* opt: reduce ShardsInfo memory usage with bitmap and sorted slice - Replace map[ShardId]*ShardInfo with sorted []ShardInfo slice - Add ShardBits (uint32) bitmap for O(1) existence checks - Use binary search for O(log n) lookups by shard ID - Maintain sorted order for efficient iteration - Add comprehensive unit tests and benchmarks Memory savings: - Map overhead: ~48 bytes per entry eliminated - Pointers: 8 bytes per entry eliminated - Total: ~56 bytes per shard saved Performance improvements: - Has(): O(1) using bitmap - Size(): O(log n) using binary search (was O(1), acceptable tradeoff) - Count(): O(1) using popcount on bitmap - Iteration: Faster due to cache locality * refactor: add methods to ShardBits type - Add Has(), Set(), Clear(), and Count() methods to ShardBits - Simplify ShardsInfo methods by using ShardBits methods - Improves code readability and encapsulation * opt: use ShardBits directly in ShardsCountFromVolumeEcShardInformationMessage Avoid creating a full ShardsInfo object just to count shards. Directly cast vi.EcIndexBits to ShardBits and use Count() method. * opt: use strings.Builder in ShardsInfo.String() for efficiency * refactor: change AsSlice to return []ShardInfo (values instead of pointers) This completes the memory optimization by avoiding unnecessary pointer slices and potential allocations. * refactor: rename ShardsCountFromVolumeEcShardInformationMessage to GetShardCount * fix: prevent deadlock in Add and Subtract methods Copy shards data from 'other' before releasing its lock to avoid potential deadlock when a.Add(b) and b.Add(a) are called concurrently. The previous implementation held other's lock while calling si.Set/Delete, which acquires si's lock. This could deadlock if two goroutines tried to add/subtract each other concurrently. * opt: avoid unnecessary locking in constructor functions ShardsInfoFromVolume and ShardsInfoFromVolumeEcShardInformationMessage now build shards slice and bitmap directly without calling Set(), which acquires a lock on every call. Since the object is local and not yet shared, locking is unnecessary and adds overhead. This improves performance during object construction. * fix: rename 'copy' variable to avoid shadowing built-in function The variable name 'copy' in TestShardsInfo_Copy shadowed the built-in copy() function, which is confusing and bad practice. Renamed to 'siCopy'. * opt: use math/bits.OnesCount32 and reorganize types 1. Replace manual popcount loop with math/bits.OnesCount32 for better performance and idiomatic Go code 2. Move ShardSize type definition to ec_shards_info.go for better code organization since it's primarily used there * refactor: Set() now accepts ShardInfo for future extensibility Changed Set(id ShardId, size ShardSize) to Set(shard ShardInfo) to support future additions to ShardInfo without changing the API. This makes the code more extensible as new fields can be added to ShardInfo (e.g., checksum, location, etc.) without breaking the Set API. * refactor: move ShardInfo and ShardSize to separate file Created ec_shard_info.go to hold the basic shard types (ShardInfo and ShardSize) for better code organization and separation of concerns. * refactor: add ShardInfo constructor and helper functions Added NewShardInfo() constructor and IsValid() method to better encapsulate ShardInfo creation and validation. Updated code to use the constructor for cleaner, more maintainable code. * fix: update remaining Set() calls to use NewShardInfo constructor Fixed compilation errors in storage and shell packages where Set() calls were not updated to use the new NewShardInfo() constructor. * fix: remove unreachable code in filer backup commands Removed unreachable return statements after infinite loops in filer_backup.go and filer_meta_backup.go to fix compilation errors. * fix: rename 'new' variable to avoid shadowing built-in Renamed 'new' to 'result' in MinusParityShards, Plus, and Minus methods to avoid shadowing Go's built-in new() function. * fix: update remaining test files to use NewShardInfo constructor Fixed Set() calls in command_volume_list_test.go and ec_rebalance_slots_test.go to use NewShardInfo() constructor.
