Merge pull request #2127 from vimalk78/pod-power

feat(pod): added pod power

Author: Sunil Thaha

cmd/kepler/main.go

@@ -15,6 +15,7 @@ import (
 	"github.com/sustainable-computing-io/kepler/internal/device"
 	"github.com/sustainable-computing-io/kepler/internal/exporter/prometheus"
 	"github.com/sustainable-computing-io/kepler/internal/exporter/stdout"
+	"github.com/sustainable-computing-io/kepler/internal/k8s/pod"
 	"github.com/sustainable-computing-io/kepler/internal/logger"
 	"github.com/sustainable-computing-io/kepler/internal/monitor"
 	"github.com/sustainable-computing-io/kepler/internal/resource"
@@ -126,10 +127,21 @@ func createServices(logger *slog.Logger, cfg *config.Config) ([]service.Service,
 	if err != nil {
 		return nil, fmt.Errorf("failed to create CPU power meter: %w", err)
 	}
+	var services []service.Service
 
-	resouceInformer, err := resource.NewInformer(
+	var podInformer pod.Informer
+	if *cfg.Kube.Enabled {
+		podInformer = pod.NewInformer(
+			pod.WithLogger(logger),
+			pod.WithKubeConfig(cfg.Kube.Config),
+			pod.WithNodeName(cfg.Kube.Node),
+		)
+		services = append(services, podInformer)
+	}
+	resourceInformer, err := resource.NewInformer(
 		resource.WithLogger(logger),
 		resource.WithProcFSPath(cfg.Host.ProcFS),
+		resource.WithPodInformer(podInformer),
 	)
 	if err != nil {
 		return nil, fmt.Errorf("failed to create resource informer: %w", err)
@@ -138,7 +150,7 @@ func createServices(logger *slog.Logger, cfg *config.Config) ([]service.Service,
 	pm := monitor.NewPowerMonitor(
 		cpuPowerMeter,
 		monitor.WithLogger(logger),
-		monitor.WithResourceInformer(resouceInformer),
+		monitor.WithResourceInformer(resourceInformer),
 		monitor.WithInterval(cfg.Monitor.Interval),
 		monitor.WithMaxStaleness(cfg.Monitor.Staleness),
 	)
@@ -147,12 +159,12 @@ func createServices(logger *slog.Logger, cfg *config.Config) ([]service.Service,
 		server.WithLogger(logger),
 	)
 
-	services := []service.Service{
+	services = append(services,
+		resourceInformer,
 		cpuPowerMeter,
-		resouceInformer,
 		apiServer,
 		pm,
-	}
+	)
 
 	// Add Prometheus exporter if enabled
 	if *cfg.Exporter.Prometheus.Enabled {

config/config.go

@@ -71,6 +71,12 @@ type (
 		Pprof PprofDebug `yaml:"pprof"`
 	}
 
+	Kube struct {
+		Enabled *bool  `yaml:"enabled"`
+		Config  string `yaml:"config"`
+		Node    string `yaml:"nodeName"`
+	}
+
 	Config struct {
 		Log      Log      `yaml:"log"`
 		Host     Host     `yaml:"host"`
@@ -80,13 +86,16 @@ type (
 		Web      Web      `yaml:"web"`
 		Debug    Debug    `yaml:"debug"`
 		Dev      Dev      `yaml:"dev"` // WARN: do not expose dev settings as flags
+
+		Kube Kube `yaml:"kube"`
 	}
 )
 
 type SkipValidation int
 
 const (
 	SkipHostValidation SkipValidation = 1
+	SkipKubeValidation SkipValidation = 2
 )
 
 const (
@@ -114,6 +123,11 @@ const (
 	// NOTE: not a flag
 	ExporterPrometheusDebugCollectors = "exporter.prometheus.debug-collectors"
 
+	// kubernetes flags
+	KubernetesFlag   = "kube.enable"
+	KubeConfigFlag   = "kube.config"
+	KubeNodeNameFlag = "kube.node-name"
+
 // WARN:  dev settings shouldn't be exposed as flags as flags are intended for end users
 )
 
@@ -149,6 +163,9 @@ func DefaultConfig() *Config {
 				Enabled: ptr.To(false),
 			},
 		},
+		Kube: Kube{
+			Enabled: ptr.To(false),
+		},
 	}
 
 	cfg.Dev.FakeCpuMeter.Enabled = ptr.To(false)
@@ -235,6 +252,10 @@ func RegisterFlags(app *kingpin.Application) ConfigUpdaterFn {
 
 	prometheusExporterEnabled := app.Flag(ExporterPrometheusEnabledFlag, "Enable Prometheus exporter").Default("true").Bool()
 
