.
|
||||||
if let Ok(mut entries) = fs::read_dir(&temp_base_dir).await {
|
if let Ok(mut entries) = fs::read_dir(&temp_base_dir).await {
|
||||||
while let Ok(Some(entry)) = entries.next_entry().await {
|
while let Ok(Some(entry)) = entries.next_entry().await {
|
||||||
let path = entry.path();
|
let path = entry.path();
|
||||||
if path.is_dir() {
|
if !path.is_dir() {
|
||||||
|
continue;
|
||||||
|
}
|
||||||
let dir_name = path.file_name().and_then(|n| n.to_str()).unwrap_or("");
|
let dir_name = path.file_name().and_then(|n| n.to_str()).unwrap_or("");
|
||||||
|
let upload_id = match strip_session_prefix(dir_name) {
|
||||||
|
Some(id) => id,
|
||||||
|
None => continue, // not ours — never touch
|
||||||
|
};
|
||||||
|
|
||||||
if !sessions.contains_key(dir_name)
|
if !sessions.contains_key(upload_id)
|
||||||
&& let Ok(metadata) = fs::metadata(&path).await
|
&& let Ok(metadata) = fs::metadata(&path).await
|
||||||
&& let Ok(modified) = metadata.modified()
|
&& let Ok(modified) = metadata.modified()
|
||||||
&& modified.elapsed().unwrap_or_default() > SESSION_EXPIRATION
|
&& modified.elapsed().unwrap_or_default() > SESSION_EXPIRATION
|
||||||
@@ -365,7 +497,6 @@ impl ChunkedUploadService {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
|
||||||
|
|
||||||
// ── Core operations ──────────────────────────────────────────────────
|
// ── Core operations ──────────────────────────────────────────────────
|
||||||
|
|
||||||
@@ -396,8 +527,11 @@ impl ChunkedUploadService {
|
|||||||
let chunk_size = chunk_size.unwrap_or(DEFAULT_CHUNK_SIZE);
|
let chunk_size = chunk_size.unwrap_or(DEFAULT_CHUNK_SIZE);
|
||||||
let chunk_count = UploadSession::calculate_chunk_count(total_size, chunk_size);
|
let chunk_count = UploadSession::calculate_chunk_count(total_size, chunk_size);
|
||||||
|
|
||||||
// Create temp directory for chunks
|
// Create temp directory for chunks. The `oxi-chunk-` prefix
|
||||||
let temp_dir = self.temp_base_dir.join(&upload_id);
|
// tags the directory as belonging to this service so the
|
||||||
|
// shared-`OXICLOUD_CHUNK_DIR` story holds — see
|
||||||
|
// `SESSION_DIR_PREFIX` for the full rationale.
|
||||||
|
let temp_dir = self.temp_base_dir.join(session_dir_name(&upload_id));
|
||||||
fs::create_dir_all(&temp_dir)
|
fs::create_dir_all(&temp_dir)
|
||||||
.await
|
.await
|
||||||
.map_err(|e| format!("Failed to create temp directory: {e}"))?;
|
.map_err(|e| format!("Failed to create temp directory: {e}"))?;
|
||||||
@@ -463,6 +597,188 @@ impl ChunkedUploadService {
|
|||||||
})
|
})
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/// Prepare a chunk write — validates session ownership and chunk
|
||||||
|
/// index, returns the on-disk path the caller should stream the
|
||||||
|
/// HTTP body to plus the expected byte count for that chunk.
|
||||||
|
///
|
||||||
|
/// Used by the streaming REST PUT path: the handler calls
|
||||||
|
/// `prepare_chunk` → streams body to disk via
|
||||||
|
/// `interfaces::upload_spool::stream_body_to_path` → calls
|
||||||
|
/// `commit_chunk` to finalise. This lets the body bypass the
|
||||||
|
/// in-memory `Bytes` allocation entirely (peak heap ~one HTTP
|
||||||
|
/// frame instead of "chunk size").
|
||||||
|
///
|
||||||
|
/// Returns `Err` if the session is unknown, owned by another user,
|
||||||
|
/// the chunk index is out of range, or the chunk is already complete.
|
||||||
|
pub async fn prepare_chunk(
|
||||||
|
&self,
|
||||||
|
upload_id: &str,
|
||||||
|
user_id: Uuid,
|
||||||
|
chunk_index: usize,
|
||||||
|
) -> Result<(PathBuf, usize), DomainError> {
|
||||||
|
self.verify_session_owner(upload_id, &user_id.to_string())
|
||||||
|
.map_err(|e| DomainError::new(ErrorKind::NotFound, "ChunkedUpload", e))?;
|
||||||
|
|
||||||
|
let session = self.sessions.get(upload_id).ok_or_else(|| {
|
||||||
|
DomainError::new(
|
||||||
|
ErrorKind::NotFound,
|
||||||
|
"ChunkedUpload",
|
||||||
|
format!("Upload session not found: {}", upload_id),
|
||||||
|
)
|
||||||
|
})?;
|
||||||
|
|
||||||
|
if chunk_index >= session.chunks.len() {
|
||||||
|
return Err(DomainError::new(
|
||||||
|
ErrorKind::InvalidInput,
|
||||||
|
"ChunkedUpload",
|
||||||
|
format!(
|
||||||
|
"Invalid chunk index: {} (max: {})",
|
||||||
|
chunk_index,
|
||||||
|
session.chunks.len() - 1
|
||||||
|
),
|
||||||
|
));
|
||||||
|
}
|
||||||
|
|
||||||
|
let chunk = &session.chunks[chunk_index];
|
||||||
|
if chunk.status == ChunkStatus::Complete {
|
||||||
|
return Err(DomainError::new(
|
||||||
|
ErrorKind::InvalidInput,
|
||||||
|
"ChunkedUpload",
|
||||||
|
format!("Chunk {} already uploaded", chunk_index),
|
||||||
|
));
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok((
|
||||||
|
session.temp_dir.join(format!("chunk_{:06}", chunk_index)),
|
||||||
|
chunk.size,
|
||||||
|
))
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Finalise a chunk write — verifies the actually-written byte count
|
||||||
|
/// matches the chunk's declared size, validates an optional
|
||||||
|
/// algorithm-tagged checksum, and updates session state. The chunk
|
||||||
|
/// file at `{session.temp_dir}/chunk_{index:06}` must already have
|
||||||
|
/// been written by the caller (typically via
|
||||||
|
/// `stream_body_to_path`).
|
||||||
|
///
|
||||||
|
/// `actual_size` is the byte count the streaming write reported;
|
||||||
|
/// `computed_checksum` is the hex digest computed during streaming
|
||||||
|
/// (or `None` if the client didn't request a checksum). When
|
||||||
|
/// `expected_checksum` is supplied the two are compared; a
|
||||||
|
/// mismatch removes the partial file and returns `ValidationError`
|
||||||
|
/// so a client retry against the same chunk index gets a clean
|
||||||
|
/// slot. A size mismatch does the same.
|
||||||
|
pub async fn commit_chunk(
|
||||||
|
&self,
|
||||||
|
upload_id: &str,
|
||||||
|
user_id: Uuid,
|
||||||
|
chunk_index: usize,
|
||||||
|
actual_size: u64,
|
||||||
|
computed_checksum: Option<String>,
|
||||||
|
expected_checksum: Option<String>,
|
||||||
|
) -> Result<ChunkUploadResponseDto, DomainError> {
|
||||||
|
self.verify_session_owner(upload_id, &user_id.to_string())
|
||||||
|
.map_err(|e| DomainError::new(ErrorKind::NotFound, "ChunkedUpload", e))?;
|
||||||
|
|
||||||
|
// Re-fetch chunk metadata under fresh lock — guards against the
|
||||||
|
// (vanishingly unlikely) case of a session expiry / cancellation
|
||||||
|
// racing with the write.
|
||||||
|
let (chunk_path, expected_size, persist_path) = {
|
||||||
|
let session = self.sessions.get(upload_id).ok_or_else(|| {
|
||||||
|
DomainError::new(
|
||||||
|
ErrorKind::NotFound,
|
||||||
|
"ChunkedUpload",
|
||||||
|
"Session disappeared".to_string(),
|
||||||
|
)
|
||||||
|
})?;
|
||||||
|
if chunk_index >= session.chunks.len() {
|
||||||
|
return Err(DomainError::new(
|
||||||
|
ErrorKind::InvalidInput,
|
||||||
|
"ChunkedUpload",
|
||||||
|
format!("Invalid chunk index: {}", chunk_index),
|
||||||
|
));
|
||||||
|
}
|
||||||
|
(
|
||||||
|
session.temp_dir.join(format!("chunk_{:06}", chunk_index)),
|
||||||
|
session.chunks[chunk_index].size,
|
||||||
|
session.temp_dir.join(PROGRESS_FILE),
|
||||||
|
)
|
||||||
|
};
|
||||||
|
|
||||||
|
// Size check — the streaming body may have been truncated by
|
||||||
|
// the client mid-flight or exceeded the chunk's declared
|
||||||
|
// length. Either way we don't want a partial chunk to count
|
||||||
|
// as complete; nuke it and ask the client to retry.
|
||||||
|
if actual_size != expected_size as u64 {
|
||||||
|
let _ = fs::remove_file(&chunk_path).await;
|
||||||
|
return Err(DomainError::new(
|
||||||
|
ErrorKind::InvalidInput,
|
||||||
|
"ChunkedUpload",
|
||||||
|
format!(
|
||||||
|
"Invalid chunk size: expected {} bytes, got {} bytes",
|
||||||
|
expected_size, actual_size
|
||||||
|
),
|
||||||
|
));
|
||||||
|
}
|
||||||
|
|
||||||
|
// Checksum check — case-insensitive compare so clients that
|
||||||
|
// send uppercase hex still match.
|
||||||
|
if let Some(expected) = expected_checksum.as_ref()
|
||||||
|
&& let Some(actual) = computed_checksum.as_ref()
|
||||||
|
&& !expected.eq_ignore_ascii_case(actual)
|
||||||
|
{
|
||||||
|
let _ = fs::remove_file(&chunk_path).await;
|
||||||
|
return Err(DomainError::new(
|
||||||
|
ErrorKind::InvalidInput,
|
||||||
|
"ChunkedUpload",
|
||||||
|
format!("Checksum mismatch: expected {}, got {}", expected, actual),
|
||||||
|
));
|
||||||
|
}
|
||||||
|
|
||||||
|
// Update session state — DashMap shard lock held only for the
|
||||||
|
// RAM updates (~µs). The bitmask write happens AFTER the ref
|
||||||
|
// is dropped so concurrent uploads to other sessions are never
|
||||||
|
// blocked. Mirrors the legacy `upload_chunk_inner` semantics.
|
||||||
|
let (bytes_received, progress, is_complete, persist_bitmask) = {
|
||||||
|
let mut session = self.sessions.get_mut(upload_id).ok_or_else(|| {
|
||||||
|
DomainError::new(
|
||||||
|
ErrorKind::NotFound,
|
||||||
|
"ChunkedUpload",
|
||||||
|
"Session disappeared".to_string(),
|
||||||
|
)
|
||||||
|
})?;
|
||||||
|
session.chunks[chunk_index].status = ChunkStatus::Complete;
|
||||||
|
session.chunks[chunk_index].checksum = expected_checksum;
|
||||||
|
session.bytes_received += actual_size;
|
||||||
|
session.last_activity = Utc::now();
|
||||||
|
let bitmask = session.build_progress_bitmask();
|
||||||
|
(
|
||||||
|
session.bytes_received,
|
||||||
|
session.progress(),
|
||||||
|
session.is_complete(),
|
||||||
|
bitmask,
|
||||||
|
)
|
||||||
|
};
|
||||||
|
|
||||||
|
if let Err(e) = fs::write(&persist_path, &persist_bitmask).await {
|
||||||
|
tracing::warn!("Failed to persist progress for {upload_id}: {e}");
|
||||||
|
}
|
||||||
|
|
||||||
|
tracing::debug!(
|
||||||
|
"📦 Chunk {} committed for {} ({:.1}% complete)",
|
||||||
|
chunk_index,
|
||||||
|
upload_id,
|
||||||
|
progress * 100.0
|
||||||
|
);
|
||||||
|
|
||||||
|
Ok(ChunkUploadResponseDto {
|
||||||
|
chunk_index,
|
||||||
|
bytes_received,
|
||||||
|
progress,
|
||||||
|
is_complete,
|
||||||
|
})
|
||||||
|
}
|
||||||
|
|
||||||
/// Upload a single chunk (persists `progress.bin` after success)
|
/// Upload a single chunk (persists `progress.bin` after success)
|
||||||
async fn upload_chunk_inner(
|
async fn upload_chunk_inner(
|
||||||
&self,
|
&self,
|
||||||
@@ -723,6 +1039,22 @@ impl ChunkedUploadService {
|
|||||||
output
|
output
|
||||||
.flush()
|
.flush()
|
||||||
.map_err(|e| format!("Failed to flush assembled file: {e}"))?;
|
.map_err(|e| format!("Failed to flush assembled file: {e}"))?;
|
||||||
|
// ── Durability boundary ────────────────────────────────────
|
||||||
|
// `flush` drains BufWriter's userspace buffer but leaves the
|
||||||
|
// bytes in the kernel page cache. Without `sync_all`, a
|
||||||
|
// power loss between this `complete_upload` returning 2xx
|
||||||
|
// and the OS writeback timer firing (~5 s default) loses
|
||||||
|
// the merged blob — and PG's metadata row references a hash
|
||||||
|
// that no longer exists on disk. Reclaim the BufWriter's
|
||||||
|
// inner File via `into_inner` so we can `sync_all` it; the
|
||||||
|
// BufWriter would otherwise drop without flushing on the
|
||||||
|
// inner handle.
|
||||||
|
let raw_output = output
|
||||||
|
.into_inner()
|
||||||
|
.map_err(|e| format!("into_inner on BufWriter failed: {e}"))?;
|
||||||
|
raw_output
|
||||||
|
.sync_all()
|
||||||
|
.map_err(|e| format!("Failed to fsync assembled file: {e}"))?;
|
||||||
|
|
||||||
// Clean up chunk files (keep assembled) — already on a blocking thread
|
// Clean up chunk files (keep assembled) — already on a blocking thread
|
||||||
for (_index, chunk_path) in &chunks_meta {
|
for (_index, chunk_path) in &chunks_meta {
|
||||||
@@ -1056,7 +1388,7 @@ mod tests {
|
|||||||
.expect("upload_chunk 0");
|
.expect("upload_chunk 0");
|
||||||
|
|
||||||
// Verify files exist on disk
|
// Verify files exist on disk
|
||||||
let session_dir = base.join(&upload_id);
|
let session_dir = base.join(session_dir_name(&upload_id));
|
||||||
assert!(session_dir.join(SESSION_META_FILE).exists());
|
assert!(session_dir.join(SESSION_META_FILE).exists());
|
||||||
assert!(session_dir.join(PROGRESS_FILE).exists());
|
assert!(session_dir.join(PROGRESS_FILE).exists());
|
||||||
assert!(session_dir.join("chunk_000000").exists());
|
assert!(session_dir.join("chunk_000000").exists());
|
||||||
@@ -1168,7 +1500,7 @@ mod tests {
|
|||||||
.await
|
.await
|
||||||
.expect("create");
|
.expect("create");
|
||||||
|
|
||||||
let session_dir = base.join(&resp.upload_id);
|
let session_dir = base.join(session_dir_name(&resp.upload_id));
|
||||||
assert!(session_dir.exists());
|
assert!(session_dir.exists());
|
||||||
|
|
||||||
service
|
service
|
||||||
@@ -1187,8 +1519,10 @@ mod tests {
|
|||||||
let base = std::env::temp_dir().join(format!("oxicloud_test_{}", Uuid::new_v4()));
|
let base = std::env::temp_dir().join(format!("oxicloud_test_{}", Uuid::new_v4()));
|
||||||
let _ = fs::create_dir_all(&base).await;
|
let _ = fs::create_dir_all(&base).await;
|
||||||
|
|
||||||
// Manually create an expired session on disk
|
// Manually create an expired session on disk. The dir name MUST
|
||||||
let session_dir = base.join("expired-session");
|
// carry the `oxi-chunk-` prefix or recovery will (correctly) skip
|
||||||
|
// it as belonging to another writer co-located in chunk_dir.
|
||||||
|
let session_dir = base.join(session_dir_name("expired-session"));
|
||||||
let _ = fs::create_dir_all(&session_dir).await;
|
let _ = fs::create_dir_all(&session_dir).await;
|
||||||
|
|
||||||
let expired_session = UploadSession {
|
let expired_session = UploadSession {
|
||||||
@@ -1231,7 +1565,7 @@ mod tests {
|
|||||||
let base = std::env::temp_dir().join(format!("oxicloud_test_{}", Uuid::new_v4()));
|
let base = std::env::temp_dir().join(format!("oxicloud_test_{}", Uuid::new_v4()));
|
||||||
let _ = fs::create_dir_all(&base).await;
|
let _ = fs::create_dir_all(&base).await;
|
||||||
|
|
||||||
let session_dir = base.join("partial-session");
|
let session_dir = base.join(session_dir_name("partial-session"));
|
||||||
let _ = fs::create_dir_all(&session_dir).await;
|
let _ = fs::create_dir_all(&session_dir).await;
|
||||||
|
|
||||||
let session = UploadSession {
|
let session = UploadSession {
|
||||||
@@ -1294,4 +1628,139 @@ mod tests {
|
|||||||
|
|
||||||
let _ = fs::remove_dir_all(&base).await;
|
let _ = fs::remove_dir_all(&base).await;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/// Upgrade-path scenario: a pre-prefix session directory (the layout
|
||||||
|
/// used by builds before the `oxi-chunk-` prefix change) gets renamed
|
||||||
|
/// in place when the service starts, then recovered normally. Without
|
||||||
|
/// the migration, the upgrade would orphan every in-flight REST
|
||||||
|
/// chunked upload because recovery filters strictly on the prefix.
|
||||||
|
#[tokio::test]
|
||||||
|
async fn test_migrate_pre_prefix_session_on_boot() {
|
||||||
|
let base = std::env::temp_dir().join(format!("oxicloud_test_{}", Uuid::new_v4()));
|
||||||
|
let _ = fs::create_dir_all(&base).await;
|
||||||
|
|
||||||
|
// Pre-upgrade layout: `{base}/legacy-upload-id/session.json`
|
||||||
|
// (no `oxi-chunk-` prefix on the directory name).
