diff options
| author | Dmitriy Vyukov <dvyukov@google.com> | 2013-01-10 09:57:06 +0400 |
|---|---|---|
| committer | Dmitriy Vyukov <dvyukov@google.com> | 2013-01-10 09:57:06 +0400 |
| commit | f82db7d9e4ccf04b19a087561ab0f521fc36e5b1 (patch) | |
| tree | 17307311faba0dc26fadc8044e0808fc6ee04a4d /src/pkg/runtime/runtime.h | |
| parent | 7d403871cb7e319cb1f52ce2ff04c80bdc5ac92a (diff) | |
| download | go-f82db7d9e4ccf04b19a087561ab0f521fc36e5b1.tar.xz | |
runtime: less aggressive per-thread stack segment caching
Introduce global stack segment cache and limit per-thread cache size.
This greatly reduces StackSys memory on workloads that create lots of threads.
benchmark old ns/op new ns/op delta
BenchmarkStackGrowth 665 656 -1.35%
BenchmarkStackGrowth-2 333 328 -1.50%
BenchmarkStackGrowth-4 224 172 -23.21%
BenchmarkStackGrowth-8 124 91 -26.13%
BenchmarkStackGrowth-16 82 47 -41.94%
BenchmarkStackGrowth-32 73 40 -44.79%
BenchmarkStackGrowthDeep 97231 94391 -2.92%
BenchmarkStackGrowthDeep-2 47230 58562 +23.99%
BenchmarkStackGrowthDeep-4 24993 49356 +97.48%
BenchmarkStackGrowthDeep-8 15105 30072 +99.09%
BenchmarkStackGrowthDeep-16 10005 15623 +56.15%
BenchmarkStackGrowthDeep-32 12517 13069 +4.41%
TestStackMem#1,MB 310 12 -96.13%
TestStackMem#2,MB 296 14 -95.27%
TestStackMem#3,MB 479 14 -97.08%
TestStackMem#1,sec 3.22 2.26 -29.81%
TestStackMem#2,sec 2.43 2.15 -11.52%
TestStackMem#3,sec 2.50 2.38 -4.80%
R=sougou, no.smile.face, rsc
CC=golang-dev, msolomon
https://golang.org/cl/7029044
Diffstat (limited to 'src/pkg/runtime/runtime.h')
| -rw-r--r-- | src/pkg/runtime/runtime.h | 12 |
1 files changed, 11 insertions, 1 deletions
diff --git a/src/pkg/runtime/runtime.h b/src/pkg/runtime/runtime.h index a228b06e32..47a7b6e78b 100644 --- a/src/pkg/runtime/runtime.h +++ b/src/pkg/runtime/runtime.h @@ -128,6 +128,13 @@ enum { PtrSize = sizeof(void*), }; +enum +{ + // Per-M stack segment cache size. + StackCacheSize = 32, + // Global <-> per-M stack segment cache transfer batch size. + StackCacheBatch = 16, +}; /* * structures @@ -262,7 +269,10 @@ struct M M* schedlink; uint32 machport; // Return address for Mach IPC (OS X) MCache *mcache; - FixAlloc *stackalloc; + int32 stackinuse; + uint32 stackcachepos; + uint32 stackcachecnt; + void* stackcache[StackCacheSize]; G* lockedg; G* idleg; uintptr createstack[32]; // Stack that created this thread. |