2015-02-19 11:38:46 -07:00
|
|
|
// 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.
|
|
|
|
|
|
|
|
// Garbage collector: marking and scanning
|
|
|
|
|
|
|
|
package runtime
|
|
|
|
|
|
|
|
import "unsafe"
|
|
|
|
|
|
|
|
// Scan all of the stacks, greying (or graying if in America) the referents
|
|
|
|
// but not blackening them since the mark write barrier isn't installed.
|
|
|
|
//go:nowritebarrier
|
|
|
|
func gcscan_m() {
|
|
|
|
_g_ := getg()
|
|
|
|
|
|
|
|
// Grab the g that called us and potentially allow rescheduling.
|
|
|
|
// This allows it to be scanned like other goroutines.
|
|
|
|
mastergp := _g_.m.curg
|
|
|
|
casgstatus(mastergp, _Grunning, _Gwaiting)
|
|
|
|
mastergp.waitreason = "garbage collection scan"
|
|
|
|
|
|
|
|
// Span sweeping has been done by finishsweep_m.
|
|
|
|
// Long term we will want to make this goroutine runnable
|
|
|
|
// by placing it onto a scanenqueue state and then calling
|
|
|
|
// runtime·restartg(mastergp) to make it Grunnable.
|
|
|
|
// At the bottom we will want to return this p back to the scheduler.
|
|
|
|
|
|
|
|
// Prepare flag indicating that the scan has not been completed.
|
2015-02-24 20:20:38 -07:00
|
|
|
local_allglen := gcResetGState()
|
2015-02-19 11:38:46 -07:00
|
|
|
|
|
|
|
work.nwait = 0
|
|
|
|
work.ndone = 0
|
|
|
|
work.nproc = 1 // For now do not do this in parallel.
|
|
|
|
// ackgcphase is not needed since we are not scanning running goroutines.
|
|
|
|
parforsetup(work.markfor, work.nproc, uint32(_RootCount+local_allglen), false, markroot)
|
|
|
|
parfordo(work.markfor)
|
|
|
|
|
|
|
|
lock(&allglock)
|
|
|
|
// Check that gc work is done.
|
2015-02-24 20:20:38 -07:00
|
|
|
for i := 0; i < local_allglen; i++ {
|
2015-02-19 11:38:46 -07:00
|
|
|
gp := allgs[i]
|
|
|
|
if !gp.gcworkdone {
|
|
|
|
throw("scan missed a g")
|
|
|
|
}
|
|
|
|
}
|
|
|
|
unlock(&allglock)
|
|
|
|
|
|
|
|
casgstatus(mastergp, _Gwaiting, _Grunning)
|
|
|
|
// Let the g that called us continue to run.
|
|
|
|
}
|
|
|
|
|
|
|
|
// ptrmask for an allocation containing a single pointer.
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
var oneptrmask = [...]uint8{1}
|
2015-02-19 11:38:46 -07:00
|
|
|
|
|
|
|
//go:nowritebarrier
|
|
|
|
func markroot(desc *parfor, i uint32) {
|
runtime: replace per-M workbuf cache with per-P gcWork cache
Currently, each M has a cache of the most recently used *workbuf. This
is used primarily by the write barrier so it doesn't have to access
the global workbuf lists on every write barrier. It's also used by
stack scanning because it's convenient.
This cache is important for write barrier performance, but this
particular approach has several downsides. It's faster than no cache,
but far from optimal (as the benchmarks below show). It's complex:
access to the cache is sprinkled through most of the workbuf list
operations and it requires special care to transform into and back out
of the gcWork cache that's actually used for scanning and marking. It
requires atomic exchanges to take ownership of the cached workbuf and
to return it to the M's cache even though it's almost always used by
only the current M. Since it's per-M, flushing these caches is O(# of
Ms), which may be high. And it has some significant subtleties: for
example, in general the cache shouldn't be used after the
harvestwbufs() in mark termination because it could hide work from
mark termination, but stack scanning can happen after this and *will*
use the cache (but it turns out this is okay because it will always be
followed by a getfull(), which drains the cache).
This change replaces this cache with a per-P gcWork object. This
gcWork cache can be used directly by scanning and marking (as long as
preemption is disabled, which is a general requirement of gcWork).
Since it's per-P, it doesn't require synchronization, which simplifies
things and means the only atomic operations in the write barrier are
occasionally fetching new work buffers and setting a mark bit if the
object isn't already marked. This cache can be flushed in O(# of Ps),
which is generally small. It follows a simple flushing rule: the cache
can be used during any phase, but during mark termination it must be
flushed before allowing preemption. This also makes the dispose during
mutator assist no longer necessary, which eliminates the vast majority
of gcWork dispose calls and reduces contention on the global workbuf
lists. And it's a lot faster on some benchmarks:
benchmark old ns/op new ns/op delta
BenchmarkBinaryTree17 11963668673 11206112763 -6.33%
BenchmarkFannkuch11 2643217136 2649182499 +0.23%
BenchmarkFmtFprintfEmpty 70.4 70.2 -0.28%
BenchmarkFmtFprintfString 364 307 -15.66%
BenchmarkFmtFprintfInt 317 282 -11.04%
BenchmarkFmtFprintfIntInt 512 483 -5.66%
BenchmarkFmtFprintfPrefixedInt 404 380 -5.94%
BenchmarkFmtFprintfFloat 521 479 -8.06%
BenchmarkFmtManyArgs 2164 1894 -12.48%
BenchmarkGobDecode 30366146 22429593 -26.14%
BenchmarkGobEncode 29867472 26663152 -10.73%
BenchmarkGzip 391236616 396779490 +1.42%
BenchmarkGunzip 96639491 96297024 -0.35%
BenchmarkHTTPClientServer 100110 70763 -29.31%
BenchmarkJSONEncode 51866051 52511382 +1.24%
BenchmarkJSONDecode 103813138 86094963 -17.07%
BenchmarkMandelbrot200 4121834 4120886 -0.02%
BenchmarkGoParse 16472789 5879949 -64.31%
BenchmarkRegexpMatchEasy0_32 140 140 +0.00%
BenchmarkRegexpMatchEasy0_1K 394 394 +0.00%
BenchmarkRegexpMatchEasy1_32 120 120 +0.00%
BenchmarkRegexpMatchEasy1_1K 621 614 -1.13%
BenchmarkRegexpMatchMedium_32 209 202 -3.35%
BenchmarkRegexpMatchMedium_1K 54889 55175 +0.52%
BenchmarkRegexpMatchHard_32 2682 2675 -0.26%
BenchmarkRegexpMatchHard_1K 79383 79524 +0.18%
BenchmarkRevcomp 584116718 584595320 +0.08%
BenchmarkTemplate 125400565 109620196 -12.58%
BenchmarkTimeParse 386 387 +0.26%
BenchmarkTimeFormat 580 447 -22.93%
(Best out of 10 runs. The delta of averages is similar.)
This also puts us in a good position to flush these caches when
nearing the end of concurrent marking, which will let us increase the
size of the work buffers while still controlling mark termination
pause time.
Change-Id: I2dd94c8517a19297a98ec280203cccaa58792522
Reviewed-on: https://go-review.googlesource.com/9178
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
2015-04-19 13:22:20 -06:00
|
|
|
// TODO: Consider using getg().m.p.ptr().gcw.
|
2015-03-12 11:09:30 -06:00
|
|
|
var gcw gcWork
|
2015-02-19 11:38:46 -07:00
|
|
|
|
2015-03-11 13:58:47 -06:00
|
|
|
// Note: if you add a case here, please also update heapdump.go:dumproots.
|
2015-02-19 11:38:46 -07:00
|
|
|
switch i {
|
|
|
|
case _RootData:
|
2015-04-06 18:55:02 -06:00
|
|
|
for datap := &firstmoduledata; datap != nil; datap = datap.next {
|
2015-03-29 15:59:00 -06:00
|
|
|
scanblock(datap.data, datap.edata-datap.data, datap.gcdatamask.bytedata, &gcw)
|
|
|
|
}
|
2015-02-19 11:38:46 -07:00
|
|
|
|
|
|
|
case _RootBss:
|
2015-04-06 18:55:02 -06:00
|
|
|
for datap := &firstmoduledata; datap != nil; datap = datap.next {
|
2015-03-29 15:59:00 -06:00
|
|
|
scanblock(datap.bss, datap.ebss-datap.bss, datap.gcbssmask.bytedata, &gcw)
|
|
|
|
}
|
2015-02-19 11:38:46 -07:00
|
|
|
|
|
|
|
case _RootFinalizers:
|
|
|
|
for fb := allfin; fb != nil; fb = fb.alllink {
|
|
|
|
scanblock(uintptr(unsafe.Pointer(&fb.fin[0])), uintptr(fb.cnt)*unsafe.Sizeof(fb.fin[0]), &finptrmask[0], &gcw)
|
|
|
|
}
|
|
|
|
|
|
|
|
case _RootSpans:
|
|
|
|
// mark MSpan.specials
|
|
|
|
sg := mheap_.sweepgen
|
|
|
|
for spanidx := uint32(0); spanidx < uint32(len(work.spans)); spanidx++ {
|
|
|
|
s := work.spans[spanidx]
|
|
|
|
if s.state != mSpanInUse {
|
|
|
|
continue
|
|
|
|
}
|
2015-02-19 14:43:27 -07:00
|
|
|
if !useCheckmark && s.sweepgen != sg {
|
2015-02-19 11:38:46 -07:00
|
|
|
// sweepgen was updated (+2) during non-checkmark GC pass
|
|
|
|
print("sweep ", s.sweepgen, " ", sg, "\n")
|
|
|
|
throw("gc: unswept span")
|
|
|
|
}
|
|
|
|
for sp := s.specials; sp != nil; sp = sp.next {
|
|
|
|
if sp.kind != _KindSpecialFinalizer {
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
// don't mark finalized object, but scan it so we
|
|
|
|
// retain everything it points to.
|
|
|
|
spf := (*specialfinalizer)(unsafe.Pointer(sp))
|
|
|
|
// A finalizer can be set for an inner byte of an object, find object beginning.