|
||||||
|
let legacy_id = "legacy-upload-id";
|
||||||
|
let legacy_dir = base.join(legacy_id);
|
||||||
|
let _ = fs::create_dir_all(&legacy_dir).await;
|
||||||
|
|
||||||
|
let session = UploadSession {
|
||||||
|
id: legacy_id.into(),
|
||||||
|
user_id: "user-1".into(),
|
||||||
|
filename: "in-flight.bin".into(),
|
||||||
|
folder_id: None,
|
||||||
|
content_type: "application/octet-stream".into(),
|
||||||
|
total_size: 1024,
|
||||||
|
chunk_size: 1024,
|
||||||
|
chunks: vec![ChunkInfo {
|
||||||
|
index: 0,
|
||||||
|
offset: 0,
|
||||||
|
size: 1024,
|
||||||
|
status: ChunkStatus::Pending,
|
||||||
|
checksum: None,
|
||||||
|
}],
|
||||||
|
created_at: Utc::now(),
|
||||||
|
last_activity: Utc::now(),
|
||||||
|
// `temp_dir` here is the legacy path — after migration the
|
||||||
|
// session.json's path won't match the new location on disk,
|
||||||
|
// but recovery doesn't use temp_dir for lookups; chunk
|
||||||
|
// I/O within commit_chunk computes paths from the current
|
||||||
|
// session dir, which is the renamed location.
|
||||||
|
temp_dir: legacy_dir.clone(),
|
||||||
|
bytes_received: 0,
|
||||||
|
};
|
||||||
|
fs::write(
|
||||||
|
legacy_dir.join(SESSION_META_FILE),
|
||||||
|
serde_json::to_vec(&session).unwrap(),
|
||||||
|
)
|
||||||
|
.await
|
||||||
|
.unwrap();
|
||||||
|
|
||||||
|
// Boot the service — migration runs as part of `new`.
|
||||||
|
let svc = ChunkedUploadService::new(base.clone()).await;
|
||||||
|
|
||||||
|
// Legacy path must be gone, prefixed path must exist + carry the
|
||||||
|
// session.json.
|
||||||
|
assert!(
|
||||||
|
!legacy_dir.exists(),
|
||||||
|
"Legacy un-prefixed dir should have been renamed away"
|
||||||
|
);
|
||||||
|
let new_dir = base.join(session_dir_name(legacy_id));
|
||||||
|
assert!(
|
||||||
|
new_dir.exists(),
|
||||||
|
"Prefixed dir should exist post-migration at {}",
|
||||||
|
new_dir.display()
|
||||||
|
);
|
||||||
|
assert!(
|
||||||
|
new_dir.join(SESSION_META_FILE).exists(),
|
||||||
|
"session.json must travel with the rename"
|
||||||
|
);
|
||||||
|
|
||||||
|
// Recovery picks it up — the session is now in the live map
|
||||||
|
// keyed by its original upload_id.
|
||||||
|
assert!(
|
||||||
|
svc.sessions.contains_key(legacy_id),
|
||||||
|
"Recovered session must be keyed by its original upload_id"
|
||||||
|
);
|
||||||
|
|
||||||
|
let _ = fs::remove_dir_all(&base).await;
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Idempotency: running migration twice (a second boot after a
|
||||||
|
/// successful migration) must be a no-op. The already-prefixed
|
||||||
|
/// directory is left untouched, no spurious double-prefixing.
|
||||||
|
#[tokio::test]
|
||||||
|
async fn test_migration_is_idempotent() {
|
||||||
|
let base = std::env::temp_dir().join(format!("oxicloud_test_{}", Uuid::new_v4()));
|
||||||
|
let _ = fs::create_dir_all(&base).await;
|
||||||
|
|
||||||
|
let upload_id = "already-prefixed";
|
||||||
|
let prefixed_dir = base.join(session_dir_name(upload_id));
|
||||||
|
let _ = fs::create_dir_all(&prefixed_dir).await;
|
||||||
|
|
||||||
|
// Minimal session.json — just enough to count as a session for
|
||||||
|
// the migration's identification heuristic.
|
||||||
|
let session = UploadSession {
|
||||||
|
id: upload_id.into(),
|
||||||
|
user_id: "user-1".into(),
|
||||||
|
filename: "x.bin".into(),
|
||||||
|
folder_id: None,
|
||||||
|
content_type: "application/octet-stream".into(),
|
||||||
|
total_size: 1,
|
||||||
|
chunk_size: 1,
|
||||||
|
chunks: vec![ChunkInfo {
|
||||||
|
index: 0,
|
||||||
|
offset: 0,
|
||||||
|
size: 1,
|
||||||
|
status: ChunkStatus::Pending,
|
||||||
|
checksum: None,
|
||||||
|
}],
|
||||||
|
created_at: Utc::now(),
|
||||||
|
last_activity: Utc::now(),
|
||||||
|
temp_dir: prefixed_dir.clone(),
|
||||||
|
bytes_received: 0,
|
||||||
|
};
|
||||||
|
fs::write(
|
||||||
|
prefixed_dir.join(SESSION_META_FILE),
|
||||||
|
serde_json::to_vec(&session).unwrap(),
|
||||||
|
)
|
||||||
|
.await
|
||||||
|
.unwrap();
|
||||||
|
|
||||||
|
// Two migration runs in a row.
|
||||||
|
ChunkedUploadService::migrate_pre_prefix_sessions(&base).await;
|
||||||
|
ChunkedUploadService::migrate_pre_prefix_sessions(&base).await;
|
||||||
|
|
||||||
|
// The dir is still there, with the SAME (single) prefix —
|
||||||
|
// not `oxi-chunk-oxi-chunk-already-prefixed/`.
|
||||||
|
assert!(prefixed_dir.exists());
|
||||||
|
let double_prefixed = base.join(session_dir_name(&session_dir_name(upload_id)));
|
||||||
|
assert!(
|
||||||
|
!double_prefixed.exists(),
|
||||||
|
"Migration must not double-prefix an already-prefixed dir"
|
||||||
|
);
|
||||||
|
|
||||||
|
let _ = fs::remove_dir_all(&base).await;
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -6,7 +6,7 @@
|
|||||||
use std::path::{Path, PathBuf};
|
use std::path::{Path, PathBuf};
|
||||||
use std::pin::Pin;
|
use std::pin::Pin;
|
||||||
use tokio::fs::{self, File};
|
use tokio::fs::{self, File};
|
||||||
use tokio::io::AsyncSeekExt;
|
use tokio::io::{AsyncSeekExt, AsyncWriteExt};
|
||||||
use tokio_util::io::ReaderStream;
|
use tokio_util::io::ReaderStream;
|
||||||
|
|
||||||
use bytes::Bytes;
|
use bytes::Bytes;
|
||||||
@@ -16,6 +16,53 @@ use crate::application::ports::blob_storage_ports::{
|
|||||||
};
|
};
|
||||||
use crate::domain::errors::{DomainError, ErrorKind};
|
use crate::domain::errors::{DomainError, ErrorKind};
|
||||||
|
|
||||||
|
/// Fsync the directory containing `child_path` so a preceding rename
|
||||||
|
/// or create on `child_path` becomes durable across power loss.
|
||||||
|
///
|
||||||
|
/// On Linux this issues `fsync(2)` on the directory file descriptor —
|
||||||
|
/// the canonical "make the dirent change durable" idiom. macOS does
|
||||||
|
/// the same but only persists to the disk controller (true persistence
|
||||||
|
/// would need `fcntl(F_FULLFSYNC)`, which tokio doesn't expose). On
|
||||||
|
/// Windows, opening a directory needs `FILE_FLAG_BACKUP_SEMANTICS` that
|
||||||
|
/// tokio's `File::open` doesn't set; that platform falls through to
|
||||||
|
/// `Ok(())` after a debug log.
|
||||||
|
///
|
||||||
|
/// Best-effort by design: a failure here is logged but does NOT fail
|
||||||
|
/// the upload, because the blob file itself was just `sync_all`'d and
|
||||||
|
/// is durable on its own. Worst case post-crash recovery: a rename
|
||||||
|
/// "reverts" to the un-renamed name (or stays renamed); the dedup-GC
|
||||||
|
/// cleanup pass handles either side.
|
||||||
|
async fn fsync_parent_dir(child_path: &Path) {
|
||||||
|
let Some(parent) = child_path.parent() else {
|
||||||
|
return;
|
||||||
|
};
|
||||||
|
let parent = parent.to_owned();
|
||||||
|
// std::fs (synchronous) opens directories reliably on Linux/macOS;
|
||||||
|
// do it on the blocking pool so we don't park the tokio worker.
|
||||||
|
let result = tokio::task::spawn_blocking(move || -> std::io::Result<()> {
|
||||||
|
let dir = std::fs::File::open(&parent)?;
|
||||||
|
dir.sync_all()
|
||||||
|
})
|
||||||
|
.await;
|
||||||
|
match result {
|
||||||
|
Ok(Ok(())) => {}
|
||||||
|
Ok(Err(e)) => {
|
||||||
|
tracing::warn!(
|
||||||
|
error = %e,
|
||||||
|
path = %child_path.display(),
|
||||||
|
"Blob parent-dir fsync failed (rename durability not guaranteed)"
|
||||||
|
);
|
||||||
|
}
|
||||||
|
Err(e) => {
|
||||||
|
tracing::warn!(
|
||||||
|
error = %e,
|
||||||
|
path = %child_path.display(),
|
||||||
|
"Blob parent-dir fsync task join failed"
|
||||||
|
);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
/// Chunk size for streaming file reads (256 KB).
|
/// Chunk size for streaming file reads (256 KB).
|
||||||
const STREAM_CHUNK_SIZE: usize = 256 * 1024;
|
const STREAM_CHUNK_SIZE: usize = 256 * 1024;
|
||||||
|
|
||||||
@@ -122,15 +169,30 @@ impl BlobStorageBackend for LocalBlobBackend {
|
|||||||
|
|
||||||
// Atomic rename (same filesystem). Falls back to copy+delete for
|
// Atomic rename (same filesystem). Falls back to copy+delete for
|
||||||
// cross-device moves (EXDEV errno 18).
|
// cross-device moves (EXDEV errno 18).
|
||||||
|
//
|
||||||
|
// Durability boundary: the caller is responsible for
|
||||||
|
// having sync_all'd the source file before invoking this
|
||||||
|
// function — both `interfaces::upload_spool::spool_body_to_temp`
|
||||||
|
// and `chunked_upload_service::complete_upload_inner`
|
||||||
|
// (the two production producers of `source_path`) now do
|
||||||
|
// so. We fsync the parent of `blob_path` AFTER the rename
|
||||||
|
// so the dirent change itself becomes durable; without
|
||||||
|
// that, a power loss can resurrect the old (unrenamed)
|
||||||
|
// name even when the file contents survive.
|
||||||
if let Err(e) = fs::rename(&source_path, &blob_path).await {
|
if let Err(e) = fs::rename(&source_path, &blob_path).await {
|
||||||
if e.raw_os_error() == Some(18) {
|
if e.raw_os_error() == Some(18) {
|
||||||
// EXDEV — cross-device link
|
// EXDEV — cross-device link. The copy() target is
|
||||||
|
// a fresh file we created, so fsync it before the
|
||||||
|
// parent-dir fsync below.
|
||||||
fs::copy(&source_path, &blob_path).await.map_err(|ce| {
|
fs::copy(&source_path, &blob_path).await.map_err(|ce| {
|
||||||
DomainError::internal_error(
|
DomainError::internal_error(
|
||||||
"Blob",
|
"Blob",
|
||||||
format!("Failed to copy file to blob store: {}", ce),
|
format!("Failed to copy file to blob store: {}", ce),
|
||||||
)
|
)
|
||||||
})?;
|
})?;
|
||||||
|
if let Ok(f) = fs::File::open(&blob_path).await {
|
||||||
|
let _ = f.sync_all().await;
|
||||||
|
}
|
||||||
let _ = fs::remove_file(&source_path).await;
|
let _ = fs::remove_file(&source_path).await;
|
||||||
} else if fs::try_exists(&blob_path).await.unwrap_or(false) {
|
} else if fs::try_exists(&blob_path).await.unwrap_or(false) {
|
||||||
// Concurrent writer placed the blob — discard our copy
|
// Concurrent writer placed the blob — discard our copy
|
||||||
@@ -144,6 +206,8 @@ impl BlobStorageBackend for LocalBlobBackend {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
fsync_parent_dir(&blob_path).await;
|
||||||
|
|
||||||
Ok(file_size)
|
Ok(file_size)
|
||||||
})
|
})
|
||||||
}
|
}
|
||||||
@@ -163,13 +227,27 @@ impl BlobStorageBackend for LocalBlobBackend {
|
|||||||
return Ok(size);
|
return Ok(size);
|
||||||
}
|
}
|
||||||
|
|
||||||
// Write directly to blob path
|
// Write directly to blob path. `fs::write` is `create +
|
||||||
fs::write(&blob_path, &data).await.map_err(|e| {
|
// write_all + close` — but the close on tokio::fs::File
|
||||||
|
// does NOT fsync, so we open explicitly to keep the
|
||||||
|
// `sync_all` call site obvious. Same durability story as
|
||||||
|
// `put_blob`: the blob file is fsync'd before the parent
|
||||||
|
// directory is, so both the content and the dirent
|
||||||
|
// creation survive a power loss in the same step.
|
||||||
|
let mut file = fs::File::create(&blob_path).await.map_err(|e| {
|
||||||
|
DomainError::internal_error("Blob", format!("Failed to create blob file: {}", e))
|
||||||
|
})?;
|
||||||
|
file.write_all(&data).await.map_err(|e| {
|
||||||
DomainError::internal_error(
|
DomainError::internal_error(
|
||||||
"Blob",
|
"Blob",
|
||||||
format!("Failed to write blob from bytes: {}", e),
|
format!("Failed to write blob from bytes: {}", e),
|
||||||
)
|
)
|
||||||
})?;
|
})?;
|
||||||
|
file.sync_all().await.map_err(|e| {
|
||||||
|
DomainError::internal_error("Blob", format!("Failed to fsync blob file: {}", e))
|
||||||
|
})?;
|
||||||
|
drop(file);
|
||||||
|
fsync_parent_dir(&blob_path).await;
|
||||||
|
|
||||||
Ok(size)
|
Ok(size)
|
||||||
})
|
})
|
||||||
|
|||||||
@@ -52,7 +52,30 @@ impl NextcloudChunkedUploadService {
|
|||||||
Ok(())
|
Ok(())
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Store a chunk in the session directory.
|
/// Resolve and validate the filesystem path for a chunk file.
|
||||||
|
///
|
||||||
|
/// Public so the interface layer can stream an HTTP body straight into
|
||||||
|
/// the chunk file without copying through the service. The service
|
||||||
|
/// retains responsibility for path-component validation; the caller
|
||||||
|
/// owns the I/O (open, write, fsync, size enforcement, cleanup on
|
||||||
|
/// failure). All three `validate_path_component` calls run before the
|
||||||
|
/// path is constructed, so a returned `PathBuf` is always inside
|
||||||
|
/// `base_dir/{user}/{upload_id}`.
|
||||||
|
pub fn safe_chunk_path(
|
||||||
|
&self,
|
||||||
|
user: &str,
|
||||||
|
upload_id: &str,
|
||||||
|
chunk_name: &str,
|
||||||
|
) -> Result<PathBuf> {
|
||||||
|
Self::validate_path_component(chunk_name, "chunk_name")?;
|
||||||
|
Ok(self.safe_session_dir(user, upload_id)?.join(chunk_name))
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Store a chunk in the session directory. Buffers `data` in memory —
|
||||||
|
/// use [`safe_chunk_path`](Self::safe_chunk_path) + the
|
||||||
|
/// `interfaces/upload_spool::stream_body_to_path` helper to stream the
|
||||||
|
/// HTTP body directly to disk and avoid materialising the whole chunk
|
||||||
|
/// in RAM.
|
||||||
pub async fn store_chunk(
|
pub async fn store_chunk(
|
||||||
&self,
|
&self,
|
||||||
user: &str,
|
user: &str,
|
||||||
@@ -60,8 +83,7 @@ impl NextcloudChunkedUploadService {
|
|||||||
chunk_name: &str,
|
chunk_name: &str,
|
||||||
data: &[u8],
|
data: &[u8],
|
||||||
) -> Result<()> {
|
) -> Result<()> {
|
||||||
Self::validate_path_component(chunk_name, "chunk_name")?;
|
let chunk_path = self.safe_chunk_path(user, upload_id, chunk_name)?;
|
||||||
let chunk_path = self.safe_session_dir(user, upload_id)?.join(chunk_name);
|
|
||||||
let mut file = fs::File::create(&chunk_path)
|
let mut file = fs::File::create(&chunk_path)
|
||||||
.await
|
.await
|
||||||
.map_err(|e| DomainError::internal_error("ChunkedUpload", e.to_string()))?;
|
.map_err(|e| DomainError::internal_error("ChunkedUpload", e.to_string()))?;
|
||||||
@@ -71,11 +93,24 @@ impl NextcloudChunkedUploadService {
|
|||||||
Ok(())
|
Ok(())
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Assemble all chunks in numeric order into a temp file.
|
/// Assemble all chunks in numeric order into a temp file, computing
|
||||||
|
/// the BLAKE3 of the concatenated stream **during** the same read/
|
||||||
|
/// write pass (hash-on-write).
|
||||||
///
|
///
|
||||||
/// Returns `(temp_path, total_size)`. The caller is responsible for
|
/// Returns `(temp_path, total_size, blake3_hex)`. The caller passes
|
||||||
/// cleaning up the temp file after use.
|
/// the hash to the upload service as `pre_computed_hash` so the
|
||||||
pub async fn assemble(&self, user: &str, upload_id: &str) -> Result<(PathBuf, u64)> {
|
/// downstream dedup layer never has to re-read the assembled file
|
||||||
|
/// to compute it — saving one full file-sized read pass per upload.
|
||||||
|
///
|
||||||
|
/// The read/hash/write loop runs inside `spawn_blocking` because
|
||||||
|
/// BLAKE3 is CPU-bound and would otherwise starve the Tokio worker
|
||||||
|
/// running other connections; synchronous I/O is used inside the
|
||||||
|
/// blocking thread because the workload is sequential and the
|
||||||
|
/// async reactor overhead would only slow it down. For files larger
|
||||||
|
/// than ~10 MB BLAKE3's Rayon mode parallelises across cores —
|
||||||
|
/// mirrors what `ChunkedUploadService::complete_upload_inner` does
|
||||||
|
/// for the REST chunked path.
|
||||||
|
pub async fn assemble(&self, user: &str, upload_id: &str) -> Result<(PathBuf, u64, String)> {
|
||||||
let session_dir = self.safe_session_dir(user, upload_id)?;
|
let session_dir = self.safe_session_dir(user, upload_id)?;
|
||||||
let mut entries: Vec<String> = Vec::new();
|
let mut entries: Vec<String> = Vec::new();
|
||||||
|
|
||||||
@@ -98,28 +133,74 @@ impl NextcloudChunkedUploadService {
|
|||||||
// Sort chunks numerically (Nextcloud sends them as "00001", "00002", ...).
|
// Sort chunks numerically (Nextcloud sends them as "00001", "00002", ...).
