Files
upstream-seaweedfs/weed/cluster/lock_manager/lock_manager.go
upstream-mirror 89f5be005d
Some checks failed
go: build dev binaries / cleanup (push) Successful in 4s
Codespell / Check for spelling errors (push) Failing after 3s
docker: build dev containers / build-rust-binaries (amd64, x86_64-unknown-linux-musl) (push) Failing after 3s
docker: build dev containers / build-dev-containers (push) Has been skipped
docker: build dev containers / build-rust-binaries (arm64, true, aarch64-unknown-linux-musl) (push) Failing after 3s
End to End / FUSE Mount (push) Failing after 2s
EC Integration Tests / EC Integration Tests (push) Failing after 30s
FUSE DLM Integration Tests / FUSE DLM Integration Tests (push) Failing after 3s
FUSE Volume Server Failover Tests / FUSE Volume Server Failover (push) Failing after 3s
FUSE Integration Tests / FUSE Integration Testing (push) Failing after 2s
FUSE P2P Peer Chunk Sharing Integration Tests / FUSE P2P Peer Chunk Sharing (push) Failing after 3s
go: build binary / Go Vet (push) Failing after 2s
go: build binary / Go Vet 32-bit (push) Failing after 3s
go: build binary / Build (push) Failing after 4s
go: build binary / Build cross-platform (freebsd/amd64) (push) Failing after 3s
go: build binary / Build cross-platform (windows/amd64) (push) Failing after 3s
go: build binary / Build cross-platform (darwin/arm64) (push) Failing after 3s
go: build binary / Build cross-platform (windows/arm64) (push) Failing after 3s
go: build binary / Test (push) Failing after 2s
go: build binary / Test 32-bit (push) Failing after 3s
helm: lint and test charts / lint-test (push) Failing after 3s
Java Client Integration Tests / Java Integration Tests (11) (push) Failing after 3s
Java Client Integration Tests / Java Integration Tests (17) (push) Failing after 3s
go: build dev binaries / build_dev_linux_windows (amd64, linux) (push) Failing after 2s
go: build dev binaries / build_dev_linux_windows (amd64, windows) (push) Failing after 3s
go: build dev binaries / build_dev_darwin (amd64, darwin) (push) Has been skipped
go: build dev binaries / build_dev_darwin (arm64, darwin) (push) Has been skipped
Java Client Unit Tests / Java Unit Tests (11) (push) Failing after 3s
Java Client Unit Tests / Java Unit Tests (17) (push) Failing after 2s
Java Client Unit Tests / Java Unit Tests (21) (push) Failing after 3s
Java Client Unit Tests / Java Unit Tests (8) (push) Failing after 3s
Kafka Quick Test (Load Test with Schema Registry) / Kafka Client Load Test (Quick) (push) Failing after 3s
Kafka Gateway Tests / Kafka Unit Tests (unit-tests-1) (push) Failing after 11s
Kafka Gateway Tests / Kafka Integration Tests (Critical) (integration-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka End-to-End Tests (with SMQ) (e2e-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka Consumer Group Tests (Highly Isolated) (consumer-group-1) (push) Failing after 2s
Kafka Gateway Tests / Kafka Client Compatibility (with SMQ) (client-compat-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka SMQ Integration Tests (Full Stack) (smq-integration-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka Protocol Tests (Isolated) (protocol-1) (push) Failing after 3s
KMS Tests / KMS Provider Integration Tests (push) Failing after 2s
KMS Tests / S3 KMS End-to-End Tests (push) Failing after 3s
Master Cold Start Tests / Master Cold Start Tests (push) Failing after 4s
Metadata Subscribe Integration Tests / Metadata Subscribe Integration Tests (push) Failing after 3s
Multi-Master Tests / Multi-Master Failover Tests (push) Failing after 3s
Performance / CPU and Heap Profile (push) Failing after 2s
Performance / S3 Read/Write Benchmark (rust volume) (push) Failing after 3s
pjdfstest POSIX Compliance / pjdfstest (push) Failing after 2s
Plugin Worker Integration Tests / Plugin Worker: erasure_coding (push) Failing after 3s
Plugin Worker Integration Tests / Plugin Worker: vacuum (push) Failing after 3s
