mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-07-22 07:53:38 +00:00
25ab4c3cac
* remote storage: carry Content-Encoding into mounted entries A RemoteEntry now records the remote object's Content-Encoding, and every path that materializes a local entry from remote metadata (lazy fetch, lazy listing, remote.mount, remote.meta.sync, remote.cache) stamps it into the entry extended attributes, so HTTP and S3 HeadObject/GetObject return the header. GCS and Azure populate it on listing and stat; S3 only exposes it via HeadObject, so listings leave it empty. * remote storage: set Content-Encoding when uploading to the remote An entry carrying Content-Encoding in its extended attributes (a native S3 upload, or a value pulled from the remote) now keeps it when filer.remote.sync or remote.copy.local writes the object to GCS, S3, or Azure, instead of silently dropping it. * gcs: read remote objects without decompressive transcoding GCS transparently decompresses gzip-encoded objects on download, which ignores range requests and returns byte counts that disagree with the tracked RemoteSize. Request the stored bytes instead; chunked reads of gzip-encoded objects then behave like any other object. * remote storage: track Content-Encoding presence so removals propagate A listing that does not report encodings (S3) leaves the field unset and the local header untouched, while an authoritative report of no encoding (GCS, Azure, any stat) now clears a previously stamped header instead of leaving it stale. remote.cache also schedules a metadata update when only the reported encoding changes. * remote storage: propagate Content-Encoding on metadata-only updates filer.remote.sync routes same-content changes through UpdateFileMetadata, which only touched custom metadata (GCS, Azure) or tags (S3), so a Content-Encoding change in the extended attributes never reached the remote object's real header. GCS now patches contentEncoding alongside the metadata, and Azure reissues the blob's HTTP headers with the new value, carrying the others over since the call replaces the full set. S3 stays tags-only: changing the header there means rewriting the object, which the sync already does whenever content changes. * remote.meta.sync: optional per-file stat for listing-omitted metadata S3 listings carry no Content-Encoding, so entries synced from them never learn it and the lazy-stat path never runs once an entry exists. With -statFiles, each new or changed file whose listing left the encoding unreported is stat-ed before reconciling, and the stat-derived value is persisted so the next run only stats files that changed. Off by default: it costs one remote request per file, and GCS and Azure listings already carry the encoding. * s3: apply metadata-only Content-Encoding changes with an in-place copy Content-Encoding is S3 system metadata, so the tags-only metadata update silently left the object's real header untouched. When the encoding differs, reissue the object as a self-copy with replaced metadata, carrying the content type and configured storage class like a fresh write does. CopyObject caps at 5 GiB; beyond that the change is logged and applies on the next content write. * azure: skip the metadata call when user metadata is unchanged An encoding-only change reissues the blob's HTTP headers; sending the unchanged user metadata alongside it wastes a round trip and bumps the blob's ETag once more than needed. * s3: carry existing object metadata through the encoding copy The replace directive drops everything not resent, and a mounted entry usually has no local mime or user metadata, so the in-place copy wiped the object's Content-Type, Cache-Control, user metadata, encryption settings, and storage class. Read them back with a HeadObject first and carry them over, overriding only what SeaweedFS manages: the encoding, a locally set mime, and the configured storage class. S3 reports Expires as a string while the copy input wants a time, so it is parsed and skipped when malformed.
