3770b0e60c
gc: implement nil chan support
...
The spec has defined nil chans this way for months.
I'm behind.
R=ken2
CC=golang-dev
https://golang.org/cl/4897050
2011-08-17 15:54:17 -04:00
65bde087ae
gc: implement nil map support
...
The spec has defined nil maps this way for months.
I'm behind.
R=ken2
CC=golang-dev
https://golang.org/cl/4901052
2011-08-17 14:56:27 -04:00
a2677cf363
runtime: fix GC bitmap corruption
...
The corruption can occur when GOMAXPROCS
is changed from >1 to 1, since GOMAXPROCS=1
does not imply there is only 1 goroutine running,
other goroutines can still be not parked after
the change.
R=golang-dev, rsc
CC=golang-dev
https://golang.org/cl/4873050
2011-08-16 16:53:02 -04:00
175849295c
runtime: fix pseudo-randomness on some selects
...
Fixes #2152 .
R=golang-dev, dvyukov
CC=golang-dev
https://golang.org/cl/4888044
2011-08-15 03:51:51 -03:00
c8ee9c60d2
runtime: better checks for syscall.NewCallback parameter
...
R=golang-dev, rsc
CC=golang-dev
https://golang.org/cl/4859042
2011-08-11 12:23:55 +10:00
c02423902d
build: allow builds without cgo
...
R=bradfitz, dsymonds, fshahriar
CC=golang-dev
https://golang.org/cl/4859043
2011-08-10 21:36:48 -04:00
9c774c3f26
runtime: correct seh installation during callbacks
...
Every time we enter callback from Windows, it is
possible that go exception handler is not at the top
of per-thread exception handlers chain. So it needs
to be installed again. At this moment this is done
by replacing top SEH frame with SEH frame as at time
of syscall for the time of callback. This is incorrect,
because, if exception strike, we won't be able to call
any exception handlers installed inside syscall,
because they are not in the chain. This changes
procedure to add new SEH frame on top of existing
chain instead.
I also removed m sehframe field, because I don't
think it is needed. We use single global exception
handler everywhere.
R=golang-dev, r
CC=golang-dev, hectorchu
https://golang.org/cl/4832060
2011-08-10 17:17:28 +10:00
21ac258e07
runtime: openbsd amd64 runtime support
...
Add support for the go runtime on openbsd/amd64. This is based on
the existing freebsd runtime.
Threads are implemented using OpenBSD's rthreads, which are currently
disabled by default, however can be enabled via the kern.rthreads
sysctl.
For now, cgo is disabled.
R=rsc
CC=golang-dev
https://golang.org/cl/4815067
2011-08-08 09:56:38 -04:00
54e9406ffb
runtime: add more specialized type algorithms
...
The change adds specialized type algorithms
for slices and types of size 8/16/32/64/128.
It significantly accelerates chan and map operations
for most builtin types as well as user structs.
benchmark old,ns/op new,ns/op
BenchmarkChanUncontended 226 94
(on Intel Xeon E5620, 2.4GHz, Linux 64 bit)
R=golang-dev, rsc
CC=golang-dev
https://golang.org/cl/4815087
2011-08-08 09:35:32 -04:00
d770aadee5
runtime: faster chan creation on Linux/FreeBSD/Plan9
...
The change removes chan finalizer (Lock destructor)
if it is not required on the platform.
benchmark old ns/op new ns/op delta
BenchmarkChanCreation 1132.00 381.00 -66.34%
BenchmarkChanCreation-2 1215.00 243.00 -80.00%
BenchmarkChanCreation-4 1084.00 186.00 -82.84%
BenchmarkChanCreation-8 1415.00 154.00 -89.12%
BenchmarkChanCreation-16 1386.00 144.00 -89.61%
(on 2 x Intel Xeon E5620, 8 HT cores, 2.4 GHz, Linux)
R=golang-dev, rsc
CC=golang-dev
https://golang.org/cl/4841041
2011-08-04 08:31:03 -04:00
6500065543
runtime: remove unnecessary locking
...