|
||||||
entries.sort();
|
entries.sort();
|
||||||
|
|
||||||
// Stream chunks to a temp file instead of buffering in memory.
|
|
||||||
let temp_path = session_dir.join(".assembled");
|
let temp_path = session_dir.join(".assembled");
|
||||||
let mut out = fs::File::create(&temp_path)
|
let chunk_paths: Vec<PathBuf> = entries.iter().map(|n| session_dir.join(n)).collect();
|
||||||
.await
|
let assembled_for_blocking = temp_path.clone();
|
||||||
.map_err(|e| DomainError::internal_error("ChunkedUpload", e.to_string()))?;
|
|
||||||
|
|
||||||
let mut total_size: u64 = 0;
|
// Read/hash/write loop runs synchronously on the blocking pool.
|
||||||
for chunk_name in &entries {
|
// BLAKE3 is computed in the same pass that copies bytes from chunk
|
||||||
let mut chunk_file = fs::File::open(session_dir.join(chunk_name))
|
// files into the assembled file — no second read after the fact.
|
||||||
.await
|
let (total_size, hash) =
|
||||||
.map_err(|e| DomainError::internal_error("ChunkedUpload", e.to_string()))?;
|
tokio::task::spawn_blocking(move || -> std::io::Result<(u64, String)> {
|
||||||
let copied = tokio::io::copy(&mut chunk_file, &mut out)
|
use std::io::{BufWriter as StdBufWriter, Read, Write};
|
||||||
.await
|
|
||||||
.map_err(|e| DomainError::internal_error("ChunkedUpload", e.to_string()))?;
|
let raw_output = std::fs::OpenOptions::new()
|
||||||
total_size += copied;
|
.create(true)
|
||||||
|
.write(true)
|
||||||
|
.truncate(true)
|
||||||
|
.open(&assembled_for_blocking)?;
|
||||||
|
|
||||||
|
// 512 KB write buffer — 8× fewer syscalls than 64 KB.
|
||||||
|
let mut output = StdBufWriter::with_capacity(524_288, raw_output);
|
||||||
|
let mut hasher = blake3::Hasher::new();
|
||||||
|
let mut buf = vec![0u8; 524_288];
|
||||||
|
let mut total: u64 = 0;
|
||||||
|
|
||||||
|
// Files >10 MB benefit from BLAKE3's multi-threaded mode.
|
||||||
|
// The threshold matches the REST chunked path's heuristic.
|
||||||
|
const RAYON_THRESHOLD_PER_FRAME: usize = 128 * 1024;
|
||||||
|
|
||||||
|
for chunk_path in &chunk_paths {
|
||||||
|
let mut chunk_file = std::fs::File::open(chunk_path)?;
|
||||||
|
loop {
|
||||||
|
let n = chunk_file.read(&mut buf)?;
|
||||||
|
if n == 0 {
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
if n >= RAYON_THRESHOLD_PER_FRAME {
|
||||||
|
hasher.update_rayon(&buf[..n]);
|
||||||
|
} else {
|
||||||
|
hasher.update(&buf[..n]);
|
||||||
|
}
|
||||||
|
output.write_all(&buf[..n])?;
|
||||||
|
total += n as u64;
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
out.flush()
|
output.flush()?;
|
||||||
|
// ── Durability boundary ─────────────────────────────────
|
||||||
|
// sync_all is the actual fsync; without it, a power loss
|
||||||
|
// before the kernel writeback timer (~5 s) loses
|
||||||
|
// acknowledged data. Pull the inner File out of the
|
||||||
|
// BufWriter so we can sync the underlying handle —
|
||||||
|
// dropping the BufWriter wouldn't trigger fsync. macOS
|
||||||
|
// caveat: fsync there flushes to the disk controller
|
||||||
|
// only; true durability needs F_FULLFSYNC, not exposed
|
||||||
|
// by std.
|
||||||
|
let raw_output = output
|
||||||
|
.into_inner()
|
||||||
|
.map_err(|e| std::io::Error::other(format!("into_inner: {e}")))?;
|
||||||
|
raw_output.sync_all()?;
|
||||||
|
|
||||||
|
Ok((total, hasher.finalize().to_hex().to_string()))
|
||||||
|
})
|
||||||
.await
|
.await
|
||||||
|
.map_err(|e| {
|
||||||
|
DomainError::internal_error("ChunkedUpload", format!("assemble task: {e}"))
|
||||||
|
})?
|
||||||
.map_err(|e| DomainError::internal_error("ChunkedUpload", e.to_string()))?;
|
.map_err(|e| DomainError::internal_error("ChunkedUpload", e.to_string()))?;
|
||||||
|
|
||||||
Ok((temp_path, total_size))
|
Ok((temp_path, total_size, hash))
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Delete the upload session directory.
|
/// Delete the upload session directory.
|
||||||
@@ -262,10 +343,16 @@ mod tests {
|
|||||||
.await
|
.await
|
||||||
.unwrap();
|
.unwrap();
|
||||||
|
|
||||||
let (temp_path, size) = svc.assemble("alice", "upload-002").await.unwrap();
|
let (temp_path, size, hash) = svc.assemble("alice", "upload-002").await.unwrap();
|
||||||
let assembled = fs::read(&temp_path).await.unwrap();
|
let assembled = fs::read(&temp_path).await.unwrap();
|
||||||
assert_eq!(assembled, b"Hello, World!");
|
assert_eq!(assembled, b"Hello, World!");
|
||||||
assert_eq!(size, 13);
|
assert_eq!(size, 13);
|
||||||
|
// BLAKE3("Hello, World!") — proves hash-on-write happens during
|
||||||
|
// the assemble pass, not via a re-read.
|
||||||
|
assert_eq!(
|
||||||
|
hash,
|
||||||
|
"288a86a79f20a3d6dccdca7713beaed178798296bdfa7913fa2a62d9727bf8f8"
|
||||||
|
);
|
||||||
}
|
}
|
||||||
|
|
||||||
#[tokio::test]
|
#[tokio::test]
|
||||||
@@ -284,10 +371,16 @@ mod tests {
|
|||||||
.await
|
.await
|
||||||
.unwrap();
|
.unwrap();
|
||||||
|
|
||||||
let (temp_path, size) = svc.assemble("alice", "upload-003").await.unwrap();
|
let (temp_path, size, hash) = svc.assemble("alice", "upload-003").await.unwrap();
|
||||||
let assembled = fs::read(&temp_path).await.unwrap();
|
let assembled = fs::read(&temp_path).await.unwrap();
|
||||||
assert_eq!(assembled, b"ABC");
|
assert_eq!(assembled, b"ABC");
|
||||||
assert_eq!(size, 3);
|
assert_eq!(size, 3);
|
||||||
|
// BLAKE3("ABC") — confirms sort happened (chunks were stored in
|
||||||
|
// order 3,1,2 but the hash matches "ABC", not "CAB" or "BAC").
|
||||||
|
assert_eq!(
|
||||||
|
hash,
|
||||||
|
"d1717274597cf0289694f75d96d444b992a096f1afd8e7bbfa6ebb1d360fedfc"
|
||||||
|
);
|
||||||
}
|
}
|
||||||
|
|
||||||
#[tokio::test]
|
#[tokio::test]
|
||||||
|
|||||||
@@ -13,11 +13,11 @@ use axum::{
|
|||||||
http::{HeaderMap, StatusCode, header},
|
http::{HeaderMap, StatusCode, header},
|
||||||
response::{IntoResponse, Response},
|
response::{IntoResponse, Response},
|
||||||
};
|
};
|
||||||
use bytes::Bytes;
|
|
||||||
use serde::{Deserialize, Serialize};
|
use serde::{Deserialize, Serialize};
|
||||||
use std::sync::Arc;
|
use std::sync::Arc;
|
||||||
use utoipa::ToSchema;
|
use utoipa::ToSchema;
|
||||||
|
|
||||||
|
use crate::application::ports::chunked_upload_ports::ChecksumAlg;
|
||||||
use crate::application::ports::chunked_upload_ports::ChunkedUploadPort;
|
use crate::application::ports::chunked_upload_ports::ChunkedUploadPort;
|
||||||
use crate::application::ports::chunked_upload_ports::DEFAULT_CHUNK_SIZE;
|
use crate::application::ports::chunked_upload_ports::DEFAULT_CHUNK_SIZE;
|
||||||
use crate::application::ports::file_ports::FileUploadUseCase;
|
use crate::application::ports::file_ports::FileUploadUseCase;
|
||||||
@@ -27,6 +27,7 @@ use crate::common::di::AppState;
|
|||||||
use crate::domain::services::authorization::Permission;
|
use crate::domain::services::authorization::Permission;
|
||||||
use crate::interfaces::errors::AppError;
|
use crate::interfaces::errors::AppError;
|
||||||
use crate::interfaces::middleware::auth::AuthUser;
|
use crate::interfaces::middleware::auth::AuthUser;
|
||||||
|
use crate::interfaces::upload_spool::stream_body_to_path;
|
||||||
|
|
||||||
/// Request body for creating an upload session
|
/// Request body for creating an upload session
|
||||||
#[derive(Debug, Deserialize, ToSchema)]
|
#[derive(Debug, Deserialize, ToSchema)]
|
||||||
@@ -38,11 +39,17 @@ pub struct CreateUploadRequest {
|
|||||||
pub chunk_size: Option<usize>,
|
pub chunk_size: Option<usize>,
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Query params for chunk upload
|
/// Query params for chunk upload.
|
||||||
|
///
|
||||||
|
/// `checksumalg` is parsed via [`ChecksumAlg::parse`] and defaults to
|
||||||
|
/// `Md5` when absent — matching the legacy `Content-MD5` contract that
|
||||||
|
/// older clients rely on. Unknown algorithm names produce a 400 with the
|
||||||
|
/// offending value echoed back.
|
||||||
#[derive(Debug, Deserialize)]
|
#[derive(Debug, Deserialize)]
|
||||||
pub struct ChunkUploadParams {
|
pub struct ChunkUploadParams {
|
||||||
pub chunk_index: usize,
|
pub chunk_index: usize,
|
||||||
pub checksum: Option<String>,
|
pub checksum: Option<String>,
|
||||||
|
pub checksumalg: Option<String>,
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Final response after completing upload
|
/// Final response after completing upload
|
||||||
@@ -54,6 +61,41 @@ pub struct CompleteUploadResponse {
|
|||||||
pub path: String,
|
pub path: String,
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/// Optional body for `POST /api/uploads/{id}/complete`.
|
||||||
|
///
|
||||||
|
/// When the client supplies `checksum`, the server compares it against
|
||||||
|
/// the assembled file's hash BEFORE promoting the blob to storage —
|
||||||
|
/// failure aborts the upload atomically (no orphaned blob, no DB row).
|
||||||
|
/// This is the end-to-end integrity check: per-chunk MD5 proves each
|
||||||
|
/// chunk arrived intact, but only the final hash catches assembly /
|
||||||
|
/// promotion bugs and mis-ordered chunks.
|
||||||
|
///
|
||||||
|
/// **`blake3` is highly recommended** — it's the algorithm the server
|
||||||
|
/// already runs over the assembled file during hash-on-write
|
||||||
|
/// assembly, so verification is a string comparison with zero extra
|
||||||
|
/// I/O and zero extra CPU. It's also the same algorithm the server
|
||||||
|
/// uses for blob-storage addressing, so the value the client sends
|
||||||
|
/// equals the `content_hash` they'd later read back from
|
||||||
|
/// `GET /api/files/{id}`. `md5` and `sha256` are accepted for
|
||||||
|
/// compatibility with legacy client tooling but each triggers a
|
||||||
|
/// second hash pass over the assembled file (~30–100 ms depending
|
||||||
|
/// on size).
|
||||||
|
///
|
||||||
|
/// `Default` keeps the existing wire shape: clients that POST with no
|
||||||
|
/// body get today's behavior (no verification, server just returns
|
||||||
|
/// what it computed).
|
||||||
|
#[derive(Debug, Default, Deserialize, ToSchema)]
|
||||||
|
pub struct CompleteUploadRequest {
|
||||||
|
/// Lowercase hex digest the client expects the assembled file to
|
||||||
|
/// hash to. Compared case-insensitively. Omit to skip verification.
|
||||||
|
pub checksum: Option<String>,
|
||||||
|
/// Algorithm name. `blake3` is the recommended choice (default —
|
||||||
|
/// matches the server's hash-on-write algorithm, zero extra cost).
|
||||||
|
/// `md5`, `sha256` / `sha-256` are accepted but trigger an extra
|
||||||
|
/// hash pass. Unknown values return 400.
|
||||||
|
pub checksumalg: Option<String>,
|
||||||
|
}
|
||||||
|
|
||||||
/// Chunked Upload Handler
|
/// Chunked Upload Handler
|
||||||
///
|
///
|
||||||
/// The handler struct exists as a named grouping. All route functions are free
|
/// The handler struct exists as a named grouping. All route functions are free
|
||||||
@@ -120,6 +162,33 @@ impl ChunkedUploadHandler {
|
|||||||
.into_response();
|
.into_response();
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// ── Whole-file cap ──────────────────────────────────────────
|
||||||
|
// Reject upfront, before any chunk is uploaded — wasting
|
||||||
|
// bandwidth + server disk on an upload that's going to be
|
||||||
|
// rejected at /complete is the worst-of-both-worlds outcome.
|
||||||
|
// `max_upload_size` is the same ceiling that bounds direct
|
||||||
|
// PUTs (per-byte during streaming there; declared per-session
|
||||||
|
// here). When quotas are disabled, this is the only whole-file
|
||||||
|
// limit for chunked uploads — without it a hostile client
|
||||||
|
// could declare `total_size: 1 TB` and accumulate chunks
|
||||||
|
// until disk fills.
|
||||||
|
let max_upload = state.core.config.storage.max_upload_size as u64;
|
||||||
|
if request.total_size > max_upload {
|
||||||
|
tracing::warn!(
|
||||||
|
"⛔ CHUNKED UPLOAD REJECTED (total_size cap): user={}, file={}, declared={}, max={}",
|
||||||
|
auth_user.username,
|
||||||
|
request.filename,
|
||||||
|
request.total_size,
|
||||||
|
max_upload
|
||||||
|
);
|
||||||
|
return AppError::payload_too_large(format!(
|
||||||
|
"Declared total_size {} exceeds the server's `max_upload_size` cap ({} bytes). \
|
||||||
|
Raise OXICLOUD_MAX_UPLOAD_SIZE on the server if larger uploads are expected.",
|
||||||
|
request.total_size, max_upload
|
||||||
|
))
|
||||||
|
.into_response();
|
||||||
|
}
|
||||||
|
|
||||||
// ── Permission pre-check: caller must have Create on the target
|
// ── Permission pre-check: caller must have Create on the target
|
||||||
// folder BEFORE we allocate a session and accept chunks. The
|
// folder BEFORE we allocate a session and accept chunks. The
|
||||||
// upload service re-checks at finalize time, but failing here
|
// upload service re-checks at finalize time, but failing here
|
||||||
@@ -200,58 +269,12 @@ impl ChunkedUploadHandler {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
/// PATCH /api/uploads/:upload_id - Upload a chunk
|
// PATCH /api/uploads/:upload_id — moved entirely to the free
|
||||||
///
|
// function `upload_chunk` below so the body can be streamed
|
||||||
/// Query params:
|
// (axum::body::Body) instead of materialised as `Bytes` here.
|
||||||
/// - chunk_index: The index of the chunk (0-based)
|
// The port-level `ChunkedUploadPort::upload_chunk` (Bytes-based)
|
||||||
/// - checksum: Optional MD5 checksum for verification
|
// remains for tests and any future caller that genuinely has the
|
||||||
///
|
// bytes already in memory.
|
||||||
/// Body: Raw bytes of the chunk
|
|
||||||
pub(super) async fn upload_chunk_impl(
|
|
||||||
State(state): State<Arc<AppState>>,
|
|
||||||
auth_user: AuthUser,
|
|
||||||
Path(upload_id): Path<String>,
|
|
||||||
Query(params): Query<ChunkUploadParams>,
|
|
||||||
headers: HeaderMap,
|
|
||||||
body: Bytes,
|
|
||||||
) -> impl IntoResponse {
|
|
||||||
let chunked_service = &state.core.chunked_upload_service;
|
|
||||||
|
|
||||||
// Extract checksum from header or query param
|
|
||||||
let checksum = params.checksum.or_else(|| {
|
|
||||||
headers
|
|
||||||
.get("Content-MD5")
|
|
||||||
.and_then(|v| v.to_str().ok())
|
|
||||||
.map(|s| s.to_string())
|
|
||||||
});
|
|
||||||
|
|
||||||
match chunked_service
|
|
||||||
.upload_chunk(&upload_id, auth_user.id, params.chunk_index, body, checksum)
|
|
||||||
.await
|
|
||||||
{
|
|
||||||
Ok(response) => {
|
|
||||||
let mut resp = Response::builder()
|
|
||||||
.status(StatusCode::OK)
|
|
||||||
.header(header::CONTENT_TYPE, "application/json")
|
|
||||||
.header("Upload-Offset", response.bytes_received.to_string())
|
|
||||||
.header(
|
|
||||||
"Upload-Progress",
|
|
||||||
format!("{:.2}", response.progress * 100.0),
|
|
||||||
);
|
|
||||||
|
|
||||||
if response.is_complete {
|
|
||||||
resp = resp.header("Upload-Complete", "true");
|
|
||||||
}
|
|
||||||
|
|
||||||
resp.body(axum::body::Body::from(
|
|
||||||
serde_json::to_string(&response).unwrap(),
|
|
||||||
))
|
|
||||||
.unwrap()
|
|
||||||
.into_response()
|
|
||||||
}
|
|
||||||
Err(e) => AppError::from(e).into_response(),
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
/// HEAD /api/uploads/:upload_id - Get upload status
|
/// HEAD /api/uploads/:upload_id - Get upload status
|
||||||
///
|
///
|
||||||
@@ -284,19 +307,97 @@ impl ChunkedUploadHandler {
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/// Compute the requested checksum of the assembled file.
|
||||||
|
///
|
||||||
|
/// For `Blake3` the server already has the hash from hash-on-write
|
||||||
|
/// assembly — we just return it (zero I/O, zero CPU). For `Md5` and
|
||||||
|
/// `Sha256` we re-read the assembled file on the blocking pool and
|
||||||
|
/// hash it; the cost (~30–100 ms for typical files) is the trade-off
|
||||||
|
/// for accepting non-default algorithms.
|
||||||
|
async fn compute_assembled_hash(
|
||||||
|
assembled_path: &std::path::Path,
|
||||||
|
alg: ChecksumAlg,
|
||||||
|
blake3_already_computed: &str,
|
||||||
|
) -> Result<String, std::io::Error> {
|
||||||
|
match alg {
|
||||||
|
ChecksumAlg::Blake3 => Ok(blake3_already_computed.to_string()),
|
||||||
|
ChecksumAlg::Md5 | ChecksumAlg::Sha256 => {
|
||||||
|
let path = assembled_path.to_path_buf();
|
||||||
|
tokio::task::spawn_blocking(move || -> Result<String, std::io::Error> {
|
||||||
|
use std::io::Read;
|
||||||
|
let mut file = std::fs::File::open(&path)?;
|
||||||
|
let mut buf = vec![0u8; 524_288];
|
||||||
|
match alg {
|
||||||
|
ChecksumAlg::Md5 => {
|
||||||
|
use md5::Digest as _;
|
||||||
|
let mut h = md5::Md5::new();
|
||||||
|
loop {
|
||||||
|
let n = file.read(&mut buf)?;
|
||||||
|
if n == 0 {
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
h.update(&buf[..n]);
|
||||||
|
}
|
||||||
|
Ok(h.finalize().iter().map(|b| format!("{b:02x}")).collect())
|
||||||
|
}
|
||||||
|
ChecksumAlg::Sha256 => {
|
||||||
|
use sha2::Digest as _;
|
||||||
|
let mut h = sha2::Sha256::new();
|
||||||
|
loop {
|
||||||
|
let n = file.read(&mut buf)?;
|
||||||
|
if n == 0 {
|
||||||
|
break;
|
||||||
|
}
|
||||||
|
h.update(&buf[..n]);
|
||||||
|
}
|
||||||
|
Ok(h.finalize().iter().map(|b| format!("{b:02x}")).collect())
|
||||||
|
}
|
||||||
|
// Blake3 handled above — this branch is unreachable but
|
||||||
|
// keeps the match exhaustive without an else-clause.
|
||||||
|
ChecksumAlg::Blake3 => unreachable!(),
|
||||||
|
}
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| std::io::Error::other(format!("hash task join failed: {e}")))?
