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
2025-07-30 12:38:03 -07:00
committed by GitHub
parent 64198dad83
commit 891a2fb6eb
130 changed files with 27737 additions and 4429 deletions

View File

@@ -402,3 +402,120 @@ func (vs *VolumeServer) CopyFile(req *volume_server_pb.CopyFileRequest, stream v
return nil
}
// ReceiveFile receives a file stream from client and writes it to storage
func (vs *VolumeServer) ReceiveFile(stream volume_server_pb.VolumeServer_ReceiveFileServer) error {
var fileInfo *volume_server_pb.ReceiveFileInfo
var targetFile *os.File
var filePath string
var bytesWritten uint64
defer func() {
if targetFile != nil {
targetFile.Close()
}
}()
for {
req, err := stream.Recv()
if err == io.EOF {
// Stream completed successfully
if targetFile != nil {
targetFile.Sync()
glog.V(1).Infof("Successfully received file %s (%d bytes)", filePath, bytesWritten)
}
return stream.SendAndClose(&volume_server_pb.ReceiveFileResponse{
BytesWritten: bytesWritten,
})
}
if err != nil {
// Clean up on error
if targetFile != nil {
targetFile.Close()
os.Remove(filePath)
}
glog.Errorf("Failed to receive stream: %v", err)
return fmt.Errorf("failed to receive stream: %v", err)
}
switch data := req.Data.(type) {
case *volume_server_pb.ReceiveFileRequest_Info:
// First message contains file info
fileInfo = data.Info
glog.V(1).Infof("ReceiveFile: volume %d, ext %s, collection %s, shard %d, size %d",
fileInfo.VolumeId, fileInfo.Ext, fileInfo.Collection, fileInfo.ShardId, fileInfo.FileSize)
// Create file path based on file info
if fileInfo.IsEcVolume {
// Find storage location for EC shard
var targetLocation *storage.DiskLocation
for _, location := range vs.store.Locations {
if location.DiskType == types.HardDriveType {
targetLocation = location
break
}
}
if targetLocation == nil && len(vs.store.Locations) > 0 {
targetLocation = vs.store.Locations[0] // Fall back to first available location
}
if targetLocation == nil {
glog.Errorf("ReceiveFile: no storage location available")
return stream.SendAndClose(&volume_server_pb.ReceiveFileResponse{
Error: "no storage location available",
})
}
// Create EC shard file path
baseFileName := erasure_coding.EcShardBaseFileName(fileInfo.Collection, int(fileInfo.VolumeId))
filePath = util.Join(targetLocation.Directory, baseFileName+fileInfo.Ext)
} else {
// Regular volume file
v := vs.store.GetVolume(needle.VolumeId(fileInfo.VolumeId))
if v == nil {
glog.Errorf("ReceiveFile: volume %d not found", fileInfo.VolumeId)
return stream.SendAndClose(&volume_server_pb.ReceiveFileResponse{
Error: fmt.Sprintf("volume %d not found", fileInfo.VolumeId),
})
}
filePath = v.FileName(fileInfo.Ext)
}
// Create target file
targetFile, err = os.Create(filePath)
if err != nil {
glog.Errorf("ReceiveFile: failed to create file %s: %v", filePath, err)
return stream.SendAndClose(&volume_server_pb.ReceiveFileResponse{
Error: fmt.Sprintf("failed to create file: %v", err),
})
}
glog.V(1).Infof("ReceiveFile: created target file %s", filePath)
case *volume_server_pb.ReceiveFileRequest_FileContent:
// Subsequent messages contain file content
if targetFile == nil {
glog.Errorf("ReceiveFile: file info must be sent first")
return stream.SendAndClose(&volume_server_pb.ReceiveFileResponse{
Error: "file info must be sent first",
})
}
n, err := targetFile.Write(data.FileContent)
if err != nil {
targetFile.Close()
os.Remove(filePath)
glog.Errorf("ReceiveFile: failed to write to file %s: %v", filePath, err)
return stream.SendAndClose(&volume_server_pb.ReceiveFileResponse{
Error: fmt.Sprintf("failed to write file: %v", err),
})
}
bytesWritten += uint64(n)
glog.V(2).Infof("ReceiveFile: wrote %d bytes to %s (total: %d)", n, filePath, bytesWritten)
default:
glog.Errorf("ReceiveFile: unknown message type")
return stream.SendAndClose(&volume_server_pb.ReceiveFileResponse{
Error: "unknown message type",
})
}
}
}