R=rsc, dvyukov
CC=golang-dev
https://golang.org/cl/4819051
2011-08-04 00:22:39 -04:00
a496c9eaa6
runtime: correct Note documentation
...
Reflect the fact that notesleep() can be called
by exactly one thread.
R=golang-dev, rsc
CC=golang-dev
https://golang.org/cl/4816064
2011-08-03 15:51:55 -04:00
9bc58accce
runtime: fix scheduling race
...
Affects programs using cgo or runtime.LockOSThread.
Fixes #2100 .
R=rsc, dvyukov
CC=golang-dev
https://golang.org/cl/4810059
2011-07-29 17:39:02 -04:00
91f0f18100
runtime: fix data race in findfunc()
...
The data race can lead to reads of partially
initialized concurrently mutated symbol data.
The change also adds a simple sanity test
for Caller() and FuncForPC().
R=rsc
CC=golang-dev
https://golang.org/cl/4817058
2011-07-29 13:47:24 -04:00
4e5086b993
runtime: improve Linux mutex
...
The implementation is hybrid active/passive spin/blocking mutex.
The design minimizes amount of context switches and futex calls.
The idea is that all critical sections in runtime are intentially
small, so pure blocking mutex behaves badly causing
a lot of context switches, thread parking/unparking and kernel calls.
Note that some synthetic benchmarks become somewhat slower,
that's due to increased contention on other data structures,
it should not affect programs that do any real work.
On 2 x Intel E5620, 8 HT cores, 2.4GHz
benchmark old ns/op new ns/op delta
BenchmarkSelectContended 521.00 503.00 -3.45%
BenchmarkSelectContended-2 661.00 320.00 -51.59%
BenchmarkSelectContended-4 1139.00 629.00 -44.78%
BenchmarkSelectContended-8 2870.00 878.00 -69.41%
BenchmarkSelectContended-16 5276.00 818.00 -84.50%
BenchmarkChanContended 112.00 103.00 -8.04%
BenchmarkChanContended-2 631.00 174.00 -72.42%
BenchmarkChanContended-4 682.00 272.00 -60.12%
BenchmarkChanContended-8 1601.00 520.00 -67.52%
BenchmarkChanContended-16 3100.00 372.00 -88.00%
BenchmarkChanSync 253.00 239.00 -5.53%
BenchmarkChanSync-2 5030.00 4648.00 -7.59%
BenchmarkChanSync-4 4826.00 4694.00 -2.74%
BenchmarkChanSync-8 4778.00 4713.00 -1.36%
BenchmarkChanSync-16 5289.00 4710.00 -10.95%
BenchmarkChanProdCons0 273.00 254.00 -6.96%
BenchmarkChanProdCons0-2 599.00 400.00 -33.22%
BenchmarkChanProdCons0-4 1168.00 659.00 -43.58%
BenchmarkChanProdCons0-8 2831.00 1057.00 -62.66%
BenchmarkChanProdCons0-16 4197.00 1037.00 -75.29%
BenchmarkChanProdCons10 150.00 140.00 -6.67%
BenchmarkChanProdCons10-2 607.00 268.00 -55.85%
BenchmarkChanProdCons10-4 1137.00 404.00 -64.47%
BenchmarkChanProdCons10-8 2115.00 828.00 -60.85%
BenchmarkChanProdCons10-16 4283.00 855.00 -80.04%