|
|
|
|
p := uintptr(s.start<<_PageShift) + uintptr(spf.special.offset)/s.elemsize*s.elemsize
|
|
|
|
if gcphase != _GCscan {
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
scanobject(p, &gcw) // scanned during mark termination
|
2015-02-19 11:38:46 -07:00
|
|
|
}
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
scanblock(uintptr(unsafe.Pointer(&spf.fn)), ptrSize, &oneptrmask[0], &gcw)
|
2015-02-19 11:38:46 -07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
case _RootFlushCaches:
|
|
|
|
if gcphase != _GCscan { // Do not flush mcaches during GCscan phase.
|
|
|
|
flushallmcaches()
|
|
|
|
}
|
|
|
|
|
|
|
|
default:
|
|
|
|
// the rest is scanning goroutine stacks
|
|
|
|
if uintptr(i-_RootCount) >= allglen {
|
|
|
|
throw("markroot: bad index")
|
|
|
|
}
|
|
|
|
gp := allgs[i-_RootCount]
|
|
|
|
|
|
|
|
// remember when we've first observed the G blocked
|
|
|
|
// needed only to output in traceback
|
|
|
|
status := readgstatus(gp) // We are not in a scan state
|
|
|
|
if (status == _Gwaiting || status == _Gsyscall) && gp.waitsince == 0 {
|
|
|
|
gp.waitsince = work.tstart
|
|
|
|
}
|
|
|
|
|
|
|
|
// Shrink a stack if not much of it is being used but not in the scan phase.
|
|
|
|
if gcphase == _GCmarktermination {
|
|
|
|
// Shrink during STW GCmarktermination phase thus avoiding
|
|
|
|
// complications introduced by shrinking during
|
|
|
|
// non-STW phases.
|
|
|
|
shrinkstack(gp)
|
|
|
|
}
|
|
|
|
if readgstatus(gp) == _Gdead {
|
|
|
|
gp.gcworkdone = true
|
|
|
|
} else {
|
|
|
|
gp.gcworkdone = false
|
|
|
|
}
|
|
|
|
restart := stopg(gp)
|
|
|
|
|
|
|
|
// goroutine will scan its own stack when it stops running.
|
|
|
|
// Wait until it has.
|
|
|
|
for readgstatus(gp) == _Grunning && !gp.gcworkdone {
|
|
|
|
}
|
|
|
|
|
|
|
|
// scanstack(gp) is done as part of gcphasework
|
|
|
|
// But to make sure we finished we need to make sure that
|
|
|
|
// the stack traps have all responded so drop into
|
|
|
|
// this while loop until they respond.
|
|
|
|
for !gp.gcworkdone {
|
|
|
|
status = readgstatus(gp)
|
|
|
|
if status == _Gdead {
|
|
|
|
gp.gcworkdone = true // scan is a noop
|
|
|
|
break
|
|
|
|
}
|
|
|
|
if status == _Gwaiting || status == _Grunnable {
|
|
|
|
restart = stopg(gp)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if restart {
|
|
|
|
restartg(gp)
|
|
|
|
}
|
|
|
|
}
|
2015-03-12 14:53:57 -06:00
|
|
|
|
2015-02-19 11:38:46 -07:00
|
|
|
gcw.dispose()
|
|
|
|
}
|
|
|
|
|
2015-03-16 12:22:00 -06:00
|
|
|
// gcAssistAlloc records and allocation of size bytes and, if
|
|
|
|
// allowAssist is true, may assist GC scanning in proportion to the
|
|
|
|
// allocations performed by this mutator since the last assist.
|
|
|
|
//
|
2015-03-27 15:01:53 -06:00
|
|
|
// It should only be called if gcAssistAlloc != 0.
|
runtime: replace per-M workbuf cache with per-P gcWork cache
Currently, each M has a cache of the most recently used *workbuf. This
is used primarily by the write barrier so it doesn't have to access
the global workbuf lists on every write barrier. It's also used by
stack scanning because it's convenient.
This cache is important for write barrier performance, but this
particular approach has several downsides. It's faster than no cache,
but far from optimal (as the benchmarks below show). It's complex:
access to the cache is sprinkled through most of the workbuf list
operations and it requires special care to transform into and back out
of the gcWork cache that's actually used for scanning and marking. It
requires atomic exchanges to take ownership of the cached workbuf and
to return it to the M's cache even though it's almost always used by
only the current M. Since it's per-M, flushing these caches is O(# of
Ms), which may be high. And it has some significant subtleties: for
example, in general the cache shouldn't be used after the
harvestwbufs() in mark termination because it could hide work from
mark termination, but stack scanning can happen after this and *will*
use the cache (but it turns out this is okay because it will always be
followed by a getfull(), which drains the cache).
This change replaces this cache with a per-P gcWork object. This
gcWork cache can be used directly by scanning and marking (as long as
preemption is disabled, which is a general requirement of gcWork).
Since it's per-P, it doesn't require synchronization, which simplifies
things and means the only atomic operations in the write barrier are
occasionally fetching new work buffers and setting a mark bit if the
object isn't already marked. This cache can be flushed in O(# of Ps),
which is generally small. It follows a simple flushing rule: the cache
can be used during any phase, but during mark termination it must be
flushed before allowing preemption. This also makes the dispose during
mutator assist no longer necessary, which eliminates the vast majority
of gcWork dispose calls and reduces contention on the global workbuf
lists. And it's a lot faster on some benchmarks:
benchmark old ns/op new ns/op delta
BenchmarkBinaryTree17 11963668673 11206112763 -6.33%
BenchmarkFannkuch11 2643217136 2649182499 +0.23%
BenchmarkFmtFprintfEmpty 70.4 70.2 -0.28%
BenchmarkFmtFprintfString 364 307 -15.66%
BenchmarkFmtFprintfInt 317 282 -11.04%
BenchmarkFmtFprintfIntInt 512 483 -5.66%
BenchmarkFmtFprintfPrefixedInt 404 380 -5.94%
BenchmarkFmtFprintfFloat 521 479 -8.06%
BenchmarkFmtManyArgs 2164 1894 -12.48%
BenchmarkGobDecode 30366146 22429593 -26.14%
BenchmarkGobEncode 29867472 26663152 -10.73%
BenchmarkGzip 391236616 396779490 +1.42%
BenchmarkGunzip 96639491 96297024 -0.35%
BenchmarkHTTPClientServer 100110 70763 -29.31%
BenchmarkJSONEncode 51866051 52511382 +1.24%
BenchmarkJSONDecode 103813138 86094963 -17.07%
BenchmarkMandelbrot200 4121834 4120886 -0.02%
BenchmarkGoParse 16472789 5879949 -64.31%
BenchmarkRegexpMatchEasy0_32 140 140 +0.00%
BenchmarkRegexpMatchEasy0_1K 394 394 +0.00%
BenchmarkRegexpMatchEasy1_32 120 120 +0.00%
BenchmarkRegexpMatchEasy1_1K 621 614 -1.13%
BenchmarkRegexpMatchMedium_32 209 202 -3.35%
BenchmarkRegexpMatchMedium_1K 54889 55175 +0.52%
BenchmarkRegexpMatchHard_32 2682 2675 -0.26%
BenchmarkRegexpMatchHard_1K 79383 79524 +0.18%
BenchmarkRevcomp 584116718 584595320 +0.08%
BenchmarkTemplate 125400565 109620196 -12.58%
BenchmarkTimeParse 386 387 +0.26%
BenchmarkTimeFormat 580 447 -22.93%
(Best out of 10 runs. The delta of averages is similar.)
This also puts us in a good position to flush these caches when
nearing the end of concurrent marking, which will let us increase the
size of the work buffers while still controlling mark termination
pause time.
Change-Id: I2dd94c8517a19297a98ec280203cccaa58792522
Reviewed-on: https://go-review.googlesource.com/9178
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
2015-04-19 13:22:20 -06:00
|
|
|
//
|
|
|
|
// This must be called with preemption disabled.
|
2015-02-19 11:38:46 -07:00
|
|
|
//go:nowritebarrier
|
2015-03-16 12:22:00 -06:00
|
|
|
func gcAssistAlloc(size uintptr, allowAssist bool) {
|
|
|
|
// Find the G responsible for this assist.
|
|
|
|
gp := getg()
|
|
|
|
if gp.m.curg != nil {
|
|
|
|
gp = gp.m.curg
|
|
|
|
}
|
|
|
|
|
|
|
|
// Record allocation.
|
|
|
|
gp.gcalloc += size
|
|
|
|
|
|
|
|
if !allowAssist {
|
|
|
|
return
|
|
|
|
}
|
|
|
|
|
|
|
|
// Compute the amount of assist scan work we need to do.
|
|
|
|
scanWork := int64(gcController.assistRatio*float64(gp.gcalloc)) - gp.gcscanwork
|
|
|
|
// scanWork can be negative if the last assist scanned a large
|
|
|
|
// object and we're still ahead of our assist goal.
|
|
|
|
if scanWork <= 0 {
|
|
|
|
return
|
|
|
|
}
|
|
|
|
|
|
|
|
// Steal as much credit as we can from the background GC's
|
|
|
|
// scan credit. This is racy and may drop the background
|
|
|
|
// credit below 0 if two mutators steal at the same time. This
|
|
|
|
// will just cause steals to fail until credit is accumulated
|
|
|
|
// again, so in the long run it doesn't really matter, but we
|
|
|
|
// do have to handle the negative credit case.
|
|
|
|
bgScanCredit := atomicloadint64(&gcController.bgScanCredit)
|
|
|
|
stolen := int64(0)
|
|
|
|
if bgScanCredit > 0 {
|
|
|
|
if bgScanCredit < scanWork {
|
|
|
|
stolen = bgScanCredit
|
|
|
|
} else {
|
|
|
|
stolen = scanWork
|
|
|
|
}
|
|
|
|
xaddint64(&gcController.bgScanCredit, -scanWork)
|
|
|
|
|
|
|
|
scanWork -= stolen
|
|
|
|
gp.gcscanwork += stolen
|
|
|
|
|
|
|
|
if scanWork == 0 {
|
|
|
|
return
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// Perform assist work
|
|
|
|
systemstack(func() {
|
2015-03-17 10:17:47 -06:00
|
|
|
// Track time spent in this assist. Since we're on the
|
|
|
|
// system stack, this is non-preemptible, so we can
|
|
|
|
// just measure start and end time.
|
|
|
|
startTime := nanotime()
|
|
|
|
|
runtime: multi-threaded, utilization-scheduled background mark
Currently, the concurrent mark phase is performed by the main GC
goroutine. Prior to the previous commit enabling preemption, this
caused marking to always consume 1/GOMAXPROCS of the available CPU
time. If GOMAXPROCS=1, this meant background GC would consume 100% of
the CPU (effectively a STW). If GOMAXPROCS>4, background GC would use
less than the goal of 25%. If GOMAXPROCS=4, background GC would use
the goal 25%, but if the mutator wasn't using the remaining 75%,
background marking wouldn't take advantage of the idle time. Enabling
preemption in the previous commit made GC miss CPU targets in
completely different ways, but set us up to bring everything back in
line.
