1
0
mirror of https://github.com/golang/go synced 2024-11-20 02:14:46 -07:00
go/src/sync/runtime.go
Dmitry Vyukov 0556e26273 sync: make Mutex more fair
Add new starvation mode for Mutex.
In starvation mode ownership is directly handed off from
unlocking goroutine to the next waiter. New arriving goroutines
don't compete for ownership.
Unfair wait time is now limited to 1ms.
Also fix a long standing bug that goroutines were requeued
at the tail of the wait queue. That lead to even more unfair
acquisition times with multiple waiters.

Performance of normal mode is not considerably affected.

Fixes #13086

On the provided in the issue lockskew program:

done in 1.207853ms
done in 1.177451ms
done in 1.184168ms
done in 1.198633ms
done in 1.185797ms
done in 1.182502ms
done in 1.316485ms
done in 1.211611ms
done in 1.182418ms

name                    old time/op  new time/op   delta
MutexUncontended-48     0.65ns ± 0%   0.65ns ± 1%     ~           (p=0.087 n=10+10)
Mutex-48                 112ns ± 1%    114ns ± 1%   +1.69%        (p=0.000 n=10+10)
MutexSlack-48            113ns ± 0%     87ns ± 1%  -22.65%         (p=0.000 n=8+10)
MutexWork-48             149ns ± 0%    145ns ± 0%   -2.48%         (p=0.000 n=9+10)
MutexWorkSlack-48        149ns ± 0%    122ns ± 3%  -18.26%         (p=0.000 n=6+10)
MutexNoSpin-48           103ns ± 4%    105ns ± 3%     ~           (p=0.089 n=10+10)
MutexSpin-48             490ns ± 4%    515ns ± 6%   +5.08%        (p=0.006 n=10+10)
Cond32-48               13.4µs ± 6%   13.1µs ± 5%   -2.75%        (p=0.023 n=10+10)
RWMutexWrite100-48      53.2ns ± 3%   41.2ns ± 3%  -22.57%        (p=0.000 n=10+10)
RWMutexWrite10-48       45.9ns ± 2%   43.9ns ± 2%   -4.38%        (p=0.000 n=10+10)
RWMutexWorkWrite100-48   122ns ± 2%    134ns ± 1%   +9.92%        (p=0.000 n=10+10)
RWMutexWorkWrite10-48    206ns ± 1%    188ns ± 1%   -8.52%         (p=0.000 n=8+10)
Cond32-24               12.1µs ± 3%   12.4µs ± 3%   +1.98%         (p=0.043 n=10+9)
MutexUncontended-24     0.74ns ± 1%   0.75ns ± 1%     ~           (p=0.650 n=10+10)
Mutex-24                 122ns ± 2%    124ns ± 1%   +1.31%        (p=0.007 n=10+10)
MutexSlack-24           96.9ns ± 2%  102.8ns ± 2%   +6.11%        (p=0.000 n=10+10)
MutexWork-24             146ns ± 1%    135ns ± 2%   -7.70%         (p=0.000 n=10+9)
MutexWorkSlack-24        135ns ± 1%    128ns ± 2%   -5.01%         (p=0.000 n=10+9)
MutexNoSpin-24           114ns ± 3%    110ns ± 4%   -3.84%        (p=0.000 n=10+10)
MutexSpin-24             482ns ± 4%    475ns ± 8%     ~           (p=0.286 n=10+10)
RWMutexWrite100-24      43.0ns ± 3%   43.1ns ± 2%     ~           (p=0.956 n=10+10)
RWMutexWrite10-24       43.4ns ± 1%   43.2ns ± 1%     ~            (p=0.085 n=10+9)
RWMutexWorkWrite100-24   130ns ± 3%    131ns ± 3%     ~           (p=0.747 n=10+10)
RWMutexWorkWrite10-24    191ns ± 1%    192ns ± 1%     ~           (p=0.210 n=10+10)
Cond32-12               11.5µs ± 2%   11.7µs ± 2%   +1.98%        (p=0.002 n=10+10)
MutexUncontended-12     1.48ns ± 0%   1.50ns ± 1%   +1.08%        (p=0.004 n=10+10)
Mutex-12                 141ns ± 1%    143ns ± 1%   +1.63%        (p=0.000 n=10+10)
MutexSlack-12            121ns ± 0%    119ns ± 0%   -1.65%          (p=0.001 n=8+9)
MutexWork-12             141ns ± 2%    150ns ± 3%   +6.36%         (p=0.000 n=9+10)
MutexWorkSlack-12        131ns ± 0%    138ns ± 0%   +5.73%         (p=0.000 n=9+10)
MutexNoSpin-12          87.0ns ± 1%   83.7ns ± 1%   -3.80%        (p=0.000 n=10+10)
