Admin: misc improvements on admin server and workers. EC now works. (#7055)
* initial design * added simulation as tests * reorganized the codebase to move the simulation framework and tests into their own dedicated package * integration test. ec worker task * remove "enhanced" reference * start master, volume servers, filer Current Status ✅ Master: Healthy and running (port 9333) ✅ Filer: Healthy and running (port 8888) ✅ Volume Servers: All 6 servers running (ports 8080-8085) 🔄 Admin/Workers: Will start when dependencies are ready * generate write load * tasks are assigned * admin start wtih grpc port. worker has its own working directory * Update .gitignore * working worker and admin. Task detection is not working yet. * compiles, detection uses volumeSizeLimitMB from master * compiles * worker retries connecting to admin * build and restart * rendering pending tasks * skip task ID column * sticky worker id * test canScheduleTaskNow * worker reconnect to admin * clean up logs * worker register itself first * worker can run ec work and report status but: 1. one volume should not be repeatedly worked on. 2. ec shards needs to be distributed and source data should be deleted. * move ec task logic * listing ec shards * local copy, ec. Need to distribute. * ec is mostly working now * distribution of ec shards needs improvement * need configuration to enable ec * show ec volumes * interval field UI component * rename * integration test with vauuming * garbage percentage threshold * fix warning * display ec shard sizes * fix ec volumes list * Update ui.go * show default values * ensure correct default value * MaintenanceConfig use ConfigField * use schema defined defaults * config * reduce duplication * refactor to use BaseUIProvider * each task register its schema * checkECEncodingCandidate use ecDetector * use vacuumDetector * use volumeSizeLimitMB * remove remove * remove unused * refactor * use new framework * remove v2 reference * refactor * left menu can scroll now * The maintenance manager was not being initialized when no data directory was configured for persistent storage. * saving config * Update task_config_schema_templ.go * enable/disable tasks * protobuf encoded task configurations * fix system settings * use ui component * remove logs * interface{} Reduction * reduce interface{} * reduce interface{} * avoid from/to map * reduce interface{} * refactor * keep it DRY * added logging * debug messages * debug level * debug * show the log caller line * use configured task policy * log level * handle admin heartbeat response * Update worker.go * fix EC rack and dc count * Report task status to admin server * fix task logging, simplify interface checking, use erasure_coding constants * factor in empty volume server during task planning * volume.list adds disk id * track disk id also * fix locking scheduled and manual scanning * add active topology * simplify task detector * ec task completed, but shards are not showing up * implement ec in ec_typed.go * adjust log level * dedup * implementing ec copying shards and only ecx files * use disk id when distributing ec shards 🎯 Planning: ActiveTopology creates DestinationPlan with specific TargetDisk 📦 Task Creation: maintenance_integration.go creates ECDestination with DiskId 🚀 Task Execution: EC task passes DiskId in VolumeEcShardsCopyRequest 💾 Volume Server: Receives disk_id and stores shards on specific disk (vs.store.Locations[req.DiskId]) 📂 File System: EC shards and metadata land in the exact disk directory planned * Delete original volume from all locations * clean up existing shard locations * local encoding and distributing * Update docker/admin_integration/EC-TESTING-README.md Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * check volume id range * simplify * fix tests * fix types * clean up logs and tests --------- Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Chris Lu
@@ -3,6 +3,7 @@ package command
|
||||
import (
|
||||
"os"
|
||||
"os/signal"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"syscall"
|
||||
"time"
|
||||
@@ -21,7 +22,7 @@ import (
|
||||
)
|
||||
|
||||
var cmdWorker = &Command{
|
||||
UsageLine: "worker -admin=<admin_server> [-capabilities=<task_types>] [-maxConcurrent=<num>]",
|
||||
UsageLine: "worker -admin=<admin_server> [-capabilities=<task_types>] [-maxConcurrent=<num>] [-workingDir=<path>]",
|
||||
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.