This change replaces the fixed GC goroutine with per-P background mark
goroutines. Once started, these goroutines don't go in the standard
run queues; instead, they are scheduled specially such that the time
spent in mutator assists and the background mark goroutines totals 25%
of the CPU time available to the program. Furthermore, this lets
background marking take advantage of idle Ps, which significantly
boosts GC performance for applications that under-utilize the CPU.
This requires also changing how time is reported for gctrace, so this
change splits the concurrent mark CPU time into assist/background/idle
scanning.
This also requires increasing the size of the StackRecord slice used
in a GoroutineProfile test.
Change-Id: I0936ff907d2cee6cb687a208f2df47e8988e3157
Reviewed-on: https://go-review.googlesource.com/8850
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-03-23 19:07:33 -06:00
|
|
|
xadd(&work.nwait, -1)
|
|
|
|
|
runtime: replace per-M workbuf cache with per-P gcWork cache
Currently, each M has a cache of the most recently used *workbuf. This
is used primarily by the write barrier so it doesn't have to access
the global workbuf lists on every write barrier. It's also used by
stack scanning because it's convenient.
This cache is important for write barrier performance, but this
particular approach has several downsides. It's faster than no cache,
but far from optimal (as the benchmarks below show). It's complex:
access to the cache is sprinkled through most of the workbuf list
operations and it requires special care to transform into and back out
of the gcWork cache that's actually used for scanning and marking. It
requires atomic exchanges to take ownership of the cached workbuf and
to return it to the M's cache even though it's almost always used by
only the current M. Since it's per-M, flushing these caches is O(# of
Ms), which may be high. And it has some significant subtleties: for
example, in general the cache shouldn't be used after the
harvestwbufs() in mark termination because it could hide work from
mark termination, but stack scanning can happen after this and *will*
use the cache (but it turns out this is okay because it will always be
followed by a getfull(), which drains the cache).
This change replaces this cache with a per-P gcWork object. This
gcWork cache can be used directly by scanning and marking (as long as
preemption is disabled, which is a general requirement of gcWork).
Since it's per-P, it doesn't require synchronization, which simplifies
things and means the only atomic operations in the write barrier are
occasionally fetching new work buffers and setting a mark bit if the
object isn't already marked. This cache can be flushed in O(# of Ps),
which is generally small. It follows a simple flushing rule: the cache
can be used during any phase, but during mark termination it must be
flushed before allowing preemption. This also makes the dispose during
mutator assist no longer necessary, which eliminates the vast majority
of gcWork dispose calls and reduces contention on the global workbuf
lists. And it's a lot faster on some benchmarks:
benchmark old ns/op new ns/op delta
BenchmarkBinaryTree17 11963668673 11206112763 -6.33%
BenchmarkFannkuch11 2643217136 2649182499 +0.23%
BenchmarkFmtFprintfEmpty 70.4 70.2 -0.28%
BenchmarkFmtFprintfString 364 307 -15.66%
BenchmarkFmtFprintfInt 317 282 -11.04%
BenchmarkFmtFprintfIntInt 512 483 -5.66%
BenchmarkFmtFprintfPrefixedInt 404 380 -5.94%
BenchmarkFmtFprintfFloat 521 479 -8.06%
BenchmarkFmtManyArgs 2164 1894 -12.48%
BenchmarkGobDecode 30366146 22429593 -26.14%
BenchmarkGobEncode 29867472 26663152 -10.73%
BenchmarkGzip 391236616 396779490 +1.42%
BenchmarkGunzip 96639491 96297024 -0.35%
BenchmarkHTTPClientServer 100110 70763 -29.31%
BenchmarkJSONEncode 51866051 52511382 +1.24%
BenchmarkJSONDecode 103813138 86094963 -17.07%
BenchmarkMandelbrot200 4121834 4120886 -0.02%
BenchmarkGoParse 16472789 5879949 -64.31%
BenchmarkRegexpMatchEasy0_32 140 140 +0.00%
BenchmarkRegexpMatchEasy0_1K 394 394 +0.00%
BenchmarkRegexpMatchEasy1_32 120 120 +0.00%
BenchmarkRegexpMatchEasy1_1K 621 614 -1.13%
BenchmarkRegexpMatchMedium_32 209 202 -3.35%
BenchmarkRegexpMatchMedium_1K 54889 55175 +0.52%
BenchmarkRegexpMatchHard_32 2682 2675 -0.26%
BenchmarkRegexpMatchHard_1K 79383 79524 +0.18%
BenchmarkRevcomp 584116718 584595320 +0.08%
BenchmarkTemplate 125400565 109620196 -12.58%
BenchmarkTimeParse 386 387 +0.26%
BenchmarkTimeFormat 580 447 -22.93%
(Best out of 10 runs. The delta of averages is similar.)
This also puts us in a good position to flush these caches when
nearing the end of concurrent marking, which will let us increase the
size of the work buffers while still controlling mark termination
pause time.
Change-Id: I2dd94c8517a19297a98ec280203cccaa58792522
Reviewed-on: https://go-review.googlesource.com/9178
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
2015-04-19 13:22:20 -06:00
|
|
|
// drain own cached work first in the hopes that it
|
2015-03-16 12:22:00 -06:00
|
|
|
// will be more cache friendly.
|
runtime: replace per-M workbuf cache with per-P gcWork cache
Currently, each M has a cache of the most recently used *workbuf. This
is used primarily by the write barrier so it doesn't have to access
the global workbuf lists on every write barrier. It's also used by
stack scanning because it's convenient.
This cache is important for write barrier performance, but this
particular approach has several downsides. It's faster than no cache,
but far from optimal (as the benchmarks below show). It's complex:
access to the cache is sprinkled through most of the workbuf list
operations and it requires special care to transform into and back out
of the gcWork cache that's actually used for scanning and marking. It
requires atomic exchanges to take ownership of the cached workbuf and
to return it to the M's cache even though it's almost always used by
only the current M. Since it's per-M, flushing these caches is O(# of
Ms), which may be high. And it has some significant subtleties: for
example, in general the cache shouldn't be used after the
harvestwbufs() in mark termination because it could hide work from
mark termination, but stack scanning can happen after this and *will*
use the cache (but it turns out this is okay because it will always be
followed by a getfull(), which drains the cache).
This change replaces this cache with a per-P gcWork object. This
gcWork cache can be used directly by scanning and marking (as long as
preemption is disabled, which is a general requirement of gcWork).
Since it's per-P, it doesn't require synchronization, which simplifies
things and means the only atomic operations in the write barrier are
occasionally fetching new work buffers and setting a mark bit if the
object isn't already marked. This cache can be flushed in O(# of Ps),
which is generally small. It follows a simple flushing rule: the cache
can be used during any phase, but during mark termination it must be
flushed before allowing preemption. This also makes the dispose during
mutator assist no longer necessary, which eliminates the vast majority
of gcWork dispose calls and reduces contention on the global workbuf
lists. And it's a lot faster on some benchmarks:
benchmark old ns/op new ns/op delta
BenchmarkBinaryTree17 11963668673 11206112763 -6.33%
BenchmarkFannkuch11 2643217136 2649182499 +0.23%
BenchmarkFmtFprintfEmpty 70.4 70.2 -0.28%
BenchmarkFmtFprintfString 364 307 -15.66%
BenchmarkFmtFprintfInt 317 282 -11.04%
BenchmarkFmtFprintfIntInt 512 483 -5.66%
BenchmarkFmtFprintfPrefixedInt 404 380 -5.94%
BenchmarkFmtFprintfFloat 521 479 -8.06%
BenchmarkFmtManyArgs 2164 1894 -12.48%
BenchmarkGobDecode 30366146 22429593 -26.14%
BenchmarkGobEncode 29867472 26663152 -10.73%
BenchmarkGzip 391236616 396779490 +1.42%
BenchmarkGunzip 96639491 96297024 -0.35%
BenchmarkHTTPClientServer 100110 70763 -29.31%
BenchmarkJSONEncode 51866051 52511382 +1.24%
BenchmarkJSONDecode 103813138 86094963 -17.07%
BenchmarkMandelbrot200 4121834 4120886 -0.02%
BenchmarkGoParse 16472789 5879949 -64.31%
BenchmarkRegexpMatchEasy0_32 140 140 +0.00%
BenchmarkRegexpMatchEasy0_1K 394 394 +0.00%
BenchmarkRegexpMatchEasy1_32 120 120 +0.00%
BenchmarkRegexpMatchEasy1_1K 621 614 -1.13%
BenchmarkRegexpMatchMedium_32 209 202 -3.35%
BenchmarkRegexpMatchMedium_1K 54889 55175 +0.52%
BenchmarkRegexpMatchHard_32 2682 2675 -0.26%
BenchmarkRegexpMatchHard_1K 79383 79524 +0.18%
BenchmarkRevcomp 584116718 584595320 +0.08%
BenchmarkTemplate 125400565 109620196 -12.58%
BenchmarkTimeParse 386 387 +0.26%
BenchmarkTimeFormat 580 447 -22.93%
(Best out of 10 runs. The delta of averages is similar.)
This also puts us in a good position to flush these caches when
nearing the end of concurrent marking, which will let us increase the
size of the work buffers while still controlling mark termination
pause time.
