runtime: fix background marking at 25% utilization

Currently, in accordance with the GC pacing proposal, we schedule
background marking with a goal of achieving 25% utilization *total*
between mutator assists and background marking. This is stricter than
was set out in the Go 1.5 proposal, which suggests that the garbage
collector can use 25% just for itself and anything the mutator does to
help out is on top of that. It also has several technical
drawbacks. Because mutator assist time is constantly changing and we
can't have instantaneous information on background marking time, it
effectively requires hitting a moving target based on out-of-date
information. This works out in the long run, but works poorly for
short GC cycles and on short time scales. Also, this requires
time-multiplexing all Ps between the mutator and background GC since
the goal utilization of background GC constantly fluctuates. This
results in a complicated scheduling algorithm, poor affinity, and
extra overheads from context switching.

This change modifies the way we schedule and run background marking so
that background marking always consumes 25% of GOMAXPROCS and mutator
assist is in addition to this. This enables a much more robust
scheduling algorithm where we pre-determine the number of Ps we should
dedicate to background marking as well as the utilization goal for a
single floating "remainder" mark worker.

Change-Id: I187fa4c03ab6fe78012a84d95975167299eb9168
Reviewed-on: https://go-review.googlesource.com/9013Reviewed-by: Rick Hudson <rlh@golang.org>

src/runtime/proc1.go

@@ -1338,7 +1338,7 @@ stop:
 	// We have nothing to do. If we're in the GC mark phase, run
 	// idle-time marking rather than give up the P.
 	if _p_ := _g_.m.p.ptr(); gcphase == _GCmark && _p_.gcBgMarkWorker != nil {
-		_p_.gcBgMarkIdle = true
+		_p_.gcMarkWorkerMode = gcMarkWorkerIdleMode
 		gp := _p_.gcBgMarkWorker
 		casgstatus(gp, _Gwaiting, _Grunnable)
 		if trace.enabled {

src/runtime/runtime2.go

@@ -367,9 +367,9 @@ type p struct {
 	palloc persistentAlloc // per-P to avoid mutex
 
 	// Per-P GC state
-	gcAssistTime   int64 // Nanoseconds in assistAlloc
-	gcBgMarkWorker *g
-	gcBgMarkIdle   bool
+	gcAssistTime     int64 // Nanoseconds in assistAlloc
+	gcBgMarkWorker   *g
+	gcMarkWorkerMode gcMarkWorkerMode
 
 	pad [64]byte
 }