Rust Volume Server Tests / Rust Integration Tests (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 1) (push) Failing after 2s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 1) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 2) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 2) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 3) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Distributed Tests (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Performance Tests (push) Failing after 3s
Performance / Throughput Benchmark (go volume) (push) Failing after 3s
Performance / Throughput Benchmark (rust volume) (push) Failing after 2s
Performance / S3 Read/Write Benchmark (go volume) (push) Failing after 3s
Plugin Worker Integration Tests / Plugin Worker: volume_balance (push) Failing after 3s
PostgreSQL Gateway Tests / PostgreSQL Basic Tests (push) Failing after 3s
Rust Volume Server Tests / Rust Unit Tests (push) Failing after 2s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 3) (push) Failing after 3s
Rust Plugin Worker Tests / Rust Plugin Worker Build and Unit Tests (push) Failing after 3s
rust: build dev volume server binaries / cleanup (push) Successful in 3s
S3 ETag and ACL Tests / S3 ETag + ACL Integration Tests (push) Failing after 3s
S3 IAM Integration Tests / IAM Unit Tests (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (advanced) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (basic) (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Integration Tests (group) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (policy-enforcement) (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Integration Tests (sts) (push) Failing after 4s
S3 Keycloak Integration Tests / S3 Keycloak Integration Tests (push) Failing after 3s
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.11) (push) Failing after 3s
S3 PyArrow Parquet Tests / Go Unit Tests (Implicit Directory) (push) Has been cancelled
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.12) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-darwin (darwin-amd64, x86_64-apple-darwin) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-darwin (darwin-arm64, aarch64-apple-darwin) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-linux (linux-amd64, x86_64-unknown-linux-gnu) (push) Has been cancelled
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.9) (push) Has been cancelled
S3 Proxy Signature Tests / S3 Proxy Signature Verification Tests (push) Has been cancelled
S3 SDK V2 Route Disambiguation Tests / S3 SDK V2 Routing Tests (push) Has been cancelled
S3 SSE Tests / S3 SSE Integration Tests (quick) (push) Has been cancelled
S3 SSE Tests / S3 SSE Compatibility Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Metadata Persistence Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Copy Operations Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Multipart Upload Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Performance Test (push) Has been cancelled
S3 SSE Tests / S3 Volume Encryption Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Integration Tests (comprehensive) (push) Has been cancelled
Spark Integration Tests / Spark Integration Tests (push) Failing after 2s
Telemetry Integration Tests / telemetry-integration-test (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 1) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 1) (push) Failing after 3s
Ceph S3 tests / Basic S3 tests (KV store) (push) Has been cancelled
Ceph S3 tests / S3 Versioning & Object Lock tests (push) Has been cancelled
S3 Policy Integration Tests / S3 Policy Unit Tests (push) Failing after 3s
Ceph S3 tests / S3 CORS tests (push) Has been cancelled
Ceph S3 tests / SeaweedFS Custom S3 Copy tests (push) Has been cancelled
Ceph S3 tests / Basic S3 tests (SQL store) (push) Has been cancelled
test s3 over https using aws-cli / awscli-tests (push) Has been cancelled
TLS Rotation Integration Tests / TLS Rotation Integration Tests (push) Has been cancelled
Vacuum Integration Tests / Vacuum Integration Tests (push) Has been cancelled