Change-Id: I2dd94c8517a19297a98ec280203cccaa58792522
Reviewed-on: https://go-review.googlesource.com/9178
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
2015-04-19 13:22:20 -06:00
|
|
|
gcw := &getg().m.p.ptr().gcw
|
2015-03-16 12:22:00 -06:00
|
|
|
startScanWork := gcw.scanWork
|
runtime: replace per-M workbuf cache with per-P gcWork cache
Currently, each M has a cache of the most recently used *workbuf. This
is used primarily by the write barrier so it doesn't have to access
the global workbuf lists on every write barrier. It's also used by
stack scanning because it's convenient.
This cache is important for write barrier performance, but this
particular approach has several downsides. It's faster than no cache,
but far from optimal (as the benchmarks below show). It's complex:
access to the cache is sprinkled through most of the workbuf list
operations and it requires special care to transform into and back out
of the gcWork cache that's actually used for scanning and marking. It
requires atomic exchanges to take ownership of the cached workbuf and
to return it to the M's cache even though it's almost always used by
only the current M. Since it's per-M, flushing these caches is O(# of
Ms), which may be high. And it has some significant subtleties: for
example, in general the cache shouldn't be used after the
harvestwbufs() in mark termination because it could hide work from
mark termination, but stack scanning can happen after this and *will*
use the cache (but it turns out this is okay because it will always be
followed by a getfull(), which drains the cache).
This change replaces this cache with a per-P gcWork object. This
gcWork cache can be used directly by scanning and marking (as long as
preemption is disabled, which is a general requirement of gcWork).
Since it's per-P, it doesn't require synchronization, which simplifies
things and means the only atomic operations in the write barrier are
occasionally fetching new work buffers and setting a mark bit if the
object isn't already marked. This cache can be flushed in O(# of Ps),
which is generally small. It follows a simple flushing rule: the cache
can be used during any phase, but during mark termination it must be
flushed before allowing preemption. This also makes the dispose during
mutator assist no longer necessary, which eliminates the vast majority
of gcWork dispose calls and reduces contention on the global workbuf
lists. And it's a lot faster on some benchmarks:
benchmark old ns/op new ns/op delta
BenchmarkBinaryTree17 11963668673 11206112763 -6.33%
BenchmarkFannkuch11 2643217136 2649182499 +0.23%
BenchmarkFmtFprintfEmpty 70.4 70.2 -0.28%
BenchmarkFmtFprintfString 364 307 -15.66%
BenchmarkFmtFprintfInt 317 282 -11.04%
BenchmarkFmtFprintfIntInt 512 483 -5.66%
BenchmarkFmtFprintfPrefixedInt 404 380 -5.94%
BenchmarkFmtFprintfFloat 521 479 -8.06%
BenchmarkFmtManyArgs 2164 1894 -12.48%
BenchmarkGobDecode 30366146 22429593 -26.14%
BenchmarkGobEncode 29867472 26663152 -10.73%
BenchmarkGzip 391236616 396779490 +1.42%
BenchmarkGunzip 96639491 96297024 -0.35%
BenchmarkHTTPClientServer 100110 70763 -29.31%
BenchmarkJSONEncode 51866051 52511382 +1.24%
BenchmarkJSONDecode 103813138 86094963 -17.07%
BenchmarkMandelbrot200 4121834 4120886 -0.02%
BenchmarkGoParse 16472789 5879949 -64.31%
BenchmarkRegexpMatchEasy0_32 140 140 +0.00%
BenchmarkRegexpMatchEasy0_1K 394 394 +0.00%
BenchmarkRegexpMatchEasy1_32 120 120 +0.00%
BenchmarkRegexpMatchEasy1_1K 621 614 -1.13%
BenchmarkRegexpMatchMedium_32 209 202 -3.35%
BenchmarkRegexpMatchMedium_1K 54889 55175 +0.52%
BenchmarkRegexpMatchHard_32 2682 2675 -0.26%
BenchmarkRegexpMatchHard_1K 79383 79524 +0.18%
BenchmarkRevcomp 584116718 584595320 +0.08%
BenchmarkTemplate 125400565 109620196 -12.58%
BenchmarkTimeParse 386 387 +0.26%
BenchmarkTimeFormat 580 447 -22.93%
(Best out of 10 runs. The delta of averages is similar.)
This also puts us in a good position to flush these caches when
nearing the end of concurrent marking, which will let us increase the
size of the work buffers while still controlling mark termination
pause time.
Change-Id: I2dd94c8517a19297a98ec280203cccaa58792522
Reviewed-on: https://go-review.googlesource.com/9178
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
2015-04-19 13:22:20 -06:00
|
|
|
gcDrainN(gcw, scanWork)
|
2015-03-16 12:22:00 -06:00
|
|
|
// Record that we did this much scan work.
|
|
|
|
gp.gcscanwork += gcw.scanWork - startScanWork
|
runtime: replace per-M workbuf cache with per-P gcWork cache
Currently, each M has a cache of the most recently used *workbuf. This
is used primarily by the write barrier so it doesn't have to access
the global workbuf lists on every write barrier. It's also used by
stack scanning because it's convenient.
This cache is important for write barrier performance, but this
particular approach has several downsides. It's faster than no cache,
but far from optimal (as the benchmarks below show). It's complex:
access to the cache is sprinkled through most of the workbuf list
operations and it requires special care to transform into and back out
of the gcWork cache that's actually used for scanning and marking. It
requires atomic exchanges to take ownership of the cached workbuf and
to return it to the M's cache even though it's almost always used by
only the current M. Since it's per-M, flushing these caches is O(# of
Ms), which may be high. And it has some significant subtleties: for
example, in general the cache shouldn't be used after the
harvestwbufs() in mark termination because it could hide work from
mark termination, but stack scanning can happen after this and *will*
use the cache (but it turns out this is okay because it will always be
followed by a getfull(), which drains the cache).
This change replaces this cache with a per-P gcWork object. This
gcWork cache can be used directly by scanning and marking (as long as
preemption is disabled, which is a general requirement of gcWork).
Since it's per-P, it doesn't require synchronization, which simplifies
things and means the only atomic operations in the write barrier are
occasionally fetching new work buffers and setting a mark bit if the
object isn't already marked. This cache can be flushed in O(# of Ps),
which is generally small. It follows a simple flushing rule: the cache
can be used during any phase, but during mark termination it must be
flushed before allowing preemption. This also makes the dispose during
mutator assist no longer necessary, which eliminates the vast majority
of gcWork dispose calls and reduces contention on the global workbuf
lists. And it's a lot faster on some benchmarks:
benchmark old ns/op new ns/op delta
BenchmarkBinaryTree17 11963668673 11206112763 -6.33%
BenchmarkFannkuch11 2643217136 2649182499 +0.23%
BenchmarkFmtFprintfEmpty 70.4 70.2 -0.28%
BenchmarkFmtFprintfString 364 307 -15.66%
BenchmarkFmtFprintfInt 317 282 -11.04%
BenchmarkFmtFprintfIntInt 512 483 -5.66%
BenchmarkFmtFprintfPrefixedInt 404 380 -5.94%
BenchmarkFmtFprintfFloat 521 479 -8.06%
BenchmarkFmtManyArgs 2164 1894 -12.48%
BenchmarkGobDecode 30366146 22429593 -26.14%
BenchmarkGobEncode 29867472 26663152 -10.73%
BenchmarkGzip 391236616 396779490 +1.42%
BenchmarkGunzip 96639491 96297024 -0.35%
BenchmarkHTTPClientServer 100110 70763 -29.31%
BenchmarkJSONEncode 51866051 52511382 +1.24%
BenchmarkJSONDecode 103813138 86094963 -17.07%
BenchmarkMandelbrot200 4121834 4120886 -0.02%
BenchmarkGoParse 16472789 5879949 -64.31%
BenchmarkRegexpMatchEasy0_32 140 140 +0.00%
BenchmarkRegexpMatchEasy0_1K 394 394 +0.00%
BenchmarkRegexpMatchEasy1_32 120 120 +0.00%
BenchmarkRegexpMatchEasy1_1K 621 614 -1.13%
BenchmarkRegexpMatchMedium_32 209 202 -3.35%
BenchmarkRegexpMatchMedium_1K 54889 55175 +0.52%
BenchmarkRegexpMatchHard_32 2682 2675 -0.26%
BenchmarkRegexpMatchHard_1K 79383 79524 +0.18%
BenchmarkRevcomp 584116718 584595320 +0.08%
BenchmarkTemplate 125400565 109620196 -12.58%
BenchmarkTimeParse 386 387 +0.26%
BenchmarkTimeFormat 580 447 -22.93%
(Best out of 10 runs. The delta of averages is similar.)
This also puts us in a good position to flush these caches when
nearing the end of concurrent marking, which will let us increase the
size of the work buffers while still controlling mark termination
pause time.
Change-Id: I2dd94c8517a19297a98ec280203cccaa58792522
Reviewed-on: https://go-review.googlesource.com/9178
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
2015-04-19 13:22:20 -06:00
|
|
|
// No need to dispose since we're not in mark termination.
|
2015-03-17 10:17:47 -06:00
|
|
|
|
runtime: multi-threaded, utilization-scheduled background mark
Currently, the concurrent mark phase is performed by the main GC
goroutine. Prior to the previous commit enabling preemption, this
caused marking to always consume 1/GOMAXPROCS of the available CPU
time. If GOMAXPROCS=1, this meant background GC would consume 100% of
the CPU (effectively a STW). If GOMAXPROCS>4, background GC would use
less than the goal of 25%. If GOMAXPROCS=4, background GC would use
the goal 25%, but if the mutator wasn't using the remaining 75%,
background marking wouldn't take advantage of the idle time. Enabling
preemption in the previous commit made GC miss CPU targets in
completely different ways, but set us up to bring everything back in
line.
This change replaces the fixed GC goroutine with per-P background mark
goroutines. Once started, these goroutines don't go in the standard
run queues; instead, they are scheduled specially such that the time
spent in mutator assists and the background mark goroutines totals 25%
of the CPU time available to the program. Furthermore, this lets
background marking take advantage of idle Ps, which significantly
boosts GC performance for applications that under-utilize the CPU.
This requires also changing how time is reported for gctrace, so this
change splits the concurrent mark CPU time into assist/background/idle
scanning.