BenchmarkChanProdCons100 117.00 110.00 -5.98%
BenchmarkChanProdCons100-2 558.00 218.00 -60.93%
BenchmarkChanProdCons100-4 722.00 287.00 -60.25%
BenchmarkChanProdCons100-8 1840.00 431.00 -76.58%
BenchmarkChanProdCons100-16 3394.00 448.00 -86.80%
BenchmarkChanProdConsWork0 2014.00 1996.00 -0.89%
BenchmarkChanProdConsWork0-2 1207.00 1127.00 -6.63%
BenchmarkChanProdConsWork0-4 1913.00 611.00 -68.06%
BenchmarkChanProdConsWork0-8 3016.00 949.00 -68.53%
BenchmarkChanProdConsWork0-16 4320.00 1154.00 -73.29%
BenchmarkChanProdConsWork10 1906.00 1897.00 -0.47%
BenchmarkChanProdConsWork10-2 1123.00 1033.00 -8.01%
BenchmarkChanProdConsWork10-4 1076.00 571.00 -46.93%
BenchmarkChanProdConsWork10-8 2748.00 1096.00 -60.12%
BenchmarkChanProdConsWork10-16 4600.00 1105.00 -75.98%
BenchmarkChanProdConsWork100 1884.00 1852.00 -1.70%
BenchmarkChanProdConsWork100-2 1235.00 1146.00 -7.21%
BenchmarkChanProdConsWork100-4 1217.00 619.00 -49.14%
BenchmarkChanProdConsWork100-8 1534.00 509.00 -66.82%
BenchmarkChanProdConsWork100-16 4126.00 918.00 -77.75%
BenchmarkSyscall 34.40 33.30 -3.20%
BenchmarkSyscall-2 160.00 121.00 -24.38%
BenchmarkSyscall-4 131.00 136.00 +3.82%
BenchmarkSyscall-8 139.00 131.00 -5.76%
BenchmarkSyscall-16 161.00 168.00 +4.35%
BenchmarkSyscallWork 950.00 950.00 +0.00%
BenchmarkSyscallWork-2 481.00 480.00 -0.21%
BenchmarkSyscallWork-4 268.00 270.00 +0.75%
BenchmarkSyscallWork-8 156.00 169.00 +8.33%
BenchmarkSyscallWork-16 188.00 184.00 -2.13%
BenchmarkSemaSyntNonblock 36.40 35.60 -2.20%
BenchmarkSemaSyntNonblock-2 81.40 45.10 -44.59%
BenchmarkSemaSyntNonblock-4 126.00 108.00 -14.29%
BenchmarkSemaSyntNonblock-8 112.00 112.00 +0.00%
BenchmarkSemaSyntNonblock-16 110.00 112.00 +1.82%
BenchmarkSemaSyntBlock 35.30 35.30 +0.00%
BenchmarkSemaSyntBlock-2 118.00 124.00 +5.08%
BenchmarkSemaSyntBlock-4 105.00 108.00 +2.86%
BenchmarkSemaSyntBlock-8 101.00 111.00 +9.90%
BenchmarkSemaSyntBlock-16 112.00 118.00 +5.36%
BenchmarkSemaWorkNonblock 810.00 811.00 +0.12%
BenchmarkSemaWorkNonblock-2 476.00 414.00 -13.03%
BenchmarkSemaWorkNonblock-4 238.00 228.00 -4.20%
BenchmarkSemaWorkNonblock-8 140.00 126.00 -10.00%
BenchmarkSemaWorkNonblock-16 117.00 116.00 -0.85%
BenchmarkSemaWorkBlock 810.00 811.00 +0.12%
BenchmarkSemaWorkBlock-2 454.00 466.00 +2.64%
BenchmarkSemaWorkBlock-4 243.00 241.00 -0.82%
BenchmarkSemaWorkBlock-8 145.00 137.00 -5.52%
BenchmarkSemaWorkBlock-16 132.00 123.00 -6.82%
BenchmarkContendedSemaphore 123.00 102.00 -17.07%
BenchmarkContendedSemaphore-2 34.80 34.90 +0.29%
BenchmarkContendedSemaphore-4 34.70 34.80 +0.29%
BenchmarkContendedSemaphore-8 34.70 34.70 +0.00%
