1
0
mirror of https://github.com/golang/go synced 2024-10-02 20:31:21 -06:00
go/src/pkg/runtime/sema.goc

179 lines
3.7 KiB
Plaintext
Raw Normal View History

// Copyright 2009 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.
// Semaphore implementation exposed to Go.
// Intended use is provide a sleep and wakeup
// primitive that can be used in the contended case
// of other synchronization primitives.
// Thus it targets the same goal as Linux's futex,
// but it has much simpler semantics.
//
// That is, don't think of these as semaphores.
// Think of them as a way to implement sleep and wakeup
// such that every sleep is paired with a single wakeup,
// even if, due to races, the wakeup happens before the sleep.
//
// See Mullender and Cox, ``Semaphores in Plan 9,''
// http://swtch.com/semaphore.pdf
package sync
#include "runtime.h"
#include "arch_GOARCH.h"
typedef struct Sema Sema;
struct Sema
{
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
uint32 volatile *addr;
G *g;
Sema *prev;
Sema *next;
};
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
typedef struct SemaRoot SemaRoot;
struct SemaRoot
{
Lock;
Sema *head;
Sema *tail;
// Number of waiters. Read w/o the lock.
uint32 volatile nwait;
};
// Prime to not correlate with any user patterns.
#define SEMTABLESZ 251
static union
{
SemaRoot;
uint8 pad[CacheLineSize];
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
} semtable[SEMTABLESZ];
static SemaRoot*
semroot(uint32 *addr)
{
return &semtable[((uintptr)addr >> 3) % SEMTABLESZ];
}
static void
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
semqueue(SemaRoot *root, uint32 volatile *addr, Sema *s)
{
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
s->g = g;
s->addr = addr;
s->next = nil;
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
s->prev = root->tail;
if(root->tail)
root->tail->next = s;
else
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
root->head = s;
root->tail = s;
}
static void
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
semdequeue(SemaRoot *root, Sema *s)
{
if(s->next)
s->next->prev = s->prev;
else
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
root->tail = s->prev;
if(s->prev)
s->prev->next = s->next;
else
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
root->head = s->next;
s->prev = nil;
s->next = nil;
}
static int32
cansemacquire(uint32 *addr)
{
uint32 v;
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
while((v = runtime·atomicload(addr)) > 0)
if(runtime·cas(addr, v, v-1))
return 1;
return 0;
}
void
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
runtime·semacquire(uint32 volatile *addr)
{
Sema s;
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
SemaRoot *root;
// Easy case.
if(cansemacquire(addr))
return;
// Harder case:
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
// increment waiter count
// try cansemacquire one more time, return if succeeded
// enqueue itself as a waiter
// sleep
// (waiter descriptor is dequeued by signaler)
root = semroot(addr);
for(;;) {
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
runtime·lock(root);
// Add ourselves to nwait to disable "easy case" in semrelease.
runtime·xadd(&root->nwait, 1);
// Check cansemacquire to avoid missed wakeup.
if(cansemacquire(addr)) {
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
runtime·xadd(&root->nwait, -1);
runtime·unlock(root);
return;
}
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
// Any semrelease after the cansemacquire knows we're waiting
// (we set nwait above), so go to sleep.
semqueue(root, addr, &s);
g->status = Gwaiting;
runtime: simplify stack traces Make the stack traces more readable for new Go programmers while preserving their utility for old hands. - Change status number [4] to string. - Elide frames in runtime package (internal details). - Swap file:line and arguments. - Drop 'created by' for main goroutine. - Show goroutines in order of allocation: implies main goroutine first if nothing else. There is no option to get the extra frames back. Uncomment 'return 1' at the bottom of symtab.c. $ 6.out throw: all goroutines are asleep - deadlock! goroutine 1 [chan send]: main.main() /Users/rsc/g/go/src/pkg/runtime/x.go:22 +0x8a goroutine 2 [select (no cases)]: main.sel() /Users/rsc/g/go/src/pkg/runtime/x.go:11 +0x18 created by main.main /Users/rsc/g/go/src/pkg/runtime/x.go:19 +0x23 goroutine 3 [chan receive]: main.recv(0xf8400010a0, 0x0) /Users/rsc/g/go/src/pkg/runtime/x.go:15 +0x2e created by main.main /Users/rsc/g/go/src/pkg/runtime/x.go:20 +0x50 goroutine 4 [chan receive (nil chan)]: main.recv(0x0, 0x0) /Users/rsc/g/go/src/pkg/runtime/x.go:15 +0x2e created by main.main /Users/rsc/g/go/src/pkg/runtime/x.go:21 +0x66 $ $ 6.out index panic: runtime error: index out of range goroutine 1 [running]: main.main() /Users/rsc/g/go/src/pkg/runtime/x.go:25 +0xb9 $ $ 6.out nil panic: runtime error: invalid memory address or nil pointer dereference [signal 0xb code=0x1 addr=0x0 pc=0x22ca] goroutine 1 [running]: main.main() /Users/rsc/g/go/src/pkg/runtime/x.go:28 +0x211 $ $ 6.out panic panic: panic goroutine 1 [running]: main.main() /Users/rsc/g/go/src/pkg/runtime/x.go:30 +0x101 $ R=golang-dev, qyzhai, n13m3y3r, r CC=golang-dev https://golang.org/cl/4907048
2011-08-22 21:26:39 -06:00
g->waitreason = "semacquire";
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
runtime·unlock(root);
runtime·gosched();
if(cansemacquire(addr))
return;
}
}
void
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
runtime·semrelease(uint32 volatile *addr)
{
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
Sema *s;
SemaRoot *root;
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
root = semroot(addr);
runtime·xadd(addr, 1);
// Easy case: no waiters?
