* filer.sync: show active chunk transfers when sync progress stalls
When the sync watermark is not advancing, print each in-progress chunk
transfer with its file path, bytes received so far, and current status
(downloading, uploading, or waiting with backoff duration). This helps
diagnose which files are blocking progress during replication.
Closes#8542
* filer.sync: include last error in stall diagnostics
* filer.sync: fix data races in ChunkTransferStatus
Add sync.RWMutex to ChunkTransferStatus and lock around all field
mutations in fetchAndWrite. ActiveTransfers now returns value copies
under RLock so callers get immutable snapshots.
* improve large file sync throughput for remote.cache and filer.sync
Three main throughput improvements:
1. Adaptive chunk sizing for remote.cache: targets ~32 chunks per file
instead of always starting at 5MB. A 500MB file now uses ~16MB chunks
(32 chunks) instead of 5MB chunks (100 chunks), reducing per-chunk
overhead (volume assign, gRPC call, needle write) by 3x.
2. Configurable concurrency at every layer:
- remote.cache chunk concurrency: -chunkConcurrency flag (default 8)
- remote.cache S3 download concurrency: -downloadConcurrency flag
(default raised from 1 to 5 per chunk)
- filer.sync chunk concurrency: -chunkConcurrency flag (default 32)
3. S3 multipart download concurrency raised from 1 to 5: the S3 manager
downloader was using Concurrency=1, serializing all part downloads
within each chunk. This alone can 5x per-chunk download speed.
The concurrency values flow through the gRPC request chain:
shell command → CacheRemoteObjectToLocalClusterRequest →
FetchAndWriteNeedleRequest → S3 downloader
Zero values in the request mean "use server defaults", maintaining
full backward compatibility with existing callers.
Ref #8481
* fix: use full maxMB for chunk size cap and remove loop guard
Address review feedback:
- Use full maxMB instead of maxMB/2 for maxChunkSize to avoid
unnecessarily limiting chunk size for very large files.
- Remove chunkSize < maxChunkSize guard from the safety loop so it
can always grow past maxChunkSize when needed to stay under 1000
chunks (e.g., extremely large files with small maxMB).
* address review feedback: help text, validation, naming, docs
- Fix help text for -chunkConcurrency and -downloadConcurrency flags
to say "0 = server default" instead of advertising specific numeric
defaults that could drift from the server implementation.
- Validate chunkConcurrency and downloadConcurrency are within int32
range before narrowing, returning a user-facing error if out of range.
- Rename ReadRemoteErr to readRemoteErr to follow Go naming conventions.
- Add doc comment to SetChunkConcurrency noting it must be called
during initialization before replication goroutines start.
- Replace doubling loop in chunk size safety check with direct
ceil(remoteSize/1000) computation to guarantee the 1000-chunk cap.
* address Copilot review: clamp concurrency, fix chunk count, clarify proto docs
- Use ceiling division for chunk count check to avoid overcounting
when file size is an exact multiple of chunk size.
- Clamp chunkConcurrency (max 1024) and downloadConcurrency (max 1024
at filer, max 64 at volume server) to prevent excessive goroutines.
- Always use ReadFileWithConcurrency when the client supports it,
falling back to the implementation's default when value is 0.
- Clarify proto comments that download_concurrency only applies when
the remote storage client supports it (currently S3).
- Include specific server defaults in help text (e.g., "0 = server
default 8") so users see the actual values in -h output.
* fix data race on executionErr and use %w for error wrapping
- Protect concurrent writes to executionErr in remote.cache worker
goroutines with a sync.Mutex to eliminate the data race.
- Use %w instead of %v in volume_grpc_remote.go error formatting
to preserve the error chain for errors.Is/errors.As callers.
Fix https://github.com/seaweedfs/seaweedfs/issues/3714
The destination chunks may be empty. For example, the file is updated and the volume is vacuumed. In this case, the sync would miss the old chunks. This is fine. However, the entry would have correct metadata but missing chunks.
For this case, the simple metadata comparison would be wrongly skipping data changes, and the file will stay empty unless file content md5 is changed.
Run two servers with volumes and fillers:
server -dir=Server1alpha -master.port=11000 -filer -filer.port=11001 -volume.port=11002
server -dir=Server1sigma -master.port=11006 -filer -filer.port=11007 -volume.port=11008
Run Active-Passive filler.sync:
filer.sync -a localhost:11007 -b localhost:11001 -isActivePassive
Upload file to 11007 port:
curl -F file=@/Desktop/9.xml "http://localhost:11007/testFacebook/"
If we request a file on two servers now, everything will be correct, even if we add data to the file and upload it again:
curl "http://localhost:11007/testFacebook/9.xml"
EQUALS
curl "http://localhost:11001/testFacebook/9.xml"
However, if we change the already existing data in the file (for example, we change the first line in the file, reducing its length), then this file on the second server will not be valid and will not be equivalent to the first file
Снимок экрана 2022-02-07 в 14 21 11
This problem occurs on line 202 in the filer_sink.go file. In particular, this is due to incorrect mapping of chunk names in the DoMinusChunks function. The names of deletedChunks do not match the chunks of existingEntry.Chunks, since the first chunks come from another server and have a different addressing (name) compared to the addressing on the server where the file is being overwritten.
Deleted chunks are not actually deleted on the server to which the file is replicated.