BenchmarkContendedSemaphore-16 34.80 34.70 -0.29%
BenchmarkMutex 26.80 26.00 -2.99%
BenchmarkMutex-2 108.00 45.20 -58.15%
BenchmarkMutex-4 103.00 127.00 +23.30%
BenchmarkMutex-8 109.00 147.00 +34.86%
BenchmarkMutex-16 102.00 152.00 +49.02%
BenchmarkMutexSlack 27.00 26.90 -0.37%
BenchmarkMutexSlack-2 149.00 165.00 +10.74%
BenchmarkMutexSlack-4 121.00 209.00 +72.73%
BenchmarkMutexSlack-8 101.00 158.00 +56.44%
BenchmarkMutexSlack-16 97.00 129.00 +32.99%
BenchmarkMutexWork 792.00 794.00 +0.25%
BenchmarkMutexWork-2 407.00 409.00 +0.49%
BenchmarkMutexWork-4 220.00 209.00 -5.00%
BenchmarkMutexWork-8 267.00 160.00 -40.07%
BenchmarkMutexWork-16 315.00 300.00 -4.76%
BenchmarkMutexWorkSlack 792.00 793.00 +0.13%
BenchmarkMutexWorkSlack-2 406.00 404.00 -0.49%
BenchmarkMutexWorkSlack-4 225.00 212.00 -5.78%
BenchmarkMutexWorkSlack-8 268.00 136.00 -49.25%
BenchmarkMutexWorkSlack-16 300.00 300.00 +0.00%
BenchmarkRWMutexWrite100 27.10 27.00 -0.37%
BenchmarkRWMutexWrite100-2 33.10 40.80 +23.26%
BenchmarkRWMutexWrite100-4 113.00 88.10 -22.04%
BenchmarkRWMutexWrite100-8 119.00 95.30 -19.92%
BenchmarkRWMutexWrite100-16 148.00 109.00 -26.35%
BenchmarkRWMutexWrite10 29.60 29.40 -0.68%
BenchmarkRWMutexWrite10-2 111.00 61.40 -44.68%
BenchmarkRWMutexWrite10-4 270.00 208.00 -22.96%
BenchmarkRWMutexWrite10-8 204.00 185.00 -9.31%
BenchmarkRWMutexWrite10-16 261.00 190.00 -27.20%
BenchmarkRWMutexWorkWrite100 1040.00 1036.00 -0.38%
BenchmarkRWMutexWorkWrite100-2 593.00 580.00 -2.19%
BenchmarkRWMutexWorkWrite100-4 470.00 365.00 -22.34%
BenchmarkRWMutexWorkWrite100-8 468.00 289.00 -38.25%
BenchmarkRWMutexWorkWrite100-16 604.00 374.00 -38.08%
BenchmarkRWMutexWorkWrite10 951.00 951.00 +0.00%
BenchmarkRWMutexWorkWrite10-2 1001.00 928.00 -7.29%
BenchmarkRWMutexWorkWrite10-4 1555.00 1006.00 -35.31%
BenchmarkRWMutexWorkWrite10-8 2085.00 1171.00 -43.84%
BenchmarkRWMutexWorkWrite10-16 2082.00 1614.00 -22.48%
R=rsc, iant, msolo, fw, iant
CC=golang-dev
https://golang.org/cl/4711045
2011-07-29 12:44:06 -04:00
bed7e3ed78
gc: fix pprof deadlock
...
Fixes #2051 .
R=golang-dev, dsymonds
CC=golang-dev
https://golang.org/cl/4834041
2011-07-28 21:03:40 -04:00
db9229def8
cgo: add GoBytes, fix gmp example
...
Fixes #1640 .
Fixes #2007 .
R=golang-dev, adg
CC=golang-dev
https://golang.org/cl/4815063
2011-07-28 12:39:50 -04:00
1bd4b6371a
gc: use more Go-like names for methods
...
Fixes #991 .
R=ken2
CC=golang-dev
https://golang.org/cl/4819049
2011-07-27 17:56:13 -04:00
a84abbe508
gc: zero-width struct, zero-length array fixes
...
Fixes #1774 .
Fixes #2095 .
Fixes #2097 .
