Merge pull request #3555 from j4ckstraw/add-load-d-metrics

Add uninterruptible metric load d
google · Jul 8, 2024 · f163691 · f163691
2 parents fe54aa3 + 80e7063
commit f163691
Show file tree

Hide file tree

Showing 6 changed files with 31 additions and 1 deletion.
diff --git a/info/v1/container.go b/info/v1/container.go
@@ -333,6 +333,8 @@ type CpuStats struct {
 	// Load is smoothed over the last 10 seconds. Instantaneous value can be read
 	// from LoadStats.NrRunning.
 	LoadAverage int32 `json:"load_average"`
+	// from LoadStats.NrUninterruptible
+	LoadDAverage int32 `json:"load_d_average"`
 }
 
 type PerDiskStats struct {

diff --git a/manager/container.go b/manager/container.go
@@ -73,6 +73,7 @@ type containerData struct {
 	loadReader               cpuload.CpuLoadReader
 	summaryReader            *summary.StatsSummary
 	loadAvg                  float64 // smoothed load average seen so far.
+	loadDAvg                 float64 // smoothed load.d average seen so far.
 	housekeepingInterval     time.Duration
 	maxHousekeepingInterval  time.Duration
 	allowDynamicHousekeeping bool
@@ -441,6 +442,7 @@ func newContainerData(containerName string, memoryCache *memory.InMemoryCache, h
 		allowDynamicHousekeeping: allowDynamicHousekeeping,
 		logUsage:                 logUsage,
 		loadAvg:                  -1.0, // negative value indicates uninitialized.
+		loadDAvg:                 -1.0, // negative value indicates uninitialized.
 		stop:                     make(chan struct{}),
 		collectorManager:         collectorManager,
 		onDemandChan:             make(chan chan struct{}, 100),
@@ -633,6 +635,14 @@ func (cd *containerData) updateLoad(newLoad uint64) {
 	}
 }
 
+func (cd *containerData) updateLoadD(newLoad uint64) {
+	if cd.loadDAvg < 0 {
+		cd.loadDAvg = float64(newLoad) // initialize to the first seen sample for faster stabilization.
+	} else {
+		cd.loadDAvg = cd.loadDAvg*cd.loadDecay + float64(newLoad)*(1.0-cd.loadDecay)
+	}
+}
+
 func (cd *containerData) updateStats() error {
 	stats, statsErr := cd.handler.GetStats()
 	if statsErr != nil {
@@ -659,6 +669,10 @@ func (cd *containerData) updateStats() error {
 			cd.updateLoad(loadStats.NrRunning)
 			// convert to 'milliLoad' to avoid floats and preserve precision.
 			stats.Cpu.LoadAverage = int32(cd.loadAvg * 1000)
+
+			cd.updateLoadD(loadStats.NrUninterruptible)
+			// convert to 'milliLoad' to avoid floats and preserve precision.
+			stats.Cpu.LoadDAverage = int32(cd.loadDAvg * 1000)
 		}
 	}
 	if cd.summaryReader != nil {

diff --git a/metrics/prometheus.go b/metrics/prometheus.go
@@ -270,6 +270,13 @@ func NewPrometheusCollector(i infoProvider, f ContainerLabelsFunc, includedMetri
 				getValues: func(s *info.ContainerStats) metricValues {
 					return metricValues{{value: float64(s.Cpu.LoadAverage), timestamp: s.Timestamp}}
 				},
+			}, {
+				name:      "container_cpu_load_d_average_10s",
+				help:      "Value of container cpu load.d average over the last 10 seconds.",
+				valueType: prometheus.GaugeValue,
+				getValues: func(s *info.ContainerStats) metricValues {
+					return metricValues{{value: float64(s.Cpu.LoadDAverage), timestamp: s.Timestamp}}
+				},
 			}, {
 				name:        "container_tasks_state",
 				help:        "Number of tasks in given state",

diff --git a/metrics/prometheus_fake.go b/metrics/prometheus_fake.go
@@ -326,7 +326,8 @@ func (p testSubcontainersInfoProvider) GetRequestedContainersInfo(string, v2.Req
 							RunqueueTime: 479424566378,
 							RunPeriods:   984285,
 						},
-						LoadAverage: 2,
+						LoadAverage:  2,
+						LoadDAverage: 2,
 					},
 					Memory: info.MemoryStats{
 						Usage:             8,

diff --git a/metrics/testdata/prometheus_metrics b/metrics/testdata/prometheus_metrics
@@ -21,6 +21,9 @@ container_cpu_cfs_throttled_seconds_total{container_env_foo_env="prod",container
 # HELP container_cpu_load_average_10s Value of container cpu load average over the last 10 seconds.
 # TYPE container_cpu_load_average_10s gauge
 container_cpu_load_average_10s{container_env_foo_env="prod",container_label_foo_label="bar",id="testcontainer",image="test",name="testcontaineralias",zone_name="hello"} 2 1395066363000
+# HELP container_cpu_load_d_average_10s Value of container cpu load.d average over the last 10 seconds.
+# TYPE container_cpu_load_d_average_10s gauge
+container_cpu_load_d_average_10s{container_env_foo_env="prod",container_label_foo_label="bar",id="testcontainer",image="test",name="testcontaineralias",zone_name="hello"} 2 1395066363000
 # HELP container_cpu_schedstat_run_periods_total Number of times processes of the cgroup have run on the cpu
 # TYPE container_cpu_schedstat_run_periods_total counter
 container_cpu_schedstat_run_periods_total{container_env_foo_env="prod",container_label_foo_label="bar",id="testcontainer",image="test",name="testcontaineralias",zone_name="hello"} 984285 1395066363000

diff --git a/metrics/testdata/prometheus_metrics_whitelist_filtered b/metrics/testdata/prometheus_metrics_whitelist_filtered
@@ -21,6 +21,9 @@ container_cpu_cfs_throttled_seconds_total{container_env_foo_env="prod",id="testc
 # HELP container_cpu_load_average_10s Value of container cpu load average over the last 10 seconds.
 # TYPE container_cpu_load_average_10s gauge
 container_cpu_load_average_10s{container_env_foo_env="prod",id="testcontainer",image="test",name="testcontaineralias",zone_name="hello"} 2 1395066363000
+# HELP container_cpu_load_d_average_10s Value of container cpu load.d average over the last 10 seconds.
+# TYPE container_cpu_load_d_average_10s gauge
+container_cpu_load_d_average_10s{container_env_foo_env="prod",id="testcontainer",image="test",name="testcontaineralias",zone_name="hello"} 2 1395066363000
 # HELP container_cpu_schedstat_run_periods_total Number of times processes of the cgroup have run on the cpu
 # TYPE container_cpu_schedstat_run_periods_total counter
 container_cpu_schedstat_run_periods_total{container_env_foo_env="prod",id="testcontainer",image="test",name="testcontaineralias",zone_name="hello"} 984285 1395066363000