+	kubernetes := app.Flag(KubernetesFlag, "Monitor kubernetes").Default("false").Bool()
+	kubeconfig := app.Flag(KubeConfigFlag, "Path to a kubeconfig. Only required if out-of-cluster.").ExistingFile()
+	nodeName := app.Flag(KubeNodeNameFlag, "Name of kubernetes node on which kepler is running.").String()
+
 	return func(cfg *Config) error {
 		// Logging settings
 		if flagsSet[LogLevelFlag] {
@@ -274,6 +295,18 @@ func RegisterFlags(app *kingpin.Application) ConfigUpdaterFn {
 			cfg.Exporter.Prometheus.Enabled = prometheusExporterEnabled
 		}
 
+		if flagsSet[KubernetesFlag] {
+			cfg.Kube.Enabled = kubernetes
+		}
+
+		if flagsSet[KubeConfigFlag] {
+			cfg.Kube.Config = *kubeconfig
+		}
+
+		if flagsSet[KubeNodeNameFlag] {
+			cfg.Kube.Node = *nodeName
+		}
+
 		cfg.sanitize()
 		return cfg.Validate()
 	}
@@ -293,6 +326,7 @@ func (c *Config) sanitize() {
 	for i := range c.Exporter.Prometheus.DebugCollectors {
 		c.Exporter.Prometheus.DebugCollectors[i] = strings.TrimSpace(c.Exporter.Prometheus.DebugCollectors[i])
 	}
+	c.Kube.Config = strings.TrimSpace(c.Kube.Config)
 }
 
 // Validate checks for configuration errors
@@ -351,6 +385,19 @@ func (c *Config) Validate(skips ...SkipValidation) error {
 			errs = append(errs, fmt.Sprintf("invalid monitor staleness: %s can't be negative", c.Monitor.Staleness))
 		}
 	}
+	{ // Kubernetes
+		if c.Kube.Config != "" && !ptr.Deref(c.Kube.Enabled, false) {
+			errs = append(errs, fmt.Sprintf("%s supplied but %s set to false", KubeConfigFlag, KubernetesFlag))
+		}
+		if c.Kube.Node != "" && !ptr.Deref(c.Kube.Enabled, false) {
+			errs = append(errs, fmt.Sprintf("%s supplied but %s set to false", KubeNodeNameFlag, KubernetesFlag))
+		}
+		if ptr.Deref(c.Kube.Enabled, false) && c.Kube.Config != "" {
+			if err := canReadFile(c.Kube.Config); err != nil {
+				errs = append(errs, fmt.Sprintf("unreadable kubeconfig: %s", c.Kube.Config))
+			}
+		}
+	}
 
 	if len(errs) > 0 {
 		return fmt.Errorf("invalid configuration: %s", strings.Join(errs, ", "))
@@ -423,6 +470,7 @@ func (c *Config) manualString() string {
 		{ExporterPrometheusEnabledFlag, fmt.Sprintf("%v", c.Exporter.Prometheus.Enabled)},
 		{ExporterPrometheusDebugCollectors, strings.Join(c.Exporter.Prometheus.DebugCollectors, ", ")},
 		{pprofEnabledFlag, fmt.Sprintf("%v", c.Debug.Pprof.Enabled)},
+		{KubeConfigFlag, fmt.Sprintf("%v", c.Kube.Config)},
 	}
 	sb := strings.Builder{}
 

config/config_test.go

@@ -291,6 +291,31 @@ func TestInvalidConfigurationValues(t *testing.T) {
 			},
 		},
 		error: "invalid web config file",
+	}, {
+		name: "unreadable kubeconfig",
+		config: &Config{
+			Kube: Kube{
+				Config:  "/non/existent/file",
+				Enabled: ptr.To(true),
+			},
+		},
+		error: "unreadable kubeconfig",
+	}, {
+		name: "kube not enabled, kubeconfig supplied",
+		config: &Config{
+			Kube: Kube{
+				Config: "/some/existing/file",
+			},
+		},
+		error: "kube.config supplied but kube.enable set to false",
+	}, {
+		name: "kube not enabled, nodeName supplied",
+		config: &Config{
+			Kube: Kube{
+				Node: "dummyNode",
+			},
+		},
+		error: "kube.node-name supplied but kube.enable set to false",
 	}}
 