R=ken2
CC=golang-dev
https://golang.org/cl/4826046
2011-07-27 16:47:45 -04:00
100a034120
runtime: higher goroutine arg limit, clearer error
...
Fixes #591 .
R=ken2
CC=golang-dev
https://golang.org/cl/4803054
2011-07-27 12:41:46 -04:00
12a5774cde
gc, runtime: fix range+panic line number bugs
...
Fixes #1856 .
R=ken2
CC=golang-dev
https://golang.org/cl/4810054
2011-07-26 00:52:46 -04:00
e5437ab065
runtime: fix freebsd build
...
Fixes #2078 .
R=rsc
CC=golang-dev
https://golang.org/cl/4800052
2011-07-26 00:49:32 -04:00
2aa2ceb873
runtime: Plan 9, skip calling runtime·ldt0setup.
...
R=golang-dev
CC=alex.brainman, golang-dev
https://golang.org/cl/4816049
2011-07-25 12:25:41 -04:00
33ff947cac
runtime: fix compilation of send select cases
...
Fixes #2102 .
R=fullung, rsc
CC=golang-dev
https://golang.org/cl/4825043
2011-07-25 12:25:37 -04:00
3a07d516b4
runtime: remove rnd calls that pass a second argument of 1
...
When rnd is called with a second argument of 1, it simply
returns the first argument anyway.
R=golang-dev, r
CC=golang-dev
https://golang.org/cl/4820045
2011-07-24 22:03:17 -07:00
47410a2490
runtime: replace byte-at-a-time zeroing loop with memclr
...
R=golang-dev, r, r, dsymonds, rsc
CC=golang-dev
https://golang.org/cl/4813043
2011-07-23 15:46:58 -04:00
ba134539c5
runtime: faster entersyscall/exitsyscall
...
Replace cas with xadd in scheduler.
Suggested by Dmitriy in last code review.
Verified with Promela model.
When there's actual contention for the atomic word,
this avoids the looping that compare-and-swap requires.
benchmark old ns/op new ns/op delta
runtime_test.BenchmarkSyscall 32 26 -17.08%
runtime_test.BenchmarkSyscall-2 155 59 -61.81%
runtime_test.BenchmarkSyscall-3 112 52 -52.95%
runtime_test.BenchmarkSyscall-4 94 48 -48.57%
runtime_test.BenchmarkSyscallWork 871 872 +0.11%
runtime_test.BenchmarkSyscallWork-2 481 477 -0.83%
runtime_test.BenchmarkSyscallWork-3 338 335 -0.89%
runtime_test.BenchmarkSyscallWork-4 263 256 -2.66%
R=golang-dev, iant
CC=golang-dev
https://golang.org/cl/4800047
2011-07-23 12:22:55 -04:00
226fb099d9
runtime: add UpdateMemStats, use in tests
...
Drops mallocrep1.go back to a reasonable
amount of time. (154 -> 0.8 seconds on my Mac)
Fixes #2085 .
R=golang-dev, dvyukov, r
CC=golang-dev
https://golang.org/cl/4811045
2011-07-22 00:55:01 -04:00
22853098a9
gc: select functions are no longer special
...
R=ken2
CC=golang-dev
https://golang.org/cl/4794049
2011-07-21 14:10:39 -04:00
6b2ec06587
runtime: faster select
...
Make selectsend() accept pointer to the element,
it makes it possible to make Scase fixed-size
and allocate/free Select, all Scase's and all SudoG at once.