221 lines
8.3 KiB
Go
221 lines
8.3 KiB
Go
package command
|
|
|
|
import (
|
|
"errors"
|
|
"fmt"
|
|
"regexp"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/replication/source"
|
|
"github.com/seaweedfs/seaweedfs/weed/security"
|
|
"github.com/seaweedfs/seaweedfs/weed/util"
|
|
"github.com/seaweedfs/seaweedfs/weed/util/http"
|
|
"google.golang.org/grpc"
|
|
)
|
|
|
|
type FilerBackupOptions struct {
|
|
isActivePassive *bool
|
|
filer *string
|
|
path *string
|
|
excludePaths *string
|
|
excludeFileName *string
|
|
debug *bool
|
|
proxyByFiler *bool
|
|
doDeleteFiles *bool
|
|
disableErrorRetry *bool
|
|
ignore404Error *bool
|
|
timeAgo *time.Duration
|
|
retentionDays *int
|
|
}
|
|
|
|
var (
|
|
filerBackupOptions FilerBackupOptions
|
|
)
|
|
|
|
func init() {
|
|
cmdFilerBackup.Run = runFilerBackup // break init cycle
|
|
filerBackupOptions.filer = cmdFilerBackup.Flag.String("filer", "localhost:8888", "filer of one SeaweedFS cluster")
|
|
filerBackupOptions.path = cmdFilerBackup.Flag.String("filerPath", "/", "directory to sync on filer")
|
|
filerBackupOptions.excludePaths = cmdFilerBackup.Flag.String("filerExcludePaths", "", "exclude directories to sync on filer")
|
|
filerBackupOptions.excludeFileName = cmdFilerBackup.Flag.String("filerExcludeFileName", "", "exclude file names that match the regexp to sync on filer")
|
|
filerBackupOptions.proxyByFiler = cmdFilerBackup.Flag.Bool("filerProxy", false, "read and write file chunks by filer instead of volume servers")
|
|
filerBackupOptions.doDeleteFiles = cmdFilerBackup.Flag.Bool("doDeleteFiles", false, "delete files on the destination")
|
|
filerBackupOptions.debug = cmdFilerBackup.Flag.Bool("debug", false, "debug mode to print out received files")
|
|
filerBackupOptions.timeAgo = cmdFilerBackup.Flag.Duration("timeAgo", 0, "start time before now. \"300ms\", \"1.5h\" or \"2h45m\". Valid time units are \"ns\", \"us\" (or \"µs\"), \"ms\", \"s\", \"m\", \"h\"")
|
|
filerBackupOptions.retentionDays = cmdFilerBackup.Flag.Int("retentionDays", 0, "incremental backup retention days")
|
|
filerBackupOptions.disableErrorRetry = cmdFilerBackup.Flag.Bool("disableErrorRetry", false, "disables errors retry, only logs will print")
|
|
filerBackupOptions.ignore404Error = cmdFilerBackup.Flag.Bool("ignore404Error", true, "ignore 404 errors from filer")
|
|
}
|
|
|
|
var cmdFilerBackup = &Command{
|
|
UsageLine: "filer.backup -filer=<filerHost>:<filerPort> ",
|
|
Short: "resume-able continuously replicate files from a SeaweedFS cluster to another location defined in replication.toml",
|
|
Long: `resume-able continuously replicate files from a SeaweedFS cluster to another location defined in replication.toml
|
|
|
|
filer.backup listens on filer notifications. If any file is updated, it will fetch the updated content,
|
|
and write to the destination. This is to replace filer.replicate command since additional message queue is not needed.
|
|
|
|
If restarted and "-timeAgo" is not set, the synchronization will resume from the previous checkpoints, persisted every minute.
|
|
A fresh sync will start from the earliest metadata logs. To reset the checkpoints, just set "-timeAgo" to a high value.
|
|
|
|
`,
|
|
}
|
|
|
|
func runFilerBackup(cmd *Command, args []string) bool {
|
|
|
|
util.LoadSecurityConfiguration()
|
|
util.LoadConfiguration("replication", true)
|
|
|
|
grpcDialOption := security.LoadClientTLS(util.GetViper(), "grpc.client")
|
|
|
|
clientId := util.RandomInt32()
|
|
var clientEpoch int32
|
|
|
|
for {
|
|
clientEpoch++
|
|
err := doFilerBackup(grpcDialOption, &filerBackupOptions, clientId, clientEpoch)
|
|
if err != nil {
|
|
glog.Errorf("backup from %s: %v", *filerBackupOptions.filer, err)
|
|
time.Sleep(1747 * time.Millisecond)
|
|
}
|
|
}
|
|
}
|
|
|
|
const (
|
|
BackupKeyPrefix = "backup."
|
|
)
|
|
|
|
func doFilerBackup(grpcDialOption grpc.DialOption, backupOption *FilerBackupOptions, clientId int32, clientEpoch int32) error {
|
|
|
|
// find data sink
|
|
dataSink := findSink(util.GetViper())
|
|
if dataSink == nil {
|
|
return fmt.Errorf("no data sink configured in replication.toml")
|
|
}
|
|
|
|
sourceFiler := pb.ServerAddress(*backupOption.filer)
|
|
sourcePath := *backupOption.path
|
|
excludePaths := util.StringSplit(*backupOption.excludePaths, ",")
|
|
var reExcludeFileName *regexp.Regexp
|
|
if *backupOption.excludeFileName != "" {
