mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-10-30 08:50:48 +01:00
* remote: reuse one guarded remote storage client per configuration BuildGuardedRemoteStorageClient (the filer's lazy remote stat and list, remote deletes and renames, the volume server's cold reads, the S3 gateway's remote reads) built a new client, with its own http.Transport, on every call. Each transport kept its connection idle for IdleConnTimeout (60s) and was never reused or closed, so a steady stream of remote lookups held one open connection per request. An endpoint that caps connections per source then refuses every new connection. - remote_storage: GetRemoteStorage's per-name cache becomes a bounded LRU (WEED_REMOTE_CLIENT_CACHE_MAX, default 64) keyed by kind, name, a hash of the whole configuration and a credentials version, built outside the lock once per key (singleflight) from a copy of the configuration. A client leaving the cache has its idle connections closed. GetRemoteStorageWith exposes the cache to other builders. - BuildGuardedRemoteStorageClient caches the guarded client per configuration. The endpoint is checked against the deny-list when a client is built; every new connection still dials through the guarded dialer. A gcs credentials file, and for an S3-compatible remote using the default credential chain the shared credentials file and AWS_* variables, are part of the key by content. - The shared transport keeps 32 idle connections per host, caps connections per host (WEED_REMOTE_MAX_CONNS_PER_HOST, default 64) and has dial, TLS handshake and response header deadlines, so a hung remote frees its slots. - The filer drops the clients of removed remotes (and all but the newest client per name) on every /etc/remote reload, also when /etc/remote does not exist; reloads are serialized. * remote: drop clients whose build spans a reload or whose remote is gone * server: hash the shared AWS config file into the guarded credential version * server: bound a stalled body on the shared remote transport * remote: waive path-injection on the configured credentials file * remote: keep caching remotes the local filer does not name * remote: drop the inline codeql waiver the analyzer ignores * remote: version the plain gcs client's credentials file * remote: hash the environment's inline gcs credentials GOOGLE_APPLICATION_CREDENTIALS can hold the JSON itself, which the gcs client accepts; it is not in the configuration hash, so a changed value kept the old client. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * remote: version the well-known gcs credentials file With neither the configuration nor GOOGLE_APPLICATION_CREDENTIALS set, the SDK reads application_default_credentials.json; rotating it left the cache key unchanged and the old client behind. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * remote: share the gcs credentials version with the guarded client The guarded gcs client resolves the same environment and well-known credentials as the plain one; keying it only on a configured path left those rotations invisible to the cache. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * remote: version s3 keys resolved from the environment A remote whose access and secret keys both arrive through its type's environment fallback (aliyun, baidu, contabo, filebase, storj, tencent) never entered the default-chain branch of guardedCredentialsVersion, so an in-process environment change kept serving the stale cached client. The version now hashes the resolved keys for every S3-compatible remote. * volume: reuse one remote storage client per configuration (rust) fetch_and_write_needle built a fresh aws_sdk_s3::Client per request, so every cold read kept its connector's idle connections without ever reusing them — the same leak the Go side fixes. Cache clients keyed by the configuration's protobuf encoding in an LRU of WEED_REMOTE_CLIENT_CACHE_MAX entries (default 64), mirroring weed/remote_storage/client_cache.go. An evicted entry drops the client's last Arc and with it the connector's idle connections. The per-request endpoint validation is unchanged: Rust has no dial-time guard yet, so the up-front DNS check stays on every call. --------- Co-authored-by: user.email <chrislusf@users.noreply.github.com> Co-authored-by: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
207 lines
7.6 KiB
Go
207 lines
7.6 KiB
Go
package remote_storage
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"fmt"
|
|
"io"
|
|
"sort"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/remote_pb"
|
|
)
|
|
|
|
const slash = "/"
|
|
|
|
func ParseLocationName(remote string) (locationName string) {
|
|
remote = strings.TrimSuffix(remote, slash)
|
|
parts := strings.SplitN(remote, slash, 2)
|
|
if len(parts) >= 1 {
|
|
return parts[0]
|
|
}
|
|
return
|
|
}
|
|
|
|
// Describes reports whether a stored remote entry's stamp still describes the
|
|
// live remote object: same size, and equal ETags when both are known.
|
|
func Describes(stamp, object *filer_pb.RemoteEntry) bool {
|
|
if stamp == nil || object == nil || stamp.RemoteSize != object.RemoteSize {
|
|
return false
|
|
}
|
|
return stamp.RemoteETag == "" || object.RemoteETag == "" || stamp.RemoteETag == object.RemoteETag
|
|
}
|
|
|
|
// StillCurrent reports whether live can still be the object the stored stamp
|
|
// described: not newer than the stamp, matching it on size, and not having
|
|
// dropped an ETag the stamp carried.
