mirror of
https://gitee.com/milvus-io/milvus.git
synced 2026-01-07 19:31:51 +08:00
ee216877bb
Add support for DataNode compaction using file resources in ref mode. SortCompation and StatsJobs will build text indexes, which may use file resources. relate: https://github.com/milvus-io/milvus/issues/43687 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> - Core invariant: file resources (analyzer binaries/metadata) are only fetched, downloaded and used when the node is configured in Ref mode (fileresource.IsRefMode via CommonCfg.QNFileResourceMode / DNFileResourceMode); Sync now carries a version and managers track per-resource versions/resource IDs so newer resource sets win and older entries are pruned (RefManager/SynchManager resource maps). - Logic removed / simplified: component-specific FileResourceMode flags and an indirection through a long-lived BinlogIO wrapper were consolidated — file-resource mode moved to CommonCfg, Sync/Download APIs became version- and context-aware, and compaction/index tasks accept a ChunkManager directly (binlog IO wrapper creation inlined). This eliminates duplicated config checks and wrapper indirection while preserving the same chunk/IO semantics. - Why no data loss or behavior regression: all file-resource code paths are gated by the configured mode (default remains "sync"); when not in ref-mode or when no resources exist, compaction and stats flows follow existing code paths unchanged. Versioned Sync + resourceID maps ensure newly synced sets replace older ones and RefManager prunes stale files; GetFileResources returns an error if requested IDs are missing (prevents silent use of wrong resources). Analyzer naming/parameter changes add analyzer_extra_info but default-callers pass "" so existing analyzers and index contents remain unchanged. - New capability: DataNode compaction and StatsJobs can now build text indexes using external file resources in Ref mode — DataCoord exposes GetFileResources and populates CompactionPlan.file_resources; SortCompaction/StatsTask download resources via fileresource.Manager, produce an analyzer_extra_info JSON (storage + resource->id map) via analyzer.BuildExtraResourceInfo, and propagate analyzer_extra_info into BuildIndexInfo so the tantivy bindings can load custom analyzers during text index creation. <!-- end of auto-generated comment: release notes by coderabbit.ai --> Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
91 lines
2.9 KiB
Go
91 lines
2.9 KiB
Go
package server
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
|
|
"google.golang.org/grpc"
|
|
|
|
"github.com/milvus-io/milvus/internal/streamingnode/client/handler/registry"
|
|
"github.com/milvus-io/milvus/internal/streamingnode/server/resource"
|
|
"github.com/milvus-io/milvus/internal/streamingnode/server/service"
|
|
"github.com/milvus-io/milvus/internal/streamingnode/server/walmanager"
|
|
"github.com/milvus-io/milvus/internal/util/fileresource"
|
|
"github.com/milvus-io/milvus/internal/util/initcore"
|
|
"github.com/milvus-io/milvus/internal/util/sessionutil"
|
|
"github.com/milvus-io/milvus/pkg/v2/log"
|
|
"github.com/milvus-io/milvus/pkg/v2/proto/streamingpb"
|
|
_ "github.com/milvus-io/milvus/pkg/v2/streaming/walimpls/impls/kafka"
|
|
_ "github.com/milvus-io/milvus/pkg/v2/streaming/walimpls/impls/pulsar"
|
|
_ "github.com/milvus-io/milvus/pkg/v2/streaming/walimpls/impls/rmq"
|
|
"github.com/milvus-io/milvus/pkg/v2/util/paramtable"
|
|
)
|
|
|
|
// Server is the streamingnode server.
|
|
type Server struct {
|
|
// session of current server.
|
|
session *sessionutil.Session
|
|
grpcServer *grpc.Server
|
|
|
|
// service level instances.
|
|
handlerService service.HandlerService
|
|
managerService service.ManagerService
|
|
|
|
// basic component instances.
|
|
walManager walmanager.Manager
|
|
}
|
|
|
|
// Init initializes the streamingnode server.
|
|
func (s *Server) init() {
|
|
log.Info("init streamingnode server...")
|
|
// init all basic components.
|
|
s.initBasicComponent()
|
|
|
|
// init all service.
|
|
s.initService()
|
|
|
|
// init file resource manager
|
|
fileresource.InitManager(resource.Resource().ChunkManager(), fileresource.ParseMode(paramtable.Get().CommonCfg.QNFileResourceMode.GetValue()))
|
|
|
|
log.Info("init query segcore...")
|
|
if err := initcore.InitQueryNode(context.TODO()); err != nil {
|
|
panic(fmt.Sprintf("init query node segcore failed, %+v", err))
|
|
}
|
|
|
|
log.Info("streamingnode server initialized")
|
|
}
|
|
|
|
// Stop stops the streamingnode server.
|
|
func (s *Server) Stop() {
|
|
log.Info("stopping streamingnode server...")
|
|
log.Info("close wal manager...")
|
|
s.walManager.Close()
|
|
log.Info("release streamingnode resources...")
|
|
resource.Release()
|
|
log.Info("streamingnode server stopped")
|
|
}
|
|
|
|
// initBasicComponent initialize all underlying dependency for streamingnode.
|
|
func (s *Server) initBasicComponent() {
|
|
var err error
|
|
s.walManager, err = walmanager.OpenManager()
|
|
if err != nil {
|
|
panic(fmt.Sprintf("open wal manager failed, %+v", err))
|
|
}
|
|
// Register the wal manager to the local registry.
|
|
registry.RegisterLocalWALManager(s.walManager)
|
|
}
|
|
|
|
// initService initializes the grpc service.
|
|
func (s *Server) initService() {
|
|
s.handlerService = service.NewHandlerService(s.walManager)
|
|
s.managerService = service.NewManagerService(s.walManager)
|
|
s.registerGRPCService(s.grpcServer)
|
|
}
|
|
|
|
// registerGRPCService register all grpc service to grpc server.
|
|
func (s *Server) registerGRPCService(grpcServer *grpc.Server) {
|
|
streamingpb.RegisterStreamingNodeHandlerServiceServer(grpcServer, s.handlerService)
|
|
streamingpb.RegisterStreamingNodeManagerServiceServer(grpcServer, s.managerService)
|
|
}
|