218 lines
7.1 KiB
Go
218 lines
7.1 KiB
Go
package shell
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"flag"
|
|
"fmt"
|
|
"io"
|
|
"os"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/filer"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/remote_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/remote_storage"
|
|
"github.com/seaweedfs/seaweedfs/weed/util"
|
|
"google.golang.org/protobuf/proto"
|
|
)
|
|
|
|
type MetadataCacheStrategy string
|
|
|
|
const (
|
|
MetadataCacheEager MetadataCacheStrategy = "eager"
|
|
MetadataCacheLazy MetadataCacheStrategy = "lazy"
|
|
)
|
|
|
|
func init() {
|
|
Commands = append(Commands, &commandRemoteMount{})
|
|
}
|
|
|
|
type commandRemoteMount struct {
|
|
}
|
|
|
|
func (c *commandRemoteMount) Name() string {
|
|
return "remote.mount"
|
|
}
|
|
|
|
func (c *commandRemoteMount) Help() string {
|
|
return `mount remote storage and optionally pull its metadata
|
|
|
|
# assume a remote storage is configured to name "cloud1"
|
|
remote.configure -name=cloud1 -type=s3 -s3.access_key=xxx -s3.secret_key=yyy
|
|
|
|
# mount and pull one bucket (full upfront metadata sync)
|
|
remote.mount -dir=/xxx -remote=cloud1/bucket
|
|
# mount without upfront sync; metadata is fetched lazily on access
|
|
remote.mount -dir=/xxx -remote=cloud1/bucket -metadataStrategy=lazy
|
|
# mount and pull one directory in the bucket
|
|
remote.mount -dir=/xxx -remote=cloud1/bucket/dir1
|
|
# mount with on-demand directory listing cached for 5 minutes
|
|
remote.mount -dir=/xxx -remote=cloud1/bucket -listingCacheTTL=300
|
|
|
|
# after mount, start a separate process to write updates to remote storage
|
|
weed filer.remote.sync -filer=<filerHost>:<filerPort> -dir=/xxx
|
|
|
|
`
|
|
}
|
|
|
|
func (c *commandRemoteMount) HasTag(CommandTag) bool {
|
|
return false
|
|
}
|
|
|
|
func (c *commandRemoteMount) Do(args []string, commandEnv *CommandEnv, writer io.Writer) (err error) {
|
|
|
|
remoteMountCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
|
|
|
|
dir := remoteMountCommand.String("dir", "", "a directory in filer")
|
|
nonEmpty := remoteMountCommand.Bool("nonempty", false, "allows the mounting over a non-empty directory")
|
|
metadataStrategy := remoteMountCommand.String("metadataStrategy", string(MetadataCacheEager), "lazy: skip upfront metadata pull; eager: full metadata pull (default)")
|
|
remote := remoteMountCommand.String("remote", "", "a directory in remote storage, ex. <storageName>/<bucket>/path/to/dir")
|
|
listingCacheTTL := remoteMountCommand.Int("listingCacheTTL", 0, "seconds to cache remote directory listings (0 = disabled)")
|
|
|
|
if err = remoteMountCommand.Parse(args); err != nil {
|
|
return nil
|
|
}
|
|
|
|
if *dir == "" {
|
|
_, err = listExistingRemoteStorageMounts(commandEnv, writer)
|
|
return err
|
|
}
|
|
|
|
// find configuration for remote storage
|
|
remoteConf, err := filer.ReadRemoteStorageConf(commandEnv.option.GrpcDialOption, commandEnv.option.FilerAddress, remote_storage.ParseLocationName(*remote))
|
|
if err != nil {
|
|
return fmt.Errorf("find configuration for %s: %v", *remote, err)
|
|
}
|
|
|
|
remoteStorageLocation, err := remote_storage.ParseRemoteLocation(remoteConf.Type, *remote)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
remoteStorageLocation.ListingCacheTtlSeconds = int32(*listingCacheTTL)
|
|
|
|
strategy := MetadataCacheStrategy(strings.ToLower(*metadataStrategy))
|
|
if strategy != MetadataCacheLazy && strategy != MetadataCacheEager {
|
|
return fmt.Errorf("metadataStrategy must be %s or %s, got %q", MetadataCacheLazy, MetadataCacheEager, *metadataStrategy)
|
|
}
|
|
|
|
if err = ensureMountDirectory(commandEnv, *dir, *nonEmpty, remoteConf); err != nil {
|
|
return fmt.Errorf("mount setup: %w", err)
|
|
}
|
|
|
|
if strategy == MetadataCacheEager {
|
|