|
|
func StillCurrent(stamp, live *filer_pb.RemoteEntry) bool {
|
|
if live != nil && live.RemoteMtime > stamp.GetRemoteMtime() {
|
|
return false
|
|
}
|
|
if !Describes(stamp, live) {
|
|
return false
|
|
}
|
|
return stamp.GetRemoteETag() == "" || live.RemoteETag != ""
|
|
}
|
|
|
|
func parseBucketLocation(remote string) (loc *remote_pb.RemoteStorageLocation) {
|
|
loc = &remote_pb.RemoteStorageLocation{}
|
|
remote = strings.TrimSuffix(remote, slash)
|
|
parts := strings.SplitN(remote, slash, 3)
|
|
if len(parts) >= 1 {
|
|
loc.Name = parts[0]
|
|
}
|
|
if len(parts) >= 2 {
|
|
loc.Bucket = parts[1]
|
|
}
|
|
loc.Path = remote[len(loc.Name)+1+len(loc.Bucket):]
|
|
if loc.Path == "" {
|
|
loc.Path = slash
|
|
}
|
|
return
|
|
}
|
|
|
|
func parseNoBucketLocation(remote string) (loc *remote_pb.RemoteStorageLocation) {
|
|
loc = &remote_pb.RemoteStorageLocation{}
|
|
remote = strings.TrimSuffix(remote, slash)
|
|
parts := strings.SplitN(remote, slash, 2)
|
|
if len(parts) >= 1 {
|
|
loc.Name = parts[0]
|
|
}
|
|
loc.Path = remote[len(loc.Name):]
|
|
if loc.Path == "" {
|
|
loc.Path = slash
|
|
}
|
|
return
|
|
}
|
|
|
|
func FormatLocation(loc *remote_pb.RemoteStorageLocation) string {
|
|
if loc.Bucket == "" {
|
|
return fmt.Sprintf("%s%s", loc.Name, loc.Path)
|
|
}
|
|
return fmt.Sprintf("%s/%s%s", loc.Name, loc.Bucket, loc.Path)
|
|
}
|
|
|
|
type VisitFunc func(dir string, name string, isDirectory bool, remoteEntry *filer_pb.RemoteEntry) error
|
|
|
|
// EntryContentEncoding returns the Content-Encoding stored in the entry
|
|
// extended attributes, for clients to set on uploaded remote objects.
|
|
func EntryContentEncoding(entry *filer_pb.Entry) string {
|
|
if entry == nil {
|
|
return ""
|
|
}
|
|
return string(entry.Extended["Content-Encoding"])
|
|
}
|
|
|
|
type Bucket struct {
|
|
Name string
|
|
CreatedAt time.Time
|
|
}
|
|
|
|
// ErrRemoteObjectNotFound is returned by StatFile and the ReadFile variants when the object does not exist in the remote storage backend.
|
|
var ErrRemoteObjectNotFound = errors.New("remote object not found")
|
|
|
|
type RemoteStorageClient interface {
|
|
Traverse(loc *remote_pb.RemoteStorageLocation, visitFn VisitFunc) error
|
|
ListDirectory(ctx context.Context, loc *remote_pb.RemoteStorageLocation, visitFn VisitFunc) error
|
|
StatFile(loc *remote_pb.RemoteStorageLocation) (remoteEntry *filer_pb.RemoteEntry, err error)
|
|
ReadFile(loc *remote_pb.RemoteStorageLocation, offset int64, size int64) (data []byte, err error)
|
|
WriteDirectory(loc *remote_pb.RemoteStorageLocation, entry *filer_pb.Entry) (err error)
|
|
RemoveDirectory(loc *remote_pb.RemoteStorageLocation) (err error)
|
|
WriteFile(loc *remote_pb.RemoteStorageLocation, entry *filer_pb.Entry, reader io.Reader) (remoteEntry *filer_pb.RemoteEntry, err error)
|
|
// UpdateFileMetadata returns the stamp of the object the update produced —
|
|
// a backend that rewrites the object to change its metadata can give it a
|
|
// new ETag or mtime — or nil when the object was not rewritten. Callers
|
|
// restamp their entries from the result and keep the previous stamp on nil.
|
|
UpdateFileMetadata(loc *remote_pb.RemoteStorageLocation, oldEntry *filer_pb.Entry, newEntry *filer_pb.Entry) (remoteEntry *filer_pb.RemoteEntry, err error)
|
|
DeleteFile(loc *remote_pb.RemoteStorageLocation) (err error)
|
|
ListBuckets() ([]*Bucket, error)
|
|
CreateBucket(name string) (err error)
|
|
DeleteBucket(name string) (err error)
|
|
}
|
|
|
|
// RemoteStorageConcurrentReader is an optional interface for remote storage clients
|
|
// that support configurable download concurrency for multipart downloads.
