add dcgm info to the agent data. Upgrade golangcilint (#42)

* add dcgm info to the agent data. Upgrade golangcilint

* update action

* fix lint

Author: valner

.github/workflows/check.yaml

@@ -20,7 +20,7 @@ jobs:
           go-version: '1.22'
           cache: false
       - name: golangci-lint
-        uses: golangci/golangci-lint-action@v3
+        uses: golangci/golangci-lint-action@v8
   test:
     runs-on: ubuntu-latest
     steps:

.golangci.yaml

@@ -1,58 +1,68 @@
+version: "2"
 run:
-  timeout: 30m # big timeout as github actions are sloow
   allow-parallel-runners: true
 linters:
-  disable-all: true
+  default: none
   enable:
-    - errcheck # Errcheck is a program for checking for unchecked errors in Go code. These unchecked errors can be critical bugs in some cases
-    - gosimple # Linter for Go source code that specializes in simplifying code
-    - govet # Vet examines Go source code and reports suspicious constructs, such as Printf calls whose arguments do not align with the format string.
-    - ineffassign # Detects when assignments to existing variables are not used
-    - staticcheck # It's a set of rules from staticcheck. It's not the same thing as the staticcheck binary. The author of staticcheck doesn't support or approve the use of staticcheck as a library inside golangci-lint.
-    - typecheck # like the front-end of a Go compiler, parses and type-checks Go code
-    - unused # Checks Go code for unused constants, variables, functions and types.
-    - bodyclose # Checks whether HTTP response body is closed successfully.
-    - decorder # Check declaration order and count of types, constants, variables and functions.
-    - dogsled # Checks assignments with too many blank identifiers (e.g. x, , , _, := f()).
-    - dupword # Checks for duplicate words in the source code
-    - durationcheck # Check for two durations multiplied together.
-    - errchkjson # Checks types passed to the json encoding functions. Reports unsupported types and optionally reports occasions, where the check for the returned error can be omitted.
-    - errname # Checks that sentinel errors are prefixed with the Err and error types are suffixed with the Error.
-    - errorlint # Errorlint is a linter for that can be used to find code that will cause problems with the error wrapping scheme introduced in Go 1.13.
+    - bodyclose
     - copyloopvar
-    - gocheckcompilerdirectives # Checks that go compiler directive comments (//go:) are valid.
-    - gocognit # Computes and checks the cognitive complexity of functions.
-    - goconst # Finds repeated strings that could be replaced by a constant.
-    - gocritic # Provides diagnostics that check for bugs, performance and style issues.
-    - gocyclo # Computes and checks the cyclomatic complexity of functions.
-    - gofmt # Gofmt checks whether code was gofmt-ed. By default this tool runs with -s option to check for code simplification.
-    - importas # Enforces consistent import
-    - interfacebloat # A linter that checks the number of methods inside an interface.
-    - lll # Reports long lines.
-    - makezero # Finds slice declarations with non-zero initial length.
-    - misspell # Finds commonly misspelled English words in comments.
-    - nakedret # Finds naked returns in functions greater than a specified function length.
-    - nestif # Reports deeply nested if statements.
-    - noctx # Noctx finds sending http request without context.Context.
-    - prealloc # Finds slice declarations that could potentially be pre-allocated.
-    - predeclared # Find code that shadows one of Go's predeclared identifiers.
-    - reassign # Checks that package variables are not reassigned.
-    - tenv # Tenv is analyzer that detects using os.Setenv instead of t.Setenv since Go1.17.
-    - unconvert # Remove unnecessary type conversions.
-    - unparam # Reports unused function parameters.
-    - usestdlibvars # A linter that detect the possibility to use variables/constants from the Go standard library.
-    - whitespace # Tool for detection of leading and trailing whitespace.
-linters-settings:
-  gocognit:
-    min-complexity: 30
-  govet:
-    # report about shadowed variables
-    check-shadowing: false
-  lll:
-    # Max line length, lines longer will be reported.
-    # '\t' is counted as 1 character by default, and can be changed with the tab-width option.
-    # Default: 120.
-    line-length: 200
-  gocritic:
-    disabled-checks:
-      - ifElseChain
+    - decorder
+    - dogsled
+    - dupword
+    - durationcheck
+    - errcheck
+    - errchkjson
+    - errname
+    - errorlint
+    - gocheckcompilerdirectives
+    - gocognit
+    - goconst
+    - gocritic
+    - gocyclo
+    - govet
+    - importas
+    - ineffassign
+    - interfacebloat
+    - lll
+    - makezero
+    - misspell
+    - nakedret
+    - nestif
+    - noctx
+    - prealloc
+    - predeclared
+    - reassign
+    - staticcheck
+    - unconvert
+    - unparam
+    - unused
+    - usestdlibvars
+    - whitespace
+  settings:
+    gocognit:
+      min-complexity: 30
+    gocritic:
+      disabled-checks:
+        - ifElseChain
+    lll:
+      line-length: 200
+  exclusions:
+    generated: lax
+    presets:
+      - comments
+      - common-false-positives
+      - legacy
+      - std-error-handling
+    paths:
+      - third_party$
+      - builtin$
+      - examples$
+formatters:
+  enable:
+    - gofmt
+  exclusions:
+    generated: lax
+    paths:
+      - third_party$
+      - builtin$
+      - examples$

