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
196 lines
5.0 KiB
Go
196 lines
5.0 KiB
Go
package dash
|
|
|
|
import (
|
|
"sync"
|
|
"time"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/cluster"
|
|
"github.com/seaweedfs/seaweedfs/weed/wdclient"
|
|
"github.com/seaweedfs/seaweedfs/weed/wdclient/exclusive_locks"
|
|
)
|
|
|
|
const (
|
|
adminLockName = cluster.AdminShellLockName
|
|
adminLockClientName = "admin-plugin"
|
|
)
|
|
|
|
const (
|
|
// A competing shell client polls the master once a second, while a local
|
|
// re-acquire would win immediately. Leave the lock free for slightly more
|
|
// than one poll interval so a waiting operator gets it first.
|
|
defaultAdminLockYieldWindow = 2 * time.Second
|
|
// After the lock has been held continuously for this long (overlapping
|
|
// reference-counted holds can keep it held indefinitely), new Acquire
|
|
// calls wait for a full release so shell clients are not starved.
|
|
defaultAdminLockFairnessWindow = time.Minute
|
|
)
|
|
|
|
// adminLocker is the subset of exclusive_locks.ExclusiveLocker the manager uses.
|
|
type adminLocker interface {
|
|
RequestLock(clientName string)
|
|
ReleaseLock()
|
|
SetMessage(message string)
|
|
}
|
|
|
|
// AdminLockManager coordinates exclusive admin locks with reference counting.
|
|
// It is safe for concurrent use.
|
|
type AdminLockManager struct {
|
|
locker adminLocker
|
|
clientName string
|
|
yieldWindow time.Duration
|
|
fairnessWindow time.Duration
|
|
|
|
mu sync.Mutex
|
|
cond *sync.Cond
|
|
acquiring bool
|
|
releasing bool
|
|
holdCount int
|
|
heldSince time.Time
|
|
|
|
lastAcquiredAt time.Time
|
|
lastReleasedAt time.Time
|
|
waitingSince time.Time
|
|
waitingReason string
|
|
currentReason string
|
|
}
|
|
|
|
func NewAdminLockManager(masterClient *wdclient.MasterClient, clientName string) *AdminLockManager {
|
|
if masterClient == nil {
|
|
return nil
|
|
}
|
|
if clientName == "" {
|
|
clientName = adminLockClientName
|
|
}
|
|
manager := &AdminLockManager{
|
|
locker: exclusive_locks.NewExclusiveLocker(masterClient, adminLockName),
|
|
clientName: clientName,
|
|
yieldWindow: defaultAdminLockYieldWindow,
|
|
fairnessWindow: defaultAdminLockFairnessWindow,
|
|
}
|
|
manager.cond = sync.NewCond(&manager.mu)
|
|
return manager
|
|
}
|
|
|
|
// Acquire takes the shared cluster lock, reference counted so overlapping
|
|
// admin-side holders piggyback on one lease. It must not be called while the
|
|
// caller's own call stack already holds the lock: once the fairness window
|
|
// makes new acquires wait for a full release, a nested Acquire deadlocks.
|
|
func (m *AdminLockManager) Acquire(reason string) (func(), error) {
|
|
if m == nil || m.locker == nil {
|
|
return func() {}, nil
|
|
}
|
|
|
|
m.mu.Lock()
|
|
if reason != "" {
|
|
m.locker.SetMessage(reason)
|
|
m.currentReason = reason
|
|
}
|
|
for m.acquiring || m.releasing || (m.holdCount > 0 && time.Since(m.heldSince) > m.fairnessWindow) {
|
|
m.cond.Wait()
|
|
}
|
|
if m.holdCount == 0 {
|
|
m.acquiring = true
|
|
m.waitingSince = time.Now().UTC()
|
|
m.waitingReason = reason
|
|
yield := time.Duration(0)
|
|
if !m.lastReleasedAt.IsZero() {
|
|
if since := time.Since(m.lastReleasedAt); since < m.yieldWindow {
|
|
yield = m.yieldWindow - since
|
|
}
|
|
}
|
|
m.mu.Unlock()
|
|
if yield > 0 {
|
|
time.Sleep(yield)
|
|
}
|
|
m.locker.RequestLock(m.clientName)
|
|
m.mu.Lock()
|
|
m.acquiring = false
|
|
m.holdCount = 1
|
|
m.heldSince = time.Now()
|
|
m.lastAcquiredAt = time.Now().UTC()
|
|
m.waitingSince = time.Time{}
|
|
m.waitingReason = ""
|
|
m.cond.Broadcast()
|
|
m.mu.Unlock()
|
|
return m.Release, nil
|
|
}
|
|
m.holdCount++
|
|
if reason != "" {
|
|
m.currentReason = reason
|
|
}
|
|
m.mu.Unlock()
|
|
return m.Release, nil
|
|
}
|
|
|
|
func (m *AdminLockManager) Release() {
|
|
if m == nil || m.locker == nil {
|
|
return
|
|
}
|
|
|
|
m.mu.Lock()
|
|
if m.holdCount <= 0 {
|
|
m.mu.Unlock()
|
|
return
|
|
}
|
|
m.holdCount--
|
|
shouldRelease := m.holdCount == 0
|
|
if shouldRelease {
|
|
// Block new acquires until ReleaseLock completes: a RequestLock
|
|
// issued while the locker still considers itself locked would no-op
|
|
// and leave a hold with no live lease.
|
|
m.releasing = true
|
|
}
|
|
m.mu.Unlock()
|
|
|
|
if shouldRelease {
|
|
m.locker.ReleaseLock()
|
|
m.mu.Lock()
|
|
m.releasing = false
|
|
m.lastReleasedAt = time.Now().UTC()
|
|
m.currentReason = ""
|
|
m.cond.Broadcast()
|
|
m.mu.Unlock()
|
|
}
|
|
}
|
|
|
|
type LockStatus struct {
|
|
Held bool `json:"held"`
|
|
HoldCount int `json:"hold_count"`
|
|
Acquiring bool `json:"acquiring"`
|
|
Message string `json:"message,omitempty"`
|
|
WaitingReason string `json:"waiting_reason,omitempty"`
|
|
LastAcquiredAt *time.Time `json:"last_acquired_at,omitempty"`
|
|
LastReleasedAt *time.Time `json:"last_released_at,omitempty"`
|
|
WaitingSince *time.Time `json:"waiting_since,omitempty"`
|
|
}
|
|
|
|
func (m *AdminLockManager) Status() LockStatus {
|
|
if m == nil {
|
|
return LockStatus{}
|
|
}
|
|
|
|
m.mu.Lock()
|
|
defer m.mu.Unlock()
|
|
|
|
status := LockStatus{
|
|
Held: m.holdCount > 0,
|
|
HoldCount: m.holdCount,
|
|
Acquiring: m.acquiring,
|
|
Message: m.currentReason,
|
|
WaitingReason: m.waitingReason,
|
|
}
|
|
if !m.lastAcquiredAt.IsZero() {
|
|
at := m.lastAcquiredAt
|
|
status.LastAcquiredAt = &at
|
|
}
|
|
if !m.lastReleasedAt.IsZero() {
|
|
at := m.lastReleasedAt
|
|
status.LastReleasedAt = &at
|
|
}
|
|
if !m.waitingSince.IsZero() {
|
|
at := m.waitingSince
|
|
status.WaitingSince = &at
|
|
}
|
|
return status
|
|
}
|