This also requires increasing the size of the StackRecord slice used
in a GoroutineProfile test.
Change-Id: I0936ff907d2cee6cb687a208f2df47e8988e3157
Reviewed-on: https://go-review.googlesource.com/8850
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-03-23 19:07:33 -06:00
|
|
|
// If this is the last worker and we ran out of work,
|
|
|
|
// signal a completion point.
|
|
|
|
if xadd(&work.nwait, +1) == work.nproc && work.full == 0 && work.partial == 0 {
|
|
|
|
// This has reached a background completion
|
2015-04-22 15:44:36 -06:00
|
|
|
// point.
|
|
|
|
gcBgMarkDone()
|
runtime: multi-threaded, utilization-scheduled background mark
Currently, the concurrent mark phase is performed by the main GC
goroutine. Prior to the previous commit enabling preemption, this
caused marking to always consume 1/GOMAXPROCS of the available CPU
time. If GOMAXPROCS=1, this meant background GC would consume 100% of
the CPU (effectively a STW). If GOMAXPROCS>4, background GC would use
less than the goal of 25%. If GOMAXPROCS=4, background GC would use
the goal 25%, but if the mutator wasn't using the remaining 75%,
background marking wouldn't take advantage of the idle time. Enabling
preemption in the previous commit made GC miss CPU targets in
completely different ways, but set us up to bring everything back in
line.
This change replaces the fixed GC goroutine with per-P background mark
goroutines. Once started, these goroutines don't go in the standard
run queues; instead, they are scheduled specially such that the time
spent in mutator assists and the background mark goroutines totals 25%
of the CPU time available to the program. Furthermore, this lets
background marking take advantage of idle Ps, which significantly
boosts GC performance for applications that under-utilize the CPU.
This requires also changing how time is reported for gctrace, so this
change splits the concurrent mark CPU time into assist/background/idle
scanning.
This also requires increasing the size of the StackRecord slice used
in a GoroutineProfile test.
Change-Id: I0936ff907d2cee6cb687a208f2df47e8988e3157
Reviewed-on: https://go-review.googlesource.com/8850
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-03-23 19:07:33 -06:00
|
|
|
}
|
|
|
|
|
2015-03-17 10:17:47 -06:00
|
|
|
duration := nanotime() - startTime
|
|
|
|
_p_ := gp.m.p.ptr()
|
|
|
|
_p_.gcAssistTime += duration
|
|
|
|
if _p_.gcAssistTime > gcAssistTimeSlack {
|
|
|
|
xaddint64(&gcController.assistTime, _p_.gcAssistTime)
|
|
|
|
_p_.gcAssistTime = 0
|
|
|
|
}
|
2015-03-16 12:22:00 -06:00
|
|
|
})
|
2015-02-19 11:38:46 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
// The gp has been moved to a GC safepoint. GC phase specific
|
|
|
|
// work is done here.
|
|
|
|
//go:nowritebarrier
|
|
|
|
func gcphasework(gp *g) {
|
|
|
|
switch gcphase {
|
|
|
|
default:
|
|
|
|
throw("gcphasework in bad gcphase")
|
|
|
|
case _GCoff, _GCquiesce, _GCstw, _GCsweep:
|
|
|
|
// No work.
|
|
|
|
case _GCscan:
|
|
|
|
// scan the stack, mark the objects, put pointers in work buffers
|
|
|
|
// hanging off the P where this is being run.
|
|
|
|
// Indicate that the scan is valid until the goroutine runs again
|
|
|
|
scanstack(gp)
|
|
|
|
case _GCmark:
|
|
|
|
// No work.
|
|
|
|
case _GCmarktermination:
|
|
|
|
scanstack(gp)
|
|
|
|
// All available mark work will be emptied before returning.
|
|
|
|
}
|
|
|
|
gp.gcworkdone = true
|
|
|
|
}
|
|
|
|
|
|
|
|
//go:nowritebarrier
|
|
|
|
func scanstack(gp *g) {
|
|
|
|
if gp.gcscanvalid {
|
|
|
|
return
|
|
|
|
}
|
|
|
|
|
|
|
|
if readgstatus(gp)&_Gscan == 0 {
|
|
|
|
print("runtime:scanstack: gp=", gp, ", goid=", gp.goid, ", gp->atomicstatus=", hex(readgstatus(gp)), "\n")
|
|
|
|
throw("scanstack - bad status")
|
|
|
|
}
|
|
|
|
|
|
|
|
switch readgstatus(gp) &^ _Gscan {
|
|
|
|
default:
|
|
|
|
print("runtime: gp=", gp, ", goid=", gp.goid, ", gp->atomicstatus=", readgstatus(gp), "\n")
|
|
|
|
throw("mark - bad status")
|
|
|
|
case _Gdead:
|
|
|
|
return
|
|
|
|
case _Grunning:
|
|
|
|
print("runtime: gp=", gp, ", goid=", gp.goid, ", gp->atomicstatus=", readgstatus(gp), "\n")
|
|
|
|
throw("scanstack: goroutine not stopped")
|
|
|
|
case _Grunnable, _Gsyscall, _Gwaiting:
|
|
|
|
// ok
|
|
|
|
}
|
|
|
|
|
|
|
|
if gp == getg() {
|
|
|
|
throw("can't scan our own stack")
|
|
|
|
}
|
|
|
|
mp := gp.m
|
|
|
|
if mp != nil && mp.helpgc != 0 {
|
|
|
|
throw("can't scan gchelper stack")
|
|
|
|
}
|
|
|
|
|
runtime: replace per-M workbuf cache with per-P gcWork cache
Currently, each M has a cache of the most recently used *workbuf. This
is used primarily by the write barrier so it doesn't have to access
the global workbuf lists on every write barrier. It's also used by
stack scanning because it's convenient.
This cache is important for write barrier performance, but this
particular approach has several downsides. It's faster than no cache,
but far from optimal (as the benchmarks below show). It's complex:
access to the cache is sprinkled through most of the workbuf list
operations and it requires special care to transform into and back out
of the gcWork cache that's actually used for scanning and marking. It
requires atomic exchanges to take ownership of the cached workbuf and
to return it to the M's cache even though it's almost always used by
only the current M. Since it's per-M, flushing these caches is O(# of
Ms), which may be high. And it has some significant subtleties: for
example, in general the cache shouldn't be used after the
harvestwbufs() in mark termination because it could hide work from
mark termination, but stack scanning can happen after this and *will*
use the cache (but it turns out this is okay because it will always be
followed by a getfull(), which drains the cache).
This change replaces this cache with a per-P gcWork object. This
gcWork cache can be used directly by scanning and marking (as long as
preemption is disabled, which is a general requirement of gcWork).
Since it's per-P, it doesn't require synchronization, which simplifies
things and means the only atomic operations in the write barrier are
occasionally fetching new work buffers and setting a mark bit if the
object isn't already marked. This cache can be flushed in O(# of Ps),
which is generally small. It follows a simple flushing rule: the cache
can be used during any phase, but during mark termination it must be
flushed before allowing preemption. This also makes the dispose during
mutator assist no longer necessary, which eliminates the vast majority
of gcWork dispose calls and reduces contention on the global workbuf
lists. And it's a lot faster on some benchmarks:
benchmark old ns/op new ns/op delta
BenchmarkBinaryTree17 11963668673 11206112763 -6.33%
BenchmarkFannkuch11 2643217136 2649182499 +0.23%
BenchmarkFmtFprintfEmpty 70.4 70.2 -0.28%
BenchmarkFmtFprintfString 364 307 -15.66%
BenchmarkFmtFprintfInt 317 282 -11.04%
BenchmarkFmtFprintfIntInt 512 483 -5.66%
BenchmarkFmtFprintfPrefixedInt 404 380 -5.94%
BenchmarkFmtFprintfFloat 521 479 -8.06%
BenchmarkFmtManyArgs 2164 1894 -12.48%
BenchmarkGobDecode 30366146 22429593 -26.14%
BenchmarkGobEncode 29867472 26663152 -10.73%
BenchmarkGzip 391236616 396779490 +1.42%
BenchmarkGunzip 96639491 96297024 -0.35%
BenchmarkHTTPClientServer 100110 70763 -29.31%
BenchmarkJSONEncode 51866051 52511382 +1.24%
BenchmarkJSONDecode 103813138 86094963 -17.07%
BenchmarkMandelbrot200 4121834 4120886 -0.02%
BenchmarkGoParse 16472789 5879949 -64.31%
BenchmarkRegexpMatchEasy0_32 140 140 +0.00%
BenchmarkRegexpMatchEasy0_1K 394 394 +0.00%
BenchmarkRegexpMatchEasy1_32 120 120 +0.00%
BenchmarkRegexpMatchEasy1_1K 621 614 -1.13%
BenchmarkRegexpMatchMedium_32 209 202 -3.35%
BenchmarkRegexpMatchMedium_1K 54889 55175 +0.52%
BenchmarkRegexpMatchHard_32 2682 2675 -0.26%
BenchmarkRegexpMatchHard_1K 79383 79524 +0.18%
BenchmarkRevcomp 584116718 584595320 +0.08%
BenchmarkTemplate 125400565 109620196 -12.58%
BenchmarkTimeParse 386 387 +0.26%
BenchmarkTimeFormat 580 447 -22.93%
(Best out of 10 runs. The delta of averages is similar.)
This also puts us in a good position to flush these caches when
nearing the end of concurrent marking, which will let us increase the
size of the work buffers while still controlling mark termination
pause time.
Change-Id: I2dd94c8517a19297a98ec280203cccaa58792522
Reviewed-on: https://go-review.googlesource.com/9178
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
2015-04-19 13:22:20 -06:00
|
|
|
gcw := &getg().m.p.ptr().gcw
|
2015-02-19 11:38:46 -07:00
|
|
|
scanframe := func(frame *stkframe, unused unsafe.Pointer) bool {
|
|
|
|
// Pick up gcw as free variable so gentraceback and friends can
|
|
|
|
// keep the same signature.
|
runtime: replace per-M workbuf cache with per-P gcWork cache
Currently, each M has a cache of the most recently used *workbuf. This
is used primarily by the write barrier so it doesn't have to access
the global workbuf lists on every write barrier. It's also used by
stack scanning because it's convenient.