S3 Policy Integration Tests / S3 Policy Variables Integration Tests (push) Failing after 3s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (advanced-policy) (push) Failing after 3s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (basic-policy) (push) Failing after 2s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (contextual-policy) (push) Failing after 4s
S3 Policy Integration Tests / Trusted Proxy Detection Tests (push) Failing after 2s
S3 Policy Integration Tests / S3 Policy Shell Integration Tests (push) Failing after 3s
Samba on FUSE Integration / samba-integration (push) Failing after 2s
SFTP Integration Tests / SFTP Integration Testing (push) Failing after 3s
terraform: validate and test modules / fmt, validate, plan-level tests (push) Failing after 3s
terraform: validate and test modules / local cluster smoke test (real weed) (push) Failing after 2s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 3) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 2) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 2) (push) Failing after 2s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 3) (push) Failing after 5s
mount: windows conformance / WinFsp conformance (push) Has been cancelled
mount: windows / Mount on Windows (push) Has been cancelled
snapshot of https://github.com/seaweedfs/seaweedfs.git (master, 2026-09-16; blobs > 131072B omitted)
2026-09-16 03:23:42 +05:00

354 lines
10 KiB
Go

package lock_manager
import (
"fmt"
"sync"
"sync/atomic"
"time"
"github.com/google/uuid"
"github.com/seaweedfs/seaweedfs/weed/glog"
)
var LockErrorNonEmptyTokenOnNewLock = fmt.Errorf("lock: non-empty token on a new lock")
var LockErrorNonEmptyTokenOnExpiredLock = fmt.Errorf("lock: non-empty token on an expired lock")
var LockErrorTokenMismatch = fmt.Errorf("lock: token mismatch")
var UnlockErrorTokenMismatch = fmt.Errorf("unlock: token mismatch")
var LockNotFound = fmt.Errorf("lock not found")
// LockManager local lock manager, used by distributed lock manager
type LockManager struct {
locks map[string]*Lock
accessLock sync.RWMutex
nextGeneration atomic.Int64
}
type Lock struct {
Token string
ExpiredAtNs int64
Key string // only used for moving locks
Owner string
IsBackup bool // true if this node holds the lock as a backup
Generation int64 // monotonic fencing token, increments on fresh acquisition
Seq int64 // per-lock sequence number, increments on every mutation (acquire/renew/unlock)
}
func NewLockManager() *LockManager {
t := &LockManager{
locks: make(map[string]*Lock),
}
go t.CleanUp()
return t
}
func (lm *LockManager) NextGeneration() int64 {
return lm.nextGeneration.Add(1)
}
func compareMutationVersion(generation, seq int64, existingGeneration, existingSeq int64) int {
switch {
case generation < existingGeneration:
return -1
case generation > existingGeneration:
return 1
case seq < existingSeq:
return -1
case seq > existingSeq:
return 1
default:
return 0
}
}
func (lm *LockManager) advanceGenerationFloor(generation int64) {
for {
current := lm.nextGeneration.Load()
if generation < current {
return
}
if lm.nextGeneration.CompareAndSwap(current, generation) {
return
}
}
}
func (lm *LockManager) Lock(path string, expiredAtNs int64, token string, owner string) (lockOwner, renewToken string, generation int64, seq int64, err error) {
lm.accessLock.Lock()
defer lm.accessLock.Unlock()
glog.V(4).Infof("lock %s %v %v %v", path, time.Unix(0, expiredAtNs), token, owner)
if oldValue, found := lm.locks[path]; found {
if oldValue.ExpiredAtNs > 0 && oldValue.ExpiredAtNs < time.Now().UnixNano() {
// lock is expired, set to a new lock
if token != "" {
glog.V(4).Infof("lock expired key %s non-empty token %v owner %v ts %s", path, token, owner, time.Unix(0, oldValue.ExpiredAtNs))
err = LockErrorNonEmptyTokenOnExpiredLock
return
} else {
// new lock
renewToken = uuid.New().String()
generation = lm.NextGeneration()
seq = 1
glog.V(4).Infof("key %s new token %v owner %v generation %d", path, renewToken, owner, generation)