// This check must happen after the xadd, to avoid a missed wakeup
// (see loop in semacquire).
if(runtime·atomicload(&root->nwait) == 0)
return;
// Harder case: search for a waiter and wake it.
runtime·lock(root);
if(runtime·atomicload(&root->nwait) == 0) {
// The count is already consumed by another goroutine,
// so no need to wake up another goroutine.
runtime·unlock(root);
return;
}
for(s = root->head; s; s = s->next) {
if(s->addr == addr) {
runtime·xadd(&root->nwait, -1);
semdequeue(root, s);
break;
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
}
}
runtime: replace Semacquire/Semrelease implementation 1. The implementation uses distributed hash table of waitlists instead of a centralized one. It significantly improves scalability for uncontended semaphores. 2. The implementation provides wait-free fast-path for signalers. 3. The implementation uses less locks (1 lock/unlock instead of 5 for Semacquire). 4. runtime·ready() call is moved out of critical section. 5. Semacquire() does not call semwake(). Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz) are as follows: benchmark old ns/op new ns/op delta runtime_test.BenchmarkSemaUncontended 58.20 36.30 -37.63% runtime_test.BenchmarkSemaUncontended-2 199.00 18.30 -90.80% runtime_test.BenchmarkSemaUncontended-4 327.00 9.20 -97.19% runtime_test.BenchmarkSemaUncontended-8 491.00 5.32 -98.92% runtime_test.BenchmarkSemaUncontended-16 946.00 4.18 -99.56% runtime_test.BenchmarkSemaSyntNonblock 59.00 36.80 -37.63% runtime_test.BenchmarkSemaSyntNonblock-2 167.00 138.00 -17.37% runtime_test.BenchmarkSemaSyntNonblock-4 333.00 129.00 -61.26% runtime_test.BenchmarkSemaSyntNonblock-8 464.00 130.00 -71.98% runtime_test.BenchmarkSemaSyntNonblock-16 1015.00 136.00 -86.60% runtime_test.BenchmarkSemaSyntBlock 58.80 36.70 -37.59% runtime_test.BenchmarkSemaSyntBlock-2 294.00 149.00 -49.32% runtime_test.BenchmarkSemaSyntBlock-4 333.00 177.00 -46.85% runtime_test.BenchmarkSemaSyntBlock-8 471.00 221.00 -53.08% runtime_test.BenchmarkSemaSyntBlock-16 990.00 227.00 -77.07% runtime_test.BenchmarkSemaWorkNonblock 829.00 832.00 +0.36% runtime_test.BenchmarkSemaWorkNonblock-2 425.00 419.00 -1.41% runtime_test.BenchmarkSemaWorkNonblock-4 308.00 220.00 -28.57% runtime_test.BenchmarkSemaWorkNonblock-8 394.00 147.00 -62.69% runtime_test.BenchmarkSemaWorkNonblock-16 1510.00 149.00 -90.13% runtime_test.BenchmarkSemaWorkBlock 828.00 813.00 -1.81% runtime_test.BenchmarkSemaWorkBlock-2 428.00 436.00 +1.87% runtime_test.BenchmarkSemaWorkBlock-4 232.00 219.00 -5.60% runtime_test.BenchmarkSemaWorkBlock-8 392.00 251.00 -35.97% runtime_test.BenchmarkSemaWorkBlock-16 1524.00 298.00 -80.45% sync_test.BenchmarkMutexUncontended 24.10 24.00 -0.41% sync_test.BenchmarkMutexUncontended-2 12.00 12.00 +0.00% sync_test.BenchmarkMutexUncontended-4 6.25 6.17 -1.28% sync_test.BenchmarkMutexUncontended-8 3.43 3.34 -2.62% sync_test.BenchmarkMutexUncontended-16 2.34 2.32 -0.85% sync_test.BenchmarkMutex 24.70 24.70 +0.00% sync_test.BenchmarkMutex-2 208.00 99.50 -52.16% sync_test.BenchmarkMutex-4 2744.00 256.00 -90.67% sync_test.BenchmarkMutex-8 5137.00 556.00 -89.18% sync_test.BenchmarkMutex-16 5368.00 1284.00 -76.08% sync_test.BenchmarkMutexSlack 24.70 25.00 +1.21% sync_test.BenchmarkMutexSlack-2 1094.00 186.00 -83.00% sync_test.BenchmarkMutexSlack-4 3430.00 402.00 -88.28% sync_test.BenchmarkMutexSlack-8 5051.00 1066.00 -78.90% sync_test.BenchmarkMutexSlack-16 6806.00 1363.00 -79.97% sync_test.BenchmarkMutexWork 793.00 792.00 -0.13% sync_test.BenchmarkMutexWork-2 398.00 398.00 +0.00% sync_test.BenchmarkMutexWork-4 1441.00 308.00 -78.63% sync_test.BenchmarkMutexWork-8 8532.00 847.00 -90.07% sync_test.BenchmarkMutexWork-16 8225.00 2760.00 -66.44% sync_test.BenchmarkMutexWorkSlack 793.00 793.00 +0.00% sync_test.BenchmarkMutexWorkSlack-2 418.00 414.00 -0.96% sync_test.BenchmarkMutexWorkSlack-4 4481.00 480.00 -89.29% sync_test.BenchmarkMutexWorkSlack-8 6317.00 1598.00 -74.70% sync_test.BenchmarkMutexWorkSlack-16 9111.00 3038.00 -66.66% R=rsc CC=golang-dev https://golang.org/cl/4631059
2011-06-28 13:09:53 -06:00
runtime·unlock(root);
if(s)
runtime·ready(s->g);
}
func runtime_Semacquire(addr *uint32) {
runtime·semacquire(addr);
}
func runtime_Semrelease(addr *uint32) {
runtime·semrelease(addr);
}