This cache is important for write barrier performance, but this
particular approach has several downsides. It's faster than no cache,
but far from optimal (as the benchmarks below show). It's complex:
access to the cache is sprinkled through most of the workbuf list
operations and it requires special care to transform into and back out
of the gcWork cache that's actually used for scanning and marking. It
requires atomic exchanges to take ownership of the cached workbuf and
to return it to the M's cache even though it's almost always used by
only the current M. Since it's per-M, flushing these caches is O(# of
Ms), which may be high. And it has some significant subtleties: for
example, in general the cache shouldn't be used after the
harvestwbufs() in mark termination because it could hide work from
mark termination, but stack scanning can happen after this and *will*
use the cache (but it turns out this is okay because it will always be
followed by a getfull(), which drains the cache).
This change replaces this cache with a per-P gcWork object. This
gcWork cache can be used directly by scanning and marking (as long as
preemption is disabled, which is a general requirement of gcWork).
Since it's per-P, it doesn't require synchronization, which simplifies
things and means the only atomic operations in the write barrier are
occasionally fetching new work buffers and setting a mark bit if the
object isn't already marked. This cache can be flushed in O(# of Ps),
which is generally small. It follows a simple flushing rule: the cache
can be used during any phase, but during mark termination it must be
flushed before allowing preemption. This also makes the dispose during
mutator assist no longer necessary, which eliminates the vast majority
of gcWork dispose calls and reduces contention on the global workbuf
lists. And it's a lot faster on some benchmarks:
benchmark old ns/op new ns/op delta
BenchmarkBinaryTree17 11963668673 11206112763 -6.33%
BenchmarkFannkuch11 2643217136 2649182499 +0.23%
BenchmarkFmtFprintfEmpty 70.4 70.2 -0.28%
BenchmarkFmtFprintfString 364 307 -15.66%
BenchmarkFmtFprintfInt 317 282 -11.04%
BenchmarkFmtFprintfIntInt 512 483 -5.66%
BenchmarkFmtFprintfPrefixedInt 404 380 -5.94%
BenchmarkFmtFprintfFloat 521 479 -8.06%
BenchmarkFmtManyArgs 2164 1894 -12.48%
BenchmarkGobDecode 30366146 22429593 -26.14%
BenchmarkGobEncode 29867472 26663152 -10.73%
BenchmarkGzip 391236616 396779490 +1.42%
BenchmarkGunzip 96639491 96297024 -0.35%
BenchmarkHTTPClientServer 100110 70763 -29.31%
BenchmarkJSONEncode 51866051 52511382 +1.24%
BenchmarkJSONDecode 103813138 86094963 -17.07%
BenchmarkMandelbrot200 4121834 4120886 -0.02%
BenchmarkGoParse 16472789 5879949 -64.31%
BenchmarkRegexpMatchEasy0_32 140 140 +0.00%
BenchmarkRegexpMatchEasy0_1K 394 394 +0.00%
BenchmarkRegexpMatchEasy1_32 120 120 +0.00%
BenchmarkRegexpMatchEasy1_1K 621 614 -1.13%
BenchmarkRegexpMatchMedium_32 209 202 -3.35%
BenchmarkRegexpMatchMedium_1K 54889 55175 +0.52%
BenchmarkRegexpMatchHard_32 2682 2675 -0.26%
BenchmarkRegexpMatchHard_1K 79383 79524 +0.18%
BenchmarkRevcomp 584116718 584595320 +0.08%
BenchmarkTemplate 125400565 109620196 -12.58%
BenchmarkTimeParse 386 387 +0.26%
BenchmarkTimeFormat 580 447 -22.93%
(Best out of 10 runs. The delta of averages is similar.)
This also puts us in a good position to flush these caches when
nearing the end of concurrent marking, which will let us increase the
size of the work buffers while still controlling mark termination
pause time.
Change-Id: I2dd94c8517a19297a98ec280203cccaa58792522
Reviewed-on: https://go-review.googlesource.com/9178
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
2015-04-19 13:22:20 -06:00
|
|
|
scanframeworker(frame, unused, gcw)
|
2015-02-19 11:38:46 -07:00
|
|
|
return true
|
|
|
|
}
|
|
|
|
gentraceback(^uintptr(0), ^uintptr(0), 0, gp, 0, nil, 0x7fffffff, scanframe, nil, 0)
|
|
|
|
tracebackdefers(gp, scanframe, nil)
|
runtime: replace per-M workbuf cache with per-P gcWork cache
Currently, each M has a cache of the most recently used *workbuf. This
is used primarily by the write barrier so it doesn't have to access
the global workbuf lists on every write barrier. It's also used by
stack scanning because it's convenient.
This cache is important for write barrier performance, but this
particular approach has several downsides. It's faster than no cache,
but far from optimal (as the benchmarks below show). It's complex:
access to the cache is sprinkled through most of the workbuf list
operations and it requires special care to transform into and back out
of the gcWork cache that's actually used for scanning and marking. It
requires atomic exchanges to take ownership of the cached workbuf and
to return it to the M's cache even though it's almost always used by
only the current M. Since it's per-M, flushing these caches is O(# of
Ms), which may be high. And it has some significant subtleties: for
example, in general the cache shouldn't be used after the
harvestwbufs() in mark termination because it could hide work from
mark termination, but stack scanning can happen after this and *will*
use the cache (but it turns out this is okay because it will always be
followed by a getfull(), which drains the cache).
This change replaces this cache with a per-P gcWork object. This
gcWork cache can be used directly by scanning and marking (as long as
preemption is disabled, which is a general requirement of gcWork).
Since it's per-P, it doesn't require synchronization, which simplifies
things and means the only atomic operations in the write barrier are
occasionally fetching new work buffers and setting a mark bit if the
object isn't already marked. This cache can be flushed in O(# of Ps),
which is generally small. It follows a simple flushing rule: the cache
can be used during any phase, but during mark termination it must be
flushed before allowing preemption. This also makes the dispose during
mutator assist no longer necessary, which eliminates the vast majority
of gcWork dispose calls and reduces contention on the global workbuf
lists. And it's a lot faster on some benchmarks:
benchmark old ns/op new ns/op delta
BenchmarkBinaryTree17 11963668673 11206112763 -6.33%
BenchmarkFannkuch11 2643217136 2649182499 +0.23%
BenchmarkFmtFprintfEmpty 70.4 70.2 -0.28%
BenchmarkFmtFprintfString 364 307 -15.66%
BenchmarkFmtFprintfInt 317 282 -11.04%
BenchmarkFmtFprintfIntInt 512 483 -5.66%
BenchmarkFmtFprintfPrefixedInt 404 380 -5.94%
BenchmarkFmtFprintfFloat 521 479 -8.06%
BenchmarkFmtManyArgs 2164 1894 -12.48%
BenchmarkGobDecode 30366146 22429593 -26.14%
BenchmarkGobEncode 29867472 26663152 -10.73%
BenchmarkGzip 391236616 396779490 +1.42%
BenchmarkGunzip 96639491 96297024 -0.35%
BenchmarkHTTPClientServer 100110 70763 -29.31%
BenchmarkJSONEncode 51866051 52511382 +1.24%
BenchmarkJSONDecode 103813138 86094963 -17.07%
BenchmarkMandelbrot200 4121834 4120886 -0.02%
BenchmarkGoParse 16472789 5879949 -64.31%
BenchmarkRegexpMatchEasy0_32 140 140 +0.00%
BenchmarkRegexpMatchEasy0_1K 394 394 +0.00%
BenchmarkRegexpMatchEasy1_32 120 120 +0.00%
BenchmarkRegexpMatchEasy1_1K 621 614 -1.13%
BenchmarkRegexpMatchMedium_32 209 202 -3.35%
BenchmarkRegexpMatchMedium_1K 54889 55175 +0.52%
BenchmarkRegexpMatchHard_32 2682 2675 -0.26%
BenchmarkRegexpMatchHard_1K 79383 79524 +0.18%
BenchmarkRevcomp 584116718 584595320 +0.08%
BenchmarkTemplate 125400565 109620196 -12.58%
BenchmarkTimeParse 386 387 +0.26%
BenchmarkTimeFormat 580 447 -22.93%
(Best out of 10 runs. The delta of averages is similar.)
This also puts us in a good position to flush these caches when
nearing the end of concurrent marking, which will let us increase the
size of the work buffers while still controlling mark termination
pause time.
Change-Id: I2dd94c8517a19297a98ec280203cccaa58792522
Reviewed-on: https://go-review.googlesource.com/9178
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
2015-04-19 13:22:20 -06:00
|
|
|
if gcphase == _GCmarktermination {
|
|
|
|
gcw.dispose()
|
|
|
|
}
|
2015-02-19 11:38:46 -07:00
|
|
|
gp.gcscanvalid = true
|
|
|
|
}
|
|
|
|
|
|
|
|
// Scan a stack frame: local variables and function arguments/results.
|
|
|
|
//go:nowritebarrier
|
2015-03-12 11:09:30 -06:00
|
|
|
func scanframeworker(frame *stkframe, unused unsafe.Pointer, gcw *gcWork) {
|
2015-02-19 11:38:46 -07:00
|
|
|
|
|
|
|
f := frame.fn
|
|
|
|
targetpc := frame.continpc
|
|
|
|
if targetpc == 0 {
|
|
|
|
// Frame is dead.
|
|
|
|
return
|
|
|
|
}
|
|
|
|
if _DebugGC > 1 {
|
|
|
|
print("scanframe ", funcname(f), "\n")
|
|
|
|
}
|
|
|
|
if targetpc != f.entry {
|
|
|
|
targetpc--
|
|
|
|
}
|
|
|
|
pcdata := pcdatavalue(f, _PCDATA_StackMapIndex, targetpc)
|
|
|
|
if pcdata == -1 {
|
|
|
|
// We do not have a valid pcdata value but there might be a
|
|
|
|
// stackmap for this function. It is likely that we are looking
|
|
|
|
// at the function prologue, assume so and hope for the best.
|
|
|
|
pcdata = 0
|
|
|
|
}
|
|
|
|
|
|
|
|
// Scan local variables if stack frame has been allocated.