|
|
type RemoteStorageConcurrentReader interface {
|
|
ReadFileWithConcurrency(loc *remote_pb.RemoteStorageLocation, offset int64, size int64, concurrency int) (data []byte, err error)
|
|
}
|
|
|
|
// RemoteStorageStreamReader is an optional interface for remote storage clients
|
|
// that support streaming reads with io.Reader for efficient memory usage.
|
|
type RemoteStorageStreamReader interface {
|
|
ReadFileAsStream(ctx context.Context, loc *remote_pb.RemoteStorageLocation, offset int64, size int64) (reader io.ReadCloser, err error)
|
|
}
|
|
|
|
// RemoteStorageObjectCopier is an optional interface for remote storage clients
|
|
// that copy an object to another key within the storage, without the content
|
|
// passing through the client. A rename of an entry whose content exists only
|
|
// on the remote needs it.
|
|
type RemoteStorageObjectCopier interface {
|
|
CopyFile(src *remote_pb.RemoteStorageLocation, dst *remote_pb.RemoteStorageLocation) (remoteEntry *filer_pb.RemoteEntry, err error)
|
|
}
|
|
|
|
// RemoteStorageConditionalDeleter is an optional interface for remote storage
|
|
// clients whose backend can delete an object only while it is still the one a
|
|
// stat described, enforced with a backend version precondition (S3 and Azure:
|
|
// ETag, GCS: generation). deleted is false without an error when the object
|
|
// differs from stamp or changed between the stat and the delete.
|
|
type RemoteStorageConditionalDeleter interface {
|
|
DeleteFileIfUnchanged(loc *remote_pb.RemoteStorageLocation, stamp *filer_pb.RemoteEntry) (deleted bool, err error)
|
|
}
|
|
|
|
// CacheWaitTimeout is how long a read of an uncached remote-only object waits
|
|
// for the local cache before serving another way: small files wait longer since
|
|
// their cache completes quickly, large files fail fast for better TTFB. A mount
|
|
// carrying cache_wait_ms replaces the size tiers, and 0 means never wait.
|
|
func CacheWaitTimeout(remoteSize int64, mountedLocation *remote_pb.RemoteStorageLocation) time.Duration {
|
|
if mountedLocation != nil && mountedLocation.CacheWaitMs != nil {
|
|
return max(0, time.Duration(*mountedLocation.CacheWaitMs)*time.Millisecond)
|
|
}
|
|
switch {
|
|
case remoteSize > 500*1024*1024:
|
|
return 2 * time.Second
|
|
case remoteSize > 0 && remoteSize < 50*1024*1024:
|
|
return 10 * time.Second
|
|
default:
|
|
return 5 * time.Second
|
|
}
|
|
}
|
|
|
|
type RemoteStorageClientMaker interface {
|
|
Make(remoteConf *remote_pb.RemoteConf) (RemoteStorageClient, error)
|
|
HasBucket() bool
|
|
}
|
|
|
|
var RemoteStorageClientMakers = make(map[string]RemoteStorageClientMaker)
|
|
|
|
func GetAllRemoteStorageNames() string {
|
|
var storageNames []string
|
|
for k := range RemoteStorageClientMakers {
|
|
storageNames = append(storageNames, k)
|
|
}
|
|
sort.Strings(storageNames)
|
|
return strings.Join(storageNames, "|")
|
|
}
|
|
|
|
func ParseRemoteLocation(remoteConfType string, remote string) (remoteStorageLocation *remote_pb.RemoteStorageLocation, err error) {
|
|
maker, found := RemoteStorageClientMakers[remoteConfType]
|
|
if !found {
|
|
return nil, fmt.Errorf("remote storage type %s not found", remoteConfType)
|
|
}
|
|
|
|
if !maker.HasBucket() {
|
|
return parseNoBucketLocation(remote), nil
|
|
}
|
|
return parseBucketLocation(remote), nil
|
|
}
|
|
|
|
func makeRemoteStorageClient(remoteConf *remote_pb.RemoteConf) (RemoteStorageClient, error) {
|
|
maker, found := RemoteStorageClientMakers[remoteConf.Type]
|
|
if !found {
|
|
return nil, fmt.Errorf("remote storage type %s not found", remoteConf.Type)
|
|
}
|
|
return maker.Make(remoteConf)
|
|
}
|