runtime: report GC CPU utilization in MemStats

This adds a GCCPUFraction field to MemStats that reports the
cumulative fraction of the program's execution time spent in the
garbage collector. This is equivalent to the utilization percent shown
in the gctrace output and makes this available programmatically.

This does make one small effect on the gctrace output: we now report
the duration of mark termination up to just before the final
start-the-world, rather than up to just after. However, unlike
stop-the-world, I don't believe there's any way that start-the-world
can block, so it should take negligible time.

While there are many statistics one might want to expose via MemStats,
this is one of the few that will undoubtedly remain meaningful
regardless of future changes to the memory system.

The diff for this change is larger than the actual change. Mostly it
lifts the code for computing the GC CPU utilization out of the
debug.gctrace path.

Updates #10323.

Change-Id: I0f7dc3fdcafe95e8d1233ceb79de606b48acd989
Reviewed-on: https://go-review.googlesource.com/12844Reviewed-by: Russ Cox <rsc@golang.org>

src/runtime/mgc.go

@@ -1121,6 +1121,21 @@ func gc(mode int) {
 	memstats.pause_end[memstats.numgc%uint32(len(memstats.pause_end))] = uint64(unixNow)
 	memstats.pause_total_ns += uint64(pauseNS)
 
+	// Update work.totaltime.
+	sweepTermCpu := int64(stwprocs) * (tScan - tSweepTerm)
+	scanCpu := tInstallWB - tScan
+	installWBCpu := int64(0)
+	// We report idle marking time below, but omit it from the
+	// overall utilization here since it's "free".
+	markCpu := gcController.assistTime + gcController.dedicatedMarkTime + gcController.fractionalMarkTime
+	markTermCpu := int64(stwprocs) * (now - tMarkTerm)
+	cycleCpu := sweepTermCpu + scanCpu + installWBCpu + markCpu + markTermCpu
+	work.totaltime += cycleCpu
+
+	// Compute overall GC CPU utilization.
+	totalCpu := sched.totaltime + (now-sched.procresizetime)*int64(gomaxprocs)
+	memstats.gc_cpu_fraction = float64(work.totaltime) / float64(totalCpu)
+
 	memstats.numgc++
 
 	systemstack(startTheWorldWithSema)
@@ -1130,22 +1145,8 @@ func gc(mode int) {
 	mp = nil
 
 	if debug.gctrace > 0 {
-		tEnd := nanotime()
-
-		// Update work.totaltime
-		sweepTermCpu := int64(stwprocs) * (tScan - tSweepTerm)
-		scanCpu := tInstallWB - tScan
-		installWBCpu := int64(0)
-		// We report idle marking time below, but omit it from
-		// the overall utilization here since it's "free".
-		markCpu := gcController.assistTime + gcController.dedicatedMarkTime + gcController.fractionalMarkTime
-		markTermCpu := int64(stwprocs) * (tEnd - tMarkTerm)
-		cycleCpu := sweepTermCpu + scanCpu + installWBCpu + markCpu + markTermCpu
-		work.totaltime += cycleCpu
-
-		// Compute overall utilization
-		totalCpu := sched.totaltime + (tEnd-sched.procresizetime)*int64(gomaxprocs)
-		util := work.totaltime * 100 / totalCpu
+		tEnd := now
+		util := int(memstats.gc_cpu_fraction * 100)
 
 		var sbuf [24]byte
 		printlock()

src/runtime/mstats.go

@@ -9,7 +9,7 @@ package runtime
 import "unsafe"
 
 // Statistics.
-// Shared with Go: if you edit this structure, also edit type MemStats in mem.go.
+// If you edit this structure, also edit type MemStats below.
 type mstats struct {
 	// General statistics.
 	alloc       uint64 // bytes allocated and not yet freed
@@ -42,14 +42,15 @@ type mstats struct {
 
 	// Statistics about garbage collector.
 	// Protected by mheap or stopping the world during GC.
-	next_gc        uint64 // next gc (in heap_alloc time)
-	last_gc        uint64 // last gc (in absolute time)
-	pause_total_ns uint64
-	pause_ns       [256]uint64 // circular buffer of recent gc pause lengths
-	pause_end      [256]uint64 // circular buffer of recent gc end times (nanoseconds since 1970)
-	numgc          uint32
-	enablegc       bool
-	debuggc        bool
+	next_gc         uint64 // next gc (in heap_alloc time)
+	last_gc         uint64 // last gc (in absolute time)
+	pause_total_ns  uint64
+	pause_ns        [256]uint64 // circular buffer of recent gc pause lengths
+	pause_end       [256]uint64 // circular buffer of recent gc end times (nanoseconds since 1970)
+	numgc           uint32
+	gc_cpu_fraction float64 // fraction of CPU time used by GC
+	enablegc        bool
+	debuggc         bool
 
 	// Statistics about allocation size classes.
 
@@ -119,14 +120,15 @@ type MemStats struct {
 	OtherSys    uint64 // other system allocations
 
 	// Garbage collector statistics.
-	NextGC       uint64 // next collection will happen when HeapAlloc ≥ this amount
-	LastGC       uint64 // end time of last collection (nanoseconds since 1970)
-	PauseTotalNs uint64
-	PauseNs      [256]uint64 // circular buffer of recent GC pause durations, most recent at [(NumGC+255)%256]
-	PauseEnd     [256]uint64 // circular buffer of recent GC pause end times
-	NumGC        uint32
-	EnableGC     bool
-	DebugGC      bool
+	NextGC        uint64 // next collection will happen when HeapAlloc ≥ this amount
+	LastGC        uint64 // end time of last collection (nanoseconds since 1970)
+	PauseTotalNs  uint64
+	PauseNs       [256]uint64 // circular buffer of recent GC pause durations, most recent at [(NumGC+255)%256]
+	PauseEnd      [256]uint64 // circular buffer of recent GC pause end times
+	NumGC         uint32
+	GCCPUFraction float64 // fraction of CPU time used by GC
+	EnableGC      bool
+	DebugGC       bool
 
 	// Per-size allocation statistics.
 	// 61 is NumSizeClasses in the C code.