nodemon

package
v0.0.79 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Jun 2, 2026 License: Apache-2.0 Imports: 31 Imported by: 0

Documentation

Index

Constants

View Source 
const (
	KindPod         = "Pod"
	KindJob         = "Job"
	KindCronJob     = "CronJob"
	KindRollout     = "Rollout"
	KindDaemonSet   = "DaemonSet"
	KindDeployment  = "Deployment"
	KindStatefulSet = "StatefulSet"
	KindReplicaSet  = "ReplicaSet"
)

Variables

View Source 
var EnabledMetrics = map[MetricName]struct{}{
	MetricStreamingMultiProcessorActive:    {},
	MetricStreamingMultiProcessorOccupancy: {},
	MetricStreamingMultiProcessorTensor:    {},
	MetricDRAMActive:                       {},
	MetricPCIeTXBytes:                      {},
	MetricPCIeRXBytes:                      {},
	MetricNVLinkTXBytes:                    {},
	MetricNVLinkRXBytes:                    {},
	MetricGraphicsEngineActive:             {},
	MetricFrameBufferTotal:                 {},
	MetricFrameBufferUsed:                  {},
	MetricFrameBufferFree:                  {},
	MetricPCIeLinkGen:                      {},
	MetricPCIeLinkWidth:                    {},
	MetricGPUTemperature:                   {},
	MetricMemoryTemperature:                {},
	MetricPowerUsage:                       {},
	MetricGPUUtilization:                   {},
	MetricIntPipeActive:                    {},
	MetricFloat16PipeActive:                {},
	MetricFloat32PipeActive:                {},
	MetricFloat64PipeActive:                {},
	MetricClocksEventReasons:               {},
	MetricXIDErrors:                        {},
	MetricPowerViolation:                   {},
	MetricThermalViolation:                 {},
	MetricSMClock:                          {},
	MetricMemClock:                         {},
}

EnabledMetrics is the set of DCGM metrics to scrape and process.

Functions

func NewContainerMetricsHandler 

func NewContainerMetricsHandler(querier MetricsQuerier, log logr.Logger) http.Handler

NewContainerMetricsHandler creates an HTTP handler for GET /container/metrics.

func NewJVMMetricsHandler added in v0.0.78 

func NewJVMMetricsHandler(querier JVMMetricsQuerier, log logr.Logger) http.Handler

NewJVMMetricsHandler creates an HTTP handler for GET /container/jvm-metrics. Supports ?container=, ?pod=, ?namespace=, ?node= query filters.

func NewServerMux 

func NewServerMux(containerMetricsHandler http.Handler, jvmMetricsHandler http.Handler) *http.ServeMux

NewServerMux creates the HTTP mux for the nodemon.

func ParseJVMFlagsWithSources added in v0.0.78 

func ParseJVMFlagsWithSources(cmdline string, envJavaOpts map[string]string) (JVMFlagsExtracted, JVMFlagSources, string)

ParseJVMFlagsWithSources extracts sizing-related JVM flags and also returns where each value came from.

We cannot observe the final JVM argument list directly (env-injected options don’t appear in /proc/<pid>/cmdline), so this is best-effort:

  • cmdline is treated as highest precedence
  • env vars are applied in the following precedence order: JAVA_TOOL_OPTIONS, JDK_JAVA_OPTIONS, JAVA_OPTS

The returned effectiveCmdline is the cmdline plus the env options appended as tokens for observability.

Types

type Exporter 

type Exporter struct {
	// contains filtered or unexported fields
}

Exporter ties together the scraper, mapper, and DCGM pod discovery.

func NewExporter 

func NewExporter(
	cfg ExporterConfig,
	dynClient dynamic.Interface,
	scraper Scraper,
	mapper MetricMapper,
	log logr.Logger,
) *Exporter

NewExporter creates a new GPU metrics exporter.

func (*Exporter) QueryMetrics 

func (e *Exporter) QueryMetrics(ctx context.Context) ([]GPUMetric, error)

QueryMetrics scrapes DCGM exporters on demand and returns mapped GPU metrics.