As a consequence SudoG freelist die out.
benchmark old,ns/op new,ns/op
BenchmarkSelectUncontended 1080 558
BenchmarkSelectUncontended-2 675 264
BenchmarkSelectUncontended-4 459 205
BenchmarkSelectContended 1086 560
BenchmarkSelectContended-2 1775 1672
BenchmarkSelectContended-4 2668 2149
(on Intel Q6600, 4 cores, 2.4GHz)
benchmark old ns/op new ns/op delta
BenchmarkSelectUncontended 517.00 326.00 -36.94%
BenchmarkSelectUncontended-2 281.00 166.00 -40.93%
BenchmarkSelectUncontended-4 250.00 83.10 -66.76%
BenchmarkSelectUncontended-8 107.00 47.40 -55.70%
BenchmarkSelectUncontended-16 67.80 41.30 -39.09%
BenchmarkSelectContended 513.00 325.00 -36.65%
BenchmarkSelectContended-2 699.00 628.00 -10.16%
BenchmarkSelectContended-4 1085.00 1092.00 +0.65%
BenchmarkSelectContended-8 3253.00 2477.00 -23.85%
BenchmarkSelectContended-16 5313.00 5116.00 -3.71%
(on Intel E5620, 8 HT cores, 2.4 GHz)
R=rsc, ken
CC=golang-dev
https://golang.org/cl/4811041
2011-07-21 13:57:13 -04:00
d6ed1b70ad
runtime: replace centralized ncgocall counter with a distributed one
...
R=golang-dev, rsc
CC=golang-dev
https://golang.org/cl/4809042
2011-07-21 11:29:08 -04:00
102b5b34a7
runtime: apply minor tweaks to channels
...
Remove complicated PRNG algorithm
(argument is limited by uint16 and can't be <= 1).
Do not require chansend/chanrecv selgen to be bumped with CAS.
R=rsc, ken
CC=golang-dev
https://golang.org/cl/4816041
2011-07-20 14:28:55 -04:00
90f3cb13fb
runtime: improve performance of sync channels
...
1. SudoG always contains a pointer to the element
(thus no variable size, and less copying).
2. chansend/chanrecv allocate SudoG on the stack.
3. Copying of elements and gorotuine notifications
are moved out of critical sections.
benchmark old ns/op new ns/op delta
BenchmarkSelectUncontended 515.00 514.00 -0.19%
BenchmarkSelectUncontended-2 291.00 281.00 -3.44%
BenchmarkSelectUncontended-4 213.00 189.00 -11.27%
BenchmarkSelectUncontended-8 78.30 79.00 +0.89%
BenchmarkSelectContended 518.00 514.00 -0.77%
BenchmarkSelectContended-2 655.00 631.00 -3.66%
BenchmarkSelectContended-4 1026.00 1051.00 +2.44%
BenchmarkSelectContended-8 2026.00 2128.00 +5.03%
BenchmarkSelectNonblock 175.00 173.00 -1.14%
BenchmarkSelectNonblock-2 85.10 87.70 +3.06%
BenchmarkSelectNonblock-4 60.10 43.30 -27.95%
BenchmarkSelectNonblock-8 37.60 25.50 -32.18%
BenchmarkChanUncontended 109.00 114.00 +4.59%
BenchmarkChanUncontended-2 54.60 57.20 +4.76%
BenchmarkChanUncontended-4 27.40 28.70 +4.74%
BenchmarkChanUncontended-8 14.60 15.10 +3.42%
BenchmarkChanContended 108.00 114.00 +5.56%
BenchmarkChanContended-2 621.00 617.00 -0.64%
BenchmarkChanContended-4 759.00 677.00 -10.80%
BenchmarkChanContended-8 1635.00 1517.00 -7.22%
BenchmarkChanSync 299.00 256.00 -14.38%
BenchmarkChanSync-2 5055.00 4624.00 -8.53%
BenchmarkChanSync-4 4998.00 4680.00 -6.36%
BenchmarkChanSync-8 5019.00 4760.00 -5.16%
BenchmarkChanProdCons0 316.00 274.00 -13.29%
BenchmarkChanProdCons0-2 1280.00 617.00 -51.80%
BenchmarkChanProdCons0-4 2433.00 1332.00 -45.25%
BenchmarkChanProdCons0-8 3651.00 1934.00 -47.03%
BenchmarkChanProdCons10 153.00 152.00 -0.65%
BenchmarkChanProdCons10-2 626.00 581.00 -7.19%
BenchmarkChanProdCons10-4 1440.00 1323.00 -8.12%
BenchmarkChanProdCons10-8 2036.00 2017.00 -0.93%
R=rsc, ken
CC=golang-dev
https://golang.org/cl/4790042
2011-07-20 11:51:25 -04:00
b546f50716
runtime: make goc2c build on Plan 9
...