|
|
|
|
size := frame.varp - frame.sp
|
|
|
|
var minsize uintptr
|
2015-03-08 07:20:20 -06:00
|
|
|
switch thechar {
|
|
|
|
case '6', '8':
|
2015-02-19 11:38:46 -07:00
|
|
|
minsize = 0
|
2015-03-08 07:20:20 -06:00
|
|
|
case '7':
|
|
|
|
minsize = spAlign
|
|
|
|
default:
|
|
|
|
minsize = ptrSize
|
2015-02-19 11:38:46 -07:00
|
|
|
}
|
|
|
|
if size > minsize {
|
|
|
|
stkmap := (*stackmap)(funcdata(f, _FUNCDATA_LocalsPointerMaps))
|
|
|
|
if stkmap == nil || stkmap.n <= 0 {
|
|
|
|
print("runtime: frame ", funcname(f), " untyped locals ", hex(frame.varp-size), "+", hex(size), "\n")
|
|
|
|
throw("missing stackmap")
|
|
|
|
}
|
|
|
|
|
|
|
|
// Locals bitmap information, scan just the pointers in locals.
|
|
|
|
if pcdata < 0 || pcdata >= stkmap.n {
|
|
|
|
// don't know where we are
|
|
|
|
print("runtime: pcdata is ", pcdata, " and ", stkmap.n, " locals stack map entries for ", funcname(f), " (targetpc=", targetpc, ")\n")
|
|
|
|
throw("scanframe: bad symbol table")
|
|
|
|
}
|
|
|
|
bv := stackmapdata(stkmap, pcdata)
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
size = uintptr(bv.n) * ptrSize
|
2015-02-19 11:38:46 -07:00
|
|
|
scanblock(frame.varp-size, size, bv.bytedata, gcw)
|
|
|
|
}
|
|
|
|
|
|
|
|
// Scan arguments.
|
|
|
|
if frame.arglen > 0 {
|
|
|
|
var bv bitvector
|
|
|
|
if frame.argmap != nil {
|
|
|
|
bv = *frame.argmap
|
|
|
|
} else {
|
|
|
|
stkmap := (*stackmap)(funcdata(f, _FUNCDATA_ArgsPointerMaps))
|
|
|
|
if stkmap == nil || stkmap.n <= 0 {
|
|
|
|
print("runtime: frame ", funcname(f), " untyped args ", hex(frame.argp), "+", hex(frame.arglen), "\n")
|
|
|
|
throw("missing stackmap")
|
|
|
|
}
|
|
|
|
if pcdata < 0 || pcdata >= stkmap.n {
|
|
|
|
// don't know where we are
|
|
|
|
print("runtime: pcdata is ", pcdata, " and ", stkmap.n, " args stack map entries for ", funcname(f), " (targetpc=", targetpc, ")\n")
|
|
|
|
throw("scanframe: bad symbol table")
|
|
|
|
}
|
|
|
|
bv = stackmapdata(stkmap, pcdata)
|
|
|
|
}
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
scanblock(frame.argp, uintptr(bv.n)*ptrSize, bv.bytedata, gcw)
|
2015-02-19 11:38:46 -07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
runtime: multi-threaded, utilization-scheduled background mark
Currently, the concurrent mark phase is performed by the main GC
goroutine. Prior to the previous commit enabling preemption, this
caused marking to always consume 1/GOMAXPROCS of the available CPU
time. If GOMAXPROCS=1, this meant background GC would consume 100% of
the CPU (effectively a STW). If GOMAXPROCS>4, background GC would use
less than the goal of 25%. If GOMAXPROCS=4, background GC would use
the goal 25%, but if the mutator wasn't using the remaining 75%,
background marking wouldn't take advantage of the idle time. Enabling
preemption in the previous commit made GC miss CPU targets in
completely different ways, but set us up to bring everything back in
line.
This change replaces the fixed GC goroutine with per-P background mark
goroutines. Once started, these goroutines don't go in the standard
run queues; instead, they are scheduled specially such that the time
spent in mutator assists and the background mark goroutines totals 25%
of the CPU time available to the program. Furthermore, this lets
background marking take advantage of idle Ps, which significantly
boosts GC performance for applications that under-utilize the CPU.
This requires also changing how time is reported for gctrace, so this
change splits the concurrent mark CPU time into assist/background/idle
scanning.
This also requires increasing the size of the StackRecord slice used
in a GoroutineProfile test.
Change-Id: I0936ff907d2cee6cb687a208f2df47e8988e3157
Reviewed-on: https://go-review.googlesource.com/8850
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-03-23 19:07:33 -06:00
|
|
|
// TODO(austin): Can we consolidate the gcDrain* functions?
|
|
|
|
|
2015-03-20 11:21:51 -06:00
|
|
|
// gcDrain scans objects in work buffers, blackening grey
|
2015-02-19 11:38:46 -07:00
|
|
|
// objects until all work buffers have been drained.
|
2015-03-13 11:29:23 -06:00
|
|
|
// If flushScanCredit != -1, gcDrain flushes accumulated scan work
|
|
|
|
// credit to gcController.bgScanCredit whenever gcw's local scan work
|
|
|
|
// credit exceeds flushScanCredit.
|
2015-02-19 11:38:46 -07:00
|
|
|
//go:nowritebarrier
|
2015-03-13 11:29:23 -06:00
|
|
|
func gcDrain(gcw *gcWork, flushScanCredit int64) {
|
2015-02-19 11:38:46 -07:00
|
|
|
if gcphase != _GCmark && gcphase != _GCmarktermination {
|
|
|
|
throw("scanblock phase incorrect")
|
|
|
|
}
|
|
|
|
|
2015-03-13 11:29:23 -06:00
|
|
|
var lastScanFlush, nextScanFlush int64
|
|
|
|
if flushScanCredit != -1 {
|
|
|
|
lastScanFlush = gcw.scanWork
|
|
|
|
nextScanFlush = lastScanFlush + flushScanCredit
|
|
|
|
} else {
|
|
|
|
nextScanFlush = int64(^uint64(0) >> 1)
|
|
|
|
}
|
|
|
|
|
2015-02-19 11:38:46 -07:00
|
|
|
for {
|
|
|
|
// If another proc wants a pointer, give it some.
|
|
|
|
if work.nwait > 0 && work.full == 0 {
|
|
|
|
gcw.balance()
|
|
|
|
}
|
|
|
|
|
|
|
|
b := gcw.get()
|
|
|
|
if b == 0 {
|
|
|
|
// work barrier reached
|
|
|
|
break
|
|
|
|
}
|
|
|
|
// If the current wbuf is filled by the scan a new wbuf might be
|
|
|
|
// returned that could possibly hold only a single object. This
|
|
|
|
// could result in each iteration draining only a single object
|
|
|
|
// out of the wbuf passed in + a single object placed
|
|
|
|
// into an empty wbuf in scanobject so there could be
|
|
|
|
// a performance hit as we keep fetching fresh wbufs.
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
scanobject(b, gcw)
|
2015-03-13 11:29:23 -06:00
|
|
|
|
|
|
|
// Flush background scan work credit to the global
|
|
|
|
// account if we've accumulated enough locally so
|
|
|
|
// mutator assists can draw on it.
|
|
|
|
if gcw.scanWork >= nextScanFlush {
|
|
|
|
credit := gcw.scanWork - lastScanFlush
|
|
|
|
xaddint64(&gcController.bgScanCredit, credit)
|
|
|
|
lastScanFlush = gcw.scanWork
|
|
|
|
nextScanFlush = lastScanFlush + flushScanCredit
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if flushScanCredit != -1 {
|
|
|
|
credit := gcw.scanWork - lastScanFlush
|
|
|
|
xaddint64(&gcController.bgScanCredit, credit)
|
2015-02-19 11:38:46 -07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
runtime: multi-threaded, utilization-scheduled background mark
Currently, the concurrent mark phase is performed by the main GC
goroutine. Prior to the previous commit enabling preemption, this
caused marking to always consume 1/GOMAXPROCS of the available CPU
time. If GOMAXPROCS=1, this meant background GC would consume 100% of
the CPU (effectively a STW). If GOMAXPROCS>4, background GC would use
less than the goal of 25%. If GOMAXPROCS=4, background GC would use
the goal 25%, but if the mutator wasn't using the remaining 75%,
background marking wouldn't take advantage of the idle time. Enabling
preemption in the previous commit made GC miss CPU targets in
completely different ways, but set us up to bring everything back in
line.
This change replaces the fixed GC goroutine with per-P background mark
goroutines. Once started, these goroutines don't go in the standard
run queues; instead, they are scheduled specially such that the time
spent in mutator assists and the background mark goroutines totals 25%
of the CPU time available to the program. Furthermore, this lets
background marking take advantage of idle Ps, which significantly
boosts GC performance for applications that under-utilize the CPU.
This requires also changing how time is reported for gctrace, so this
change splits the concurrent mark CPU time into assist/background/idle
scanning.
This also requires increasing the size of the StackRecord slice used
in a GoroutineProfile test.