if err = pullMetadata(commandEnv, writer, util.FullPath(*dir), remoteStorageLocation, util.FullPath(*dir), remoteConf, false, false); err != nil {
|
|
return fmt.Errorf("cache metadata: %w", err)
|
|
}
|
|
}
|
|
|
|
// store a mount configuration in filer
|
|
if err = filer.InsertMountMapping(commandEnv, *dir, remoteStorageLocation); err != nil {
|
|
return fmt.Errorf("save mount mapping: %w", err)
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
func listExistingRemoteStorageMounts(commandEnv *CommandEnv, writer io.Writer) (mappings *remote_pb.RemoteStorageMapping, err error) {
|
|
|
|
// read current mapping
|
|
mappings, err = filer.ReadMountMappings(commandEnv.option.GrpcDialOption, commandEnv.option.FilerAddress)
|
|
if err != nil {
|
|
return mappings, err
|
|
}
|
|
|
|
jsonPrintln(writer, mappings)
|
|
|
|
return
|
|
|
|
}
|
|
|
|
func jsonPrintln(writer io.Writer, message proto.Message) error {
|
|
return filer.ProtoToText(writer, message)
|
|
}
|
|
|
|
func ensureMountDirectory(commandEnv *CommandEnv, dir string, nonEmpty bool, remoteConf *remote_pb.RemoteConf) error {
|
|
return commandEnv.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
|
|
parent, name := util.FullPath(dir).DirAndName()
|
|
_, lookupErr := filer_pb.LookupEntry(context.Background(), client, &filer_pb.LookupDirectoryEntryRequest{
|
|
Directory: parent,
|
|
Name: name,
|
|
})
|
|
if lookupErr != nil {
|
|
if errors.Is(lookupErr, filer_pb.ErrNotFound) {
|
|
_, createErr := client.CreateEntry(context.Background(), &filer_pb.CreateEntryRequest{
|
|
Directory: parent,
|
|
Entry: &filer_pb.Entry{
|
|
Name: name,
|
|
IsDirectory: true,
|
|
Attributes: &filer_pb.FuseAttributes{
|
|
Mtime: time.Now().Unix(),
|
|
Crtime: time.Now().Unix(),
|
|
FileMode: uint32(0755 | os.ModeDir),
|
|
},
|
|
RemoteEntry: &filer_pb.RemoteEntry{
|
|
StorageName: remoteConf.Name,
|
|
},
|
|
},
|
|
})
|
|
return createErr
|
|
}
|
|
return lookupErr
|
|
}
|
|
|
|
mountToDirIsEmpty := true
|
|
listErr := filer_pb.SeaweedList(context.Background(), client, dir, "", func(entry *filer_pb.Entry, isLast bool) error {
|
|
mountToDirIsEmpty = false
|
|
return nil
|
|
}, "", false, 1)
|
|
|
|
if listErr != nil {
|
|
return fmt.Errorf("list %s: %v", dir, listErr)
|
|
}
|
|
|
|
if !mountToDirIsEmpty {
|
|
if !nonEmpty {
|
|
return fmt.Errorf("dir %s is not empty", dir)
|
|
}
|
|
}
|
|
|
|
return nil
|
|
})
|
|
}
|
|
|
|
// if an entry has synchronized metadata but has not synchronized content
|
|
//
|
|
// entry.Attributes.FileSize == entry.RemoteEntry.RemoteSize
|
|
// entry.Attributes.Mtime == entry.RemoteEntry.RemoteMtime
|
|
// entry.RemoteEntry.LastLocalSyncTsNs == 0
|
|
//
|
|
// if an entry has synchronized metadata but has synchronized content before
|
|
//
|
|
// entry.Attributes.FileSize == entry.RemoteEntry.RemoteSize
|
|
// entry.Attributes.Mtime == entry.RemoteEntry.RemoteMtime
|
|
// entry.RemoteEntry.LastLocalSyncTsNs > 0
|
|
//
|
|
// if an entry has synchronized metadata but has new updates
|
|
//
|
|
// entry.Attributes.Mtime * 1,000,000,000 > entry.RemoteEntry.LastLocalSyncTsNs
|
|
func doSaveRemoteEntry(client filer_pb.SeaweedFilerClient, localDir string, existingEntry *filer_pb.Entry, remoteEntry *filer_pb.RemoteEntry) error {
|
|
existingEntry.RemoteEntry = remoteEntry
|
|
existingEntry.Attributes.FileSize = uint64(remoteEntry.RemoteSize)
|
|
existingEntry.Attributes.Mtime = remoteEntry.RemoteMtime
|
|
existingEntry.Attributes.Md5 = nil
|
|
existingEntry.Attributes.TtlSec = 0 // Remote entries should not have TTL
|
|
existingEntry.Extended = filer.MergeRemoteContentEncoding(remoteEntry, existingEntry.Extended)
|
|
existingEntry.Chunks = nil
|
|
existingEntry.Content = nil
|
|
_, updateErr := client.UpdateEntry(context.Background(), &filer_pb.UpdateEntryRequest{
|
|
Directory: localDir,
|
|
Entry: existingEntry,
|
|
})
|
|
if updateErr != nil {
|
|
return updateErr
|
|
}
|
|
return nil
|
|
}
|