cmd/nebius-observability-agent-updater/main.go

@@ -7,6 +7,7 @@ import (
 	"github.com/nebius/nebius-observability-agent-updater/internal/application"
 	"github.com/nebius/nebius-observability-agent-updater/internal/client"
 	"github.com/nebius/nebius-observability-agent-updater/internal/config"
+	"github.com/nebius/nebius-observability-agent-updater/internal/dcgm"
 	"github.com/nebius/nebius-observability-agent-updater/internal/loggerhelper"
 	"github.com/nebius/nebius-observability-agent-updater/internal/metadata"
 	"github.com/nebius/nebius-observability-agent-updater/internal/osutils"
@@ -32,7 +33,8 @@ func main() {
 	logger := loggerhelper.InitLogger(&cfg.Logger)
 	metadataReader := metadata.NewReader(cfg.Metadata, logger)
 	oh := osutils.NewOsHelper()
-	cli, err := client.New(metadataReader, oh, cfg, logger, metadataReader.GetIamToken)
+	dh := dcgm.NewDcgmHelper()
+	cli, err := client.New(metadataReader, oh, dh, cfg, logger, metadataReader.GetIamToken)
 	if err != nil {
 		logger.Error("failed to create client", "error", err)
 		defer syscall.Exit(1)

go.mod

@@ -6,7 +6,7 @@ toolchain go1.23.3
 
 require (
 	github.com/cenkalti/backoff/v4 v4.3.0
-	github.com/nebius/gosdk v0.0.0-20250321225023-d65cca70d9a3
+	github.com/nebius/gosdk v0.0.0-20250505140419-9e3daa7d020f
 	github.com/shirou/gopsutil/v3 v3.24.5
 	github.com/stretchr/testify v1.9.0
 	go.uber.org/goleak v1.3.0

go.sum

@@ -14,8 +14,8 @@ github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
 github.com/lufia/plan9stats v0.0.0-20211012122336-39d0f177ccd0 h1:6E+4a0GO5zZEnZ81pIr0yLvtUWk2if982qA3F3QD6H4=
 github.com/lufia/plan9stats v0.0.0-20211012122336-39d0f177ccd0/go.mod h1:zJYVVT2jmtg6P3p1VtQj7WsuWi/y4VnjVBn7F8KPB3I=
-github.com/nebius/gosdk v0.0.0-20250321225023-d65cca70d9a3 h1:v5ET1Sv93c8y6+o3/GTGFfJiAag/LYIVdLJDGRP1z4I=
-github.com/nebius/gosdk v0.0.0-20250321225023-d65cca70d9a3/go.mod h1:d0iaJFMQofs+hV0K25+8wVvMHdNxPmxMbIYfhOpZAt8=
+github.com/nebius/gosdk v0.0.0-20250505140419-9e3daa7d020f h1:gPkLTbF+zYVsbid0drTulDbiPbcbKcVGKMdzlgJW/cY=
+github.com/nebius/gosdk v0.0.0-20250505140419-9e3daa7d020f/go.mod h1:d0iaJFMQofs+hV0K25+8wVvMHdNxPmxMbIYfhOpZAt8=
 github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
 github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/power-devops/perfstat v0.0.0-20210106213030-5aafc221ea8c h1:ncq/mPwQF4JjgDlrVEn3C11VoGHZN7m8qihwgMEtzYw=

internal/client/client.go

@@ -42,6 +42,11 @@ type oshelper interface {
 	GetLastLogs(serviceName string, lines int) (string, error)
 }
 
+type dcgmhelper interface {
+	GetDCGMVersion() (string, error)
+	GetGpuInfo() (model string, number int, err error)
+}
+
 const (
 	ENDPOINT_ENV     = "NEBIUS_OBSERVABILITY_AGENT_UPDATER_ENDPOINT"
 	UserAgent        = "nebius-observability-agent-updater"
@@ -58,11 +63,12 @@ type Client struct {
 	client           agentmanager.VersionServiceClient
 	logger           *slog.Logger
 	oh               oshelper
+	dh               dcgmhelper
 	retryBackoff     backoff.BackOff
 	getTokenCallback func() (string, error)
 }
 
