wip

Change-Id: I62576667da33589a32cb90e5417bac64a0192355

cmd/dcgm-exporter/main.go

@@ -20,6 +20,8 @@ import (
 	"log/slog"
 	"os"
 
+	_ "go.uber.org/automaxprocs"
+
 	"github.com/NVIDIA/dcgm-exporter/pkg/cmd"
 )
 

internal/pkg/transformation/kubernetes_test.go

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021, NVIDIA CORPORATION.  All rights reserved.
+ * Copyright (c) 2024, NVIDIA CORPORATION.  All rights reserved.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -20,6 +20,10 @@ import (
 	"fmt"
 	"testing"
 
+	"testing"
+
+	"github.com/sirupsen/logrus"
+
 	mockdeviceinfo "github.com/NVIDIA/dcgm-exporter/internal/mocks/pkg/deviceinfo"
 
 	mocknvmlprovider "github.com/NVIDIA/dcgm-exporter/internal/mocks/pkg/nvmlprovider"
@@ -33,13 +37,15 @@ import (
 	"github.com/NVIDIA/dcgm-exporter/internal/pkg/appconfig"
 	"github.com/NVIDIA/dcgm-exporter/internal/pkg/collector"
 	"github.com/NVIDIA/dcgm-exporter/internal/pkg/counters"
+	"github.com/NVIDIA/dcgm-exporter/internal/pkg/dcgmprovider"
 	"github.com/NVIDIA/dcgm-exporter/internal/pkg/deviceinfo"
 	"github.com/NVIDIA/dcgm-exporter/internal/pkg/nvmlprovider"
 	"github.com/NVIDIA/dcgm-exporter/internal/pkg/testutils"
 )
 
 func TestProcessPodMapper_WithD_Different_Format_Of_DeviceID(t *testing.T) {
 	testutils.RequireLinux(t)
+	logrus.SetLevel(logrus.DebugLevel)
 
 	type TestCase struct {
 		KubernetesGPUIDType  appconfig.KubernetesGPUIDType
@@ -275,13 +281,16 @@ func TestProcessPodMapper_WithD_Different_Format_Of_DeviceID(t *testing.T) {
 				defer cleanup()
 				socketPath := tmpDir + "/kubelet.sock"
 				server := grpc.NewServer()
+				config := &appconfig.Config{
+					UseRemoteHE: false,
+				}
 
-				cleanup, err := dcgm.Init(dcgm.Embedded)
-				require.NoError(t, err)
-				defer cleanup()
+				dcgmprovider.Initialize(config)
+				defer dcgmprovider.Client().Cleanup()
 
 				gpus := tc.PODGPUIDs
-				podresourcesapi.RegisterPodResourcesListerServer(server, testutils.NewMockPodResourcesServer(tc.ResourceName, gpus))
+				podresourcesapi.RegisterPodResourcesListerServer(server,
+					testutils.NewMockPodResourcesServer(tc.ResourceName, gpus))
 
 				cleanup = testutils.StartMockServer(t, server, socketPath)
 				defer cleanup()
@@ -291,6 +300,7 @@ func TestProcessPodMapper_WithD_Different_Format_Of_DeviceID(t *testing.T) {
 					GPUInstanceID:     3,
 					ComputeInstanceID: 0,
 				}
+
 				ctrl := gomock.NewController(t)
 				mockNVMLProvider := mocknvmlprovider.NewMockNVML(ctrl)
 				mockNVMLProvider.EXPECT().GetMIGDeviceInfoByID(gomock.Any()).Return(migDeviceInfo, nil).AnyTimes()
@@ -337,7 +347,7 @@ func TestProcessPodMapper_WithD_Different_Format_Of_DeviceID(t *testing.T) {
 				mockSystemInfo.EXPECT().GPUCount().Return(uint(1)).AnyTimes()
 				mockSystemInfo.EXPECT().GPU(uint(0)).Return(mockGPU).AnyTimes()
 
-				err = podMapper.Process(metrics, mockSystemInfo)
+				err := podMapper.Process(metrics, mockSystemInfo)
 				require.NoError(t, err)
 				assert.Len(t, metrics, 1)
 				if tc.KubernetesVirtualGPU {