|
|
var err error
|
|
if reExcludeFileName, err = regexp.Compile(*backupOption.excludeFileName); err != nil {
|
|
return fmt.Errorf("error compile regexp %v for exclude file name: %+v", *backupOption.excludeFileName, err)
|
|
}
|
|
}
|
|
timeAgo := *backupOption.timeAgo
|
|
targetPath := dataSink.GetSinkToDirectory()
|
|
debug := *backupOption.debug
|
|
|
|
// get start time for the data sink
|
|
startFrom := time.Unix(0, 0)
|
|
sinkId := util.HashStringToLong(dataSink.GetName() + dataSink.GetSinkToDirectory())
|
|
if timeAgo.Milliseconds() == 0 {
|
|
lastOffsetTsNs, err := getOffset(grpcDialOption, sourceFiler, BackupKeyPrefix, int32(sinkId))
|
|
if err != nil {
|
|
glog.V(0).Infof("starting from %v", startFrom)
|
|
} else {
|
|
startFrom = time.Unix(0, lastOffsetTsNs)
|
|
glog.V(0).Infof("resuming from %v", startFrom)
|
|
}
|
|
} else {
|
|
startFrom = time.Now().Add(-timeAgo)
|
|
glog.V(0).Infof("start time is set to %v", startFrom)
|
|
}
|
|
|
|
// create filer sink
|
|
filerSource := &source.FilerSource{}
|
|
filerSource.DoInitialize(
|
|
sourceFiler.ToHttpAddress(),
|
|
sourceFiler.ToGrpcAddress(),
|
|
sourcePath,
|
|
*backupOption.proxyByFiler)
|
|
dataSink.SetSourceFiler(filerSource)
|
|
|
|
var processEventFn func(*filer_pb.SubscribeMetadataResponse) error
|
|
if *backupOption.ignore404Error {
|
|
processEventFnGenerated := genProcessFunction(sourcePath, targetPath, excludePaths, reExcludeFileName, dataSink, *backupOption.doDeleteFiles, debug)
|
|
processEventFn = func(resp *filer_pb.SubscribeMetadataResponse) error {
|
|
err := processEventFnGenerated(resp)
|
|
if err == nil {
|
|
return nil
|
|
}
|
|
// ignore HTTP 404 from remote reads
|
|
if errors.Is(err, http.ErrNotFound) {
|
|
glog.V(0).Infof("got 404 error for %s, ignore it: %s", getSourceKey(resp), err.Error())
|
|
return nil
|
|
}
|
|
// also ignore missing volume/lookup errors coming from LookupFileId or vid map
|
|
errStr := err.Error()
|
|
if strings.Contains(errStr, "LookupFileId") || (strings.Contains(errStr, "volume id") && strings.Contains(errStr, "not found")) {
|
|
glog.V(0).Infof("got missing-volume error for %s, ignore it: %s", getSourceKey(resp), errStr)
|
|
return nil
|
|
}
|
|
return err
|
|
}
|
|
} else {
|
|
processEventFn = genProcessFunction(sourcePath, targetPath, excludePaths, reExcludeFileName, dataSink, *backupOption.doDeleteFiles, debug)
|
|
}
|
|
|
|
processEventFnWithOffset := pb.AddOffsetFunc(processEventFn, 3*time.Second, func(counter int64, lastTsNs int64) error {
|
|
glog.V(0).Infof("backup %s progressed to %v %0.2f/sec", sourceFiler, time.Unix(0, lastTsNs), float64(counter)/float64(3))
|
|
return setOffset(grpcDialOption, sourceFiler, BackupKeyPrefix, int32(sinkId), lastTsNs)
|
|
})
|
|
|
|
if dataSink.IsIncremental() && *filerBackupOptions.retentionDays > 0 {
|
|
go func() {
|
|
for {
|
|
now := time.Now()
|
|
time.Sleep(time.Hour * 24)
|
|
key := util.Join(targetPath, now.Add(-1*time.Hour*24*time.Duration(*filerBackupOptions.retentionDays)).Format("2006-01-02"))
|
|
_ = dataSink.DeleteEntry(util.Join(targetPath, key), true, true, nil)
|
|
glog.V(0).Infof("incremental backup delete directory:%s", key)
|
|
}
|
|
}()
|
|
}
|
|
|
|
prefix := sourcePath
|
|
if !strings.HasSuffix(prefix, "/") {
|
|
prefix = prefix + "/"
|
|
}
|
|
|
|
eventErrorType := pb.RetryForeverOnError
|
|
if *backupOption.disableErrorRetry {
|
|
eventErrorType = pb.TrivialOnError
|
|
}
|
|
|
|
metadataFollowOption := &pb.MetadataFollowOption{
|
|
ClientName: "backup_" + dataSink.GetName(),
|
|
ClientId: clientId,
|
|
ClientEpoch: clientEpoch,
|
|
SelfSignature: 0,
|
|
PathPrefix: prefix,
|
|
AdditionalPathPrefixes: nil,
|
|
DirectoriesToWatch: nil,
|
|
StartTsNs: startFrom.UnixNano(),
|
|
StopTsNs: 0,
|
|
EventErrorType: eventErrorType,
|
|
}
|
|
|
|
return pb.FollowMetadata(sourceFiler, grpcDialOption, metadataFollowOption, processEventFnWithOffset)
|
|
|
|
}
|
|
|
|
func getSourceKey(resp *filer_pb.SubscribeMetadataResponse) string {
|
|
if resp == nil || resp.EventNotification == nil {
|
|
return ""
|
|
}
|
|
message := resp.EventNotification
|
|
if message.NewEntry != nil {
|
|
return string(util.FullPath(message.NewParentPath).Child(message.NewEntry.Name))
|
|
}
|
|
if message.OldEntry != nil {
|
|
return string(util.FullPath(resp.Directory).Child(message.OldEntry.Name))
|
|
}
|
|
return ""
|
|
}
|