type ExporterConfig 

type ExporterConfig struct {
	HTTPListenPort      int
	DCGMHost            string
	DCGMPort            int
	DCGMMetricsEndpoint string
	DCGMLabels          string // label selector, e.g. "app.kubernetes.io/name=dcgm-exporter"
	NodeName            string
}

ExporterConfig holds environment-driven configuration.

type GPUMetric 

type GPUMetric struct {
	NodeName      string `json:"node_name"`
	ModelName     string `json:"model_name"`
	Device        string `json:"device"`
	DeviceID      string `json:"device_id"`
	DeviceUUID    string `json:"device_uuid"`
	MIGProfile    string `json:"mig_profile,omitempty"`
	MIGInstanceID string `json:"mig_instance_id,omitempty"`

	Pod          string `json:"pod"`
	Container    string `json:"container"`
	Namespace    string `json:"namespace"`
	WorkloadName string `json:"workload_name,omitempty"`
	WorkloadKind string `json:"workload_kind,omitempty"`

	SMActive             float64 `json:"sm_active"`
	SMOccupancy          float64 `json:"sm_occupancy"`
	TensorActive         float64 `json:"tensor_active"`
	DRAMActive           float64 `json:"dram_active"`
	PCIeTXBytes          float64 `json:"pcie_tx_bytes"`
	PCIeRXBytes          float64 `json:"pcie_rx_bytes"`
	NVLinkTXBytes        float64 `json:"nvlink_tx_bytes"`
	NVLinkRXBytes        float64 `json:"nvlink_rx_bytes"`
	GraphicsEngineActive float64 `json:"graphics_engine_active"`
	FramebufferTotal     float64 `json:"framebuffer_total"`
	FramebufferUsed      float64 `json:"framebuffer_used"`
	FramebufferFree      float64 `json:"framebuffer_free"`
	PCIeLinkGen          float64 `json:"pcie_link_gen"`
	PCIeLinkWidth        float64 `json:"pcie_link_width"`
	Temperature          float64 `json:"temperature"`
	MemoryTemperature    float64 `json:"memory_temperature"`
	PowerUsage           float64 `json:"power_usage"`
	GPUUtilization       float64 `json:"gpu_utilization"`
	IntPipeActive        float64 `json:"int_pipe_active"`
	FP16PipeActive       float64 `json:"fp16_pipe_active"`
	FP32PipeActive       float64 `json:"fp32_pipe_active"`
	FP64PipeActive       float64 `json:"fp64_pipe_active"`
	ClocksEventReasons   float64 `json:"clocks_event_reasons"`
	XIDErrors            float64 `json:"xid_errors"`
	PowerViolation       float64 `json:"power_violation"`
	ThermalViolation     float64 `json:"thermal_violation"`
	SMClock              float64 `json:"sm_clock"`
	MemClock             float64 `json:"mem_clock"`

	Timestamp time.Time `json:"timestamp"`
}

GPUMetric represents a single GPU's metrics for a container.

type GPUMetricResponse 

type GPUMetricResponse struct {
	NodeName      string `json:"node_name"`
	ModelName     string `json:"model_name"`
	Device        string `json:"device"`
	DeviceID      string `json:"device_id"`
	DeviceUUID    string `json:"device_uuid"`
	MIGProfile    string `json:"mig_profile,omitempty"`
	MIGInstanceID string `json:"mig_instance_id,omitempty"`

	Pod          string `json:"pod"`
	Container    string `json:"container"`
	Namespace    string `json:"namespace"`
	WorkloadName string `json:"workload_name,omitempty"`
	WorkloadKind string `json:"workload_kind,omitempty"`