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
/// POST /api/uploads/:upload_id/complete - Finalize upload
|
/// POST /api/uploads/:upload_id/complete - Finalize upload
|
||||||
///
|
///
|
||||||
/// Assembles all chunks into the final file and creates the file record
|
/// Assembles all chunks into the final file and creates the file record.
|
||||||
// TODO: how is implemented security (owneship, permission ?)
|
/// When `body.checksum` is supplied, the assembled file's hash is
|
||||||
|
/// verified before the blob is promoted to storage — mismatch
|
||||||
|
/// returns 400 and the assembled temp is removed (the session
|
||||||
|
/// itself is kept so the client can re-issue complete after
|
||||||
|
/// diagnosing).
|
||||||
pub(super) async fn complete_upload_impl(
|
pub(super) async fn complete_upload_impl(
|
||||||
State(state): State<Arc<AppState>>,
|
State(state): State<Arc<AppState>>,
|
||||||
auth_user: AuthUser,
|
auth_user: AuthUser,
|
||||||
Path(upload_id): Path<String>,
|
Path(upload_id): Path<String>,
|
||||||
|
body: CompleteUploadRequest,
|
||||||
) -> impl IntoResponse {
|
) -> impl IntoResponse {
|
||||||
let chunked_service = &state.core.chunked_upload_service;
|
let chunked_service = &state.core.chunked_upload_service;
|
||||||
let upload_service = &state.applications.file_upload_service;
|
let upload_service = &state.applications.file_upload_service;
|
||||||
|
|
||||||
// Assemble chunks (hash-on-write: SHA-256 computed during assembly)
|
// ── Parse the optional algorithm BEFORE assembly so a bad
|
||||||
|
// `checksumalg` doesn't waste the (potentially expensive)
|
||||||
|
// hash work on a request we'll reject anyway.
|
||||||
|
let alg = match body.checksumalg.as_deref() {
|
||||||
|
Some(name) => match ChecksumAlg::parse(name) {
|
||||||
|
Some(a) => Some(a),
|
||||||
|
None => {
|
||||||
|
return AppError::bad_request(format!(
|
||||||
|
"Unsupported checksumalg: {name} (supported: md5, sha256, blake3)"
|
||||||
|
))
|
||||||
|
.into_response();
|
||||||
|
}
|
||||||
|
},
|
||||||
|
None => None,
|
||||||
|
};
|
||||||
|
let expected_checksum = body.checksum.as_deref();
|
||||||
|
|
||||||
|
// Assemble chunks (hash-on-write: BLAKE3 computed during assembly)
|
||||||
let (assembled_path, filename, folder_id, content_type, total_size, hash) =
|
let (assembled_path, filename, folder_id, content_type, total_size, hash) =
|
||||||
match chunked_service
|
match chunked_service
|
||||||
.complete_upload(&upload_id, auth_user.id)
|
.complete_upload(&upload_id, auth_user.id)
|
||||||
@@ -308,6 +409,46 @@ impl ChunkedUploadHandler {
|
|||||||
}
|
}
|
||||||
};
|
};
|
||||||
|
|
||||||
|
// ── End-to-end integrity verification ───────────────────────
|
||||||
|
// Only fires when the client supplied an `expected` checksum.
|
||||||
|
// For BLAKE3 (the documented preferred choice) this is a string
|
||||||
|
// comparison against the hash assembly already produced. For
|
||||||
|
// MD5/SHA-256 we re-hash the assembled file on the blocking pool.
|
||||||
|
if let Some(expected) = expected_checksum {
|
||||||
|
let alg = alg.unwrap_or(ChecksumAlg::Blake3);
|
||||||
|
let computed = match Self::compute_assembled_hash(&assembled_path, alg, &hash).await {
|
||||||
|
Ok(c) => c,
|
||||||
|
Err(e) => {
|
||||||
|
let _ = tokio::fs::remove_file(&assembled_path).await;
|
||||||
|
return AppError::internal_error(format!(
|
||||||
|
"Failed to compute assembled checksum: {e}"
|
||||||
|
))
|
||||||
|
.into_response();
|
||||||
|
}
|
||||||
|
};
|
||||||
|
if !computed.eq_ignore_ascii_case(expected) {
|
||||||
|
let _ = tokio::fs::remove_file(&assembled_path).await;
|
||||||
|
tracing::warn!(
|
||||||
|
target: "audit",
|
||||||
|
event = "chunked_upload.checksum_mismatch",
|
||||||
|
reason = "final_checksum_mismatch",
|
||||||
|
upload_id = %upload_id,
|
||||||
|
user_id = %auth_user.id,
|
||||||
|
alg = alg.as_str(),
|
||||||
|
expected = %expected,
|
||||||
|
actual = %computed,
|
||||||
|
"👮🏻♂️ Chunked upload complete: client checksum mismatch — blob not promoted"
|
||||||
|
);
|
||||||
|
return AppError::bad_request(format!(
|
||||||
|
"Checksum mismatch ({}): expected {}, got {}",
|
||||||
|
alg.as_str(),
|
||||||
|
expected,
|
||||||
|
computed
|
||||||
|
))
|
||||||
|
.into_response();
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
// ── MIME detection (magic bytes + extension fallback) ─────
|
// ── MIME detection (magic bytes + extension fallback) ─────
|
||||||
let content_type = crate::common::mime_detect::refine_content_type_from_file(
|
let content_type = crate::common::mime_detect::refine_content_type_from_file(
|
||||||
&assembled_path,
|
&assembled_path,
|
||||||
@@ -420,29 +561,142 @@ pub async fn create_upload(
|
|||||||
params(
|
params(
|
||||||
("upload_id" = String, Path, description = "Upload session ID"),
|
("upload_id" = String, Path, description = "Upload session ID"),
|
||||||
("chunk_index" = usize, Query, description = "Zero-based chunk index"),
|
("chunk_index" = usize, Query, description = "Zero-based chunk index"),
|
||||||
("checksum" = Option<String>, Query, description = "Optional MD5 checksum for integrity verification"),
|
(
|
||||||
|
"checksum" = Option<String>,
|
||||||
|
Query,
|
||||||
|
description = "Optional hex-encoded checksum for integrity verification. \
|
||||||
|
Computed incrementally during the streaming write. \
|
||||||
|
Algorithm is selected by `checksumalg` (default `md5`). \
|
||||||
|
Also accepted via the legacy `Content-MD5` request header."
|
||||||
|
),
|
||||||
|
(
|
||||||
|
"checksumalg" = Option<String>,
|
||||||
|
Query,
|
||||||
|
description = "Algorithm used by `checksum`. One of: `md5` (default, legacy), `sha256` / `sha-256`, `blake3`. \
|
||||||
|
Unknown values return 400."
|
||||||
|
),
|
||||||
),
|
),
|
||||||
request_body(content_type = "application/octet-stream", description = "Raw chunk bytes"),
|
request_body(content_type = "application/octet-stream", description = "Raw chunk bytes"),
|
||||||
responses(
|
responses(
|
||||||
(status = 200, description = "Chunk received", body = crate::application::ports::chunked_upload_ports::ChunkUploadResponseDto),
|
(status = 200, description = "Chunk received", body = crate::application::ports::chunked_upload_ports::ChunkUploadResponseDto),
|
||||||
(status = 400, description = "Invalid chunk or checksum mismatch"),
|
(status = 400, description = "Invalid chunk, size mismatch, checksum mismatch, or unknown `checksumalg`"),
|
||||||
(status = 404, description = "Upload session not found"),
|
(status = 404, description = "Upload session not found"),
|
||||||
|
(status = 413, description = "Chunk exceeds `storage.chunk_max_bytes` cap"),
|
||||||
),
|
),
|
||||||
tag = "uploads",
|
tag = "uploads",
|
||||||
security(("bearerAuth" = []))
|
security(("bearerAuth" = []))
|
||||||
)]
|
)]
|
||||||
pub async fn upload_chunk(
|
pub async fn upload_chunk(
|
||||||
state: State<Arc<AppState>>,
|
State(state): State<Arc<AppState>>,
|
||||||
auth_user: AuthUser,
|
auth_user: AuthUser,
|
||||||
path: Path<String>,
|
Path(upload_id): Path<String>,
|
||||||
query: Query<ChunkUploadParams>,
|
Query(params): Query<ChunkUploadParams>,
|
||||||
headers: HeaderMap,
|
headers: HeaderMap,
|
||||||
request: Request,
|
request: Request,
|
||||||
) -> impl IntoResponse {
|
) -> impl IntoResponse {
|
||||||
let body = axum::body::to_bytes(request.into_body(), usize::MAX)
|
let chunked_service = &state.core.chunked_upload_service;
|
||||||
|
let max_chunk = state.core.config.storage.chunk_max_bytes;
|
||||||
|
|
||||||
|
// ── Resolve the client's checksum + algorithm ────────────────────
|
||||||
|
// Wire shape: `?checksum=<hex>&checksumalg=<name>` (or `Content-MD5`
|
||||||
|
// header for older clients). When `checksumalg` is omitted we
|
||||||
|
// default to MD5, matching the legacy contract — switching the
|
||||||
|
// default would silently break any client still relying on
|
||||||
|
// `Content-MD5` semantics.
|
||||||
|
let expected_checksum = params.checksum.clone().or_else(|| {
|
||||||
|
headers
|
||||||
|
.get("Content-MD5")
|
||||||
|
.and_then(|v| v.to_str().ok())
|
||||||
|
.map(|s| s.to_string())
|
||||||
|
});
|
||||||
|
let alg = match params.checksumalg.as_deref() {
|
||||||
|
Some(name) => match ChecksumAlg::parse(name) {
|
||||||
|
Some(a) => a,
|
||||||
|
None => {
|
||||||
|
return AppError::bad_request(format!(
|
||||||
|
"Unsupported checksumalg: {name} (supported: md5, sha256, blake3)"
|
||||||
|
))
|
||||||
|
.into_response();
|
||||||
|
}
|
||||||
|
},
|
||||||
|
None => ChecksumAlg::Md5,
|
||||||
|
};
|
||||||
|
// Only compute the hash when the client supplied an `expected_checksum`
|
||||||
|
// to verify against — saves ~30 ms per chunk for clients that don't.
|
||||||
|
let alg_to_compute = expected_checksum.as_ref().map(|_| alg);
|
||||||
|
|
||||||
|
// ── Phase 1: prepare ─────────────────────────────────────────────
|
||||||
|
// Validates session ownership + chunk index, returns the on-disk
|
||||||
|
// path and the chunk's declared size. The handler streams the body
|
||||||
|
// to that path; service finalises bookkeeping after the write.
|
||||||
|
let (chunk_path, _expected_size) = match chunked_service
|
||||||
|
.prepare_chunk(&upload_id, auth_user.id, params.chunk_index)
|
||||||
.await
|
.await
|
||||||
.unwrap_or_default();
|
{
|
||||||
ChunkedUploadHandler::upload_chunk_impl(state, auth_user, path, query, headers, body).await
|
Ok(p) => p,
|
||||||
|
Err(e) => return AppError::from(e).into_response(),
|
||||||
|
};
|
||||||
|
|
||||||
|
// ── Phase 2: stream the body straight to disk ────────────────────
|
||||||
|
// Peak heap ~one HTTP frame (~64 KB) regardless of chunk size or
|
||||||
|
// `chunk_max_bytes`. Optional incremental hashing happens here so
|
||||||
|
// verification doesn't require reading the chunk file back.
|
||||||
|
let streamed = match stream_body_to_path(
|
||||||
|
request.into_body(),
|
||||||
|
&chunk_path,
|
||||||
|
max_chunk,
|
||||||
|
alg_to_compute,
|
||||||
|
)
|
||||||
|
.await
|
||||||
|
{
|
||||||
|
Ok(s) => s,
|
||||||
|
Err(e) => {
|
||||||
|
tracing::warn!(
|
||||||
|
error = ?e,
|
||||||
|
upload_id = %upload_id,
|
||||||
|
chunk_index = params.chunk_index,
|
||||||
|
max_chunk,
|
||||||
|
"Chunked upload PATCH rejected — streaming write failed (cap, transport, or IO)"
|
||||||
|
);
|
||||||
|
return e.into_response();
|
||||||
|
}
|
||||||
|
};
|
||||||
|
|
||||||
|
// ── Phase 3: commit ──────────────────────────────────────────────
|
||||||
|
// Size + checksum verification + session state update. Same RAM-only
|
||||||
|
// DashMap shard ownership pattern as the legacy `upload_chunk_inner`
|
||||||
|
// (held only for ~µs; bitmask persist done after release).
|
||||||
|
let response = match chunked_service
|
||||||
|
.commit_chunk(
|
||||||
|
&upload_id,
|
||||||
|
auth_user.id,
|
||||||
|
params.chunk_index,
|
||||||
|
streamed.bytes_written,
|
||||||
|
streamed.checksum_hex,
|
||||||
|
expected_checksum,
|
||||||
|
)
|
||||||
|
.await
|
||||||
|
{
|
||||||
|
Ok(r) => r,
|
||||||
|
Err(e) => return AppError::from(e).into_response(),
|
||||||
|
};
|
||||||
|
|
||||||
|
let mut resp = Response::builder()
|
||||||
|
.status(StatusCode::OK)
|
||||||
|
.header(header::CONTENT_TYPE, "application/json")
|
||||||
|
.header("Upload-Offset", response.bytes_received.to_string())
|
||||||
|
.header(
|
||||||
|
"Upload-Progress",
|
||||||
|
format!("{:.2}", response.progress * 100.0),
|
||||||
|
);
|
||||||
|
if response.is_complete {
|
||||||
|
resp = resp.header("Upload-Complete", "true");
|
||||||
|
}
|
||||||
|
resp.body(axum::body::Body::from(
|
||||||
|
serde_json::to_string(&response).unwrap(),
|
||||||
|
))
|
||||||
|
.unwrap()
|
||||||
|
.into_response()
|
||||||
}
|
}
|
||||||
|
|
||||||
#[utoipa::path(
|
#[utoipa::path(
|
||||||
@@ -472,10 +726,23 @@ pub async fn get_upload_status(
|
|||||||
params(
|
params(
|
||||||
("upload_id" = String, Path, description = "Upload session ID"),
|
("upload_id" = String, Path, description = "Upload session ID"),
|
||||||
),
|
),
|
||||||
|
request_body(
|
||||||
|
content = CompleteUploadRequest,
|
||||||
|
content_type = "application/json",
|
||||||
|
description = "Optional. End-to-end integrity verification of the assembled file. \
|
||||||
|
**`blake3` is highly recommended** as the `checksumalg` value — the server already \
|
||||||
|
computes BLAKE3 over the assembled file during hash-on-write assembly, so \
|
||||||
|
verification is a string comparison with zero extra CPU/IO. \
|
||||||
|
Picking `md5` or `sha256` is supported for legacy client tooling but triggers a \
|
||||||
|
second full hash pass over the assembled file. \
|
||||||
|
Clients that POST with no body (or with an empty JSON object) get today's \
|
||||||
|
behavior: no verification, server returns the BLAKE3 it computed."
|
||||||
|
),
|
||||||
responses(
|
responses(
|
||||||
(status = 201, description = "File assembled and created", body = CompleteUploadResponse),
|
(status = 201, description = "File assembled and created", body = CompleteUploadResponse),
|
||||||
|
(status = 400, description = "Unknown `checksumalg` or final-checksum mismatch"),
|
||||||
(status = 404, description = "Upload session not found"),
|
(status = 404, description = "Upload session not found"),
|
||||||
(status = 500, description = "Assembly or file creation failed"),
|
(status = 500, description = "Assembly, hashing, or file creation failed"),
|
||||||
),
|
),
|
||||||
tag = "uploads",
|
tag = "uploads",
|
||||||
security(("bearerAuth" = []))
|
security(("bearerAuth" = []))
|
||||||
@@ -484,8 +751,13 @@ pub async fn complete_upload(
|
|||||||
state: State<Arc<AppState>>,
|
state: State<Arc<AppState>>,
|
||||||
auth_user: AuthUser,
|
auth_user: AuthUser,
|
||||||
path: Path<String>,
|
path: Path<String>,
|
||||||
|
// Empty body → `None` → default `CompleteUploadRequest`, preserving the
|
||||||
|
// pre-checksum wire shape. Clients that DO send a body get strict
|
||||||
|
// parsing (a malformed JSON returns 400 via the Json extractor).
|
||||||
|
body: Option<Json<CompleteUploadRequest>>,
|
||||||
) -> impl IntoResponse {
|
) -> impl IntoResponse {
|
||||||
ChunkedUploadHandler::complete_upload_impl(state, auth_user, path).await
|
let req = body.map(|Json(r)| r).unwrap_or_default();
|
||||||
|
ChunkedUploadHandler::complete_upload_impl(state, auth_user, path, req).await
|
||||||
}
|
}
|
||||||
|
|
||||||
#[utoipa::path(
|
#[utoipa::path(
|
||||||
|
|||||||
@@ -940,8 +940,10 @@ async fn handle_put(
|
|||||||
// another user — acceptable risk since PathResolver should always
|
// another user — acceptable risk since PathResolver should always
|
||||||
// be enabled in production)
|
// be enabled in production)
|
||||||
|
|
||||||
// Hard upload size limit from config
|
// Direct PUT cap — see `nextcloud/webdav_handler::handle_put` for
|
||||||
let max_upload = state.core.config.storage.max_upload_size;
|
// the reasoning. Files above `direct_put_max_bytes` must go through
|
||||||
|
// the chunked-upload protocol (`/api/uploads/…`) which is resumable.