 	// test yaml marshall

go.mod

@@ -1,51 +1,94 @@
 module github.com/sustainable-computing-io/kepler
 
-go 1.23
+go 1.23.0
 
 toolchain go1.23.3
 
 require (
 	dario.cat/mergo v1.0.2
 	github.com/alecthomas/kingpin/v2 v2.4.0
+	github.com/go-logr/logr v1.4.2
 	github.com/oklog/run v1.1.0
 	github.com/olekukonko/tablewriter v1.0.5
 	github.com/prometheus/client_golang v1.22.0
 	github.com/prometheus/client_model v0.6.1
 	github.com/prometheus/exporter-toolkit v0.14.0
 	github.com/prometheus/procfs v0.15.1
 	github.com/stretchr/testify v1.10.0
-	golang.org/x/sync v0.10.0
+	go.uber.org/zap v1.26.0
+	golang.org/x/sync v0.12.0
 	gopkg.in/yaml.v3 v3.0.1
+	k8s.io/api v0.31.0
+	k8s.io/apimachinery v0.31.0
+	k8s.io/client-go v0.31.0
 	k8s.io/utils v0.0.0-20250321185631-1f6e0b77f77e
+	sigs.k8s.io/controller-runtime v0.19.0
 )
 
 require (
 	github.com/alecthomas/units v0.0.0-20211218093645-b94a6e3cc137 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
 	github.com/coreos/go-systemd/v22 v22.5.0 // indirect
-	github.com/davecgh/go-spew v1.1.1 // indirect
+	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
+	github.com/emicklei/go-restful/v3 v3.11.0 // indirect
+	github.com/evanphx/json-patch/v5 v5.9.0 // indirect
 	github.com/fatih/color v1.15.0 // indirect
+	github.com/fsnotify/fsnotify v1.7.0 // indirect
+	github.com/fxamacker/cbor/v2 v2.7.0 // indirect
+	github.com/go-logr/zapr v1.3.0 // indirect
+	github.com/go-openapi/jsonpointer v0.19.6 // indirect
+	github.com/go-openapi/jsonreference v0.20.2 // indirect
+	github.com/go-openapi/swag v0.22.4 // indirect
+	github.com/gogo/protobuf v1.3.2 // indirect
+	github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
+	github.com/golang/protobuf v1.5.4 // indirect
+	github.com/google/gnostic-models v0.6.8 // indirect
+	github.com/google/go-cmp v0.7.0 // indirect
+	github.com/google/gofuzz v1.2.0 // indirect
+	github.com/google/uuid v1.6.0 // indirect
+	github.com/imdario/mergo v0.3.6 // indirect
+	github.com/josharian/intern v1.0.0 // indirect
 	github.com/jpillora/backoff v1.0.0 // indirect
+	github.com/json-iterator/go v1.1.12 // indirect
+	github.com/mailru/easyjson v0.7.7 // indirect
 	github.com/mattn/go-colorable v0.1.13 // indirect
 	github.com/mattn/go-isatty v0.0.19 // indirect
 	github.com/mattn/go-runewidth v0.0.16 // indirect
 	github.com/mdlayher/socket v0.4.1 // indirect
 	github.com/mdlayher/vsock v1.2.1 // indirect
+	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
+	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
 	github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f // indirect
 	github.com/olekukonko/errors v0.0.0-20250405072817-4e6d85265da6 // indirect
 	github.com/olekukonko/ll v0.0.7 // indirect
-	github.com/pmezard/go-difflib v1.0.0 // indirect
+	github.com/pkg/errors v0.9.1 // indirect
+	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	github.com/prometheus/common v0.62.0 // indirect
 	github.com/rivo/uniseg v0.2.0 // indirect
+	github.com/spf13/pflag v1.0.5 // indirect
 	github.com/stretchr/objx v0.5.2 // indirect
+	github.com/x448/float16 v0.8.4 // indirect
 	github.com/xhit/go-str2duration/v2 v2.1.0 // indirect
+	go.uber.org/multierr v1.11.0 // indirect
 	golang.org/x/crypto v0.32.0 // indirect
+	golang.org/x/exp v0.0.0-20230515195305-f3d0a9c9a5cc // indirect
 	golang.org/x/net v0.33.0 // indirect
 	golang.org/x/oauth2 v0.24.0 // indirect
 	golang.org/x/sys v0.30.0 // indirect
+	golang.org/x/term v0.28.0 // indirect
 	golang.org/x/text v0.21.0 // indirect
+	golang.org/x/time v0.3.0 // indirect
+	gomodules.xyz/jsonpatch/v2 v2.4.0 // indirect
 	google.golang.org/protobuf v1.36.5 // indirect
+	gopkg.in/evanphx/json-patch.v4 v4.12.0 // indirect
+	gopkg.in/inf.v0 v0.9.1 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
+	k8s.io/apiextensions-apiserver v0.31.0 // indirect
+	k8s.io/klog/v2 v2.130.1 // indirect
+	k8s.io/kube-openapi v0.0.0-20240228011516-70dd3763d340 // indirect
+	sigs.k8s.io/json v0.0.0-20221116044647-bc3834ca7abd // indirect
+	sigs.k8s.io/structured-merge-diff/v4 v4.4.1 // indirect
+	sigs.k8s.io/yaml v1.4.0 // indirect
 )