	SMActive             float64 `json:"sm_active"`
	SMOccupancy          float64 `json:"sm_occupancy"`
	TensorActive         float64 `json:"tensor_active"`
	DRAMActive           float64 `json:"dram_active"`
	PCIeTXBytes          float64 `json:"pcie_tx_bytes"`
	PCIeRXBytes          float64 `json:"pcie_rx_bytes"`
	NVLinkTXBytes        float64 `json:"nvlink_tx_bytes"`
	NVLinkRXBytes        float64 `json:"nvlink_rx_bytes"`
	GraphicsEngineActive float64 `json:"graphics_engine_active"`
	FramebufferTotal     float64 `json:"framebuffer_total"`
	FramebufferUsed      float64 `json:"framebuffer_used"`
	FramebufferFree      float64 `json:"framebuffer_free"`
	PCIeLinkGen          float64 `json:"pcie_link_gen"`
	PCIeLinkWidth        float64 `json:"pcie_link_width"`
	Temperature          float64 `json:"temperature"`
	MemoryTemperature    float64 `json:"memory_temperature"`
	PowerUsage           float64 `json:"power_usage"`
	GPUUtilization       float64 `json:"gpu_utilization"`
	IntPipeActive        float64 `json:"int_pipe_active"`
	FP16PipeActive       float64 `json:"fp16_pipe_active"`
	FP32PipeActive       float64 `json:"fp32_pipe_active"`
	FP64PipeActive       float64 `json:"fp64_pipe_active"`
	ClocksEventReasons   float64 `json:"clocks_event_reasons"`
	XIDErrors            float64 `json:"xid_errors"`
	PowerViolation       float64 `json:"power_violation"`
	ThermalViolation     float64 `json:"thermal_violation"`
	SMClock              float64 `json:"sm_clock"`
	MemClock             float64 `json:"mem_clock"`

	Timestamp time.Time `json:"timestamp"`
}

GPUMetricResponse is the JSON API contract for the /container/metrics endpoint.

type HTTPClient 

type HTTPClient interface {
	Do(req *http.Request) (*http.Response, error)
}

HTTPClient abstracts *http.Client for testing.

type JVMCollector added in v0.0.78 

type JVMCollector struct {
	// contains filtered or unexported fields
}

JVMCollector collects JVM metrics from hsperfdata files via /proc. Requires the pod to run with hostPID: true and as UID 0 to read /proc/<pid>/root/tmp/hsperfdata_*/<nsPid> for other containers.

func NewJVMCollector added in v0.0.78 

func NewJVMCollector(nodeName string, k8sClient kubernetes.Interface, log logr.Logger) *JVMCollector

NewJVMCollector creates a JVMCollector. procRoot defaults to "/proc".

func (*JVMCollector) QueryJVMMetrics added in v0.0.78 

func (c *JVMCollector) QueryJVMMetrics(ctx context.Context) ([]JVMMetric, error)

QueryJVMMetrics returns JVM metrics for all discovered Java containers on this node.

func (*JVMCollector) Start added in v0.0.78 

func (c *JVMCollector) Start() error

Start creates a node-scoped pod informer and waits for the cache to sync. Must be called exactly once before serving HTTP requests.

func (*JVMCollector) Stop added in v0.0.78 

func (c *JVMCollector) Stop()

Stop shuts down the informer factory. Safe to call multiple times.

type JVMFlagSources added in v0.0.78 

type JVMFlagSources struct {
	XmsBytes            string `json:"xms_bytes,omitempty"`
	XmxBytes            string `json:"xmx_bytes,omitempty"`
	MaxRamPercentage    string `json:"max_ram_percentage,omitempty"`
	UseContainerSupport string `json:"use_container_support,omitempty"`
}

JVMFlagSources describes where each extracted JVM flag value came from. This is best-effort; precedence rules are implemented in ParseJVMFlagsWithSources.

type JVMFlagsExtracted added in v0.0.78 

type JVMFlagsExtracted struct {
	XmsBytes            *int64   `json:"xms_bytes,omitempty"`
	XmxBytes            *int64   `json:"xmx_bytes,omitempty"`
	MaxRamPercentage    *float64 `json:"max_ram_percentage,omitempty"`
	UseContainerSupport *bool    `json:"use_container_support,omitempty"`
}

JVMFlagsExtracted holds JVM flags parsed from the process cmdline and/or env.

func ParseJVMFlags added in v0.0.78 

func ParseJVMFlags(cmdline string) JVMFlagsExtracted

ParseJVMFlags parses JVM memory and container-awareness flags from a process cmdline string.