|
||||
@@ -34,6 +35,7 @@ Examples:
|
||||
weed worker -admin=admin.example.com:23646
|
||||
weed worker -admin=localhost:23646 -capabilities=vacuum,replication
|
||||
weed worker -admin=localhost:23646 -maxConcurrent=4
|
||||
weed worker -admin=localhost:23646 -workingDir=/tmp/worker
|
||||
`,
|
||||
}
|
||||
|
||||
@@ -43,6 +45,7 @@ var (
|
||||
workerMaxConcurrent = cmdWorker.Flag.Int("maxConcurrent", 2, "maximum number of concurrent tasks")
|
||||
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")
|
||||
)
|
||||
|
||||
func init() {
|
||||
@@ -67,6 +70,45 @@ func runWorker(cmd *Command, args []string) bool {
|
||||
return false
|
||||
}
|
||||
|
||||
// Set working directory and create task-specific subdirectories
|
||||
var baseWorkingDir string
|
||||
if *workerWorkingDir != "" {
|
||||
glog.Infof("Setting working directory to: %s", *workerWorkingDir)
|
||||
if err := os.Chdir(*workerWorkingDir); err != nil {
|
||||
glog.Fatalf("Failed to change working directory: %v", err)
|
||||
return false
|
||||
}
|
||||
wd, err := os.Getwd()
|
||||
if err != nil {
|
||||
glog.Fatalf("Failed to get working directory: %v", err)
|
||||
return false
|
||||
}
|
||||
baseWorkingDir = wd
|
||||
glog.Infof("Current working directory: %s", baseWorkingDir)
|
||||
} else {
|
||||
// Use default working directory when not specified
|
||||
wd, err := os.Getwd()
|
||||
if err != nil {
|
||||
glog.Fatalf("Failed to get current working directory: %v", err)
|
||||
return false
|
||||
}
|
||||
baseWorkingDir = wd
|
||||
glog.Infof("Using current working directory: %s", baseWorkingDir)
|
||||
}
|
||||
|
||||
// Create task-specific subdirectories
|
||||
for _, capability := range capabilities {
|
||||
taskDir := filepath.Join(baseWorkingDir, string(capability))
|
||||
if err := os.MkdirAll(taskDir, 0755); err != nil {
|
||||
glog.Fatalf("Failed to create task directory %s: %v", taskDir, err)
|
||||
return false
|
||||
}
|
||||
glog.Infof("Created task directory: %s", taskDir)
|
||||
}
|
||||
|
||||
// Create gRPC dial option using TLS configuration
|
||||
grpcDialOption := security.LoadClientTLS(util.GetViper(), "grpc.worker")
|
||||
|
||||
// Create worker configuration
|
||||
config := &types.WorkerConfig{
|
||||
AdminServer: *workerAdminServer,
|
||||
@@ -74,6 +116,8 @@ func runWorker(cmd *Command, args []string) bool {
|
||||
MaxConcurrent: *workerMaxConcurrent,
|
||||
HeartbeatInterval: *workerHeartbeatInterval,
|
||||
TaskRequestInterval: *workerTaskRequestInterval,
|
||||
BaseWorkingDir: baseWorkingDir,
|
||||
GrpcDialOption: grpcDialOption,
|
||||
}
|
||||
|
||||
// Create worker instance
|
||||
@@ -82,9 +126,6 @@ func runWorker(cmd *Command, args []string) bool {
|
||||
glog.Fatalf("Failed to create worker: %v", err)
|
||||
return false
|
||||
}
|
||||
|
||||
// Create admin client with LoadClientTLS
|
||||
grpcDialOption := security.LoadClientTLS(util.GetViper(), "grpc.worker")
|
||||
adminClient, err := worker.CreateAdminClient(*workerAdminServer, workerInstance.ID(), grpcDialOption)
|
||||
if err != nil {
|
||||
glog.Fatalf("Failed to create admin client: %v", err)
|
||||
@@ -94,10 +135,25 @@ func runWorker(cmd *Command, args []string) bool {
|
||||
// Set admin client
|
||||
workerInstance.SetAdminClient(adminClient)
|
||||
|
||||
// Set working directory
|
||||
if *workerWorkingDir != "" {
|
||||
glog.Infof("Setting working directory to: %s", *workerWorkingDir)
|
||||
if err := os.Chdir(*workerWorkingDir); err != nil {
|
||||
glog.Fatalf("Failed to change working directory: %v", err)
|
||||
return false
|
||||
}
|
||||
wd, err := os.Getwd()
|
||||
if err != nil {
|
||||
glog.Fatalf("Failed to get working directory: %v", err)
|
||||
return false
|
||||
}
|
||||
glog.Infof("Current working directory: %s", wd)
|
||||
}
|
||||
|
||||
// Start the worker
|
||||
err = workerInstance.Start()
|
||||
if err != nil {
|
||||
glog.Fatalf("Failed to start worker: %v", err)
|
||||
glog.Errorf("Failed to start worker: %v", err)
|
||||
return false
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user