mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-09-20 13:30:46 +02:00
* 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>
144 lines
4.3 KiB
Go
144 lines
4.3 KiB
Go
package backend
|
|
|
|
import (
|
|
"io"
|
|
"os"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/volume_server_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/util"
|
|
)
|
|
|
|
type BackendStorageFile interface {
|
|
io.ReaderAt
|
|
io.WriterAt
|
|
Truncate(off int64) error
|
|
io.Closer
|
|
GetStat() (datSize int64, modTime time.Time, err error)
|
|
Name() string
|
|
Sync() error
|
|
}
|
|
|
|
type BackendStorage interface {
|
|
ToProperties() map[string]string
|
|
NewStorageFile(key string, tierInfo *volume_server_pb.VolumeInfo) BackendStorageFile
|
|
// concurrency > 0 caps concurrent network transfers; <= 0 uses the backend default.
|
|
CopyFile(f *os.File, fn func(progressed int64, percentage float32) error, concurrency int) (key string, size int64, err error)
|
|
DownloadFile(fileName string, key string, fn func(progressed int64, percentage float32) error, concurrency int) (size int64, err error)
|
|
DeleteFile(key string) (err error)
|
|
}
|
|
|
|
type StringProperties interface {
|
|
GetString(key string) string
|
|
}
|
|
type StorageType string
|
|
type BackendStorageFactory interface {
|
|
StorageType() StorageType
|
|
BuildStorage(configuration StringProperties, configPrefix string, id string) (BackendStorage, error)
|
|
}
|
|
|
|
var (
|
|
BackendStorageFactories = make(map[StorageType]BackendStorageFactory)
|
|
BackendStorages = make(map[string]BackendStorage)
|
|
)
|
|
|
|
// used by master to load remote storage configurations
|
|
func LoadConfiguration(config *util.ViperProxy) {
|
|
|
|
StorageBackendPrefix := "storage.backend"
|
|
|
|
for backendTypeName := range config.GetStringMap(StorageBackendPrefix) {
|
|
backendStorageFactory, found := BackendStorageFactories[StorageType(backendTypeName)]
|
|
if !found {
|
|
glog.Fatalf("backend storage type %s not found", backendTypeName)
|
|
}
|
|
for backendStorageId := range config.GetStringMap(StorageBackendPrefix + "." + backendTypeName) {
|
|
if !config.GetBool(StorageBackendPrefix + "." + backendTypeName + "." + backendStorageId + ".enabled") {
|
|
continue
|
|
}
|
|
if _, found := BackendStorages[backendTypeName+"."+backendStorageId]; found {
|
|
continue
|
|
}
|
|
backendStorage, buildErr := backendStorageFactory.BuildStorage(config,
|
|
StorageBackendPrefix+"."+backendTypeName+"."+backendStorageId+".", backendStorageId)
|
|
if buildErr != nil {
|
|
glog.Fatalf("fail to create backend storage %s.%s", backendTypeName, backendStorageId)
|
|
}
|
|
BackendStorages[backendTypeName+"."+backendStorageId] = backendStorage
|
|
if backendStorageId == "default" {
|
|
BackendStorages[backendTypeName] = backendStorage
|
|
}
|
|
}
|
|
}
|
|
|
|
}
|
|
|
|
// used by volume server to receive remote storage configurations from master
|
|
func LoadFromPbStorageBackends(storageBackends []*master_pb.StorageBackend) {
|
|
|
|
for _, storageBackend := range storageBackends {
|
|
backendStorageFactory, found := BackendStorageFactories[StorageType(storageBackend.Type)]
|
|
if !found {
|
|
glog.Warningf("storage type %s not found", storageBackend.Type)
|
|
continue
|
|
}
|
|
if _, found := BackendStorages[storageBackend.Type+"."+storageBackend.Id]; found {
|
|
continue
|
|
}
|
|
backendStorage, buildErr := backendStorageFactory.BuildStorage(newProperties(storageBackend.Properties), "", storageBackend.Id)
|
|
if buildErr != nil {
|
|
glog.Fatalf("fail to create backend storage %s.%s", storageBackend.Type, storageBackend.Id)
|
|
}
|
|
BackendStorages[storageBackend.Type+"."+storageBackend.Id] = backendStorage
|
|
if storageBackend.Id == "default" {
|
|
BackendStorages[storageBackend.Type] = backendStorage
|
|
}
|
|
}
|
|
}
|
|
|
|
type Properties struct {
|
|
m map[string]string
|
|
}
|
|
|
|
func newProperties(m map[string]string) *Properties {
|
|
return &Properties{m: m}
|
|
}
|
|
|
|
func (p *Properties) GetString(key string) string {
|
|
if v, found := p.m[key]; found {
|
|
return v
|
|
}
|
|
return ""
|
|
}
|
|
|
|
func ToPbStorageBackends() (backends []*master_pb.StorageBackend) {
|
|
for sName, s := range BackendStorages {
|
|
sType, sId := BackendNameToTypeId(sName)
|
|
if sType == "" {
|
|
continue
|
|
}
|
|
backends = append(backends, &master_pb.StorageBackend{
|
|
Type: sType,
|
|
Id: sId,
|
|
Properties: s.ToProperties(),
|
|
})
|
|
}
|
|
return
|
|
}
|
|
|
|
func BackendNameToTypeId(backendName string) (backendType, backendId string) {
|
|
parts := strings.Split(backendName, ".")
|
|
if len(parts) == 1 {
|
|
return backendName, "default"
|
|
}
|
|
if len(parts) != 2 {
|
|
return
|
|
}
|
|
|
|
backendType, backendId = parts[0], parts[1]
|
|
return
|
|
}
|