MutexSpin-12             364ns ± 1%    377ns ± 1%   +3.77%        (p=0.000 n=10+10)
RWMutexWrite100-12      42.8ns ± 1%   43.9ns ± 1%   +2.41%         (p=0.000 n=8+10)
RWMutexWrite10-12       39.8ns ± 4%   39.3ns ± 1%     ~            (p=0.433 n=10+9)
RWMutexWorkWrite100-12   131ns ± 1%    131ns ± 0%     ~            (p=0.591 n=10+9)
RWMutexWorkWrite10-12    173ns ± 1%    174ns ± 0%     ~            (p=0.059 n=10+8)
Cond32-6                10.9µs ± 2%   10.9µs ± 2%     ~           (p=0.739 n=10+10)
MutexUncontended-6      2.97ns ± 0%   2.97ns ± 0%     ~     (all samples are equal)
Mutex-6                  122ns ± 6%    122ns ± 2%     ~           (p=0.668 n=10+10)
MutexSlack-6             149ns ± 3%    142ns ± 3%   -4.63%        (p=0.000 n=10+10)
MutexWork-6              136ns ± 3%    140ns ± 5%     ~           (p=0.077 n=10+10)
MutexWorkSlack-6         152ns ± 0%    138ns ± 2%   -9.21%         (p=0.000 n=6+10)
MutexNoSpin-6            150ns ± 1%    152ns ± 0%   +1.50%         (p=0.000 n=8+10)
MutexSpin-6              726ns ± 0%    730ns ± 1%     ~           (p=0.069 n=10+10)
RWMutexWrite100-6       40.6ns ± 1%   40.9ns ± 1%   +0.91%         (p=0.001 n=8+10)
RWMutexWrite10-6        37.1ns ± 0%   37.0ns ± 1%     ~            (p=0.386 n=9+10)
RWMutexWorkWrite100-6    133ns ± 1%    134ns ± 1%   +1.01%         (p=0.005 n=9+10)
RWMutexWorkWrite10-6     152ns ± 0%    152ns ± 0%     ~     (all samples are equal)
Cond32-2                7.86µs ± 2%   7.95µs ± 2%   +1.10%        (p=0.023 n=10+10)
MutexUncontended-2      8.10ns ± 0%   9.11ns ± 4%  +12.44%         (p=0.000 n=9+10)
Mutex-2                 32.9ns ± 9%   38.4ns ± 6%  +16.58%        (p=0.000 n=10+10)
MutexSlack-2            93.4ns ± 1%   98.5ns ± 2%   +5.39%         (p=0.000 n=10+9)
MutexWork-2             40.8ns ± 3%   43.8ns ± 7%   +7.38%         (p=0.000 n=10+9)
MutexWorkSlack-2        98.6ns ± 5%  108.2ns ± 2%   +9.80%         (p=0.000 n=10+8)
MutexNoSpin-2            399ns ± 1%    398ns ± 2%     ~             (p=0.463 n=8+9)
MutexSpin-2             1.99µs ± 3%   1.97µs ± 1%   -0.81%          (p=0.003 n=9+8)
RWMutexWrite100-2       37.6ns ± 5%   46.0ns ± 4%  +22.17%         (p=0.000 n=10+8)
RWMutexWrite10-2        50.1ns ± 6%   36.8ns ±12%  -26.46%         (p=0.000 n=9+10)
RWMutexWorkWrite100-2    136ns ± 0%    134ns ± 2%   -1.80%          (p=0.001 n=7+9)
RWMutexWorkWrite10-2     140ns ± 1%    138ns ± 1%   -1.50%        (p=0.000 n=10+10)
Cond32                  5.93µs ± 1%   5.91µs ± 0%     ~            (p=0.411 n=9+10)
MutexUncontended        15.9ns ± 0%   15.8ns ± 0%   -0.63%          (p=0.000 n=8+8)
Mutex                   15.9ns ± 0%   15.8ns ± 0%   -0.44%        (p=0.003 n=10+10)
MutexSlack              26.9ns ± 3%   26.7ns ± 2%     ~           (p=0.084 n=10+10)
MutexWork               47.8ns ± 0%   47.9ns ± 0%   +0.21%          (p=0.014 n=9+8)
MutexWorkSlack          54.9ns ± 3%   54.5ns ± 3%     ~           (p=0.254 n=10+10)
MutexNoSpin              786ns ± 2%    765ns ± 1%   -2.66%        (p=0.000 n=10+10)
MutexSpin               3.87µs ± 1%   3.83µs ± 0%   -0.85%          (p=0.005 n=9+8)
RWMutexWrite100         21.2ns ± 2%   21.0ns ± 1%   -0.88%         (p=0.018 n=10+9)
RWMutexWrite10          22.6ns ± 1%   22.6ns ± 0%     ~             (p=0.471 n=9+9)
RWMutexWorkWrite100      132ns ± 0%    132ns ± 0%     ~     (all samples are equal)
RWMutexWorkWrite10       124ns ± 0%    123ns ± 0%     ~           (p=0.656 n=10+10)