lm.locks[path] = &Lock{Token: renewToken, ExpiredAtNs: expiredAtNs, Owner: owner, Generation: generation, Seq: seq}
return
}
}
// not expired
lockOwner = oldValue.Owner
if oldValue.Token == token {
// token matches, renew the lock
renewToken = uuid.New().String()
generation = oldValue.Generation // keep same generation on renewal
seq = oldValue.Seq + 1
glog.V(4).Infof("key %s old token %v owner %v => %v owner %v", path, oldValue.Token, oldValue.Owner, renewToken, owner)
lm.locks[path] = &Lock{Token: renewToken, ExpiredAtNs: expiredAtNs, Owner: owner, Generation: generation, Seq: seq}
return
} else {
if token == "" {
// new lock
glog.V(4).Infof("key %s locked by %v", path, oldValue.Owner)
err = fmt.Errorf("lock already owned by %v", oldValue.Owner)
return
}
glog.V(4).Infof("key %s expected token %v owner %v received %v from %v", path, oldValue.Token, oldValue.Owner, token, owner)
err = fmt.Errorf("lock: token mismatch")
return
}
} else {
glog.V(4).Infof("key %s no lock owner %v", path, owner)
if token == "" {
// new lock
renewToken = uuid.New().String()
generation = lm.NextGeneration()
seq = 1
glog.V(4).Infof("key %s new token %v owner %v generation %d", path, renewToken, owner, generation)
lm.locks[path] = &Lock{Token: renewToken, ExpiredAtNs: expiredAtNs, Owner: owner, Generation: generation, Seq: seq}
return
} else {
glog.V(4).Infof("key %s non-empty token %v owner %v", path, token, owner)
err = LockErrorNonEmptyTokenOnNewLock
return
}
}
}
func (lm *LockManager) Unlock(path string, token string) (isUnlocked bool, generation int64, seq int64, err error) {
lm.accessLock.Lock()
defer lm.accessLock.Unlock()
if oldValue, found := lm.locks[path]; found {
now := time.Now()
if oldValue.ExpiredAtNs > 0 && oldValue.ExpiredAtNs < now.UnixNano() {
// lock is expired, delete it
isUnlocked = true
generation = oldValue.Generation
seq = oldValue.Seq + 1
glog.V(4).Infof("key %s expired at %v", path, time.Unix(0, oldValue.ExpiredAtNs))
delete(lm.locks, path)
return
}
if oldValue.Token == token {
isUnlocked = true
generation = oldValue.Generation
seq = oldValue.Seq + 1
glog.V(4).Infof("key %s unlocked with %v", path, token)
delete(lm.locks, path)
return
} else {
isUnlocked = false
err = UnlockErrorTokenMismatch
return
}
}
err = LockNotFound
return
}
func (lm *LockManager) CleanUp() {
for {
time.Sleep(1 * time.Minute)
now := time.Now().UnixNano()
lm.accessLock.Lock()
for key, value := range lm.locks {
if value == nil {
continue
}
if now > value.ExpiredAtNs {
glog.V(4).Infof("key %s expired at %v", key, time.Unix(0, value.ExpiredAtNs))
delete(lm.locks, key)
}
}
lm.accessLock.Unlock()
}
}
// SelectLocks takes out locks by key
// if selectFn returns true, the lock will be removed and returned
func (lm *LockManager) SelectLocks(selectFn func(key string) bool) (locks []*Lock) {
lm.accessLock.Lock()
defer lm.accessLock.Unlock()
now := time.Now().UnixNano()
for key, lock := range lm.locks {
if now > lock.ExpiredAtNs {
glog.V(4).Infof("key %s expired at %v", key, time.Unix(0, lock.ExpiredAtNs))
delete(lm.locks, key)
continue
}
if selectFn(key) {
glog.V(4).Infof("key %s selected and deleted", key)
delete(lm.locks, key)
lock.Key = key
locks = append(locks, lock)
}
}
return
}
// InsertLock inserts a lock from a transfer if it is newer than the current state.
func (lm *LockManager) InsertLock(path string, expiredAtNs int64, token string, owner string, generation int64, seq int64) bool {
lm.accessLock.Lock()
defer lm.accessLock.Unlock()
if existing, found := lm.locks[path]; found {
if compareMutationVersion(generation, seq, existing.Generation, existing.Seq) <= 0 {
glog.V(4).Infof("lock %s: rejecting stale transfer gen=%d seq=%d (current gen=%d seq=%d)", path, generation, seq, existing.Generation, existing.Seq)
return false
}
}
lm.locks[path] = &Lock{Token: token, ExpiredAtNs: expiredAtNs, Owner: owner, Generation: generation, Seq: seq}
lm.advanceGenerationFloor(generation)
return true
}
// InsertBackupLock inserts or updates a lock as a backup copy.