pkg/runtime/Makefile:
. Adjusted so "goc2c.c" is built using the Plan 9 libraries.
pkg/runtime/goc2c.c:
. Added/subtracted #include headers to correspond to Plan 9
toolkit.
. Changed fprintf(stderr,...)/exit() combinations to
sysfatal() calls, adjusted the "%u" format to "%ud".
. Added exits(0) at the end of main().
. Made main() a void-returning function and removed the
"return 0" at the end of it.
Tested on UBUNTU and Plan 9 only.
R=r, rsc
CC=golang-dev
https://golang.org/cl/4626093
2011-07-19 11:04:33 -04:00
025abd530e
runtime: faster entersyscall, exitsyscall
...
Uses atomic memory accesses to avoid the need to acquire
and release schedlock on fast paths.
benchmark old ns/op new ns/op delta
runtime_test.BenchmarkSyscall 73 31 -56.63%
runtime_test.BenchmarkSyscall-2 538 74 -86.23%
runtime_test.BenchmarkSyscall-3 508 103 -79.72%
runtime_test.BenchmarkSyscall-4 721 97 -86.52%
runtime_test.BenchmarkSyscallWork 920 873 -5.11%
runtime_test.BenchmarkSyscallWork-2 516 481 -6.78%
runtime_test.BenchmarkSyscallWork-3 550 343 -37.64%
runtime_test.BenchmarkSyscallWork-4 632 263 -58.39%
(Intel Core i7 L640 2.13 GHz-based Lenovo X201s)
Reduced a less artificial server benchmark
from 11.5r 12.0u 8.0s to 8.3r 9.1u 1.0s.
R=dvyukov, r, bradfitz, r, iant, iant
CC=golang-dev
https://golang.org/cl/4723042
2011-07-19 11:01:17 -04:00
9f636598ba
cgo: windows amd64 port
...
R=golang-dev, rsc
CC=golang-dev
https://golang.org/cl/4725041
2011-07-19 10:47:33 -04:00
47e6042f73
runtime: fix select pass 3
...
Fixes #2075
R=rsc, ken, r
CC=golang-dev
https://golang.org/cl/4748045
2011-07-18 16:15:01 -04:00
bd77619142
runtime: track running goroutine count
...
Used to use mcpu+msyscall but that's
problematic for packing into a single
atomic word. The running goroutine count
(where running == Go code or syscall)
can be maintained separately, always
manipulated under lock.
R=golang-dev, bradfitz
CC=golang-dev
https://golang.org/cl/4767041
2011-07-18 15:50:55 -04:00
27753ff108
runtime: add per-M caches for MemStats
...
Avoid touching centralized state during
memory manager operations.
R=mirtchovski
CC=golang-dev, rsc
https://golang.org/cl/4766042
2011-07-18 14:56:22 -04:00
66d5c9b1e9
runtime: add per-M caches for MemStats
...
Avoid touching centralized state during
memory manager opreations.
R=rsc
CC=golang-dev
https://golang.org/cl/4766042
2011-07-18 14:52:57 -04:00
c1f035ba4c
runtime: fix data race in Plan9 sysalloc
...
Add mutex to protect brk limit.
Add mstats.sys update.
R=rsc
CC=golang-dev
https://golang.org/cl/4762045
2011-07-18 10:50:04 -04:00
95323c59ea
runtime: fix panic for make(chan [0]byte).
...