Change-Id: I66412a3a0980df1233ad7a5a0cd9723b4274528b
Reviewed-on: https://go-review.googlesource.com/34310
Run-TryBot: Russ Cox <rsc@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
2017-02-17 17:24:59 +00:00

64 lines
1.9 KiB
Go

// Copyright 2012 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package sync
import "unsafe"
// defined in package runtime
// Semacquire waits until *s > 0 and then atomically decrements it.
// It is intended as a simple sleep primitive for use by the synchronization
// library and should not be used directly.
func runtime_Semacquire(s *uint32)
// SemacquireMutex is like Semacquire, but for profiling contended Mutexes.
// If lifo is true, queue waiter at the head of wait queue.
func runtime_SemacquireMutex(s *uint32, lifo bool)
// Semrelease atomically increments *s and notifies a waiting goroutine
// if one is blocked in Semacquire.
// It is intended as a simple wakeup primitive for use by the synchronization
// library and should not be used directly.
// If handoff is true, pass count directly to the first waiter.
func runtime_Semrelease(s *uint32, handoff bool)
// Approximation of notifyList in runtime/sema.go. Size and alignment must
// agree.
type notifyList struct {
wait uint32
notify uint32
lock uintptr
head unsafe.Pointer
tail unsafe.Pointer
}
// See runtime/sema.go for documentation.
func runtime_notifyListAdd(l *notifyList) uint32
// See runtime/sema.go for documentation.
func runtime_notifyListWait(l *notifyList, t uint32)
// See runtime/sema.go for documentation.
func runtime_notifyListNotifyAll(l *notifyList)
// See runtime/sema.go for documentation.
func runtime_notifyListNotifyOne(l *notifyList)
// Ensure that sync and runtime agree on size of notifyList.
func runtime_notifyListCheck(size uintptr)
func init() {
var n notifyList
runtime_notifyListCheck(unsafe.Sizeof(n))
}
// Active spinning runtime support.
// runtime_canSpin returns true is spinning makes sense at the moment.
func runtime_canSpin(i int) bool
// runtime_doSpin does active spinning.
func runtime_doSpin()
func runtime_nanotime() int64