feat(bmc): add redfish support

Signed-off-by: Sunil Thaha <sthaha@redhat.com>

Author: sthaha

cmd/kepler/main.go

@@ -11,13 +11,16 @@ import (
 	"syscall"
 
 	"github.com/alecthomas/kingpin/v2"
+	"k8s.io/utils/ptr"
+
 	"github.com/sustainable-computing-io/kepler/config"
 	"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/platform/redfish"
 	"github.com/sustainable-computing-io/kepler/internal/resource"
 	"github.com/sustainable-computing-io/kepler/internal/server"
 	"github.com/sustainable-computing-io/kepler/internal/service"
@@ -157,6 +160,8 @@ func createServices(logger *slog.Logger, cfg *config.Config) ([]service.Service,
 		monitor.WithMinTerminatedEnergyThreshold(monitor.Energy(cfg.Monitor.MinTerminatedEnergyThreshold)*monitor.Joule),
 	)
 
+	// Create Redfish service if enabled (experimental feature)
+
 	apiServer := server.NewAPIServer(
 		server.WithLogger(logger),
 		server.WithListenAddress(cfg.Web.ListenAddresses),
@@ -170,9 +175,20 @@ func createServices(logger *slog.Logger, cfg *config.Config) ([]service.Service,
 		pm,
 	)
 
+	// Add Redfish service if enabled
+	var redfishService *redfish.Service
+	if ptr.Deref(cfg.Experimental.Platform.Redfish.Enabled, false) {
+		rs, err := createRedfishService(logger, cfg)
+		if err != nil {
+			return nil, fmt.Errorf("failed to create Redfish service: %w", err)
+		}
+		services = append(services, rs)
+		redfishService = rs
+	}
+
 	// Add Prometheus exporter if enabled
 	if *cfg.Exporter.Prometheus.Enabled {
-		promExporter, err := createPrometheusExporter(logger, cfg, apiServer, pm)
+		promExporter, err := createPrometheusExporter(logger, cfg, apiServer, pm, redfishService)
 		if err != nil {
 			return nil, fmt.Errorf("failed to create Prometheus exporter: %w", err)
 		}
@@ -194,19 +210,51 @@ func createServices(logger *slog.Logger, cfg *config.Config) ([]service.Service,
 	return services, nil
 }
 
-func createPrometheusExporter(logger *slog.Logger, cfg *config.Config, apiServer *server.APIServer, pm *monitor.PowerMonitor) (*prometheus.Exporter, error) {
+func createRedfishService(logger *slog.Logger, cfg *config.Config) (*redfish.Service, error) {
+	// Resolve node ID using new priority logic
+	redfishCfg := cfg.Experimental.Platform.Redfish
+
+	nodeID, err := redfish.ResolveNodeID(redfishCfg.NodeID, cfg.Kube.Node)
+	if err != nil {
+		return nil, fmt.Errorf("failed to resolve node ID for Redfish service: %w", err)
+	}
+
+	rs, err := redfish.NewService(
+		cfg.Experimental.Platform.Redfish.ConfigFile,
+		nodeID,
+		logger,
+	)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create Redfish service: %w", err)
+	}
+
+	return rs, nil
+}
+
+func createPrometheusExporter(
+	logger *slog.Logger, cfg *config.Config,
+	apiServer *server.APIServer, pm *monitor.PowerMonitor,
+	rs *redfish.Service,
+) (*prometheus.Exporter, error) {
 	logger.Debug("Creating Prometheus exporter")
 
 	// Use metrics level from configuration (already parsed)
 	metricsLevel := cfg.Exporter.Prometheus.MetricsLevel
 
-	collectors, err := prometheus.CreateCollectors(
-		pm,
+	var collectorOpts []prometheus.OptionFn
+	collectorOpts = append(collectorOpts,
 		prometheus.WithLogger(logger),
 		prometheus.WithProcFSPath(cfg.Host.ProcFS),
 		prometheus.WithNodeName(cfg.Kube.Node),
 		prometheus.WithMetricsLevel(metricsLevel),
 	)
+
+	// Add platform data provider if Redfish service is available
+	if rs != nil {
+		collectorOpts = append(collectorOpts, prometheus.WithPlatformDataProvider(rs))
+	}
+
+	collectors, err := prometheus.CreateCollectors(pm, collectorOpts...)
 	if err != nil {
 		return nil, fmt.Errorf("failed to create Prometheus collectors: %w", err)
 	}