// It rejects stale mutations by comparing (generation, seq). If a current primary
// already exists on this node, newer replicated state refreshes that primary copy
// without demoting it back to a backup.
func (lm *LockManager) InsertBackupLock(path string, expiredAtNs int64, token string, owner string, generation int64, seq int64) {
lm.accessLock.Lock()
defer lm.accessLock.Unlock()
if existing, found := lm.locks[path]; found {
if compareMutationVersion(generation, seq, existing.Generation, existing.Seq) <= 0 {
glog.V(4).Infof("backup lock %s: rejecting stale gen=%d seq=%d (current gen=%d seq=%d)", path, generation, seq, existing.Generation, existing.Seq)
return
}
lm.locks[path] = &Lock{
Token: token,
ExpiredAtNs: expiredAtNs,
Owner: owner,
IsBackup: existing.IsBackup,
Generation: generation,
Seq: seq,
}
lm.advanceGenerationFloor(generation)
return
}
lm.locks[path] = &Lock{Token: token, ExpiredAtNs: expiredAtNs, Owner: owner, IsBackup: true, Generation: generation, Seq: seq}
lm.advanceGenerationFloor(generation)
}
// RemoveLock removes a lock by key
func (lm *LockManager) RemoveLock(path string) {
lm.accessLock.Lock()
defer lm.accessLock.Unlock()
delete(lm.locks, path)
}
// RemoveBackupLockIfSeq removes the local copy only if the incoming mutation is
// not older than the current (generation, seq). This prevents a late unlock from
// deleting a newer reacquired lock whose seq has reset.
func (lm *LockManager) RemoveBackupLockIfSeq(path string, generation int64, seq int64) bool {
lm.accessLock.Lock()
defer lm.accessLock.Unlock()
if existing, found := lm.locks[path]; found {
if compareMutationVersion(generation, seq, existing.Generation, existing.Seq) >= 0 {
delete(lm.locks, path)
return true
}
glog.V(4).Infof("backup lock %s: rejecting stale unlock gen=%d seq=%d (current gen=%d seq=%d)", path, generation, seq, existing.Generation, existing.Seq)
return false
}
return true
}
// GetLock returns a copy of the lock for a key, if it exists and is not expired
func (lm *LockManager) GetLock(key string) (*Lock, bool) {
lm.accessLock.RLock()
defer lm.accessLock.RUnlock()
lock, found := lm.locks[key]
if !found {
return nil, false
}
if time.Now().UnixNano() > lock.ExpiredAtNs {
return nil, false
}
// Return a copy
cp := *lock
return &cp, true
}
func (lm *LockManager) GetLockOwner(key string) (owner string, err error) {
lm.accessLock.RLock()
defer lm.accessLock.RUnlock()
if lock, found := lm.locks[key]; found {
if time.Now().UnixNano() > lock.ExpiredAtNs {
err = LockNotFound
return
}
return lock.Owner, nil
}
err = LockNotFound
return
}
// AllLocks returns a copy of all non-expired locks
func (lm *LockManager) AllLocks() []*Lock {
lm.accessLock.RLock()
defer lm.accessLock.RUnlock()
now := time.Now().UnixNano()
var result []*Lock
for key, lock := range lm.locks {
if now > lock.ExpiredAtNs {
continue
}
cp := *lock
cp.Key = key
result = append(result, &cp)
}
return result
}
// PromoteLock changes a backup lock to a primary lock
func (lm *LockManager) PromoteLock(key string) bool {
lm.accessLock.Lock()
defer lm.accessLock.Unlock()
if lock, found := lm.locks[key]; found && lock.IsBackup {
lock.IsBackup = false
return true
}
return false
}
// DemoteLock changes a primary lock to a backup lock
func (lm *LockManager) DemoteLock(key string) bool {
lm.accessLock.Lock()
defer lm.accessLock.Unlock()
if lock, found := lm.locks[key]; found && !lock.IsBackup {
lock.IsBackup = true
return true
}
return false
}