seaweedfs/weed/shell/command_remote_meta_sync.go

179 lines
6.2 KiB
Go
Raw Normal View History

2021-08-15 08:53:46 +00:00
package shell
import (
"context"
"flag"
"fmt"
"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"
2021-08-15 08:53:46 +00:00
"io"
)
func init() {
Commands = append(Commands, &commandRemoteMetaSync{})
}
type commandRemoteMetaSync struct {
}
func (c *commandRemoteMetaSync) Name() string {
return "remote.meta.sync"
}
func (c *commandRemoteMetaSync) Help() string {
return `synchronize the local file meta data with the remote file metadata
# assume a remote storage is configured to name "cloud1"
2021-11-07 20:38:35 +00:00
remote.configure -name=cloud1 -type=s3 -s3.access_key=xxx -s3.secret_key=yyy
2021-08-15 08:53:46 +00:00
# mount and pull one bucket
remote.mount -dir=/xxx -remote=cloud1/bucket
After mount, if the remote file can be changed,
run this command to synchronize the metadata of the mounted folder or any sub folder
remote.meta.sync -dir=/xxx
remote.meta.sync -dir=/xxx/some/subdir
This is designed to run regularly. So you can add it to some cronjob.
If there are no other operations changing remote files, this operation is not needed.
`
}
func (c *commandRemoteMetaSync) Do(args []string, commandEnv *CommandEnv, writer io.Writer) (err error) {
remoteMetaSyncCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
dir := remoteMetaSyncCommand.String("dir", "", "a directory in filer")
if err = remoteMetaSyncCommand.Parse(args); err != nil {
return nil
}
2021-08-15 19:09:54 +00:00
mappings, localMountedDir, remoteStorageMountedLocation, remoteStorageConf, detectErr := detectMountInfo(commandEnv, writer, *dir)
if detectErr != nil {
2021-08-15 19:09:54 +00:00
jsonPrintln(writer, mappings)
2021-08-15 08:53:46 +00:00
return detectErr
}
// pull metadata from remote
if err = pullMetadata(commandEnv, writer, util.FullPath(localMountedDir), remoteStorageMountedLocation, util.FullPath(*dir), remoteStorageConf); err != nil {
2021-08-31 08:07:34 +00:00
return fmt.Errorf("cache meta data: %v", err)
2021-08-15 08:53:46 +00:00
}
return nil
}
2021-08-26 22:18:34 +00:00
func detectMountInfo(commandEnv *CommandEnv, writer io.Writer, dir string) (*remote_pb.RemoteStorageMapping, string, *remote_pb.RemoteStorageLocation, *remote_pb.RemoteConf, error) {
return filer.DetectMountInfo(commandEnv.option.GrpcDialOption, commandEnv.option.FilerAddress, dir)
2021-08-15 08:53:46 +00:00
}
/*
This function update entry.RemoteEntry if the remote has any changes.
To pull remote updates, or created for the first time, the criteria is:
2021-08-30 22:56:11 +00:00
entry == nil or (entry.RemoteEntry != nil and (entry.RemoteEntry.RemoteTag != remote.RemoteTag or entry.RemoteEntry.RemoteMTime < remote.RemoteMTime ))
2021-08-15 08:53:46 +00:00
After the meta pull, the entry.RemoteEntry will have:
remoteEntry.LastLocalSyncTsNs == 0
Attributes.FileSize = uint64(remoteEntry.RemoteSize)
Attributes.Mtime = remoteEntry.RemoteMtime
remoteEntry.RemoteTag = actual remote tag
chunks = nil
When reading the file content or pulling the file content in "remote.cache", the criteria is:
Attributes.FileSize > 0 and len(chunks) == 0
After caching the file content, the entry.RemoteEntry will be
remoteEntry.LastLocalSyncTsNs == time.Now.UnixNano()
Attributes.FileSize = uint64(remoteEntry.RemoteSize)
Attributes.Mtime = remoteEntry.RemoteMtime
chunks = non-emtpy
When "weed filer.remote.sync" to upload local changes to remote, the criteria is:
Attributes.Mtime > remoteEntry.RemoteMtime
Right after "weed filer.remote.sync", the entry.RemoteEntry will be
remoteEntry.LastLocalSyncTsNs = time.Now.UnixNano()
remoteEntry.RemoteSize = actual remote size, which should equal to entry.Attributes.FileSize
remoteEntry.RemoteMtime = actual remote mtime, which should be a little greater than entry.Attributes.Mtime
remoteEntry.RemoteTag = actual remote tag
If entry does not exists, need to pull meta
If entry.RemoteEntry == nil, this is a new local change and should not be overwritten
If entry.RemoteEntry.RemoteTag != remoteEntry.RemoteTag {
the remote version is updated, need to pull meta
}
*/
2021-08-26 22:18:34 +00:00
func pullMetadata(commandEnv *CommandEnv, writer io.Writer, localMountedDir util.FullPath, remoteMountedLocation *remote_pb.RemoteStorageLocation, dirToCache util.FullPath, remoteConf *remote_pb.RemoteConf) error {
2021-08-15 08:53:46 +00:00
// visit remote storage
remoteStorage, err := remote_storage.GetRemoteStorage(remoteConf)
if err != nil {
return err
}
remote := filer.MapFullPathToRemoteStorageLocation(localMountedDir, remoteMountedLocation, dirToCache)
err = commandEnv.WithFilerClient(false, func(client filer_pb.SeaweedFilerClient) error {
2021-08-15 08:53:46 +00:00
ctx := context.Background()
err = remoteStorage.Traverse(remote, func(remoteDir, name string, isDirectory bool, remoteEntry *filer_pb.RemoteEntry) error {
localDir := filer.MapRemoteStorageLocationPathToFullPath(localMountedDir, remoteMountedLocation, remoteDir)
fmt.Fprint(writer, localDir.Child(name))
lookupResponse, lookupErr := filer_pb.LookupEntry(client, &filer_pb.LookupDirectoryEntryRequest{
Directory: string(localDir),
Name: name,
})
var existingEntry *filer_pb.Entry
if lookupErr != nil {
if lookupErr != filer_pb.ErrNotFound {
return lookupErr
}
} else {
existingEntry = lookupResponse.Entry
}
if existingEntry == nil {
_, createErr := client.CreateEntry(ctx, &filer_pb.CreateEntryRequest{
Directory: string(localDir),
Entry: &filer_pb.Entry{
Name: name,
IsDirectory: isDirectory,
Attributes: &filer_pb.FuseAttributes{
FileSize: uint64(remoteEntry.RemoteSize),
Mtime: remoteEntry.RemoteMtime,
FileMode: uint32(0644),
},
RemoteEntry: remoteEntry,
},
})
fmt.Fprintln(writer, " (create)")
return createErr
} else {
if existingEntry.RemoteEntry == nil {
// this is a new local change and should not be overwritten
fmt.Fprintln(writer, " (skip)")
return nil
}
if existingEntry.RemoteEntry.RemoteETag != remoteEntry.RemoteETag || existingEntry.RemoteEntry.RemoteMtime < remoteEntry.RemoteMtime {
2021-08-15 08:53:46 +00:00
// the remote version is updated, need to pull meta
fmt.Fprintln(writer, " (update)")
return doSaveRemoteEntry(client, string(localDir), existingEntry, remoteEntry)
}
}
fmt.Fprintln(writer, " (skip)")
return nil
})
return err
})
if err != nil {
return err
}
return nil
}