I suspect that this was introduced by
http://code.google.com/p/go/source/detail?r=6e4ee32fffd1
R=r
CC=golang-dev
https://golang.org/cl/4764045
2011-07-18 15:54:11 +10:00
491aa1579d
runtime: native xadd for 386/amd64
...
benchmark old ns/op new ns/op delta
BenchmarkSemaUncontended 37.40 34.10 -8.82%
BenchmarkSemaUncontended-2 18.90 17.70 -6.35%
BenchmarkSemaUncontended-4 11.90 10.90 -8.40%
BenchmarkSemaUncontended-8 6.26 5.19 -17.09%
BenchmarkSemaUncontended-16 4.39 3.91 -10.93%
BenchmarkSemaSyntNonblock 38.00 35.30 -7.11%
BenchmarkSemaSyntNonblock-2 83.00 46.70 -43.73%
BenchmarkSemaSyntNonblock-4 124.00 101.00 -18.55%
BenchmarkSemaSyntNonblock-8 124.00 116.00 -6.45%
BenchmarkSemaSyntNonblock-16 148.00 114.00 -22.97%
(on HP Z600 2 x Xeon E5620, 8 HT cores, 2.40GHz)
R=golang-dev, rsc
CC=golang-dev
https://golang.org/cl/4755041
2011-07-15 11:27:16 -04:00
29125be5c7
runtime: make TestSideEffectOrder work twice
...
R=golang-dev, adg
CC=golang-dev
https://golang.org/cl/4714045
2011-07-14 23:43:03 -04:00
dde435587d
runtime: correct FixedStack value (fixes windows build)
...
Fixes #2068 .
R=rsc
CC=golang-dev
https://golang.org/cl/4705046
2011-07-14 09:13:39 +10:00
a6e60916c1
runtime: stdcall_raw stack 16byte align for Win64
...
R=alex.brainman, rsc
CC=golang-dev
https://golang.org/cl/4681049
2011-07-13 11:44:44 -07:00
86a659cad0
runtime: fix data race during Itab hash update/lookup
...
The data race is on newly published Itab nodes, which are
both unsafely published and unsafely acquired. It can
break on IA-32/Intel64 due to compiler optimizations
(most likely not an issue as of now) and on ARM due to
hardware memory access reorderings.
R=rsc
CC=golang-dev
https://golang.org/cl/4673055
2011-07-13 11:22:41 -07:00
fe9991e8b2
runtime: replace runtime.mcpy with runtime.memmove
...
faster string operations, and more
tested on linux/386
runtime_test.BenchmarkSliceToString 642 532 -17.13%
runtime_test.BenchmarkStringToSlice 636 528 -16.98%
runtime_test.BenchmarkConcatString 1109 897 -19.12%
R=r, iant, rsc
CC=golang-dev
https://golang.org/cl/4674042
2011-07-12 17:30:40 -07:00
86e7323bdf
runtime: eliminate false sharing during stack growth
...
Remove static variable from runtime·oldstack().
Benchmark results on HP Z600 (2 x Xeon E5620, 8 HT cores, 2.40GHz)
are as follows (with CL 4657091 applied):
benchmark old ns/op new ns/op delta
BenchmarkStackGrowth 1183.00 1180.00 -0.25%
BenchmarkStackGrowth-2 1249.00 1211.00 -3.04%
BenchmarkStackGrowth-4 954.00 805.00 -15.62%
BenchmarkStackGrowth-8 701.00 683.00 -2.57%
BenchmarkStackGrowth-16 465.00 415.00 -10.75%
R=rsc
CC=golang-dev
https://golang.org/cl/4693042
2011-07-12 10:56:21 -07:00
88e0c0517a
runtime: fix comment (lost in shuffle)
...
TBR=dvyukov
CC=golang-dev
https://golang.org/cl/4710041
2011-07-12 09:26:05 -07:00
Russ Cox
Dmitriy Vyukov
Gustavo Niemeyer
Alex Brainman
Joel Sing
Hector Chu
Mikio Hara
Yuval Pavel Zholkover
Ian Lance Taylor
Quan Yong Zhai
Lucio De Re
Wei Guangjing
Nigel Tao