|
||||||
|
let max_upload = state.core.config.storage.direct_put_max_bytes;
|
||||||
|
|
||||||
// Extract content type before consuming the request
|
// Extract content type before consuming the request
|
||||||
let content_type = req
|
let content_type = req
|
||||||
|
|||||||
@@ -1,5 +1,5 @@
|
|||||||
use axum::{
|
use axum::{
|
||||||
body::{self, Body},
|
body::Body,
|
||||||
http::{Request, StatusCode, header},
|
http::{Request, StatusCode, header},
|
||||||
response::Response,
|
response::Response,
|
||||||
};
|
};
|
||||||
@@ -10,6 +10,7 @@ use crate::common::di::AppState;
|
|||||||
use crate::common::mime_detect::{filename_from_path, refine_content_type_from_file};
|
use crate::common::mime_detect::{filename_from_path, refine_content_type_from_file};
|
||||||
use crate::interfaces::errors::AppError;
|
use crate::interfaces::errors::AppError;
|
||||||
use crate::interfaces::middleware::auth::{AuthUser, CurrentUser};
|
use crate::interfaces::middleware::auth::{AuthUser, CurrentUser};
|
||||||
|
use crate::interfaces::upload_spool::stream_body_to_path;
|
||||||
|
|
||||||
/// Dispatch Nextcloud chunked upload WebDAV requests.
|
/// Dispatch Nextcloud chunked upload WebDAV requests.
|
||||||
///
|
///
|
||||||
@@ -164,6 +165,14 @@ async fn handle_mkcol(
|
|||||||
}
|
}
|
||||||
|
|
||||||
/// PUT — store a chunk.
|
/// PUT — store a chunk.
|
||||||
|
///
|
||||||
|
/// Streams the request body straight to the chunk file with peak heap of
|
||||||
|
/// ~one HTTP frame, regardless of chunk size or the configured cap. The
|
||||||
|
/// `storage.chunk_max_bytes` config (env `OXICLOUD_CHUNK_MAX_BYTES`,
|
||||||
|
/// default 100 MB) bounds a single PUT — separate from `max_upload_size`
|
||||||
|
/// which governs whole-file uploads. Without this separation, a client
|
||||||
|
/// could submit a chunk up to the whole-file cap (10 GB default) and
|
||||||
|
/// monopolise server memory.
|
||||||
async fn handle_put_chunk(
|
async fn handle_put_chunk(
|
||||||
state: Arc<AppState>,
|
state: Arc<AppState>,
|
||||||
req: Request<Body>,
|
req: Request<Body>,
|
||||||
@@ -181,15 +190,17 @@ async fn handle_put_chunk(
|
|||||||
return Err(AppError::bad_request("Missing chunk name"));
|
return Err(AppError::bad_request("Missing chunk name"));
|
||||||
}
|
}
|
||||||
|
|
||||||
let max_upload = state.core.config.storage.max_upload_size;
|
let chunk_path = nc
|
||||||
let body_bytes = body::to_bytes(req.into_body(), max_upload)
|
.chunked_uploads
|
||||||
.await
|
.safe_chunk_path(&user.username, upload_id, chunk_name)
|
||||||
.map_err(|e| AppError::bad_request(format!("Failed to read chunk body: {}", e)))?;
|
.map_err(|e| AppError::bad_request(format!("Invalid chunk path: {}", e)))?;
|
||||||
|
|
||||||
nc.chunked_uploads
|
let max_chunk = state.core.config.storage.chunk_max_bytes;
|
||||||
.store_chunk(&user.username, upload_id, chunk_name, &body_bytes)
|
// No client-side integrity contract on the NC chunked surface — the
|
||||||
.await
|
// NC desktop client validates the assembled-file ETag against the
|
||||||
.map_err(|e| AppError::internal_error(format!("Failed to store chunk: {}", e)))?;
|
// server-side `oc:checksums` after MOVE. So we skip per-chunk
|
||||||
|
// hashing here (peak heap stays at ~one HTTP frame).
|
||||||
|
stream_body_to_path(req.into_body(), &chunk_path, max_chunk, None).await?;
|
||||||
|
|
||||||
Ok(Response::builder()
|
Ok(Response::builder()
|
||||||
.status(StatusCode::CREATED)
|
.status(StatusCode::CREATED)
|
||||||
@@ -228,8 +239,12 @@ async fn handle_assemble(
|
|||||||
let dest_subpath = extract_files_subpath(&destination, &user.username)
|
let dest_subpath = extract_files_subpath(&destination, &user.username)
|
||||||
.ok_or_else(|| AppError::bad_request("Invalid Destination URL"))?;
|
.ok_or_else(|| AppError::bad_request("Invalid Destination URL"))?;
|
||||||
|
|
||||||
// Assemble chunks into a temp file (no full-file buffering in RAM).
|
// Assemble chunks into a temp file with hash-on-write (BLAKE3 computed
|
||||||
let (temp_path, size) = nc
|
// during the same read/write loop that copies chunks into the
|
||||||
|
// assembled file). The hash is passed downstream as `pre_computed_hash`
|
||||||
|
// so the dedup layer never re-reads the assembled file just to compute
|
||||||
|
// it — saves one full file-sized read pass per upload.
|
||||||
|
let (temp_path, size, blake3_hash) = nc
|
||||||
.chunked_uploads
|
.chunked_uploads
|
||||||
.assemble(&user.username, upload_id)
|
.assemble(&user.username, upload_id)
|
||||||
.await
|
.await
|
||||||
@@ -238,6 +253,7 @@ async fn handle_assemble(
|
|||||||
// Write assembled file to storage via the upload service.
|
// Write assembled file to storage via the upload service.
|
||||||
let upload_service = &state.applications.file_upload_service;
|
let upload_service = &state.applications.file_upload_service;
|
||||||
let file_service = &state.applications.file_retrieval_service;
|
let file_service = &state.applications.file_retrieval_service;
|
||||||
|
let folder_service = &state.applications.folder_service;
|
||||||
|
|
||||||
let internal_path = format!(
|
let internal_path = format!(
|
||||||
"My Folder - {}/{}",
|
"My Folder - {}/{}",
|
||||||
@@ -260,7 +276,7 @@ async fn handle_assemble(
|
|||||||
&temp_path,
|
&temp_path,
|
||||||
size,
|
size,
|
||||||
&content_type,
|
&content_type,
|
||||||
None,
|
Some(blake3_hash.clone()),
|
||||||
oc_mtime,
|
oc_mtime,
|
||||||
)
|
)
|
||||||
.await
|
.await
|
||||||
@@ -268,11 +284,12 @@ async fn handle_assemble(
|
|||||||
|
|
||||||
Some(dto.etag)
|
Some(dto.etag)
|
||||||
} else {
|
} else {
|
||||||
// For new files we still need to read the temp file since create_file takes &[u8].
|
// New-file branch: resolve the parent folder by path and pass the
|
||||||
let assembled = tokio::fs::read(&temp_path).await.map_err(|e| {
|
// assembled file's path directly to `upload_file_from_path` so the
|
||||||
AppError::internal_error(format!("Failed to read assembled file: {}", e))
|
// bytes never get read back into RAM. Previously this branch did
|
||||||
})?;
|
// `tokio::fs::read(&temp_path)` — an extra full file-sized read
|
||||||
|
// pass AND a peak-RAM allocation equal to the upload size, which
|
||||||
|
// defeated the streaming model on large NC uploads.
|
||||||
let (parent_sub, filename) = match dest_subpath.rsplit_once('/') {
|
let (parent_sub, filename) = match dest_subpath.rsplit_once('/') {
|
||||||
Some((p, n)) => (p, n),
|
Some((p, n)) => (p, n),
|
||||||
None => ("", dest_subpath.as_str()),
|
None => ("", dest_subpath.as_str()),
|
||||||
@@ -284,8 +301,20 @@ async fn handle_assemble(
|
|||||||
);
|
);
|
||||||
let parent_internal = parent_internal.trim_end_matches('/');
|
let parent_internal = parent_internal.trim_end_matches('/');
|
||||||
|
|
||||||
|
use crate::application::ports::folder_ports::FolderUseCase;
|
||||||
|
let parent_folder = folder_service
|
||||||
|
.get_folder_by_path(parent_internal)
|
||||||
|
.await
|
||||||
|
.map_err(|e| AppError::internal_error(format!("Parent folder lookup failed: {}", e)))?;
|
||||||
|
|
||||||
let dto = upload_service
|
let dto = upload_service
|
||||||
.create_file(parent_internal, filename, &assembled, &content_type)
|
.upload_file_from_path(
|
||||||
|
filename.to_string(),
|
||||||
|
Some(parent_folder.id),
|
||||||
|
content_type.to_string(),
|
||||||
|
&temp_path,
|
||||||
|
Some(blake3_hash),
|
||||||
|
)
|
||||||
.await
|
.await
|
||||||
.map_err(|e| AppError::internal_error(format!("Failed to create file: {}", e)))?;
|
.map_err(|e| AppError::internal_error(format!("Failed to create file: {}", e)))?;
|
||||||
|
|
||||||
|
|||||||
@@ -596,7 +596,14 @@ async fn handle_put(
|
|||||||
.and_then(|v| v.to_str().ok())
|
.and_then(|v| v.to_str().ok())
|
||||||
.and_then(|v| v.parse::<i64>().ok());
|
.and_then(|v| v.parse::<i64>().ok());
|
||||||
|
|
||||||
let max_upload = state.core.config.storage.max_upload_size;
|
// ── Direct PUT cap ───────────────────────────────────────────────
|
||||||
|
// We use `direct_put_max_bytes` (default 1 GiB), not `max_upload_size`
|
||||||
|
// (default 10 GB). Larger files must come through the chunked upload
|
||||||
|
// protocol (`/dav/uploads/...`) which is resumable on failure and
|
||||||
|
// bounded per-request by `chunk_max_bytes`. Trying to stream a
|
||||||
|
// multi-GB body through a single PUT is a footgun: a connection drop
|
||||||
|
// at 95 % loses everything.
|
||||||
|
let max_upload = state.core.config.storage.direct_put_max_bytes;
|
||||||
|
|
||||||
// Stream the body to a temp file + incremental hash — never buffer the
|
// Stream the body to a temp file + incremental hash — never buffer the
|
||||||
// full upload in RAM. The old `body::to_bytes` path loaded the entire
|
// full upload in RAM. The old `body::to_bytes` path loaded the entire
|
||||||
|
|||||||
@@ -6,14 +6,21 @@
|
|||||||
//! file (off tmpfs when [`StorageConfig::upload_temp_dir`] is configured) and
|
//! file (off tmpfs when [`StorageConfig::upload_temp_dir`] is configured) and
|
||||||
//! BLAKE3-hashed on the fly so the dedup layer can short-circuit on a hit.
|
//! BLAKE3-hashed on the fly so the dedup layer can short-circuit on a hit.
|
||||||
|
|
||||||
use std::path::PathBuf;
|
use std::path::{Path, PathBuf};
|
||||||
|
|
||||||
use axum::body::Body;
|
use axum::body::Body;
|
||||||
use http_body_util::BodyStream;
|
use http_body_util::BodyStream;
|
||||||
|
// The `Digest` trait (re-exported by both `md5` and `sha2` from the
|
||||||
|
// `digest` crate) gives `Md5` and `Sha256` their `new` / `update` /
|
||||||
|
// `finalize` methods. Importing once via `sha2` covers both —
|
||||||
|
// otherwise every call site would need fully-qualified
|
||||||
|
// `<md5::Md5 as md5::Digest>::…` syntax.
|
||||||
|
use sha2::Digest as _;
|
||||||
use tempfile::NamedTempFile;
|
use tempfile::NamedTempFile;
|
||||||
use tokio::io::AsyncWriteExt;
|
use tokio::io::AsyncWriteExt;
|
||||||
use tokio_stream::StreamExt;
|
use tokio_stream::StreamExt;
|
||||||
|
|
||||||
|
use crate::application::ports::chunked_upload_ports::ChecksumAlg;
|
||||||
use crate::common::temp::new_spool_temp_file;
|
use crate::common::temp::new_spool_temp_file;
|
||||||
use crate::interfaces::errors::AppError;
|
use crate::interfaces::errors::AppError;
|
||||||
|
|
||||||
@@ -63,7 +70,10 @@ pub async fn spool_body_to_temp(
|
|||||||
drop(file);
|
drop(file);
|
||||||
let _ = tokio::fs::remove_file(&temp_path).await;
|
let _ = tokio::fs::remove_file(&temp_path).await;
|
||||||
return Err(AppError::payload_too_large(format!(
|
return Err(AppError::payload_too_large(format!(
|
||||||
"Upload exceeds maximum size of {max_upload} bytes"
|
"Upload body exceeds the direct-PUT cap ({max_upload} bytes). \
|
||||||
|
Use the chunked-upload protocol (REST: `/api/uploads/...`, \
|
||||||
|
NextCloud: `/remote.php/dav/uploads/...`) for files larger than this. \
|
||||||
|
Chunked uploads are resumable on transient failure."
|
||||||
)));
|
)));
|
||||||
}
|
}
|
||||||
hasher.update(chunk);
|
hasher.update(chunk);
|
||||||
@@ -84,3 +94,196 @@ pub async fn spool_body_to_temp(
|
|||||||
size: total_bytes as u64,
|
size: total_bytes as u64,
|
||||||
})
|
})
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/// Result of a streamed write to a caller-supplied path.
|
||||||
|
pub struct StreamedToPath {
|
||||||
|
/// Total bytes written.
|
||||||
|
pub bytes_written: u64,
|
||||||
|
/// Lowercase hex digest, populated only when `checksum_alg=Some(_)`
|
||||||
|
/// was passed. The algorithm is identified by [`StreamedToPath::alg`].
|
||||||
|
pub checksum_hex: Option<String>,
|
||||||
|
/// Algorithm used to compute `checksum_hex`. Echoed back so the
|
||||||
|
/// caller can include it in audit logs or response headers.
|
||||||
|
pub alg: Option<ChecksumAlg>,
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Stream an HTTP request body directly to a known destination file,
|
||||||
|
/// enforcing `max_bytes` as a hard size limit.
|
||||||
|
///
|
||||||
|
/// Used by the chunked-upload PUT handlers — each chunk has a
|
||||||
|
/// deterministic on-disk path (`NextcloudChunkedUploadService::safe_chunk_path`
|
||||||
|
/// for the NC surface, `ChunkedUploadService::prepare_chunk` for the
|
||||||
|
/// REST surface), so there's no spool/move dance. Peak heap is ~one
|
||||||
|
/// HTTP frame regardless of chunk size or `max_bytes`.
|
||||||
|
///
|
||||||
|
/// `checksum_alg` is the optional client-requested integrity check
|
||||||
|
/// (default `md5` per the legacy `Content-MD5` contract; `blake3`
|
||||||
|
/// available for forward-compat). When `Some`, the hash is computed
|
||||||
|
/// incrementally during streaming — no extra disk read for verification.
|
||||||
|
///
|
||||||
|
/// On size overflow the partial file is removed before the function
|
||||||
|
/// returns, so a client retry against the same chunk name starts from
|
||||||
|
/// a clean slate. On any other I/O error the partial file is also
|
||||||
|
/// removed and the error surfaces — callers can assume the path is
|
||||||
|
/// either fully written or absent.
|
||||||
|
pub async fn stream_body_to_path(
|
||||||
|
body: Body,
|
||||||
|
path: &Path,
|
||||||
|
max_bytes: usize,
|
||||||
|
checksum_alg: Option<ChecksumAlg>,
|
||||||
|
) -> Result<StreamedToPath, AppError> {
|
||||||
|
let mut file = tokio::fs::File::create(path)
|
||||||
|
.await
|
||||||
|
.map_err(|e| AppError::internal_error(format!("Failed to open chunk file: {e}")))?;
|
||||||
|
|
||||||
|
let mut total_bytes: usize = 0;
|
||||||
|
let mut stream = BodyStream::new(body);
|
||||||
|
let mut hasher = checksum_alg.map(IncrementalHasher::new);
|
||||||
|
|
||||||
|
while let Some(frame_result) = stream.next().await {
|
||||||
|
let frame = match frame_result {
|
||||||
|
Ok(f) => f,
|
||||||
|
Err(e) => {
|
||||||
|
drop(file);
|
||||||
|
let _ = tokio::fs::remove_file(path).await;
|
||||||
|
return Err(AppError::bad_request(format!(
|
||||||
|
"Failed to read request body: {e}"
|
||||||
|
)));
|
||||||
|
}
|
||||||
|
};
|
||||||
|
if let Some(chunk) = frame.data_ref() {
|
||||||
|
total_bytes += chunk.len();
|
||||||
|
if total_bytes > max_bytes {
|
||||||
|
drop(file);
|
||||||
|
let _ = tokio::fs::remove_file(path).await;
|
||||||
|
return Err(AppError::payload_too_large(format!(
|
||||||
|
"Chunk exceeds maximum size of {max_bytes} bytes"
|
||||||
|
)));
|
||||||
|
}
|
||||||
|
if let Some(h) = hasher.as_mut() {
|
||||||
|
h.update(chunk);
|
||||||
|
}
|
||||||
|
if let Err(e) = file.write_all(chunk).await {
|
||||||
|
drop(file);
|
||||||
|
let _ = tokio::fs::remove_file(path).await;
|
||||||
|
return Err(AppError::internal_error(format!(
|
||||||
|
"Failed to write chunk: {e}"
|
||||||
|
)));
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
file.flush()
|
||||||
|
.await
|
||||||
|
.map_err(|e| AppError::internal_error(format!("Failed to flush chunk file: {e}")))?;
|
||||||
|
drop(file);
|
||||||
|
|
||||||
|
Ok(StreamedToPath {
|
||||||
|
bytes_written: total_bytes as u64,
|
||||||
|
checksum_hex: hasher.map(IncrementalHasher::finalize_hex),
|
||||||
|
alg: checksum_alg,
|
||||||
|
})
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Algorithm-agnostic incremental hasher used by [`stream_body_to_path`].
|
||||||
|
/// Per-frame `update` is sub-millisecond for all three algorithms at the
|
||||||
|
/// 64 KB frame sizes axum's body stream produces, so we don't need
|
||||||
|
/// `spawn_blocking` (which the old buffered path used because it hashed
|
||||||
|
/// the full multi-MB chunk in one shot).