-func New(metadata metadataReader, oh oshelper, config *config.Config, logger *slog.Logger, getTokenCallback func() (string, error)) (*Client, error) {
+func New(metadata metadataReader, oh oshelper, dh dcgmhelper, config *config.Config, logger *slog.Logger, getTokenCallback func() (string, error)) (*Client, error) {
 	if config.GRPC.Endpoint == "" {
 		endpoint := os.Getenv(ENDPOINT_ENV)
 		if endpoint == "" {
@@ -96,6 +102,7 @@ func New(metadata metadataReader, oh oshelper, config *config.Config, logger *sl
 		client:           client,
 		logger:           logger,
 		oh:               oh,
+		dh:               dh,
 		retryBackoff:     getRetryBackoff(config.GRPC.Retry),
 		getTokenCallback: getTokenCallback,
 	}, nil
@@ -321,5 +328,20 @@ func (s *Client) fillRequest(agent agents.AgentData) *agentmanager.GetVersionReq
 		req.CloudInitStatus = cloudInitStatus
 	}
 
+	dcgmVersion, err := s.dh.GetDCGMVersion()
+	if err != nil {
+		s.logger.Error("failed to get DCGM version", "error", err)
+	} else {
+		req.DcgmVersion = dcgmVersion
+	}
+
+	gpuModel, gpuNumber, err := s.dh.GetGpuInfo()
+	if err != nil {
+		s.logger.Error("failed to get GPU info", "error", err)
+	} else {
+		req.GpuModel = gpuModel
+		req.GpuNumber = int32(gpuNumber)
+	}
+
 	return &req
 }

internal/client/client_test.go

@@ -92,6 +92,20 @@ func (m *mockOSHelper) GetLastLogs(string, int) (string, error) {
 	return "logs", nil
 }
 
+type mockDcgmHelper struct {
+	mock.Mock
+}
+
+func (m *mockDcgmHelper) GetDCGMVersion() (string, error) {
+	args := m.Called()
+	return args.String(0), args.Error(1)
+}
+
+func (m *mockDcgmHelper) GetGpuInfo() (string, int, error) {
+	args := m.Called()
+	return args.String(0), args.Int(1), args.Error(2)
+}
+
 type mockVersionServiceClient struct {
 	mock.Mock
 }
@@ -154,8 +168,8 @@ func TestNew(t *testing.T) {
 			Timeout:  5 * time.Second,
 		},
 	}
-
-	client, err := New(metadata, oh, &cfg, nil, tokenFunc)
+	dh := &mockDcgmHelper{}
+	client, err := New(metadata, oh, dh, &cfg, nil, tokenFunc)
 	assert.NoError(t, err)
 	assert.NotNil(t, client)
 	assert.NotNil(t, client.conn)
@@ -165,11 +179,13 @@ func TestNew(t *testing.T) {
 func TestSendAgentData(t *testing.T) {
 	metadata := &mockMetadataReader{}
 	oh := &mockOSHelper{}
+	dh := &mockDcgmHelper{}
 	mockClient := &mockVersionServiceClient{}
 
 	client := &Client{
 		metadata:     metadata,
 		oh:           oh,
+		dh:           dh,
 		client:       mockClient,
 		retryBackoff: getRetryBackoff(clientconfig.GetDefaultRetryConfig()),
 		config: &config.Config{
@@ -191,6 +207,9 @@ func TestSendAgentData(t *testing.T) {
 	oh.On("GetArch").Return("x86_64", nil)
 	oh.On("GetMk8sClusterId").Return("abcd", nil)
 
+	dh.On("GetDCGMVersion").Return("3.3.7", nil)
+	dh.On("GetGpuInfo").Return("NVIDIA H200", 2, nil)
+
 	expectedResponse := &agentmanager.GetVersionResponse{
 		Action: agentmanager.Action_NOP,
 	}
@@ -219,10 +238,12 @@ func TestSendAgentData(t *testing.T) {
 func TestFillRequest(t *testing.T) {
 	metadata := &mockMetadataReader{}
 	oh := &mockOSHelper{}
+	dh := &mockDcgmHelper{}
 
 	client := &Client{
 		metadata:     metadata,
 		oh:           oh,
+		dh:           dh,
 		retryBackoff: getRetryBackoff(clientconfig.GetDefaultRetryConfig()),
 		logger:       slog.New(slog.NewTextHandler(os.Stdout, nil)),
 		config:       &config.Config{},
@@ -239,6 +260,9 @@ func TestFillRequest(t *testing.T) {
 	oh.On("GetArch").Return("x86_64", nil)
 	oh.On("GetMk8sClusterId", mock.Anything).Return("abcd", nil)
 
