Function TestRemoteExecuteChangeServerDef

tensorflow/c/eager/c_api_test.cc:466–551

}

void TestRemoteExecuteChangeServerDef(bool async) {
  tensorflow::ServerDef server_def = GetServerDef(2);

  // This server def has the task index set to 0.
  string serialized = server_def.SerializeAsString();

  server_def.set_task_index(1);

  std::unique_ptr<tensorflow::GrpcServer> worker_server;
  ASSERT_TRUE(tensorflow::GrpcServer::Create(
                  server_def, tensorflow::Env::Default(), &worker_server)
                  .ok());
  ASSERT_TRUE(worker_server->Start().ok());

  TF_Status* status = TF_NewStatus();
  TFE_ContextOptions* opts = TFE_NewContextOptions();
  TFE_ContextOptionsSetAsync(opts, static_cast<unsigned char>(async));
  TFE_ContextOptionsSetDevicePlacementPolicy(opts, TFE_DEVICE_PLACEMENT_SILENT);
  TFE_Context* ctx = TFE_NewContext(opts, status);
  EXPECT_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);
  TFE_DeleteContextOptions(opts);

  TFE_ContextSetServerDef(ctx, 0, serialized.data(), serialized.size(), status);
  EXPECT_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);

  const char remote_device_name[] =
      "/job:localhost/replica:0/task:1/device:CPU:0";
  const char local_device_name[] =
      "/job:localhost/replica:0/task:0/device:CPU:0";
  CheckRemoteMatMulExecutesOK(ctx, remote_device_name, local_device_name);

  TFE_Executor* executor = TFE_ContextGetExecutorForThread(ctx);
  TFE_ExecutorWaitForAllPendingNodes(executor, status);
  ASSERT_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);

  // TODO(b/136478427): Figure out how to correctly shut the server down.
  worker_server.release();

  // Update the server def with a new set of names (worker instead of
  // localhost).
  tensorflow::ServerDef updated_server_def = GetServerDef("worker", 2);
  serialized = updated_server_def.SerializeAsString();

  updated_server_def.set_task_index(1);
  tensorflow::Status s = tensorflow::GrpcServer::Create(
      updated_server_def, tensorflow::Env::Default(), &worker_server);
  ASSERT_TRUE(s.ok()) << s.error_message();
  ASSERT_TRUE(worker_server->Start().ok());

  TFE_ContextSetServerDef(ctx, 0, serialized.data(), serialized.size(), status);
  EXPECT_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);

  // Create a new tensor_handle.
  TFE_TensorHandle* h0_task0_new = TestMatrixTensorHandle();

  // Check that copying it to the old remote device (named localhost) fails.
  TFE_TensorHandleCopyToDevice(h0_task0_new, ctx, remote_device_name, status);
  EXPECT_NE(TF_OK, TF_GetCode(status)) << TF_Message(status);