Files
seaweedfs/weed/operation/grpc_client.go
T
Chris LuandGitHub 2386fa550a grpc: don't tear down the shared master connection on a caller's own timeout (#9775)
A Canceled/DeadlineExceeded from the caller's per-request context was
treated like a dead channel: it closed the shared cached ClientConn and
cancelled every other in-flight RPC on it with "the client connection is
closing". Under a burst of concurrent chunk assigns (e.g. a large S3
multipart upload) one slow assign hitting its 10s attempt timeout could
poison the connection for all the rest, cascading into a flood of 500s.

Thread the caller's context into shouldInvalidateConnection and only
invalidate on Canceled/DeadlineExceeded while that context is still live,
which isolates the genuine stale-channel signal (a peer restart behind a
k8s Service VIP). To carry the context, add a ctx parameter to the
existing WithGrpcClient, WithMasterClient, and WithMasterServerClient; the
master assign and volume-lookup paths pass their per-attempt context and
every other caller passes context.Background().
2026-06-01 15:11:02 -07:00

29 lines
1.2 KiB
Go

package operation
import (
"context"
"google.golang.org/grpc"
"github.com/seaweedfs/seaweedfs/weed/pb"
"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
"github.com/seaweedfs/seaweedfs/weed/pb/volume_server_pb"
)
func WithVolumeServerClient(streamingMode bool, volumeServer pb.ServerAddress, grpcDialOption grpc.DialOption, fn func(volume_server_pb.VolumeServerClient) error) error {
return pb.WithGrpcClient(context.Background(), streamingMode, 0, func(grpcConnection *grpc.ClientConn) error {
client := volume_server_pb.NewVolumeServerClient(grpcConnection)
return fn(client)
}, volumeServer.ToGrpcAddress(), false, grpcDialOption)
}
// WithMasterServerClient threads the caller's per-request context into the
// connection-invalidation decision, so a Canceled/DeadlineExceeded from the
// caller's own timeout does not invalidate the shared cached master connection.
// Pass context.Background() when there is no per-request deadline to honor.
func WithMasterServerClient(ctx context.Context, streamingMode bool, masterServer pb.ServerAddress, grpcDialOption grpc.DialOption, fn func(masterClient master_pb.SeaweedClient) error) error {
return pb.WithMasterClient(ctx, streamingMode, masterServer, grpcDialOption, false, fn)
}