runtime: improve timers scalability on multi-CPU systems

Use per-P timers, so each P may work with its own timers.

This CL improves performance on multi-CPU systems
in the following cases:

- When serving high number of concurrent connections
  with read/write deadlines set (for instance, highly loaded
  net/http server).

- When using high number of concurrent timers. These timers
  may be implicitly created via context.WithDeadline
  or context.WithTimeout.

Production servers should usually set timeout on connections
and external requests in order to prevent from resource leakage.
See https://blog.cloudflare.com/the-complete-guide-to-golang-net-http-timeouts/

Below are relevant benchmark results for various GOMAXPROCS values
on linux/amd64:

context package:

name                                     old time/op  new time/op  delta
WithTimeout/concurrency=40      4.92µs ± 0%  5.17µs ± 1%  +5.07%  (p=0.000 n=9+9)
WithTimeout/concurrency=4000    6.03µs ± 1%  6.49µs ± 0%  +7.63%  (p=0.000 n=8+10)
WithTimeout/concurrency=400000  8.58µs ± 7%  9.02µs ± 4%  +5.02%  (p=0.019 n=10+10)

name                                     old time/op  new time/op  delta
WithTimeout/concurrency=40-2      3.70µs ± 1%  2.78µs ± 4%  -24.90%  (p=0.000 n=8+9)
WithTimeout/concurrency=4000-2    4.49µs ± 4%  3.67µs ± 5%  -18.26%  (p=0.000 n=10+10)
WithTimeout/concurrency=400000-2  6.16µs ±10%  5.15µs ±13%  -16.30%  (p=0.000 n=10+10)

name                                     old time/op  new time/op  delta
WithTimeout/concurrency=40-4      3.58µs ± 1%  2.64µs ± 2%  -26.13%  (p=0.000 n=9+10)
WithTimeout/concurrency=4000-4    4.17µs ± 0%  3.32µs ± 1%  -20.36%  (p=0.000 n=10+10)
WithTimeout/concurrency=400000-4  5.57µs ± 9%  4.83µs ±10%  -13.27%  (p=0.001 n=10+10)

time package:

name                     old time/op  new time/op  delta
AfterFunc                6.15ms ± 3%  6.07ms ± 2%     ~     (p=0.133 n=10+9)
AfterFunc-2              3.43ms ± 1%  3.56ms ± 1%   +3.91%  (p=0.000 n=10+9)
AfterFunc-4              5.04ms ± 2%  2.36ms ± 0%  -53.20%  (p=0.000 n=10+9)
After                    6.54ms ± 2%  6.49ms ± 3%     ~     (p=0.393 n=10+10)
After-2                  3.68ms ± 1%  3.87ms ± 0%   +5.14%  (p=0.000 n=9+9)
After-4                  6.66ms ± 1%  2.87ms ± 1%  -56.89%  (p=0.000 n=10+10)
Stop                      698µs ± 2%   689µs ± 1%   -1.26%  (p=0.011 n=10+10)
Stop-2                    729µs ± 2%   434µs ± 3%  -40.49%  (p=0.000 n=10+10)
Stop-4                    837µs ± 3%   333µs ± 2%  -60.20%  (p=0.000 n=10+10)
SimultaneousAfterFunc     694µs ± 1%   692µs ± 7%     ~     (p=0.481 n=10+10)
SimultaneousAfterFunc-2   714µs ± 3%   569µs ± 2%  -20.33%  (p=0.000 n=10+10)
SimultaneousAfterFunc-4   782µs ± 2%   386µs ± 2%  -50.67%  (p=0.000 n=10+10)
StartStop                 267µs ± 3%   274µs ± 0%   +2.64%  (p=0.000 n=8+9)
StartStop-2               238µs ± 2%   140µs ± 3%  -40.95%  (p=0.000 n=10+8)
StartStop-4               320µs ± 1%   125µs ± 1%  -61.02%  (p=0.000 n=9+9)
Reset                    75.0µs ± 1%  77.5µs ± 2%   +3.38%  (p=0.000 n=10+10)
Reset-2                   150µs ± 2%    40µs ± 5%  -73.09%  (p=0.000 n=10+9)
Reset-4                   226µs ± 1%    33µs ± 1%  -85.42%  (p=0.000 n=10+10)
Sleep                     857µs ± 6%   878µs ± 9%     ~     (p=0.079 n=10+9)
Sleep-2                   617µs ± 4%   585µs ± 2%   -5.21%  (p=0.000 n=10+10)
Sleep-4                   689µs ± 3%   465µs ± 4%  -32.53%  (p=0.000 n=10+10)
Ticker                   55.9ms ± 2%  55.9ms ± 2%     ~     (p=0.971 n=10+10)
Ticker-2                 28.7ms ± 2%  28.1ms ± 1%   -2.06%  (p=0.000 n=10+10)
Ticker-4                 14.6ms ± 0%  13.6ms ± 1%   -6.80%  (p=0.000 n=9+10)

Fixes #15133

Change-Id: I6f4b09d2db8c5bec93146db6501b44dbfe5c0ac4
Reviewed-on: https://go-review.googlesource.com/34784
Reviewed-by: Austin Clements <austin@google.com>

1 files changed, 4 insertions, 3 deletions

diff --git a/src/internal/trace/parser.go b/src/internal/trace/parser.go
index 31b41bcac5..2e145129eb 100644
--- a/src/internal/trace/parser.go
+++ b/src/internal/trace/parser.go
@@ -270,8 +270,9 @@ func parseHeader(buf []byte) (int, error) {
 // It does analyze and verify per-event-type arguments.
 func parseEvents(ver int, rawEvents []rawEvent, strings map[uint64]string) (events []*Event, stacks map[uint64][]*Frame, err error) {
 	var ticksPerSec, lastSeq, lastTs int64
-	var lastG, timerGoid uint64
+	var lastG uint64
 	var lastP int
+	timerGoids := make(map[uint64]bool)
 	lastGs := make(map[int]uint64) // last goroutine running on P
 	stacks = make(map[uint64][]*Frame)
 	batches := make(map[int][]*Event) // events by P
@@ -308,7 +309,7 @@ func parseEvents(ver int, rawEvents []rawEvent, strings map[uint64]string) (even
 				return
 			}
 		case EvTimerGoroutine:
-			timerGoid = raw.args[0]
+			timerGoids[raw.args[0]] = true
 		case EvStack:
 			if len(raw.args) < 2 {
 				err = fmt.Errorf("EvStack has wrong number of arguments at offset 0x%x: want at least 2, got %v",
@@ -431,7 +432,7 @@ func parseEvents(ver int, rawEvents []rawEvent, strings map[uint64]string) (even
 	for _, ev := range events {
 		ev.Ts = int64(float64(ev.Ts-minTs) * freq)
 		// Move timers and syscalls to separate fake Ps.
-		if timerGoid != 0 && ev.G == timerGoid && ev.Type == EvGoUnblock {
+		if timerGoids[ev.G] && ev.Type == EvGoUnblock {
 			ev.P = TimerP
 		}
 		if ev.Type == EvGoSysExit {