|
||||||
|
enum IncrementalHasher {
|
||||||
|
Md5(md5::Md5),
|
||||||
|
Sha256(sha2::Sha256),
|
||||||
|
// Boxing — blake3::Hasher is ~1.7 KB on the stack while md5::Md5
|
||||||
|
// (~100 bytes) and sha2::Sha256 (~100 bytes) are tiny; boxing the
|
||||||
|
// outlier keeps the enum size proportional to the common case
|
||||||
|
// rather than the worst case.
|
||||||
|
Blake3(Box<blake3::Hasher>),
|
||||||
|
}
|
||||||
|
|
||||||
|
impl IncrementalHasher {
|
||||||
|
fn new(alg: ChecksumAlg) -> Self {
|
||||||
|
match alg {
|
||||||
|
ChecksumAlg::Md5 => Self::Md5(md5::Md5::new()),
|
||||||
|
ChecksumAlg::Sha256 => Self::Sha256(sha2::Sha256::new()),
|
||||||
|
ChecksumAlg::Blake3 => Self::Blake3(Box::new(blake3::Hasher::new())),
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
fn update(&mut self, bytes: &[u8]) {
|
||||||
|
match self {
|
||||||
|
Self::Md5(h) => h.update(bytes),
|
||||||
|
Self::Sha256(h) => h.update(bytes),
|
||||||
|
Self::Blake3(h) => {
|
||||||
|
h.update(bytes);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
fn finalize_hex(self) -> String {
|
||||||
|
match self {
|
||||||
|
Self::Md5(h) => h.finalize().iter().map(|b| format!("{b:02x}")).collect(),
|
||||||
|
Self::Sha256(h) => h.finalize().iter().map(|b| format!("{b:02x}")).collect(),
|
||||||
|
Self::Blake3(h) => h.finalize().to_hex().to_string(),
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
#[cfg(test)]
|
||||||
|
mod tests {
|
||||||
|
use super::*;
|
||||||
|
use bytes::Bytes;
|
||||||
|
|
||||||
|
#[tokio::test]
|
||||||
|
async fn stream_body_to_path_caps_oversized() {
|
||||||
|
let temp_dir = tempfile::tempdir().expect("tempdir");
|
||||||
|
let path = temp_dir.path().join("chunk");
|
||||||
|
|
||||||
|
// 5 MiB body, 4 MiB cap → must reject.
|
||||||
|
let body = Body::from(Bytes::from(vec![0u8; 5 * 1024 * 1024]));
|
||||||
|
let result = stream_body_to_path(body, &path, 4 * 1024 * 1024, None).await;
|
||||||
|
assert!(
|
||||||
|
result.is_err(),
|
||||||
|
"expected PayloadTooLarge, got Ok(bytes_written={})",
|
||||||
|
result.ok().map(|r| r.bytes_written).unwrap_or(0)
|
||||||
|
);
|
||||||
|
// Partial file must be removed on rejection.
|
||||||
|
assert!(
|
||||||
|
!path.exists(),
|
||||||
|
"rejected chunk file should be removed, but {} still exists",
|
||||||
|
path.display()
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
#[tokio::test]
|
||||||
|
async fn stream_body_to_path_accepts_under_cap() {
|
||||||
|
let temp_dir = tempfile::tempdir().expect("tempdir");
|
||||||
|
let path = temp_dir.path().join("chunk");
|
||||||
|
|
||||||
|
let body = Body::from(Bytes::from(vec![1u8; 1024 * 1024])); // 1 MiB
|
||||||
|
let result = stream_body_to_path(body, &path, 4 * 1024 * 1024, None).await;
|
||||||
|
let outcome = result.expect("should succeed");
|
||||||
|
assert_eq!(outcome.bytes_written, 1024 * 1024);
|
||||||
|
assert!(outcome.checksum_hex.is_none(), "no alg requested → no hash");
|
||||||
|
assert!(path.exists());
|
||||||
|
}
|
||||||
|
|
||||||
|
#[tokio::test]
|
||||||
|
async fn stream_body_to_path_caps_at_exact_boundary() {
|
||||||
|
// Edge case: body exactly equal to cap should succeed; cap+1 must fail.
|
||||||
|
let temp_dir = tempfile::tempdir().expect("tempdir");
|
||||||
|
let path = temp_dir.path().join("chunk");
|
||||||
|
|
||||||
|
let body = Body::from(Bytes::from(vec![1u8; 100]));
|
||||||
|
let outcome = stream_body_to_path(body, &path, 100, None)
|
||||||
|
.await
|
||||||
|
.expect("100 bytes at 100-byte cap should succeed");
|
||||||
|
assert_eq!(outcome.bytes_written, 100);
|
||||||
|
|
||||||
|
let path2 = temp_dir.path().join("chunk2");
|
||||||
|
let body = Body::from(Bytes::from(vec![1u8; 101]));
|
||||||
|
assert!(
|
||||||
|
stream_body_to_path(body, &path2, 100, None).await.is_err(),
|
||||||
|
"101 bytes at 100-byte cap must reject"
|
||||||
|
);
|
||||||
|
assert!(!path2.exists());
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|||||||
+12
@@ -143,6 +143,18 @@ async fn main() -> Result<(), Box<dyn std::error::Error>> {
|
|||||||
// Load configuration from environment variables
|
// Load configuration from environment variables
|
||||||
let config = common::config::AppConfig::from_env();
|
let config = common::config::AppConfig::from_env();
|
||||||
|
|
||||||
|
// Surface the upload-size limits at startup. Operators (and the
|
||||||
|
// CI runner) need to see what's actually in effect — a silent
|
||||||
|
// fallback to the 100 MB default when `OXICLOUD_CHUNK_MAX_BYTES`
|
||||||
|
// is mistyped or missing is the exact failure mode that's
|
||||||
|
// hardest to spot from chunked-upload tests.
|
||||||
|
tracing::info!(
|
||||||
|
max_upload_size_mb = config.storage.max_upload_size / (1024 * 1024),
|
||||||
|
direct_put_max_bytes_mb = config.storage.direct_put_max_bytes / (1024 * 1024),
|
||||||
|
chunk_max_bytes_mb = config.storage.chunk_max_bytes / (1024 * 1024),
|
||||||
|
"Upload limits loaded from config"
|
||||||
|
);
|
||||||
|
|
||||||
// Ensure storage and locales directories exist
|
// Ensure storage and locales directories exist
|
||||||
let storage_path = config.storage_path.clone();
|
let storage_path = config.storage_path.clone();
|
||||||
if !storage_path.exists() {
|
if !storage_path.exists() {
|
||||||
|
|||||||
@@ -0,0 +1,682 @@
|
|||||||
|
# =============================================================
|
||||||
|
# OxiCloud — Chunked upload size cap + streaming verification
|
||||||
|
# =============================================================
|
||||||
|
# Validates `storage.chunk_max_bytes` (env `OXICLOUD_CHUNK_MAX_BYTES`,
|
||||||
|
# set to 4 MiB by `tests/common/server.env`) on the REST chunked upload
|
||||||
|
# surface `/api/uploads/{id}`.
|
||||||
|
#
|
||||||
|
# Two scenarios:
|
||||||
|
# 1. SUCCESS path — uploads `hello.txt` (32 bytes) in one chunk and
|
||||||
|
# asserts the stored file's BLAKE3 matches the known hash of the
|
||||||
|
# fixture. Confirms streaming + assembly + dedup integrity.
|
||||||
|
# 2. CAP REJECTION — uploads `chunk-over-cap-5mb.bin` (5 MiB) which
|
||||||
|
# exceeds the 4 MiB cap, asserting the server returns 413 Payload
|
||||||
|
# Too Large instead of OOMing or silently truncating.
|
||||||
|
#
|
||||||
|
# Why REST chunked, not NC chunked: both surfaces share the same
|
||||||
|
# `chunk_max_bytes` config; the REST path is JWT-authed (already set
|
||||||
|
# up in this Hurl run), the NC path would require minting an app
|
||||||
|
# password mid-test.
|
||||||
|
# =============================================================
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 1 — Login and capture the JWT token
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/auth/login
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"username": "{{username}}",
|
||||||
|
"password": "{{password}}"
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 200
|
||||||
|
[Captures]
|
||||||
|
token: jsonpath "$.access_token"
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 2 — Resolve home folder id (single root folder for admin)
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
GET {{base_url}}/api/folders
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
|
||||||
|
HTTP 200
|
||||||
|
[Captures]
|
||||||
|
home_folder_id: jsonpath "$[0].id"
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 3 — Create chunked upload session for hello.txt (32 bytes)
|
||||||
|
# chunk_size = 1 MiB (server minimum is 1 MiB). With
|
||||||
|
# total_size < chunk_size the server computes a single
|
||||||
|
# chunk of `total_size` bytes for index 0.
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/uploads
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"filename": "chunked-cap-hello.txt",
|
||||||
|
"folder_id": "{{home_folder_id}}",
|
||||||
|
"content_type": "text/plain",
|
||||||
|
"total_size": 32,
|
||||||
|
"chunk_size": 1048576
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
[Captures]
|
||||||
|
upload_id_ok: jsonpath "$.upload_id"
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 4 — Upload the single 32-byte chunk → 200
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
PATCH {{base_url}}/api/uploads/{{upload_id_ok}}?chunk_index=0
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/octet-stream
|
||||||
|
file,fixtures/hello.txt;
|
||||||
|
|
||||||
|
HTTP 200
|
||||||
|
[Asserts]
|
||||||
|
header "Upload-Complete" == "true"
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 5 — Complete the upload → 201, capture file id
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/uploads/{{upload_id_ok}}/complete
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
[Captures]
|
||||||
|
file_id: jsonpath "$.file_id"
|
||||||
|
[Asserts]
|
||||||
|
jsonpath "$.filename" == "chunked-cap-hello.txt"
|
||||||
|
jsonpath "$.size" == 32
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 6 — Verify the stored file's BLAKE3 matches the known
|
||||||
|
# hash of `tests/fixtures/hello.txt`. This proves the
|
||||||
|
# streaming path wrote the exact bytes — no truncation,
|
||||||
|
# no buffering corruption, no off-by-one.
|
||||||
|
#
|
||||||
|
# Expected hash:
|
||||||
|
# b2208c5dc33ff951227bd0c139f5eccb04105d6da6a7519ee23f7bc00a17bb5a
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
GET {{base_url}}/api/files?folder_id={{home_folder_id}}
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
|
||||||
|
HTTP 200
|
||||||
|
[Asserts]
|
||||||
|
jsonpath "$[?(@.id == '{{file_id}}')].content_hash" == "b2208c5dc33ff951227bd0c139f5eccb04105d6da6a7519ee23f7bc00a17bb5a"
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 7 — CAP REJECTION: create a session declaring a 5 MiB
|
||||||
|
# chunk and attempt to upload exactly 5 MiB → 413.
|
||||||
|
#
|
||||||
|
# The cap fires in `axum::body::to_bytes(req, max_chunk)`
|
||||||
|
# BEFORE the inner chunk-size check, so the server never
|
||||||
|
# materialises the full 5 MiB body in memory.
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/uploads
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"filename": "chunked-cap-over.bin",
|
||||||
|
"folder_id": "{{home_folder_id}}",
|
||||||
|
"content_type": "application/octet-stream",
|
||||||
|
"total_size": 5242880,
|
||||||
|
"chunk_size": 5242880
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
[Captures]
|
||||||
|
upload_id_big: jsonpath "$.upload_id"
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 8 — Send a 5 MiB chunk → 413 (cap is 4 MiB).
|
||||||
|
# Pre-fix this PATCH would either OOM the server or be
|
||||||
|
# silently treated as an empty body (via the old
|
||||||
|
# `to_bytes(.., usize::MAX).unwrap_or_default()` path).
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
PATCH {{base_url}}/api/uploads/{{upload_id_big}}?chunk_index=0
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/octet-stream
|
||||||
|
file,fixtures/chunk-over-cap-5mb.bin;
|
||||||
|
|
||||||
|
HTTP 413
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 9 — Clean up the abandoned over-cap session.
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
DELETE {{base_url}}/api/uploads/{{upload_id_big}}
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
|
||||||
|
HTTP 204
|
||||||
|
|
||||||
|
|
||||||
|
# ═════════════════════════════════════════════════════════════
|
||||||
|
# Checksum verification scenarios
|
||||||
|
# ═════════════════════════════════════════════════════════════
|
||||||
|
# `?checksum=<hex>&checksumalg=<name>` (default md5 if alg
|
||||||
|
# omitted, preserving the legacy `Content-MD5` contract). All
|
||||||
|
# three algorithms compute incrementally during the streaming
|
||||||
|
# write — zero extra disk reads. Known hashes of hello.txt:
|
||||||
|
# md5: f02bc35b153756ad11e07885cd86cbcf
|
||||||
|
# sha256: 0237134783df857fd9634c004341dbfccd374be0a1dd3c08e257522fa4d44e20
|
||||||
|
# blake3: b2208c5dc33ff951227bd0c139f5eccb04105d6da6a7519ee23f7bc00a17bb5a
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 10 — MD5 (default alg, no `checksumalg` param).
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/uploads
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"filename": "chunked-cap-md5.txt",
|
||||||
|
"folder_id": "{{home_folder_id}}",
|
||||||
|
"content_type": "text/plain",
|
||||||
|
"total_size": 32,
|
||||||
|
"chunk_size": 1048576
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
[Captures]
|
||||||
|
upload_id_md5: jsonpath "$.upload_id"
|
||||||
|
|
||||||
|
PATCH {{base_url}}/api/uploads/{{upload_id_md5}}?chunk_index=0&checksum=f02bc35b153756ad11e07885cd86cbcf
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/octet-stream
|
||||||
|
file,fixtures/hello.txt;
|
||||||
|
|
||||||
|
HTTP 200
|
||||||
|
|
||||||
|
POST {{base_url}}/api/uploads/{{upload_id_md5}}/complete
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 11 — SHA-256 (`?checksumalg=sha256`).
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/uploads
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"filename": "chunked-cap-sha256.txt",
|
||||||
|
"folder_id": "{{home_folder_id}}",
|
||||||
|
"content_type": "text/plain",
|
||||||
|
"total_size": 32,
|
||||||
|
"chunk_size": 1048576
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
[Captures]
|
||||||
|
upload_id_sha: jsonpath "$.upload_id"
|
||||||
|
|
||||||
|
PATCH {{base_url}}/api/uploads/{{upload_id_sha}}?chunk_index=0&checksum=0237134783df857fd9634c004341dbfccd374be0a1dd3c08e257522fa4d44e20&checksumalg=sha256
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/octet-stream
|
||||||
|
file,fixtures/hello.txt;
|
||||||
|
|
||||||
|
HTTP 200
|
||||||
|
|
||||||
|
POST {{base_url}}/api/uploads/{{upload_id_sha}}/complete
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 12 — BLAKE3 (`?checksumalg=blake3`). Same algorithm the
|
||||||
|
# blob-storage layer uses for dedup, so the chunk-level
|
||||||
|
# hash and the assembled-file hash are comparable.
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/uploads
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"filename": "chunked-cap-blake3.txt",
|
||||||
|
"folder_id": "{{home_folder_id}}",
|
||||||
|
"content_type": "text/plain",
|
||||||
|
"total_size": 32,
|
||||||
|
"chunk_size": 1048576
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
[Captures]
|
||||||
|
upload_id_blake3: jsonpath "$.upload_id"
|
||||||
|
|
||||||
|
PATCH {{base_url}}/api/uploads/{{upload_id_blake3}}?chunk_index=0&checksum=b2208c5dc33ff951227bd0c139f5eccb04105d6da6a7519ee23f7bc00a17bb5a&checksumalg=blake3
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/octet-stream
|
||||||
|
file,fixtures/hello.txt;
|
||||||
|
|
||||||
|
HTTP 200
|
||||||
|
|
||||||
|
POST {{base_url}}/api/uploads/{{upload_id_blake3}}/complete
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 13 — Checksum MISMATCH: send a chunk with a deliberately
|
||||||
|
# wrong MD5. `commit_chunk` must reject (the chunk
|
||||||
|
# file is removed in the same path so a retry against
|
||||||
|
# the same index starts clean).
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/uploads
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"filename": "chunked-cap-badmd5.txt",
|
||||||
|
"folder_id": "{{home_folder_id}}",
|
||||||
|
"content_type": "text/plain",
|
||||||
|
"total_size": 32,
|
||||||
|
"chunk_size": 1048576
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
[Captures]
|
||||||
|
upload_id_bad: jsonpath "$.upload_id"
|
||||||
|
|
||||||
|
PATCH {{base_url}}/api/uploads/{{upload_id_bad}}?chunk_index=0&checksum=00000000000000000000000000000000
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/octet-stream
|
||||||
|
file,fixtures/hello.txt;
|
||||||
|
|
||||||
|
HTTP 400
|
||||||
|
|
||||||
|
DELETE {{base_url}}/api/uploads/{{upload_id_bad}}
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
|
||||||
|
HTTP 204
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 14 — Unknown checksumalg → 400 BadRequest with the
|
||||||
|
# offending value echoed back. Guards against a typo
|
||||||
|
# silently disabling integrity verification.
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/uploads
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"filename": "chunked-cap-badalg.txt",
|
||||||
|
"folder_id": "{{home_folder_id}}",
|
||||||
|
"content_type": "text/plain",
|
||||||
|
"total_size": 32,
|
||||||
|
"chunk_size": 1048576
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
[Captures]
|
||||||
|
upload_id_badalg: jsonpath "$.upload_id"
|
||||||
|
|
||||||
|
PATCH {{base_url}}/api/uploads/{{upload_id_badalg}}?chunk_index=0&checksum=deadbeef&checksumalg=zoiberg
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/octet-stream
|
||||||
|
file,fixtures/hello.txt;
|
||||||
|
|
||||||
|
HTTP 400
|
||||||
|
|
||||||
|
DELETE {{base_url}}/api/uploads/{{upload_id_badalg}}
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
|
||||||
|
HTTP 204
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 15 — Size MISMATCH: declare chunk_size 32, send 4 bytes.
|
||||||
|
# Streaming write succeeds; `commit_chunk` rejects on
|
||||||
|
# the size check, removes the partial file.
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/uploads
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"filename": "chunked-cap-shortbody.txt",
|
||||||
|
"folder_id": "{{home_folder_id}}",
|
||||||
|
"content_type": "text/plain",
|
||||||
|
"total_size": 32,
|
||||||
|
"chunk_size": 1048576
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
[Captures]
|
||||||
|
upload_id_short: jsonpath "$.upload_id"
|
||||||
|
|
||||||
|
PATCH {{base_url}}/api/uploads/{{upload_id_short}}?chunk_index=0
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/octet-stream
|
||||||
|
base64,aGFsdA==;
|
||||||
|
|
||||||
|
HTTP 400
|
||||||
|
|
||||||
|
DELETE {{base_url}}/api/uploads/{{upload_id_short}}
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
|
||||||
|
HTTP 204
|
||||||
|
|
||||||
|
|
||||||
|
# ═════════════════════════════════════════════════════════════
|
||||||
|
# End-to-end checksum on `/complete`
|
||||||
|
# ═════════════════════════════════════════════════════════════
|
||||||
|
# Optional body `{checksum, checksumalg}` on the complete request
|
||||||
|
# lets the client lock in end-to-end integrity: if the assembled
|
||||||
|
# file's hash doesn't match the value the client expected, the
|
||||||
|
# blob is NOT promoted to storage and no DB row is created.
|
||||||
|
# `blake3` is the recommended algorithm — same one the server
|
||||||
|
# computes during hash-on-write assembly, so verification costs
|
||||||
|
# nothing extra.
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 16 — `/complete` with matching BLAKE3 → 201.
