stats: register subset of go runtime metrics with prometheus

Signed-off-by: Aaron Wilson <aawilson@nvidia.com>

Author: aaronnw

stats/api.go

@@ -39,7 +39,8 @@ const (
 
 // static labels
 const (
-	ConstlabNode = "node_id"
+	ConstlabNode      = "node_id"
+	ConstlabComponent = "component"
 )
 
 // variable labels

stats/common.go

@@ -188,6 +188,8 @@ func (r *runner) RegExtMetric(snode *meta.Snode, name, kind string, extra *Extra
 func (r *runner) regCommon(snode *meta.Snode) {
 	initProm(snode)
 
+	regGoRuntime(snode.Type())
+
 	// basic counters
 	r.reg(snode, GetCount, KindCounter,
 		&Extra{

stats/common_prom.go

@@ -7,6 +7,7 @@ package stats
 
 import (
 	"net/http"
+	"regexp"
 	"strings"
 	ratomic "sync/atomic"
 	"time"
@@ -16,6 +17,7 @@ import (
 	"github.com/NVIDIA/aistore/memsys"
 
 	"github.com/prometheus/client_golang/prometheus"
+	"github.com/prometheus/client_golang/prometheus/collectors"
 	"github.com/prometheus/client_golang/prometheus/promhttp"
 )
 
@@ -46,12 +48,39 @@ var (
 )
 
 func initProm(snode *meta.Snode) {
-	// devoid of _default_ metrics go_gc*, go_mem*, and such
 	promRegistry = prometheus.NewRegistry()
 
 	staticLabs[ConstlabNode] = strings.ReplaceAll(snode.ID(), ".", "_")
 }
 
+// Expose a low-cardinality subset of Go runtime metrics on the AIS Prometheus registry:
+//   - base collector (unconditional):
+//     go_goroutines, go_threads, go_info, go_gc_duration_seconds, go_memstats_last_gc_time_seconds
+//   - default runtime/metrics matcher:
+//     go_gc_gogc_percent, go_gc_gomemlimit_bytes, go_sched_gomaxprocs_threads
+//   - explicit picks via WithGoCollectorRuntimeMetrics below (one series each)
+func regGoRuntime(daeType string) {
+	nodeLabs := prometheus.Labels{
+		ConstlabNode:      staticLabs[ConstlabNode],
+		ConstlabComponent: daeType,
+	}
+	reg := prometheus.WrapRegistererWith(nodeLabs, promRegistry)
+	reg.MustRegister(collectors.NewGoCollector(
+		// skip legacy go_memstats_* block (21 series, mostly duplicative); use runtime/metrics names instead
+		collectors.WithGoCollectorMemStatsMetricsDisabled(),
+		collectors.WithGoCollectorRuntimeMetrics(
+			collectors.GoRuntimeMetricsRule{Matcher: regexp.MustCompile(
+				`^/memory/classes/heap/objects:bytes$` + // heap in use
+					`|^/memory/classes/total:bytes$` + // total from OS
+					`|^/gc/heap/goal:bytes$` + // next GC target
+					`|^/gc/heap/allocs:bytes$` + // cumulative alloc bytes (counter)
+					`|^/cpu/classes/gc/total:cpu-seconds$` + // cumulative GC CPU time
+					`|^/gc/cycles/total:gc-cycles$`, // cumulative GC cycle count
+			)},
+		),
+	))
+}
+
 // usage: log resulting `copyValue` numbers:
 func (s *coreStats) copyT(out copyTracker, diskLowUtil ...int64) bool {
 	idle := true