compose/dev/kepler-dev/etc/kepler/config.yaml

@@ -70,3 +70,11 @@ dev:
   fake-cpu-meter:
     enabled: false
     zones: [] # zones to be enabled, empty enables all default zones
+
+# EXPERIMENTAL FEATURES - These features are experimental and may be unstable
+experimental:
+  platform:
+    redfish:
+      enabled: false # Enable experimental Redfish BMC power monitoring
+      configFile: "/etc/kepler/redfish.yaml" # Path to Redfish BMC configuration file
+      nodeID: "" # Node identifier to use (overrides Kubernetes node name and hostname fallback)

compose/dev/kepler-latest/etc/kepler/config.yaml

@@ -70,3 +70,11 @@ dev:
   fake-cpu-meter:
     enabled: false
     zones: [] # zones to be enabled, empty enables all default zones
+
+# EXPERIMENTAL FEATURES - These features are experimental and may be unstable
+experimental:
+  platform:
+    redfish:
+      enabled: false # Enable experimental Redfish BMC power monitoring
+      configFile: "/etc/kepler/redfish.yaml" # Path to Redfish BMC configuration file
+      nodeID: "" # Node identifier to use (overrides Kubernetes node name and hostname fallback)

config/config.go

@@ -93,17 +93,34 @@ type (
 		Node    string `yaml:"nodeName"`
 	}
 
-	Config struct {
-		Log      Log      `yaml:"log"`
-		Host     Host     `yaml:"host"`
-		Monitor  Monitor  `yaml:"monitor"`
-		Rapl     Rapl     `yaml:"rapl"`
-		Exporter Exporter `yaml:"exporter"`
-		Web      Web      `yaml:"web"`
-		Debug    Debug    `yaml:"debug"`
-		Dev      Dev      `yaml:"dev"` // WARN: do not expose dev settings as flags
+	// Platform contains settings for platform power monitoring
+	Platform struct {
+		Redfish Redfish `yaml:"redfish"`
+	}
+
+	// Redfish contains settings for Redfish BMC power monitoring
+	Redfish struct {
+		Enabled    *bool  `yaml:"enabled"`
+		NodeID     string `yaml:"nodeID"`
+		ConfigFile string `yaml:"configFile"`
+	}
 
-		Kube Kube `yaml:"kube"`
+	// Experimental contains experimental features (no stability guarantees)
+	Experimental struct {
+		Platform Platform `yaml:"platform"`
+	}
+
+	Config struct {
+		Log          Log          `yaml:"log"`
+		Host         Host         `yaml:"host"`
+		Monitor      Monitor      `yaml:"monitor"`
+		Rapl         Rapl         `yaml:"rapl"`
+		Exporter     Exporter     `yaml:"exporter"`
+		Web          Web          `yaml:"web"`
+		Debug        Debug        `yaml:"debug"`
+		Dev          Dev          `yaml:"dev"` // WARN: do not expose dev settings as flags
+		Experimental Experimental `yaml:"experimental"`
+		Kube         Kube         `yaml:"kube"`
 	}
 )
 
@@ -186,6 +203,11 @@ const (
 	KubeConfigFlag   = "kube.config"
 	KubeNodeNameFlag = "kube.node-name"
 
+	// Experimental Platform flags
+	ExperimentalPlatformRedfishEnabledFlag = "experimental.platform.redfish.enabled"
+	ExperimentalPlatformRedfishNodeIDFlag  = "experimental.platform.redfish.node-id"
+	ExperimentalPlatformRedfishConfigFlag  = "experimental.platform.redfish.config"
+
 // WARN:  dev settings shouldn't be exposed as flags as flags are intended for end users
 )
 
@@ -228,6 +250,15 @@ func DefaultConfig() *Config {
 		Web: Web{
 			ListenAddresses: []string{":28282"},
 		},
+		Experimental: Experimental{
+			Platform: Platform{
+				Redfish: Redfish{
+					Enabled:    ptr.To(false),
+					NodeID:     "",
+					ConfigFile: "",
+				},
+			},
+		},
 		Kube: Kube{
 			Enabled: ptr.To(false),
 		},
@@ -327,6 +358,11 @@ func RegisterFlags(app *kingpin.Application) ConfigUpdaterFn {
 	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()
 