+	dh.On("GetDCGMVersion").Return("3.3.7", nil)
+	dh.On("GetGpuInfo").Return("NVIDIA H200", 2, nil)
+
 	// Create mock health check response using the correct structure
 	checkStatuses := map[string]healthcheck.CheckStatus{
 		"process": {
@@ -294,6 +318,9 @@ func TestFillRequest(t *testing.T) {
 	assert.Equal(t, durationpb.New(1*time.Hour), req.SystemUptime)
 	assert.Equal(t, "some-error", req.LastUpdateError)
 	assert.Equal(t, "abcd", req.Mk8SClusterId)
+	assert.Equal(t, "3.3.7", req.DcgmVersion)
+	assert.Equal(t, "NVIDIA H200", req.GpuModel)
+	assert.Equal(t, int32(2), req.GpuNumber)
 
 	// Verify module health statuses
 	assert.NotNil(t, req.ModulesHealth)
@@ -313,11 +340,13 @@ func TestFillRequest(t *testing.T) {
 func TestSendAgentDataWithRetry(t *testing.T) {
 	metadata := &mockMetadataReader{}
 	oh := &mockOSHelper{}
+	dh := &mockDcgmHelper{}
 	mockClient := &mockVersionServiceClient{}
 
 	client := &Client{
 		metadata: metadata,
 		oh:       oh,
+		dh:       dh,
 		client:   mockClient,
 		config: &config.Config{
 			GRPC: clientconfig.GRPCConfig{
@@ -344,6 +373,8 @@ func TestSendAgentDataWithRetry(t *testing.T) {
 	oh.On("GetArch").Return("x86_64", nil)
 	oh.On("GetMk8sClusterId").Return("abcd", nil)
 
+	dh.On("GetDCGMVersion").Return("3.3.7", nil)
+	dh.On("GetGpuInfo").Return("NVIDIA H200", 2, nil)
 	expectedResponse := &agentmanager.GetVersionResponse{
 		Action: agentmanager.Action_NOP,
 	}
@@ -381,11 +412,13 @@ func TestSendAgentDataWithRetry(t *testing.T) {
 func TestSendAgentDataWithRetryFailure(t *testing.T) {
 	metadata := &mockMetadataReader{}
 	oh := &mockOSHelper{}
+	dh := &mockDcgmHelper{}
 	mockClient := &mockVersionServiceClient{}
 
 	client := &Client{
 		metadata: metadata,
 		oh:       oh,
+		dh:       dh,
 		client:   mockClient,
 		config: &config.Config{
 			GRPC: clientconfig.GRPCConfig{
@@ -414,6 +447,9 @@ func TestSendAgentDataWithRetryFailure(t *testing.T) {
 	oh.On("GetArch").Return("x86_64", nil)
 	oh.On("GetMk8sClusterId").Return("abcd", nil)
 
+	dh.On("GetDCGMVersion").Return("3.3.7", nil)
+	dh.On("GetGpuInfo").Return("NVIDIA H200", 2, nil)
+
 	// Simulate continuous failures
 	mockClient.On("GetVersion", mock.Anything, mock.Anything, mock.Anything).
 		Return(nil, status.Error(codes.Unavailable, "Service unavailable")).Times(4)
@@ -444,10 +480,12 @@ func TestSendAgentDataWithRetryFailure(t *testing.T) {
 func TestFillRequestDebNotFound(t *testing.T) {
 	metadata := &mockMetadataReader{}
 	oh := &mockOSHelper{}
+	dh := &mockDcgmHelper{}
 
 	client := &Client{
 		metadata:     metadata,
 		oh:           oh,
+		dh:           dh,
 		logger:       slog.New(slog.NewTextHandler(os.Stdout, nil)),
 		retryBackoff: getRetryBackoff(clientconfig.GetDefaultRetryConfig()),
 		config:       &config.Config{},
@@ -472,6 +510,9 @@ func TestFillRequestDebNotFound(t *testing.T) {
 	oh.On("GetSystemUptime").Return(1*time.Hour, nil)
 	oh.On("GetMk8sClusterId").Return("abcd", nil)
 
+	dh.On("GetDCGMVersion").Return("3.3.7", nil)
+	dh.On("GetGpuInfo").Return("NVIDIA H200", 2, nil)
+
 	req := client.fillRequest(agentData)
 
 	assert.NotNil(t, req)