fix(worker): add metrics HTTP server and health checks for Kubernetes (#7860)

* feat(worker): add metrics HTTP server and debug profiling support

- Add -metricsPort flag to enable Prometheus metrics endpoint
- Add -metricsIp flag to configure metrics server bind address
- Implement /metrics endpoint for Prometheus-compatible metrics
- Implement /health endpoint for Kubernetes readiness/liveness probes
- Add -debug flag to enable pprof debugging server
- Add -debug.port flag to configure debug server port
- Fix stats package import naming conflict by using alias
- Update usage examples to show new flags

Fixes #7843

* feat(helm): add worker metrics and health check support

- Update worker readiness probe to use httpGet on /health endpoint
- Update worker liveness probe to use httpGet on /health endpoint
- Add metricsPort flag to worker command in deployment template
- Support both httpGet and tcpSocket probe types for backward compatibility
- Update values.yaml with health check configuration

This enables Kubernetes pod lifecycle management for worker components through
proper health checks on the new metrics HTTP endpoint.

* feat(mini): align all services to share single debug and metrics servers

- Disable S3's separate debug server in mini mode (port 6060 now shared by all)
- Add metrics server startup to embedded worker for health monitoring
- All services now share the single metrics port (9327) and single debug port (6060)
- Consistent pattern with master, filer, volume, webdav services

* fix(worker): fix variable shadowing in health check handler

- Rename http.ResponseWriter parameter from 'w' to 'rw' to avoid shadowing
  the outer 'w *worker.Worker' parameter
- Prevents potential bugs if future code tries to use worker state in handler
- Improves code clarity and follows Go best practices

* fix(worker): remove unused worker parameter in metrics server

- Change 'w *worker.Worker' parameter to '_' as it's not used
- Clarifies intent that parameter is intentionally unused
- Follows Go best practices and improves code clarity

* fix(helm): fix trailing backslash syntax errors in worker command

- Fix conditional backslash placement to prevent shell syntax errors
- Only add backslash when metricsPort OR extraArgs are present
- Prevents worker pod startup failures due to malformed command arguments
- Ensures proper shell command parsing regardless of configuration state

* refactor(worker): use standard stats.StartMetricsServer for consistency

- Replace custom metrics server implementation with stats.StartMetricsServer
  to match pattern used in master, volume, s3, filer_sync components
- Simplifies code and improves maintainability
- Uses glog.Fatal for errors (consistent with other SeaweedFS components)
- Remove unused net/http and prometheus/promhttp imports
- Automatically provides /metrics and /health endpoints via standard implementation
This commit is contained in:
Chris Lu
2025-12-23 11:46:34 -08:00
committed by GitHub
parent 621ff124f0
commit 88ed187c27
4 changed files with 52 additions and 11 deletions

View File

@@ -10,7 +10,9 @@ import (
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/security"
statsCollect "github.com/seaweedfs/seaweedfs/weed/stats"
"github.com/seaweedfs/seaweedfs/weed/util"
"github.com/seaweedfs/seaweedfs/weed/util/grace"
"github.com/seaweedfs/seaweedfs/weed/worker"
"github.com/seaweedfs/seaweedfs/weed/worker/tasks"
"github.com/seaweedfs/seaweedfs/weed/worker/types"
@@ -25,7 +27,7 @@ import (
)
var cmdWorker = &Command{
UsageLine: "worker -admin=<admin_server> [-capabilities=<task_types>] [-maxConcurrent=<num>] [-workingDir=<path>]",
UsageLine: "worker -admin=<admin_server> [-capabilities=<task_types>] [-maxConcurrent=<num>] [-workingDir=<path>] [-metricsPort=<port>] [-debug]",
Short: "start a maintenance worker to process cluster maintenance tasks",
Long: `Start a maintenance worker that connects to an admin server to process
maintenance tasks like vacuum, erasure coding, remote upload, and replication fixes.
@@ -39,6 +41,8 @@ Examples:
weed worker -admin=localhost:23646 -capabilities=vacuum,replication
weed worker -admin=localhost:23646 -maxConcurrent=4
weed worker -admin=localhost:23646 -workingDir=/tmp/worker
weed worker -admin=localhost:23646 -metricsPort=9327
weed worker -admin=localhost:23646 -debug -debug.port=6060
`,
}
@@ -49,6 +53,10 @@ var (
workerHeartbeatInterval = cmdWorker.Flag.Duration("heartbeat", 30*time.Second, "heartbeat interval")
workerTaskRequestInterval = cmdWorker.Flag.Duration("taskInterval", 5*time.Second, "task request interval")
workerWorkingDir = cmdWorker.Flag.String("workingDir", "", "working directory for the worker")
workerMetricsPort = cmdWorker.Flag.Int("metricsPort", 0, "Prometheus metrics listen port")
workerMetricsIp = cmdWorker.Flag.String("metricsIp", "0.0.0.0", "Prometheus metrics listen IP")
workerDebug = cmdWorker.Flag.Bool("debug", false, "serves runtime profiling data via pprof on the port specified by -debug.port")
workerDebugPort = cmdWorker.Flag.Int("debug.port", 6060, "http port for debugging")
)
func init() {
@@ -60,6 +68,10 @@ func init() {
}
func runWorker(cmd *Command, args []string) bool {
if *workerDebug {
grace.StartDebugServer(*workerDebugPort)
}
util.LoadConfiguration("security", false)
glog.Infof("Starting maintenance worker")
@@ -153,6 +165,11 @@ func runWorker(cmd *Command, args []string) bool {
glog.Infof("Current working directory: %s", wd)
}
// Start metrics HTTP server if port is specified
if *workerMetricsPort > 0 {
go startWorkerMetricsServer(*workerMetricsIp, *workerMetricsPort, workerInstance)
}
// Start the worker
err = workerInstance.Start()
if err != nil {
@@ -239,3 +256,9 @@ type WorkerStatus struct {
TasksCompleted int `json:"tasks_completed"`
TasksFailed int `json:"tasks_failed"`
}
// startWorkerMetricsServer starts the HTTP metrics server for the worker
func startWorkerMetricsServer(ip string, port int, _ *worker.Worker) {
// Use the standard SeaweedFS metrics server for consistency with other components
statsCollect.StartMetricsServer(ip, port)
}