NOTE: This is *best-effort* parsing for the few flags we care about for sizing.

type JVMMetric added in v0.0.78 

type JVMMetric struct {
	NodeName    string `json:"node_name"`
	Pod         string `json:"pod"`
	Namespace   string `json:"namespace"`
	Container   string `json:"container"`
	ContainerID string `json:"container_id"`
	PidHost     int    `json:"pid_host"`
	PidNS       int    `json:"pid_ns"`

	JavaCommand string `json:"java_command,omitempty"`
	JavaVersion string `json:"java_version,omitempty"`

	HeapSizeBytes    int64 `json:"heap_size_bytes"`
	HeapUsedBytes    int64 `json:"heap_used_bytes"`
	HeapMaxSizeBytes int64 `json:"heap_max_size_bytes"`

	GCTimeSecondsTotal            map[string]float64 `json:"gc_time_seconds_total"`
	SafepointTimeSecondsTotal     float64            `json:"safepoint_time_seconds_total"`
	SafepointSyncTimeSecondsTotal float64            `json:"safepoint_sync_time_seconds_total"`

	FlagsExtracted JVMFlagsExtracted `json:"flags_extracted"`
	FlagSources    JVMFlagSources    `json:"flag_sources,omitempty"`
	// RawCmdline is the effective command line including env-injected options
	// (JAVA_TOOL_OPTIONS, JDK_JAVA_OPTIONS, JAVA_OPTS). Note: this may contain
	// sensitive values if secrets are passed via JVM system properties or env vars.
	RawCmdline string    `json:"raw_cmdline,omitempty"`
	Timestamp  time.Time `json:"timestamp"`
}

JVMMetric holds per-container JVM metrics extracted from hsperfdata.

type JVMMetricsQuerier added in v0.0.78 

type JVMMetricsQuerier interface {
	QueryJVMMetrics(ctx context.Context) ([]JVMMetric, error)
}

JVMMetricsQuerier provides on-demand JVM metrics.

type JavaProcess added in v0.0.78 

type JavaProcess struct {
	PidHost     int
	PidNS       int
	ContainerID string

	CmdLine string
	// EnvJavaOpts includes any env-injected Java options found in /proc/<pid>/environ.
	// Keys are env var names (JAVA_TOOL_OPTIONS, JDK_JAVA_OPTIONS, JAVA_OPTS).
	EnvJavaOpts map[string]string

	HsperfDataPath string
}

JavaProcess holds info about a discovered Java process running inside a Kubernetes container.

type MetricFamilyMap 

type MetricFamilyMap map[string]*dto.MetricFamily

MetricFamilyMap maps a Prometheus metric name to its parsed metric family.

type MetricMapper 

type MetricMapper interface {
	MapToGPUMetrics(ctx context.Context, metrics []MetricFamilyMap) []GPUMetric
}

MetricMapper maps scraped DCGM metric families into structured GPU metrics.

func NewMapper 

func NewMapper(nodeName string, resolver WorkloadResolver, log logr.Logger) MetricMapper

NewMapper creates a new MetricMapper.

type MetricName 

type MetricName = string

MetricName identifies a DCGM metric by its Prometheus metric name. 

