1
0
Fork 0
mirror of https://github.com/chrislusf/seaweedfs synced 2025-08-16 17:12:46 +02:00
seaweedfs/weed/pb/master.proto
Chris Lu 891a2fb6eb
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>
2025-07-30 12:38:03 -07:00

444 lines
No EOL
10 KiB
Protocol Buffer

syntax = "proto3";
package master_pb;
option go_package = "github.com/seaweedfs/seaweedfs/weed/pb/master_pb";
//////////////////////////////////////////////////
service Seaweed {
rpc SendHeartbeat (stream Heartbeat) returns (stream HeartbeatResponse) {
}
rpc KeepConnected (stream KeepConnectedRequest) returns (stream KeepConnectedResponse) {
}
rpc LookupVolume (LookupVolumeRequest) returns (LookupVolumeResponse) {
}
rpc Assign (AssignRequest) returns (AssignResponse) {
}
rpc StreamAssign (stream AssignRequest) returns (stream AssignResponse) {
}
rpc Statistics (StatisticsRequest) returns (StatisticsResponse) {
}
rpc CollectionList (CollectionListRequest) returns (CollectionListResponse) {
}
rpc CollectionDelete (CollectionDeleteRequest) returns (CollectionDeleteResponse) {
}
rpc VolumeList (VolumeListRequest) returns (VolumeListResponse) {
}
rpc LookupEcVolume (LookupEcVolumeRequest) returns (LookupEcVolumeResponse) {
}
rpc VacuumVolume (VacuumVolumeRequest) returns (VacuumVolumeResponse) {
}
rpc DisableVacuum (DisableVacuumRequest) returns (DisableVacuumResponse) {
}
rpc EnableVacuum (EnableVacuumRequest) returns (EnableVacuumResponse) {
}
rpc VolumeMarkReadonly (VolumeMarkReadonlyRequest) returns (VolumeMarkReadonlyResponse) {
}
rpc GetMasterConfiguration (GetMasterConfigurationRequest) returns (GetMasterConfigurationResponse) {
}
rpc ListClusterNodes (ListClusterNodesRequest) returns (ListClusterNodesResponse) {
}
rpc LeaseAdminToken (LeaseAdminTokenRequest) returns (LeaseAdminTokenResponse) {
}
rpc ReleaseAdminToken (ReleaseAdminTokenRequest) returns (ReleaseAdminTokenResponse) {
}
rpc Ping (PingRequest) returns (PingResponse) {
}
rpc RaftListClusterServers (RaftListClusterServersRequest) returns (RaftListClusterServersResponse) {
}
rpc RaftAddServer (RaftAddServerRequest) returns (RaftAddServerResponse) {
}
rpc RaftRemoveServer (RaftRemoveServerRequest) returns (RaftRemoveServerResponse) {
}
rpc VolumeGrow (VolumeGrowRequest) returns (VolumeGrowResponse) {
}
}
//////////////////////////////////////////////////
message Heartbeat {
string ip = 1;
uint32 port = 2;
string public_url = 3;
uint64 max_file_key = 5;
string data_center = 6;
string rack = 7;
uint32 admin_port = 8;
repeated VolumeInformationMessage volumes = 9;
// delta volumes
repeated VolumeShortInformationMessage new_volumes = 10;
repeated VolumeShortInformationMessage deleted_volumes = 11;
bool has_no_volumes = 12;
// erasure coding
repeated VolumeEcShardInformationMessage ec_shards = 16;
// delta erasure coding shards
repeated VolumeEcShardInformationMessage new_ec_shards = 17;
repeated VolumeEcShardInformationMessage deleted_ec_shards = 18;
bool has_no_ec_shards = 19;
map<string, uint32> max_volume_counts = 4;
uint32 grpc_port = 20;
repeated string location_uuids = 21;
}
message HeartbeatResponse {
uint64 volume_size_limit = 1;
string leader = 2;
string metrics_address = 3;
uint32 metrics_interval_seconds = 4;
repeated StorageBackend storage_backends = 5;
repeated string duplicated_uuids = 6;
bool preallocate = 7;
}
message VolumeInformationMessage {
uint32 id = 1;
uint64 size = 2;
string collection = 3;