+	// experimental platform
+	experimentalPlatformRedfishEnabled := app.Flag(ExperimentalPlatformRedfishEnabledFlag, "Enable experimental Redfish BMC power monitoring").Default("false").Bool()
+	experimentalPlatformRedfishNodeID := app.Flag(ExperimentalPlatformRedfishNodeIDFlag, "Node identifier for experimental Redfish platform power monitoring").String()
+	experimentalPlatformRedfishConfig := app.Flag(ExperimentalPlatformRedfishConfigFlag, "Path to experimental Redfish BMC configuration file").String()
+
 	return func(cfg *Config) error {
 		// Logging settings
 		if flagsSet[LogLevelFlag] {
@@ -389,6 +425,19 @@ func RegisterFlags(app *kingpin.Application) ConfigUpdaterFn {
 			cfg.Kube.Node = *nodeName
 		}
 
+		// experimental platform settings
+		if flagsSet[ExperimentalPlatformRedfishEnabledFlag] {
+			cfg.Experimental.Platform.Redfish.Enabled = experimentalPlatformRedfishEnabled
+		}
+
+		if flagsSet[ExperimentalPlatformRedfishNodeIDFlag] {
+			cfg.Experimental.Platform.Redfish.NodeID = *experimentalPlatformRedfishNodeID
+		}
+
+		if flagsSet[ExperimentalPlatformRedfishConfigFlag] {
+			cfg.Experimental.Platform.Redfish.ConfigFile = *experimentalPlatformRedfishConfig
+		}
+
 		cfg.sanitize()
 		return cfg.Validate()
 	}
@@ -412,6 +461,8 @@ func (c *Config) sanitize() {
 		c.Exporter.Prometheus.DebugCollectors[i] = strings.TrimSpace(c.Exporter.Prometheus.DebugCollectors[i])
 	}
 	c.Kube.Config = strings.TrimSpace(c.Kube.Config)
+	c.Experimental.Platform.Redfish.NodeID = strings.TrimSpace(c.Experimental.Platform.Redfish.NodeID)
+	c.Experimental.Platform.Redfish.ConfigFile = strings.TrimSpace(c.Experimental.Platform.Redfish.ConfigFile)
 }
 
 // Validate checks for configuration errors
@@ -500,6 +551,17 @@ func (c *Config) Validate(skips ...SkipValidation) error {
 			}
 		}
 	}
+	{ // Experimental Platform
+		if ptr.Deref(c.Experimental.Platform.Redfish.Enabled, false) {
+			if c.Experimental.Platform.Redfish.ConfigFile == "" {
+				errs = append(errs, fmt.Sprintf("%s not supplied but %s set to true", ExperimentalPlatformRedfishConfigFlag, ExperimentalPlatformRedfishEnabledFlag))
+			} else {
+				if err := canReadFile(c.Experimental.Platform.Redfish.ConfigFile); err != nil {
+					errs = append(errs, fmt.Sprintf("unreadable Redfish config file: %s: %s", c.Experimental.Platform.Redfish.ConfigFile, err.Error()))
+				}
+			}
+		}
+	}
 
 	if len(errs) > 0 {
 		return fmt.Errorf("invalid configuration: %s", strings.Join(errs, ", "))

go.mod

@@ -14,6 +14,7 @@ require (
 	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/stmcginnis/gofish v0.15.0
 	github.com/stretchr/testify v1.10.0
 	go.uber.org/zap v1.26.0
 	golang.org/x/sync v0.12.0

go.sum

@@ -135,6 +135,8 @@ github.com/rogpeppe/go-internal v1.12.0 h1:exVL4IDcn6na9z1rAb56Vxr+CgyK3nn3O+epU
 github.com/rogpeppe/go-internal v1.12.0/go.mod h1:E+RYuTGaKKdloAfM02xzb0FW3Paa99yedzYV+kq4uf4=
 github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
 github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
+github.com/stmcginnis/gofish v0.15.0 h1:8TG41+lvJk/0Nf8CIIYErxbMlQUy80W0JFRZP3Ld82A=
+github.com/stmcginnis/gofish v0.15.0/go.mod h1:BLDSFTp8pDlf/xDbLZa+F7f7eW0E/CHCboggsu8CznI=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
 github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=

hack/config.yaml

@@ -70,3 +70,11 @@ dev:
   fake-cpu-meter:
     enabled: false
     zones: [] # zones to be enabled, empty enables all default zones
+
+# EXPERIMENTAL FEATURES - These features are experimental and may be unstable
+experimental:
+  platform:
+    redfish:
+      enabled: false # Enable experimental Redfish BMC power monitoring
+      configFile: "/etc/kepler/redfish.yaml" # Path to Redfish BMC configuration file
+      nodeID: "" # Node identifier to use (overrides Kubernetes node name and hostname fallback)