mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-11-15 08:18:42 +01:00
5a54009439
* filer/etcd: client keepalive and per-request deadlines An etcd member that goes silent with its connections open (a dead or hung node, a network partition, a frozen process) keeps the store's requests balanced onto it waiting forever, because the client has no keepalive and the calls have no deadline. Writes through the filer stop although the other members keep quorum. keepalive_timeout (default 3s, "0s" turns keepalive off) enables gRPC keepalive with the ping interval fixed at gRPC's 10s minimum. gRPC also sets TCP_USER_TIMEOUT to it on Linux, so a connection whose sent data goes unacknowledged that long is closed by the kernel. request_timeout (default 3s) bounds every Get, Put and Delete unless the caller set a deadline; timeout keeps its meaning as the dial timeout. DeleteFolderChildren gets no request deadline: its DeleteRange grows with the directory, and keepalive still ends it if the member goes silent. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * Update weed/filer/etcd/etcd_store.go Co-authored-by: Chris Lu <chrislusf@users.noreply.github.com> * Update weed/filer/etcd/etcd_store_test.go Co-authored-by: Chris Lu <chrislusf@users.noreply.github.com> * Update weed/command/scaffold/filer.toml Co-authored-by: Chris Lu <chrislusf@users.noreply.github.com> * filer/etcd: no request deadline on entry writes A Put whose client deadline expires may still have been committed. The filer's upload handler treats the error as a failed write and deletes the uploaded chunks, which the saved entry may then point at. InsertEntry and UpdateEntry therefore keep the caller's context: etcd's own request timeout ends a Put a live member cannot commit, and keepalive ends one on a member that goes silent. Reads and deletes keep request_timeout; a timed-out store delete returns before the filer deletes any chunks. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * filer/etcd: no request deadline on KvPut The filer wrapper stores a hard-linked file's attributes and chunk list through KvPut. An HTTP append to a hard-linked file whose KvPut times out after etcd saved it returns an error, and the upload handler deletes the appended chunks the saved hard link now points at. KvPut keeps the caller's context like InsertEntry and UpdateEntry. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> Co-authored-by: Chris Lu <chrislusf@users.noreply.github.com>
53 lines
1.2 KiB
Go
53 lines
1.2 KiB
Go
package etcd
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/filer"
|
|
)
|
|
|
|
// KvPut has no request deadline, like InsertEntry: the filer stores a hard-linked
|
|
// file's chunk list here, so a timed-out Put that was saved would leave it
|
|
// pointing at chunks the upload handler deletes.
|
|
func (store *EtcdStore) KvPut(ctx context.Context, key []byte, value []byte) (err error) {
|
|
|
|
_, err = store.client.Put(ctx, store.etcdKeyPrefix+string(key), string(value))
|
|
|
|
if err != nil {
|
|
return fmt.Errorf("kv put: %w", err)
|
|
}
|
|
|
|
return nil
|
|
}
|
|
|
|
func (store *EtcdStore) KvGet(ctx context.Context, key []byte) (value []byte, err error) {
|
|
opCtx, cancel := store.withTimeout(ctx)
|
|
defer cancel()
|
|
|
|
resp, err := store.client.Get(opCtx, store.etcdKeyPrefix+string(key), atScanRevision(ctx)...)
|
|
|
|
if err != nil {
|
|
return nil, fmt.Errorf("kv get: %w", err)
|
|
}
|
|
|
|
if len(resp.Kvs) == 0 {
|
|
return nil, filer.ErrKvNotFound
|
|
}
|
|
|
|
return resp.Kvs[0].Value, nil
|
|
}
|
|
|
|
func (store *EtcdStore) KvDelete(ctx context.Context, key []byte) (err error) {
|
|
opCtx, cancel := store.withTimeout(ctx)
|
|
defer cancel()
|
|
|
|
_, err = store.client.Delete(opCtx, store.etcdKeyPrefix+string(key))
|
|
|
|
if err != nil {
|
|
return fmt.Errorf("kv delete: %w", err)
|
|
}
|
|
|
|
return nil
|
|
}
|