uint64 file_count = 4;
uint64 delete_count = 5;
uint64 deleted_byte_count = 6;
bool read_only = 7;
uint32 replica_placement = 8;
uint32 version = 9;
uint32 ttl = 10;
uint32 compact_revision = 11;
int64 modified_at_second = 12;
string remote_storage_name = 13;
string remote_storage_key = 14;
string disk_type = 15;
uint32 disk_id = 16;
}
message VolumeShortInformationMessage {
uint32 id = 1;
string collection = 3;
uint32 replica_placement = 8;
uint32 version = 9;
uint32 ttl = 10;
string disk_type = 15;
uint32 disk_id = 16;
}
message VolumeEcShardInformationMessage {
uint32 id = 1;
string collection = 2;
uint32 ec_index_bits = 3;
string disk_type = 4;
uint64 expire_at_sec = 5; // used to record the destruction time of ec volume
uint32 disk_id = 6;
}
message StorageBackend {
string type = 1;
string id = 2;
map<string, string> properties = 3;
}
message Empty {
}
message SuperBlockExtra {
message ErasureCoding {
uint32 data = 1;
uint32 parity = 2;
repeated uint32 volume_ids = 3;
}
ErasureCoding erasure_coding = 1;
}
message KeepConnectedRequest {
string client_type = 1;
string client_address = 3;
string version = 4;
string filer_group = 5;
string data_center = 6;
string rack = 7;
}
message VolumeLocation {
string url = 1;
string public_url = 2;
repeated uint32 new_vids = 3;
repeated uint32 deleted_vids = 4;
string leader = 5; // optional when leader is not itself
string data_center = 6; // optional when DataCenter is in use
uint32 grpc_port = 7;
repeated uint32 new_ec_vids = 8;
repeated uint32 deleted_ec_vids = 9;
}
message ClusterNodeUpdate {
string node_type = 1;
string address = 2;
bool is_add = 4;
string filer_group = 5;
int64 created_at_ns = 6;
}
message KeepConnectedResponse {
VolumeLocation volume_location = 1;
ClusterNodeUpdate cluster_node_update = 2;
}
message LookupVolumeRequest {
repeated string volume_or_file_ids = 1;
string collection = 2; // optional, a bit faster if provided.
}
message LookupVolumeResponse {
message VolumeIdLocation {
string volume_or_file_id = 1;
repeated Location locations = 2;
string error = 3;
string auth = 4;
}
repeated VolumeIdLocation volume_id_locations = 1;
}
message Location {
string url = 1;
string public_url = 2;
uint32 grpc_port = 3;
string data_center = 4;
}
message AssignRequest {
uint64 count = 1;
string replication = 2;
string collection = 3;
string ttl = 4;
string data_center = 5;
string rack = 6;
string data_node = 7;
uint32 memory_map_max_size_mb = 8;
uint32 writable_volume_count = 9;
string disk_type = 10;
}
message VolumeGrowRequest {
uint32 writable_volume_count = 1;
string replication = 2;
string collection = 3;
string ttl = 4;
string data_center = 5;
string rack = 6;
string data_node = 7;
uint32 memory_map_max_size_mb = 8;
string disk_type = 9;
}
message AssignResponse {
string fid = 1;
uint64 count = 4;
string error = 5;
string auth = 6;
repeated Location replicas = 7;
Location location = 8;
}
message StatisticsRequest {
string replication = 1;
string collection = 2;
string ttl = 3;
string disk_type = 4;
}
message StatisticsResponse {
uint64 total_size = 4;
uint64 used_size = 5;
uint64 file_count = 6;
}
//
// collection related
//
message Collection {
string name = 1;
}
message CollectionListRequest {
bool include_normal_volumes = 1;
bool include_ec_volumes = 2;
}
message CollectionListResponse {
repeated Collection collections = 1;
}
message CollectionDeleteRequest {
string name = 1;
}