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/uploads
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"filename": "complete-blake3-ok.txt",
|
||||||
|
"folder_id": "{{home_folder_id}}",
|
||||||
|
"content_type": "text/plain",
|
||||||
|
"total_size": 32,
|
||||||
|
"chunk_size": 1048576
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
[Captures]
|
||||||
|
upload_id_b3_ok: jsonpath "$.upload_id"
|
||||||
|
|
||||||
|
PATCH {{base_url}}/api/uploads/{{upload_id_b3_ok}}?chunk_index=0
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/octet-stream
|
||||||
|
file,fixtures/hello.txt;
|
||||||
|
|
||||||
|
HTTP 200
|
||||||
|
|
||||||
|
POST {{base_url}}/api/uploads/{{upload_id_b3_ok}}/complete
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"checksum": "b2208c5dc33ff951227bd0c139f5eccb04105d6da6a7519ee23f7bc00a17bb5a",
|
||||||
|
"checksumalg": "blake3"
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 17 — `/complete` with matching SHA-256 → 201 (re-hashes
|
||||||
|
# the assembled file on the blocking pool).
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/uploads
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"filename": "complete-sha256-ok.txt",
|
||||||
|
"folder_id": "{{home_folder_id}}",
|
||||||
|
"content_type": "text/plain",
|
||||||
|
"total_size": 32,
|
||||||
|
"chunk_size": 1048576
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
[Captures]
|
||||||
|
upload_id_sha_ok: jsonpath "$.upload_id"
|
||||||
|
|
||||||
|
PATCH {{base_url}}/api/uploads/{{upload_id_sha_ok}}?chunk_index=0
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/octet-stream
|
||||||
|
file,fixtures/hello.txt;
|
||||||
|
|
||||||
|
HTTP 200
|
||||||
|
|
||||||
|
POST {{base_url}}/api/uploads/{{upload_id_sha_ok}}/complete
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"checksum": "0237134783df857fd9634c004341dbfccd374be0a1dd3c08e257522fa4d44e20",
|
||||||
|
"checksumalg": "sha256"
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 18 — `/complete` with MISMATCHED BLAKE3 → 400. Blob is
|
||||||
|
# NOT promoted; session stays open for retry.
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/uploads
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"filename": "complete-blake3-bad.txt",
|
||||||
|
"folder_id": "{{home_folder_id}}",
|
||||||
|
"content_type": "text/plain",
|
||||||
|
"total_size": 32,
|
||||||
|
"chunk_size": 1048576
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
[Captures]
|
||||||
|
upload_id_b3_bad: jsonpath "$.upload_id"
|
||||||
|
|
||||||
|
PATCH {{base_url}}/api/uploads/{{upload_id_b3_bad}}?chunk_index=0
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/octet-stream
|
||||||
|
file,fixtures/hello.txt;
|
||||||
|
|
||||||
|
HTTP 200
|
||||||
|
|
||||||
|
POST {{base_url}}/api/uploads/{{upload_id_b3_bad}}/complete
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"checksum": "00000000000000000000000000000000000000000000000000000000deadbeef",
|
||||||
|
"checksumalg": "blake3"
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 400
|
||||||
|
|
||||||
|
DELETE {{base_url}}/api/uploads/{{upload_id_b3_bad}}
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
|
||||||
|
HTTP 204
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 19 — `/complete` with unknown `checksumalg` → 400.
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/uploads
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"filename": "complete-badalg.txt",
|
||||||
|
"folder_id": "{{home_folder_id}}",
|
||||||
|
"content_type": "text/plain",
|
||||||
|
"total_size": 32,
|
||||||
|
"chunk_size": 1048576
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
[Captures]
|
||||||
|
upload_id_c_badalg: jsonpath "$.upload_id"
|
||||||
|
|
||||||
|
PATCH {{base_url}}/api/uploads/{{upload_id_c_badalg}}?chunk_index=0
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/octet-stream
|
||||||
|
file,fixtures/hello.txt;
|
||||||
|
|
||||||
|
HTTP 200
|
||||||
|
|
||||||
|
POST {{base_url}}/api/uploads/{{upload_id_c_badalg}}/complete
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"checksum": "deadbeef",
|
||||||
|
"checksumalg": "zoiberg"
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 400
|
||||||
|
|
||||||
|
DELETE {{base_url}}/api/uploads/{{upload_id_c_badalg}}
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
|
||||||
|
HTTP 204
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 20 — `/complete` with NO body → 201 (backwards-compat).
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/uploads
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"filename": "complete-nobody.txt",
|
||||||
|
"folder_id": "{{home_folder_id}}",
|
||||||
|
"content_type": "text/plain",
|
||||||
|
"total_size": 32,
|
||||||
|
"chunk_size": 1048576
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
[Captures]
|
||||||
|
upload_id_nobody: jsonpath "$.upload_id"
|
||||||
|
|
||||||
|
PATCH {{base_url}}/api/uploads/{{upload_id_nobody}}?chunk_index=0
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/octet-stream
|
||||||
|
file,fixtures/hello.txt;
|
||||||
|
|
||||||
|
HTTP 200
|
||||||
|
|
||||||
|
POST {{base_url}}/api/uploads/{{upload_id_nobody}}/complete
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
|
||||||
|
|
||||||
|
# ═════════════════════════════════════════════════════════════
|
||||||
|
# Whole-file size cap (OXICLOUD_MAX_UPLOAD_SIZE)
|
||||||
|
# ═════════════════════════════════════════════════════════════
|
||||||
|
# The whole-file cap is checked at session creation against the
|
||||||
|
# JSON-declared `total_size` — no upload body required to trip
|
||||||
|
# it. Test default `OXICLOUD_MAX_UPLOAD_SIZE` is 10 GiB; we
|
||||||
|
# declare 100 GiB to be safely above without bothering with a
|
||||||
|
# Hurl `--variables` override.
|
||||||
|
#
|
||||||
|
# This guards the case where chunks would otherwise accumulate
|
||||||
|
# disk space against an oversized declared upload — the reject
|
||||||
|
# fires BEFORE any chunk is PATCHed.
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 21 — POST /api/uploads with `total_size` above
|
||||||
|
# OXICLOUD_MAX_UPLOAD_SIZE → 413 Payload Too Large.
|
||||||
|
# No body bytes are sent; the check is purely
|
||||||
|
# against the declared JSON field.
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/uploads
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"filename": "way-too-big.bin",
|
||||||
|
"folder_id": "{{home_folder_id}}",
|
||||||
|
"content_type": "application/octet-stream",
|
||||||
|
"total_size": 107374182400,
|
||||||
|
"chunk_size": 5242880
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 413
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 22 — Sanity check: a session JUST BELOW the cap is
|
||||||
|
# accepted. Uses a sub-cap value (32 bytes — same
|
||||||
|
# pattern as earlier steps so no extra fixture is
|
||||||
|
# needed). Confirms that the reject in step 21 was
|
||||||
|
# the size cap, not an unrelated regression.
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
POST {{base_url}}/api/uploads
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/json
|
||||||
|
{
|
||||||
|
"filename": "small-and-fine.txt",
|
||||||
|
"folder_id": "{{home_folder_id}}",
|
||||||
|
"content_type": "text/plain",
|
||||||
|
"total_size": 32,
|
||||||
|
"chunk_size": 1048576
|
||||||
|
}
|
||||||
|
|
||||||
|
HTTP 201
|
||||||
|
[Captures]
|
||||||
|
upload_id_sanity: jsonpath "$.upload_id"
|
||||||
|
|
||||||
|
# Cleanup — cancel without uploading.
|
||||||
|
DELETE {{base_url}}/api/uploads/{{upload_id_sanity}}
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
|
||||||
|
HTTP 204
|
||||||
|
|
||||||
|
|
||||||
|
# ═════════════════════════════════════════════════════════════
|
||||||
|
# Direct-PUT body cap (OXICLOUD_DIRECT_PUT_MAX_BYTES)
|
||||||
|
# ═════════════════════════════════════════════════════════════
|
||||||
|
# `OXICLOUD_DIRECT_PUT_MAX_BYTES` (4 MiB in the test env) bounds
|
||||||
|
# a single non-chunked PUT body. Larger uploads must come through
|
||||||
|
# the chunked protocol — the server returns 413 with a hint
|
||||||
|
# pointing at `/api/uploads/...` / `/dav/uploads/...`. The cap
|
||||||
|
# fires mid-stream via the same accumulator that bounds chunks.
|
||||||
|
#
|
||||||
|
# Tested via the native REST WebDAV PUT endpoint (`/webdav/...`)
|
||||||
|
# because it's JWT-authed (no app-password mint dance) and
|
||||||
|
# straightforwardly path-mapped. The cap is wired into the same
|
||||||
|
# `spool_body_to_temp` helper from the NextCloud single-file PUT
|
||||||
|
# path, so this exercise covers both wirings.
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 23 — Direct PUT of the 5 MiB fixture → 413. The same
|
||||||
|
# fixture used in step 8 for the chunked-PATCH cap;
|
||||||
|
# here it lands against the direct-PUT cap.
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
PUT {{base_url}}/webdav/test-direct-put-over-cap.bin
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: application/octet-stream
|
||||||
|
file,fixtures/chunk-over-cap-5mb.bin;
|
||||||
|
|
||||||
|
HTTP 413
|
||||||
|
|
||||||
|
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
# Step 24 — Sanity: direct PUT WELL under the cap → 201 or 204.
|
||||||
|
# Confirms step 23's reject was the cap, not a route /
|
||||||
|
# auth / handler regression.
|
||||||
|
# ─────────────────────────────────────────────────────────────
|
||||||
|
PUT {{base_url}}/webdav/test-direct-put-under-cap.txt
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
Content-Type: text/plain
|
||||||
|
file,fixtures/hello.txt;
|
||||||
|
|
||||||
|
# WebDAV PUT returns 201 on new file, 204 on overwrite. Either
|
||||||
|
# value confirms a successful body acceptance.
|
||||||
|
HTTP *
|
||||||
|
[Asserts]
|
||||||
|
status >= 200
|
||||||
|
status < 300
|
||||||
|
|
||||||
|
# Cleanup so a re-run finds a clean slate (DELETE is idempotent
|
||||||
|
# enough for this — 204 on success, 404 if nothing left).
|
||||||
|
DELETE {{base_url}}/webdav/test-direct-put-under-cap.txt
|
||||||
|
Authorization: Bearer {{token}}
|
||||||
|
|
||||||
|
HTTP *
|
||||||
+14
-1
@@ -85,6 +85,18 @@ log "Waiting for server at $base_url..."
|
|||||||
wait_for_http "$base_url/ready" 120
|
wait_for_http "$base_url/ready" 120
|
||||||
log "Server is ready."
|
log "Server is ready."
|
||||||
|
|
||||||
|
# ── 3.5. Generate ephemeral test fixtures ─────────────────────────────────────
|
||||||
|
# chunked_upload_cap.hurl needs a body > OXICLOUD_CHUNK_MAX_BYTES (4 MiB) to
|
||||||
|
# trigger the 413. Committing a 5 MiB binary to the repo would bloat git for
|
||||||
|
# every clone; generating it at run time is reproducible and the file is in
|
||||||
|
# `.gitignore`.
|
||||||
|
|
||||||
|
OVER_CAP_FIXTURE="$REPO_ROOT/tests/fixtures/chunk-over-cap-5mb.bin"
|
||||||
|
if [[ ! -s "$OVER_CAP_FIXTURE" ]]; then
|
||||||
|
log "Generating 5 MiB fixture for chunk-cap test → $OVER_CAP_FIXTURE"
|
||||||
|
dd if=/dev/zero of="$OVER_CAP_FIXTURE" bs=1024 count=5120 status=none
|
||||||
|
fi
|
||||||
|
|
||||||
# ── 4. Run Hurl tests ─────────────────────────────────────────────────────────
|
# ── 4. Run Hurl tests ─────────────────────────────────────────────────────────
|
||||||
|
|
||||||
log "Running Hurl tests..."
|
log "Running Hurl tests..."
|
||||||
@@ -104,7 +116,8 @@ hurl --variables-file "$API_DIR/test.env" --file-root "$REPO_ROOT/tests" --test
|
|||||||
"$API_DIR/grants.hurl" \
|
"$API_DIR/grants.hurl" \
|
||||||
"$API_DIR/subject_groups.hurl" \
|
"$API_DIR/subject_groups.hurl" \
|
||||||
"$API_DIR/grants_nested_groups.hurl" \
|
"$API_DIR/grants_nested_groups.hurl" \
|
||||||
"$API_DIR/external_users.hurl"
|
"$API_DIR/external_users.hurl" \
|
||||||
|
"$API_DIR/chunked_upload_cap.hurl"
|
||||||
|
|
||||||
#bash "$API_DIR/dedup_bulk_upload.sh"
|
#bash "$API_DIR/dedup_bulk_upload.sh"
|
||||||
|
|
||||||
|
|||||||
@@ -22,6 +22,19 @@ RUST_LOG="warn,audit=info"
|
|||||||
#RUST_LOG=debug
|
#RUST_LOG=debug
|
||||||
#RUST_LOG=info
|
#RUST_LOG=info
|
||||||
|
|
||||||
|
# Per-chunk upload cap, exercised by chunked_upload_cap.hurl.
|
||||||
|
# 4 MiB: lets the existing grants.hurl single-chunk test (2.76 MB) pass
|
||||||
|
# under the cap, while the cap test sends a 5 MiB fixture to trigger 413.
|
||||||
|
OXICLOUD_CHUNK_MAX_BYTES=4194304
|
||||||
|
|
||||||
|
# Direct-PUT (non-chunked) cap, exercised by chunked_upload_cap.hurl.
|
||||||
|
# 4 MiB: same threshold as the chunked cap so the existing 5 MiB
|
||||||
|
# fixture (chunk-over-cap-5mb.bin) can prove BOTH caps with one
|
||||||
|
# generated file. All existing direct-PUT tests
|
||||||
|
# (test_dedup_webdav_multichunk.sh = 2.76 MB, _ref_count = ~66 KB,
|
||||||
|
# _nextcloud_put_blake3 = 32 B) stay safely under this cap.
|
||||||
|
OXICLOUD_DIRECT_PUT_MAX_BYTES=4194304
|
||||||
|
|
||||||
# grow up limits for tests
|
# grow up limits for tests
|
||||||
OXICLOUD_RATE_LIMIT_REFRESH_MAX=360
|
OXICLOUD_RATE_LIMIT_REFRESH_MAX=360
|
||||||
OXICLOUD_RATE_LIMIT_LOGIN_MAX=360
|
OXICLOUD_RATE_LIMIT_LOGIN_MAX=360
|
||||||
|
|||||||
+199
@@ -0,0 +1,199 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
# =============================================================
|
||||||
|
# OxiCloud — NextCloud chunked upload cap + streaming check
|
||||||
|
# =============================================================
|
||||||
|
# Validates the per-chunk `storage.chunk_max_bytes` cap on the
|
||||||
|
# NextCloud-compat chunked-upload surface (`/remote.php/dav/uploads/`),
|
||||||
|
# and round-trips a small file through MKCOL → PUT → MOVE to
|
||||||
|
# prove the streaming write at `handle_put_chunk` produces a
|
||||||
|
# byte-exact blob on disk.
|
||||||
|
#
|
||||||
|
# Sister test of `tests/api/chunked_upload_cap.hurl` (REST chunked).
|
||||||
|
# Both surfaces share the same `chunk_max_bytes` cap and the same
|
||||||
|
# `stream_body_to_path` helper; this test exercises the NC half:
|
||||||
|
# Basic Auth via app-password, WebDAV verbs, fewer protocol
|
||||||
|
# affordances than the REST API.
|
||||||
|
#
|
||||||
|
# Cases covered:
|
||||||
|
# 1. SUCCESS — MKCOL → PUT a single chunk (hello.txt, 32 B) →
|
||||||
|
# MOVE → verify the assembled file's BLAKE3 over REST.
|
||||||
|
# 2. CAP REJECTION — MKCOL a fresh session → PUT a 5 MiB chunk →
|
||||||
|
# 413 Payload Too Large.
|
||||||
|
#
|
||||||
|
# Prerequisites:
|
||||||
|
# - Server running at $base_url with admin credentials (test.env).
|
||||||
|
# - OXICLOUD_ENABLE_AUTH=true, OXICLOUD_NEXTCLOUD_ENABLED=true.
|
||||||
|
# - tests/fixtures/chunk-over-cap-5mb.bin generated by
|
||||||
|
# tests/api/run.sh (or by hand: dd if=/dev/zero of=… bs=1024 count=5120).
|
||||||
|
# - jq, dd, curl in PATH.
|
||||||
|
# =============================================================
|
||||||
|
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||||
|
REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
|
||||||
|
cd "$SCRIPT_DIR"
|
||||||
|
|
||||||
|
source test.env
|
||||||
|
source common.sh
|
||||||
|
|
||||||
|
# ── helpers ──────────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
PASS=0
|
||||||
|
FAIL=0
|
||||||
|
|
||||||
|
pass() { PASS=$(( PASS + 1 )); echo " PASS: $*"; }
|
||||||
|
fail() { FAIL=$(( FAIL + 1 )); echo " FAIL: $*" >&2; exit 1; }
|
||||||
|
|
||||||
|
rest_get() { curl -s -H "Authorization: Bearer $TOKEN" "$base_url$1"; }
|
||||||
|
rest_delete() { curl -s -o /dev/null -w "%{http_code}" -X DELETE -H "Authorization: Bearer $TOKEN" "$base_url$1"; }
|
||||||
|
|
||||||
|
purge_from_trash() {
|
||||||
|
local name="$1"
|
||||||
|
local tid
|
||||||
|
tid=$(rest_get "/api/trash" \
|
||||||
|
| jq -r --arg n "$name" 'first(.[] | select(.name == $n) | .id) // empty')
