fix: add grpc keep_alive (#141)

client/cmd/internal/connection/connection.go

@@ -12,6 +12,7 @@ import (
 	grpc_prometheus "github.com/grpc-ecosystem/go-grpc-prometheus"
 	"go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc"
 	"google.golang.org/grpc"
+	"google.golang.org/grpc/keepalive"
 
 	"github.com/goto/optimus/config"
 )
@@ -72,6 +73,11 @@ func defaultDialOptions() []grpc.DialOption {
 			otelgrpc.StreamClientInterceptor(),
 			grpc_prometheus.StreamClientInterceptor,
 		)),
+		grpc.WithKeepaliveParams(keepalive.ClientParameters{
+			Time:                time.Minute,     // send pings every 1 Minute if there is no activity
+			Timeout:             1 * time.Second, // wait 1 second for ping ack before considering the connection dead
+			PermitWithoutStream: true,            // send pings even without active streams
+		}),
 	)
 	return opts
 }

server/server.go

@@ -25,6 +25,7 @@ import (
 	"google.golang.org/grpc/codes"
 	"google.golang.org/grpc/health"
 	healthpb "google.golang.org/grpc/health/grpc_health_v1"
+	"google.golang.org/grpc/keepalive"
 	"google.golang.org/grpc/reflection"
 	"google.golang.org/grpc/status"
 
@@ -92,6 +93,10 @@ func setupGRPCServer(l log.Logger) (*grpc.Server, error) {
 		),
 		grpc.MaxRecvMsgSize(GRPCMaxRecvMsgSize),
 		grpc.MaxSendMsgSize(GRPCMaxSendMsgSize),
+		grpc.KeepaliveParams(keepalive.ServerParameters{
+			Time:    1 * time.Minute, // Ping the client if it is idle for 1 minute to ensure the connection is still active
+			Timeout: 1 * time.Second, // Wait 1 second for the ping ack before assuming the connection is dead
+		}),
 	}
 	grpcServer := grpc.NewServer(grpcOpts...)