message CollectionDeleteResponse {
}
//
// volume related
//
message DiskInfo {
string type = 1;
int64 volume_count = 2;
int64 max_volume_count = 3;
int64 free_volume_count = 4;
int64 active_volume_count = 5;
repeated VolumeInformationMessage volume_infos = 6;
repeated VolumeEcShardInformationMessage ec_shard_infos = 7;
int64 remote_volume_count = 8;
uint32 disk_id = 9;
}
message DataNodeInfo {
string id = 1;
map<string, DiskInfo> diskInfos = 2;
uint32 grpc_port = 3;
}
message RackInfo {
string id = 1;
repeated DataNodeInfo data_node_infos = 2;
map<string, DiskInfo> diskInfos = 3;
}
message DataCenterInfo {
string id = 1;
repeated RackInfo rack_infos = 2;
map<string, DiskInfo> diskInfos = 3;
}
message TopologyInfo {
string id = 1;
repeated DataCenterInfo data_center_infos = 2;
map<string, DiskInfo> diskInfos = 3;
}
message VolumeListRequest {
}
message VolumeListResponse {
TopologyInfo topology_info = 1;
uint64 volume_size_limit_mb = 2;
}
message LookupEcVolumeRequest {
uint32 volume_id = 1;
}
message LookupEcVolumeResponse {
uint32 volume_id = 1;
message EcShardIdLocation {
uint32 shard_id = 1;
repeated Location locations = 2;
}
repeated EcShardIdLocation shard_id_locations = 2;
}
message VacuumVolumeRequest {
float garbage_threshold = 1;
uint32 volume_id = 2;
string collection = 3;
}
message VacuumVolumeResponse {
}
message DisableVacuumRequest {
}
message DisableVacuumResponse {
}
message EnableVacuumRequest {
}
message EnableVacuumResponse {
}
message VolumeMarkReadonlyRequest {
string ip = 1;
uint32 port = 2;
uint32 volume_id = 4;
string collection = 5;
uint32 replica_placement = 6;
uint32 version = 7;
uint32 ttl = 8;
string disk_type = 9;
bool is_readonly = 10;
}
message VolumeMarkReadonlyResponse {
}
message GetMasterConfigurationRequest {
}
message GetMasterConfigurationResponse {
string metrics_address = 1;
uint32 metrics_interval_seconds = 2;
repeated StorageBackend storage_backends = 3;
string default_replication = 4;
string leader = 5;
uint32 volume_size_limit_m_b = 6;
bool volume_preallocate = 7;
}
message ListClusterNodesRequest {
string client_type = 1;
string filer_group = 2;
int32 limit = 4;
}
message ListClusterNodesResponse {
message ClusterNode {
string address = 1;
string version = 2;
int64 created_at_ns = 4;
string data_center = 5;
string rack = 6;
}
repeated ClusterNode cluster_nodes = 1;
}
message LeaseAdminTokenRequest {
int64 previous_token = 1;
int64 previous_lock_time = 2;
string lock_name = 3;
string client_name = 4;
string message = 5;
}
message LeaseAdminTokenResponse {
int64 token = 1;
int64 lock_ts_ns = 2;
}
message ReleaseAdminTokenRequest {
int64 previous_token = 1;
int64 previous_lock_time = 2;
string lock_name = 3;
}
message ReleaseAdminTokenResponse {
}
message PingRequest {
string target = 1; // default to ping itself
string target_type = 2;
}
message PingResponse {
int64 start_time_ns = 1;
int64 remote_time_ns = 2;
int64 stop_time_ns = 3;
}
message RaftAddServerRequest {
string id = 1;
string address = 2;
bool voter = 3;
}
message RaftAddServerResponse {
}
message RaftRemoveServerRequest {
string id = 1;
bool force = 2;
}
message RaftRemoveServerResponse {
}
message RaftListClusterServersRequest {
}
message RaftListClusterServersResponse {
message ClusterServers {
string id = 1;
string address = 2;
string suffrage = 3;
bool isLeader = 4;
}
repeated ClusterServers cluster_servers = 1;
}
message VolumeGrowResponse {
}