Files
seaweedfs/weed/storage/backend/s3_backend/s3_download.go
T
87332eb60b Cloud/remote storage & tiering: configurable multipart upload/download concurrency (#11319)
* pb: add multipart concurrency fields to RemoteConf and tier move requests

RemoteConf gains upload_concurrency/download_concurrency (0 = client
default); VolumeTierMoveDatToRemote/FromRemote requests gain a
concurrency field (0 = backend default).

* remote storage: honor RemoteConf upload/download concurrency in s3 and azure clients

s3 client: ReadFile passes conf download_concurrency to the downloader,
WriteFile uses upload_concurrency for the uploader; previously
hard-coded 1 upload / 5 download parts. 0 keeps defaults. Same for
azure client.

* storage: plumb concurrency through backend interface and tier upload/download

BackendStorage.CopyFile/DownloadFile take a concurrency hint (<=0 =
backend configured default); s3 backend reads
upload_concurrency/download_concurrency from scaffold config with
parseConcurrency fallback, rclone updated to the new signature. Tier
move gRPC handlers forward the request concurrency to the backend.

* shell: -upload_concurrency/-download_concurrency for remote.configure, -concurrent for volume.tier

remote.configure exposes upload/download concurrency persisted into
RemoteConf; volume.tier move/evict commands forward -concurrent to the
tier move requests. Documented in master-cloud.toml scaffold.

* test: cover concurrency propagation in remote tier integration test

* remote.configure: merge existing config on partial update

Load the stored RemoteConf before saving so a partial update (e.g. only
-upload_concurrency) preserves credentials, endpoints, and type instead
of replacing them with new-config defaults. Only treat a confirmed
ErrNotFound as a new configuration; propagate all other load errors so a
transient filer failure does not overwrite stored settings.

On a type transition, reset backend-specific fields to the destination
type's new-config defaults rather than inheriting the old backend's
empty values. Bound configured concurrency to a sane maximum.

* remote storage: honor configured download concurrency in S3 and Azure

ReadFileWithConcurrency now resolves a zero request override against the
client's configured download_concurrency (new downloadConcurrency()
helpers), so the remote-mount/cache read path honors
RemoteConf.DownloadConcurrency instead of the hard-coded default.

Azure also clamps the resolved value to math.MaxUint16 regardless of
whether the fallback was used, preventing uint16 wraparound when a
configured value exceeds 65535.

* shell: rename -concurrent to -concurrency and validate tier transfer bounds

Rename the -concurrent flag to -concurrency across volume.tier.upload,
volume.tier.download, and volume.tier.compact to match the proto field and
RemoteConf field names. Add validateTierConcurrency to reject values that
would wrap int32 or exceed a 1024 cap before constructing the request.

* server: clamp tier move concurrency in gRPC handlers

Add clampTierConcurrency to both VolumeTierMoveDatToRemote and
VolumeTierMoveDatFromRemote handlers so a direct gRPC caller cannot spawn
an unbounded number of network workers.

* trim verbose comments added with concurrency feature

Remove redundant doc comments on the backend interface, rclone backend,
s3_backend parseConcurrency, and test helpers that restated the obvious.

* remote.configure: apply type defaults before re-parse so explicit flags win

applyTypeDefaults ran after the second flag parse, overwriting explicit
destination flags (e.g. -s3.region=eu-west-1) with new-config defaults.
Move the type-transition default reset before the re-parse so user-supplied
flags override the destination defaults.

* remote.configure: only treat explicit -type as a type transition

The first parse defaults -type to s3, so a concurrency-only update on an
existing non-S3 config captured requestedType=s3 and wrongly triggered a
type transition, resetting the stored backend to S3. Use fs.Visit to
detect whether -type was explicitly supplied; an omitted -type keeps the
stored backend.

---------

Co-authored-by: Jack Meredith <9480542+jackusm@users.noreply.github.com>
Co-authored-by: Chris Lu <chris.lu@gmail.com>
2026-09-14 22:09:08 -07:00

108 lines
2.8 KiB
Go

package s3_backend
import (
"fmt"
"os"
"sync/atomic"
"github.com/aws/aws-sdk-go/aws"
"github.com/aws/aws-sdk-go/service/s3"
"github.com/aws/aws-sdk-go/service/s3/s3iface"
"github.com/aws/aws-sdk-go/service/s3/s3manager"
"github.com/seaweedfs/seaweedfs/weed/glog"
)
func downloadFromS3(sess s3iface.S3API, destFileName string, sourceBucket string, sourceKey string,
fn func(progressed int64, percentage float32) error, concurrency int) (fileSize int64, err error) {
if concurrency <= 0 {
concurrency = defaultDownloadConcurrency
}
fileSize, err = getFileSize(sess, sourceBucket, sourceKey)
if err != nil {
return
}
//open the file
f, err := os.OpenFile(destFileName, os.O_WRONLY|os.O_CREATE|os.O_TRUNC, 0644)
if err != nil {
return 0, fmt.Errorf("failed to open file %q, %v", destFileName, err)
}
defer f.Close()
// Create a downloader with the session and custom options
downloader := s3manager.NewDownloaderWithClient(sess, func(u *s3manager.Downloader) {
u.PartSize = int64(64 * 1024 * 1024)
u.Concurrency = concurrency
})
fileWriter := &s3DownloadProgressedWriter{
fp: f,
size: fileSize,
written: 0,
fn: fn,
}
// Download the file from S3.
fileSize, err = downloader.Download(fileWriter, &s3.GetObjectInput{
Bucket: aws.String(sourceBucket),
Key: aws.String(sourceKey),
})
if err != nil {
return fileSize, fmt.Errorf("failed to download /buckets/%s/%s to %s: %v", sourceBucket, sourceKey, destFileName, err)
}
// fsync the downloaded .dat so its content is durable before the caller trims the
// remote reference and deletes the shared remote object.
if syncErr := f.Sync(); syncErr != nil {
return fileSize, fmt.Errorf("failed to fsync %s: %v", destFileName, syncErr)
}
glog.V(1).Infof("downloaded file %s\n", destFileName)
return
}
// adapted from https://github.com/aws/aws-sdk-go/pull/1868
// and https://petersouter.xyz/s3-download-progress-bar-in-golang/
type s3DownloadProgressedWriter struct {
size int64
written int64
fn func(progressed int64, percentage float32) error
fp *os.File
}
func (w *s3DownloadProgressedWriter) WriteAt(p []byte, off int64) (int, error) {
n, err := w.fp.WriteAt(p, off)
if err != nil {
return n, err
}
// Got the length have read( or means has uploaded), and you can construct your message
atomic.AddInt64(&w.written, int64(n))
if w.fn != nil {
written := w.written
if err := w.fn(written, float32(written*100)/float32(w.size)); err != nil {
return n, err
}
}
return n, err
}
func getFileSize(svc s3iface.S3API, bucket string, key string) (filesize int64, error error) {
params := &s3.HeadObjectInput{
Bucket: aws.String(bucket),
Key: aws.String(key),
}
resp, err := svc.HeadObject(params)
if err != nil {
return 0, err
}
return *resp.ContentLength, nil
}