|
||||||
|
[[ -n "$tid" ]] && rest_delete "/api/trash/$tid" > /dev/null || true
|
||||||
|
}
|
||||||
|
|
||||||
|
# Helper: NC WebDAV request with Basic Auth, prints HTTP status.
|
||||||
|
nc_req() {
|
||||||
|
local method="$1" url="$2"
|
||||||
|
shift 2
|
||||||
|
curl -s -o /dev/null -w "%{http_code}" -X "$method" \
|
||||||
|
-u "$username:$APP_PASSWORD" \
|
||||||
|
"$@" \
|
||||||
|
"$base_url$url"
|
||||||
|
}
|
||||||
|
|
||||||
|
# ── fixtures ──────────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
FIXTURE_SMALL="$REPO_ROOT/tests/fixtures/hello.txt"
|
||||||
|
FIXTURE_BIG="$REPO_ROOT/tests/fixtures/chunk-over-cap-5mb.bin"
|
||||||
|
[[ -f "$FIXTURE_SMALL" ]] || { echo "Missing fixture: $FIXTURE_SMALL" >&2; exit 1; }
|
||||||
|
# Self-generate the 5 MiB fixture if absent — the Hurl runner
|
||||||
|
# (`tests/api/run.sh`) generates it for the REST cap test; this
|
||||||
|
# script may run standalone, so we don't depend on that runner
|
||||||
|
# having executed first.
|
||||||
|
if [[ ! -s "$FIXTURE_BIG" ]]; then
|
||||||
|
echo " Generating 5 MiB fixture → $FIXTURE_BIG"
|
||||||
|
dd if=/dev/zero of="$FIXTURE_BIG" bs=1024 count=5120 status=none
|
||||||
|
fi
|
||||||
|
|
||||||
|
# BLAKE3 of hello.txt (32 B). Asserted against `content_hash` in
|
||||||
|
# the file DTO after the round trip — proves streaming wrote the
|
||||||
|
# exact bytes with no truncation / off-by-one.
|
||||||
|
EXPECTED_BLAKE3="b2208c5dc33ff951227bd0c139f5eccb04105d6da6a7519ee23f7bc00a17bb5a"
|
||||||
|
|
||||||
|
REMOTE_NAME="nc-chunked-cap-test.txt"
|
||||||
|
UPLOAD_ID_OK="oxi-cap-ok-$(date +%s)"
|
||||||
|
UPLOAD_ID_BIG="oxi-cap-big-$(date +%s)"
|
||||||
|
|
||||||
|
echo
|
||||||
|
echo "=== NextCloud chunked upload: cap + streaming ==="
|
||||||
|
echo
|
||||||
|
|
||||||
|
# ── authenticate ──────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
oxicloud_login
|
||||||
|
|
||||||
|
# Mint an NC app password — NC endpoints use Basic Auth, not JWT.
|
||||||
|
APP_PASSWORD_RESPONSE=$(curl -s -X POST \
|
||||||
|
-H "Authorization: Bearer $TOKEN" \
|
||||||
|
-H "Content-Type: application/json" \
|
||||||
|
-d '{"label":"chunked-cap-test","scopes":"webdav"}' \
|
||||||
|
"$base_url/api/auth/app-passwords")
|
||||||
|
|
||||||
|
APP_PASSWORD=$(jq -r '.password' <<<"$APP_PASSWORD_RESPONSE")
|
||||||
|
APP_PASSWORD_ID=$(jq -r '.id' <<<"$APP_PASSWORD_RESPONSE")
|
||||||
|
[[ -n "$APP_PASSWORD" && "$APP_PASSWORD" != "null" ]] \
|
||||||
|
|| fail "Failed to mint NC app password: $APP_PASSWORD_RESPONSE"
|
||||||
|
echo " app password minted (id=$APP_PASSWORD_ID)"
|
||||||
|
|
||||||
|
# Clean up the app password when the script exits (success or fail).
|
||||||
|
trap '[[ -n "${APP_PASSWORD_ID:-}" ]] && rest_delete "/api/auth/app-passwords/$APP_PASSWORD_ID" > /dev/null || true' EXIT
|
||||||
|
|
||||||
|
# Idempotent cleanup of any leftover file from a previous failed run.
|
||||||
|
HOME_FOLDER_ID=$(rest_get "/api/folders" | jq -r '.[0].id')
|
||||||
|
EXISTING_ID=$(rest_get "/api/files?folder_id=$HOME_FOLDER_ID" \
|
||||||
|
| jq -r --arg n "$REMOTE_NAME" 'first(.[] | select(.name == $n) | .id) // empty')
|
||||||
|
if [[ -n "$EXISTING_ID" ]]; then
|
||||||
|
echo " cleaning up leftover $REMOTE_NAME (id=$EXISTING_ID)"
|
||||||
|
rest_delete "/api/files/$EXISTING_ID" > /dev/null
|
||||||
|
purge_from_trash "$REMOTE_NAME"
|
||||||
|
fi
|
||||||
|
|
||||||
|
# ── Case 1: SUCCESS path ──────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
echo
|
||||||
|
echo "[1/2] SUCCESS path — MKCOL → PUT → MOVE → verify BLAKE3"
|
||||||
|
|
||||||
|
# 1a. Create chunked-upload session.
|
||||||
|
STATUS=$(nc_req MKCOL "/remote.php/dav/uploads/$username/$UPLOAD_ID_OK")
|
||||||
|
[[ "$STATUS" =~ ^(201|204)$ ]] || fail "MKCOL upload session: got $STATUS, expected 201/204"
|
||||||
|
pass "MKCOL upload session (status=$STATUS)"
|
||||||
|
|
||||||
|
# 1b. PUT a single chunk (the whole 32-byte file).
|
||||||
|
STATUS=$(nc_req PUT \
|
||||||
|
"/remote.php/dav/uploads/$username/$UPLOAD_ID_OK/00001" \
|
||||||
|
-H "Content-Type: application/octet-stream" \
|
||||||
|
--data-binary "@$FIXTURE_SMALL")
|
||||||
|
[[ "$STATUS" == "201" ]] || fail "PUT chunk: got $STATUS, expected 201"
|
||||||
|
pass "PUT chunk (status=$STATUS)"
|
||||||
|
|
||||||
|
# 1c. MOVE to assemble into the final destination.
|
||||||
|
STATUS=$(nc_req MOVE \
|
||||||
|
"/remote.php/dav/uploads/$username/$UPLOAD_ID_OK/.file" \
|
||||||
|
-H "Destination: $base_url/remote.php/dav/files/$username/$REMOTE_NAME")
|
||||||
|
[[ "$STATUS" =~ ^(201|204)$ ]] || fail "MOVE assemble: got $STATUS, expected 201/204"
|
||||||
|
pass "MOVE assemble (status=$STATUS)"
|
||||||
|
|
||||||
|
# 1d. Verify the assembled file landed with the right BLAKE3.
|
||||||
|
ASSEMBLED=$(rest_get "/api/files?folder_id=$HOME_FOLDER_ID" \
|
||||||
|
| jq -r --arg n "$REMOTE_NAME" 'first(.[] | select(.name == $n))')
|
||||||
|
ACTUAL_HASH=$(jq -r '.content_hash' <<<"$ASSEMBLED")
|
||||||
|
ACTUAL_SIZE=$(jq -r '.size' <<<"$ASSEMBLED")
|
||||||
|
FILE_ID=$(jq -r '.id' <<<"$ASSEMBLED")
|
||||||
|
|
||||||
|
[[ "$ACTUAL_SIZE" == "32" ]] || fail "Assembled file size: got $ACTUAL_SIZE, expected 32"
|
||||||
|
[[ "$ACTUAL_HASH" == "$EXPECTED_BLAKE3" ]] \
|
||||||
|
|| fail "BLAKE3 mismatch: got $ACTUAL_HASH, expected $EXPECTED_BLAKE3"
|
||||||
|
pass "Assembled file size + BLAKE3 match fixture"
|
||||||
|
|
||||||
|
# 1e. Cleanup the assembled file so a re-run finds a clean slate.
|
||||||
|
rest_delete "/api/files/$FILE_ID" > /dev/null
|
||||||
|
purge_from_trash "$REMOTE_NAME"
|
||||||
|
|
||||||
|
# ── Case 2: CAP REJECTION ─────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
echo
|
||||||
|
echo "[2/2] CAP REJECTION — 5 MiB chunk on a 4 MiB cap → 413"
|
||||||
|
|
||||||
|
# 2a. Fresh session.
|
||||||
|
STATUS=$(nc_req MKCOL "/remote.php/dav/uploads/$username/$UPLOAD_ID_BIG")
|
||||||
|
[[ "$STATUS" =~ ^(201|204)$ ]] || fail "MKCOL over-cap session: got $STATUS"
|
||||||
|
pass "MKCOL over-cap session (status=$STATUS)"
|
||||||
|
|
||||||
|
# 2b. PUT a 5 MiB chunk → expect 413. Pre-fix this would either OOM
|
||||||
|
# the server (the body was buffered up to `max_upload_size`,
|
||||||
|
# which is the *whole-file* cap, multi-GB) or — depending on the
|
||||||
|
# code path — succeed silently and assemble a corrupted file.
|
||||||
|
STATUS=$(nc_req PUT \
|
||||||
|
"/remote.php/dav/uploads/$username/$UPLOAD_ID_BIG/00001" \
|
||||||
|
-H "Content-Type: application/octet-stream" \
|
||||||
|
--data-binary "@$FIXTURE_BIG")
|
||||||
|
[[ "$STATUS" == "413" ]] || fail "PUT over-cap chunk: got $STATUS, expected 413"
|
||||||
|
pass "PUT over-cap chunk rejected (status=$STATUS)"
|
||||||
|
|
||||||
|
# 2c. Abort the leftover session — the cap-rejected PUT removed the
|
||||||
|
# partial chunk file, but the session metadata is still in
|
||||||
|
# `chunked_uploads/`. DELETE on the session dir cleans it.
|
||||||
|
STATUS=$(nc_req DELETE "/remote.php/dav/uploads/$username/$UPLOAD_ID_BIG")
|
||||||
|
[[ "$STATUS" =~ ^(204|404)$ ]] || fail "DELETE abandoned session: got $STATUS"
|
||||||
|
pass "DELETE abandoned session (status=$STATUS)"
|
||||||
|
|
||||||
|
# ── summary ──────────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
echo
|
||||||
|
echo "=== NC chunked upload cap test: $PASS passed, $FAIL failed ==="
|
||||||
|
[[ "$FAIL" == "0" ]] || exit 1
|
||||||
Executable
+131
@@ -0,0 +1,131 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
# =============================================================
|
||||||
|
# OxiCloud — NextCloud single-file PUT BLAKE3 round-trip
|
||||||
|
# =============================================================
|
||||||
|
# Validates that the NextCloud single-file PUT surface
|
||||||
|
# (`PUT /remote.php/dav/files/{user}/{path}`) writes byte-exact
|
||||||
|
# content to blob storage. This is the spool-based streaming
|
||||||
|
# path in `nextcloud/webdav_handler::handle_put` — it streams
|
||||||
|
# the request body to a temp file via `spool_body_to_temp`
|
||||||
|
# (which also computes BLAKE3 on the fly), then promotes the
|
||||||
|
# blob into `.blobs/{prefix}/{hash}.blob`.
|
||||||
|
#
|
||||||
|
# Sister tests:
|
||||||
|
# - `test_nextcloud_chunked_upload_cap.sh` — NC chunked PUT
|
||||||
|
# (the `/dav/uploads/...` surface, which uses
|
||||||
|
# `stream_body_to_path` instead of `spool_body_to_temp`).
|
||||||
|
# - `test_dedup_webdav_multichunk.sh` — native `/webdav/...`
|
||||||
|
# PUT (different handler, same spool helper).
|
||||||
|
#
|
||||||
|
# Together these three pin BLAKE3 correctness on all three of
|
||||||
|
# OxiCloud's first-class file-write surfaces.
|
||||||
|
#
|
||||||
|
# Prerequisites:
|
||||||
|
# - Server running at $base_url with admin credentials.
|
||||||
|
# - OXICLOUD_ENABLE_AUTH=true, OXICLOUD_NEXTCLOUD_ENABLED=true.
|
||||||
|
# - jq, curl in PATH.
|
||||||
|
# =============================================================
|
||||||
|
|
||||||
|
set -euo pipefail
|
||||||
|
|
||||||
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||||
|
REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
|
||||||
|
cd "$SCRIPT_DIR"
|
||||||
|
|
||||||
|
source test.env
|
||||||
|
source common.sh
|
||||||
|
|
||||||
|
# ── helpers ──────────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
PASS=0
|
||||||
|
FAIL=0
|
||||||
|
|
||||||
|
pass() { PASS=$(( PASS + 1 )); echo " PASS: $*"; }
|
||||||
|
fail() { FAIL=$(( FAIL + 1 )); echo " FAIL: $*" >&2; exit 1; }
|
||||||
|
|
||||||
|
rest_get() { curl -s -H "Authorization: Bearer $TOKEN" "$base_url$1"; }
|
||||||
|
rest_delete() { curl -s -o /dev/null -w "%{http_code}" -X DELETE -H "Authorization: Bearer $TOKEN" "$base_url$1"; }
|
||||||
|
|
||||||
|
purge_from_trash() {
|
||||||
|
local name="$1"
|
||||||
|
local tid
|
||||||
|
tid=$(rest_get "/api/trash" \
|
||||||
|
| jq -r --arg n "$name" 'first(.[] | select(.name == $n) | .id) // empty')
|
||||||
|
[[ -n "$tid" ]] && rest_delete "/api/trash/$tid" > /dev/null || true
|
||||||
|
}
|
||||||
|
|
||||||
|
# ── fixture ──────────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
FIXTURE="$REPO_ROOT/tests/fixtures/hello.txt"
|
||||||
|
[[ -f "$FIXTURE" ]] || { echo "Missing fixture: $FIXTURE" >&2; exit 1; }
|
||||||
|
EXPECTED_BLAKE3="b2208c5dc33ff951227bd0c139f5eccb04105d6da6a7519ee23f7bc00a17bb5a"
|
||||||
|
EXPECTED_SIZE=32
|
||||||
|
REMOTE_NAME="nc-put-blake3-test.txt"
|
||||||
|
|
||||||
|
echo
|
||||||
|
echo "=== NC single-file PUT: BLAKE3 round-trip ==="
|
||||||
|
echo
|
||||||
|
|
||||||
|
# ── authenticate ─────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
oxicloud_login
|
||||||
|
|
||||||
|
APP_PASSWORD_RESPONSE=$(curl -s -X POST \
|
||||||
|
-H "Authorization: Bearer $TOKEN" \
|
||||||
|
-H "Content-Type: application/json" \
|
||||||
|
-d '{"label":"nc-put-blake3-test","scopes":"webdav"}' \
|
||||||
|
"$base_url/api/auth/app-passwords")
|
||||||
|
APP_PASSWORD=$(jq -r '.password' <<<"$APP_PASSWORD_RESPONSE")
|
||||||
|
APP_PASSWORD_ID=$(jq -r '.id' <<<"$APP_PASSWORD_RESPONSE")
|
||||||
|
[[ -n "$APP_PASSWORD" && "$APP_PASSWORD" != "null" ]] \
|
||||||
|
|| fail "Failed to mint NC app password: $APP_PASSWORD_RESPONSE"
|
||||||
|
|
||||||
|
trap '[[ -n "${APP_PASSWORD_ID:-}" ]] && rest_delete "/api/auth/app-passwords/$APP_PASSWORD_ID" > /dev/null || true' EXIT
|
||||||
|
|
||||||
|
# Idempotent cleanup of any leftover file.
|
||||||
|
HOME_FOLDER_ID=$(rest_get "/api/folders" | jq -r '.[0].id')
|
||||||
|
EXISTING_ID=$(rest_get "/api/files?folder_id=$HOME_FOLDER_ID" \
|
||||||
|
| jq -r --arg n "$REMOTE_NAME" 'first(.[] | select(.name == $n) | .id) // empty')
|
||||||
|
if [[ -n "$EXISTING_ID" ]]; then
|
||||||
|
echo " cleaning up leftover $REMOTE_NAME (id=$EXISTING_ID)"
|
||||||
|
rest_delete "/api/files/$EXISTING_ID" > /dev/null
|
||||||
|
purge_from_trash "$REMOTE_NAME"
|
||||||
|
fi
|
||||||
|
|
||||||
|
# ── PUT via the NC surface ───────────────────────────────────────────────────
|
||||||
|
|
||||||
|
echo " step 1: PUT /remote.php/dav/files/$username/$REMOTE_NAME"
|
||||||
|
STATUS=$(curl -s -o /dev/null -w "%{http_code}" \
|
||||||
|
-X PUT \
|
||||||
|
-u "$username:$APP_PASSWORD" \
|
||||||
|
-H "Content-Type: text/plain" \
|
||||||
|
--data-binary "@$FIXTURE" \
|
||||||
|
"$base_url/remote.php/dav/files/$username/$REMOTE_NAME")
|
||||||
|
# 201 = created (first PUT), 204 = updated (idempotent overwrite path).
|
||||||
|
# Either signals a successful write to the spool + blob promotion.
|
||||||
|
[[ "$STATUS" =~ ^(201|204)$ ]] || fail "PUT got $STATUS, expected 201/204"
|
||||||
|
pass "PUT status=$STATUS"
|
||||||
|
|
||||||
|
# ── Verify BLAKE3 + size via the REST listing ────────────────────────────────
|
||||||
|
|
||||||
|
echo " step 2: GET /api/files → assert content_hash + size"
|
||||||
|
LISTED=$(rest_get "/api/files?folder_id=$HOME_FOLDER_ID" \
|
||||||
|
| jq -r --arg n "$REMOTE_NAME" 'first(.[] | select(.name == $n))')
|
||||||
|
ACTUAL_HASH=$(jq -r '.content_hash' <<<"$LISTED")
|
||||||
|
ACTUAL_SIZE=$(jq -r '.size' <<<"$LISTED")
|
||||||
|
FILE_ID=$(jq -r '.id' <<<"$LISTED")
|
||||||
|
|
||||||
|
[[ "$ACTUAL_SIZE" == "$EXPECTED_SIZE" ]] \
|
||||||
|
|| fail "size mismatch: got $ACTUAL_SIZE, expected $EXPECTED_SIZE"
|
||||||
|
[[ "$ACTUAL_HASH" == "$EXPECTED_BLAKE3" ]] \
|
||||||
|
|| fail "BLAKE3 mismatch: got $ACTUAL_HASH, expected $EXPECTED_BLAKE3"
|
||||||
|
pass "content_hash + size match fixture ($EXPECTED_BLAKE3, $EXPECTED_SIZE B)"
|
||||||
|
|
||||||
|
# ── Cleanup ──────────────────────────────────────────────────────────────────
|
||||||
|
|
||||||
|
rest_delete "/api/files/$FILE_ID" > /dev/null
|
||||||
|
purge_from_trash "$REMOTE_NAME"
|
||||||
|
|
||||||
|
echo
|
||||||
|
echo "=== NC single-file PUT BLAKE3 test: $PASS passed, $FAIL failed ==="
|
||||||
|
[[ "$FAIL" == "0" ]] || exit 1
|
||||||
Reference in New Issue
Block a user