const (
	MetricStreamingMultiProcessorActive    MetricName = "DCGM_FI_PROF_SM_ACTIVE"
	MetricStreamingMultiProcessorOccupancy MetricName = "DCGM_FI_PROF_SM_OCCUPANCY"
	MetricStreamingMultiProcessorTensor    MetricName = "DCGM_FI_PROF_PIPE_TENSOR_ACTIVE"
	MetricDRAMActive                       MetricName = "DCGM_FI_PROF_DRAM_ACTIVE"
	MetricPCIeTXBytes                      MetricName = "DCGM_FI_PROF_PCIE_TX_BYTES"
	MetricPCIeRXBytes                      MetricName = "DCGM_FI_PROF_PCIE_RX_BYTES"
	MetricNVLinkTXBytes                    MetricName = "DCGM_FI_PROF_NVLINK_TX_BYTES"
	MetricNVLinkRXBytes                    MetricName = "DCGM_FI_PROF_NVLINK_RX_BYTES"
	MetricGraphicsEngineActive             MetricName = "DCGM_FI_PROF_GR_ENGINE_ACTIVE"
	MetricFrameBufferTotal                 MetricName = "DCGM_FI_DEV_FB_TOTAL"
	MetricFrameBufferUsed                  MetricName = "DCGM_FI_DEV_FB_USED"
	MetricFrameBufferFree                  MetricName = "DCGM_FI_DEV_FB_FREE"
	MetricPCIeLinkGen                      MetricName = "DCGM_FI_DEV_PCIE_LINK_GEN"
	MetricPCIeLinkWidth                    MetricName = "DCGM_FI_DEV_PCIE_LINK_WIDTH"
	MetricGPUTemperature                   MetricName = "DCGM_FI_DEV_GPU_TEMP"
	MetricMemoryTemperature                MetricName = "DCGM_FI_DEV_MEMORY_TEMP"
	MetricPowerUsage                       MetricName = "DCGM_FI_DEV_POWER_USAGE"
	MetricGPUUtilization                   MetricName = "DCGM_FI_DEV_GPU_UTIL"
	MetricIntPipeActive                    MetricName = "DCGM_FI_PROF_PIPE_INT_ACTIVE"
	MetricFloat16PipeActive                MetricName = "DCGM_FI_PROF_PIPE_FP16_ACTIVE"
	MetricFloat32PipeActive                MetricName = "DCGM_FI_PROF_PIPE_FP32_ACTIVE"
	MetricFloat64PipeActive                MetricName = "DCGM_FI_PROF_PIPE_FP64_ACTIVE"
	MetricClocksEventReasons               MetricName = "DCGM_FI_DEV_CLOCKS_EVENT_REASONS"
	MetricXIDErrors                        MetricName = "DCGM_FI_DEV_XID_ERRORS"
	MetricPowerViolation                   MetricName = "DCGM_FI_DEV_POWER_VIOLATION"
	MetricThermalViolation                 MetricName = "DCGM_FI_DEV_THERMAL_VIOLATION"
	MetricSMClock                          MetricName = "DCGM_FI_DEV_SM_CLOCK"
	MetricMemClock                         MetricName = "DCGM_FI_DEV_MEM_CLOCK"
)

DCGM metric names scraped from the DCGM exporter.

type MetricsQuerier 

type MetricsQuerier interface {
	QueryMetrics(ctx context.Context) ([]GPUMetric, error)
}

MetricsQuerier provides on-demand GPU metrics.

type Scraper 

type Scraper interface {
	Scrape(ctx context.Context, urls []string) ([]MetricFamilyMap, error)
}

Scraper fetches and parses Prometheus-format metrics from DCGM exporter endpoints.

func NewScraper 

func NewScraper(httpClient HTTPClient, log logr.Logger) Scraper

NewScraper creates a new DCGM metrics scraper.

type Workload 

type Workload struct {
	Name      string
	Namespace string
	Kind      string
}

Workload represents a resolved Kubernetes workload.

type WorkloadResolver 

type WorkloadResolver interface {
	FindWorkloadForPod(
		ctx context.Context,
		name, namespace string,
	) (kind, workloadName string, err error)
}

WorkloadResolver resolves the top-level owning workload for a pod.

func NewWorkloadResolver 

func NewWorkloadResolver(
	dynClient dynamic.Interface,
	cfg WorkloadResolverConfig,
	log logr.Logger,
) WorkloadResolver

NewWorkloadResolver creates a WorkloadResolver that uses the K8s dynamic client to walk owner references and find the top-level owning workload. Supports LRU caching and label-based workload name resolution.

type WorkloadResolverConfig 

type WorkloadResolverConfig struct {
	LabelKeys []string
	CacheSize int
}

WorkloadResolverConfig holds configuration for the workload resolver.

Source Files

View all Source files

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.