Change-Id: I0936ff907d2cee6cb687a208f2df47e8988e3157
Reviewed-on: https://go-review.googlesource.com/8850
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-03-23 19:07:33 -06:00
|
|
|
// gcDrainUntilPreempt blackens grey objects until g.preempt is set.
|
|
|
|
// This is best-effort, so it will return as soon as it is unable to
|
|
|
|
// get work, even though there may be more work in the system.
|
|
|
|
//go:nowritebarrier
|
|
|
|
func gcDrainUntilPreempt(gcw *gcWork, flushScanCredit int64) {
|
|
|
|
if gcphase != _GCmark {
|
|
|
|
println("gcphase =", gcphase)
|
|
|
|
throw("gcDrainUntilPreempt phase incorrect")
|
|
|
|
}
|
|
|
|
|
|
|
|
var lastScanFlush, nextScanFlush int64
|
|
|
|
if flushScanCredit != -1 {
|
|
|
|
lastScanFlush = gcw.scanWork
|
|
|
|
nextScanFlush = lastScanFlush + flushScanCredit
|
|
|
|
} else {
|
|
|
|
nextScanFlush = int64(^uint64(0) >> 1)
|
|
|
|
}
|
|
|
|
|
|
|
|
gp := getg()
|
|
|
|
for !gp.preempt {
|
|
|
|
// If the work queue is empty, balance. During
|
|
|
|
// concurrent mark we don't really know if anyone else
|
|
|
|
// can make use of this work, but even if we're the
|
|
|
|
// only worker, the total cost of this per cycle is
|
|
|
|
// only O(_WorkbufSize) pointer copies.
|
|
|
|
if work.full == 0 && work.partial == 0 {
|
|
|
|
gcw.balance()
|
|
|
|
}
|
|
|
|
|
|
|
|
b := gcw.tryGet()
|
|
|
|
if b == 0 {
|
|
|
|
// No more work
|
|
|
|
break
|
|
|
|
}
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
scanobject(b, gcw)
|
runtime: multi-threaded, utilization-scheduled background mark
Currently, the concurrent mark phase is performed by the main GC
goroutine. Prior to the previous commit enabling preemption, this
caused marking to always consume 1/GOMAXPROCS of the available CPU
time. If GOMAXPROCS=1, this meant background GC would consume 100% of
the CPU (effectively a STW). If GOMAXPROCS>4, background GC would use
less than the goal of 25%. If GOMAXPROCS=4, background GC would use
the goal 25%, but if the mutator wasn't using the remaining 75%,
background marking wouldn't take advantage of the idle time. Enabling
preemption in the previous commit made GC miss CPU targets in
completely different ways, but set us up to bring everything back in
line.
This change replaces the fixed GC goroutine with per-P background mark
goroutines. Once started, these goroutines don't go in the standard
run queues; instead, they are scheduled specially such that the time
spent in mutator assists and the background mark goroutines totals 25%
of the CPU time available to the program. Furthermore, this lets
background marking take advantage of idle Ps, which significantly
boosts GC performance for applications that under-utilize the CPU.
This requires also changing how time is reported for gctrace, so this
change splits the concurrent mark CPU time into assist/background/idle
scanning.
This also requires increasing the size of the StackRecord slice used
in a GoroutineProfile test.
Change-Id: I0936ff907d2cee6cb687a208f2df47e8988e3157
Reviewed-on: https://go-review.googlesource.com/8850
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-03-23 19:07:33 -06:00
|
|
|
|
|
|
|
// Flush background scan work credit to the global
|
|
|
|
// account if we've accumulated enough locally so
|
|
|
|
// mutator assists can draw on it.
|
|
|
|
if gcw.scanWork >= nextScanFlush {
|
|
|
|
credit := gcw.scanWork - lastScanFlush
|
|
|
|
xaddint64(&gcController.bgScanCredit, credit)
|
|
|
|
lastScanFlush = gcw.scanWork
|
|
|
|
nextScanFlush = lastScanFlush + flushScanCredit
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if flushScanCredit != -1 {
|
|
|
|
credit := gcw.scanWork - lastScanFlush
|
|
|
|
xaddint64(&gcController.bgScanCredit, credit)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-03-13 12:01:16 -06:00
|
|
|
// gcDrainN blackens grey objects until it has performed roughly
|
|
|
|
// scanWork units of scan work. This is best-effort, so it may perform
|
|
|
|
// less work if it fails to get a work buffer. Otherwise, it will
|
|
|
|
// perform at least n units of work, but may perform more because
|
|
|
|
// scanning is always done in whole object increments.
|
2015-02-19 11:38:46 -07:00
|
|
|
//go:nowritebarrier
|
2015-03-13 12:01:16 -06:00
|
|
|
func gcDrainN(gcw *gcWork, scanWork int64) {
|
|
|
|
targetScanWork := gcw.scanWork + scanWork
|
|
|
|
for gcw.scanWork < targetScanWork {
|
2015-02-19 11:38:46 -07:00
|
|
|
// This might be a good place to add prefetch code...
|
|
|
|
// if(wbuf.nobj > 4) {
|
|
|
|
// PREFETCH(wbuf->obj[wbuf.nobj - 3];
|
|
|
|
// }
|
|
|
|
b := gcw.tryGet()
|
|
|
|
if b == 0 {
|
|
|
|
return
|
|
|
|
}
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
scanobject(b, gcw)
|
2015-02-19 11:38:46 -07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
// scanblock scans b as scanobject would, but using an explicit
|
|
|
|
// pointer bitmap instead of the heap bitmap.
|
2015-05-04 14:10:49 -06:00
|
|
|
//
|
|
|
|
// This is used to scan non-heap roots, so it does not update
|
|
|
|
// gcw.bytesMarked or gcw.scanWork.
|
|
|
|
//
|
2015-02-19 11:38:46 -07:00
|
|
|
//go:nowritebarrier
|
2015-03-12 11:09:30 -06:00
|
|
|
func scanblock(b0, n0 uintptr, ptrmask *uint8, gcw *gcWork) {
|
2015-02-19 11:38:46 -07:00
|
|
|
// Use local copies of original parameters, so that a stack trace
|
|
|
|
// due to one of the throws below shows the original block
|
|
|
|
// base and extent.
|
|
|
|
b := b0
|
|
|
|
n := n0
|
|
|
|
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
arena_start := mheap_.arena_start
|
|
|
|
arena_used := mheap_.arena_used
|
2015-02-19 11:38:46 -07:00
|
|
|
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
for i := uintptr(0); i < n; {
|
|
|
|
// Find bits for the next word.
|
|
|
|
bits := uint32(*addb(ptrmask, i/(ptrSize*8)))
|
|
|
|
if bits == 0 {
|
|
|
|
i += ptrSize * 8
|
|
|
|
continue
|
|
|
|
}
|
|
|
|
for j := 0; j < 8 && i < n; j++ {
|
|
|
|
if bits&1 != 0 {
|
|
|
|
// Same work as in scanobject; see comments there.
|
|
|
|
obj := *(*uintptr)(unsafe.Pointer(b + i))
|
|
|
|
if obj != 0 && arena_start <= obj && obj < arena_used {
|
|
|
|
if obj, hbits, span := heapBitsForObject(obj); obj != 0 {
|
|
|
|
greyobject(obj, b, i, hbits, span, gcw)
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
bits >>= 1
|
|
|
|
i += ptrSize
|
2015-02-19 11:38:46 -07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
// scanobject scans the object starting at b, adding pointers to gcw.
|
|
|
|
// b must point to the beginning of a heap object; scanobject consults
|
|
|
|
// the GC bitmap for the pointer mask and the spans for the size of the
|
|
|
|
// object (it ignores n).
|
2015-02-19 11:38:46 -07:00
|
|
|
//go:nowritebarrier
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
func scanobject(b uintptr, gcw *gcWork) {
|
2015-02-19 11:38:46 -07:00
|
|
|
arena_start := mheap_.arena_start
|
|
|
|
arena_used := mheap_.arena_used
|
|
|
|
|
|
|
|
// Find bits of the beginning of the object.
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
// b must point to the beginning of a heap object, so
|
|
|
|
// we can get its bits and span directly.
|
|
|
|
hbits := heapBitsForAddr(b)
|
|
|
|
s := spanOfUnchecked(b)
|
|
|
|
n := s.elemsize
|
|
|
|
if n == 0 {
|
|
|
|
throw("scanobject n == 0")
|
2015-02-19 11:38:46 -07:00
|
|
|
}
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
|
2015-05-04 13:40:58 -06:00
|
|
|
var i uintptr
|
|
|
|
for i = 0; i < n; i += ptrSize {
|
2015-02-19 11:38:46 -07:00
|
|
|
// Find bits for this word.
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
if i != 0 {
|
|
|
|
// Avoid needless hbits.next() on last iteration.
|
|
|
|
hbits = hbits.next()
|
|
|
|
}
|
2015-05-04 08:19:24 -06:00
|
|
|
// During checkmarking, 1-word objects store the checkmark
|
|
|
|
// in the type bit for the one word. The only one-word objects
|
|
|
|
// are pointers, or else they'd be merged with other non-pointer
|
|
|
|
// data into larger allocations.
|
runtime: optimize heapBitsSetType
For the conversion of the heap bitmap from 4-bit to 2-bit fields,
I replaced heapBitsSetType with the dumbest thing that could possibly work:
two atomic operations (atomicand8+atomicor8) per 2-bit field.
This CL replaces that code with a proper implementation that
avoids the atomics whenever possible. Benchmarks vs base CL
(before the conversion to 2-bit heap bitmap) and vs Go 1.4 below.
Compared to Go 1.4, SetTypePtr (a 1-pointer allocation)
is 10ns slower because a race against the concurrent GC requires the
use of an atomicor8 that used to be an ordinary write. This slowdown
was present even in the base CL.
Compared to both Go 1.4 and base, SetTypeNode8 (a 10-word allocation)
is 10ns slower because it too needs a new atomic, because with the
denser representation, the byte on the end of the allocation is now shared
with the object next to it; this was not true with the 4-bit representation.
Excluding these two (fundamental) slowdowns due to the use of atomics,
the new code is noticeably faster than both Go 1.4 and the base CL.
The next CL will reintroduce the ``typeDead'' optimization.
Stats are from 5 runs on a MacBookPro10,2 (late 2012 Core i5).
Compared to base CL (** = new atomic)
name old mean new mean delta
SetTypePtr 14.1ns × (0.99,1.02) 14.7ns × (0.93,1.10) ~ (p=0.175)
SetTypePtr8 18.4ns × (1.00,1.01) 18.6ns × (0.81,1.21) ~ (p=0.866)
SetTypePtr16 28.7ns × (1.00,1.00) 22.4ns × (0.90,1.27) -21.88% (p=0.015)
SetTypePtr32 52.3ns × (1.00,1.00) 33.8ns × (0.93,1.24) -35.37% (p=0.001)
SetTypePtr64 79.2ns × (1.00,1.00) 55.1ns × (1.00,1.01) -30.43% (p=0.000)
SetTypePtr126 118ns × (1.00,1.00) 100ns × (1.00,1.00) -15.97% (p=0.000)
SetTypePtr128 130ns × (0.92,1.19) 98ns × (1.00,1.00) -24.36% (p=0.008)
SetTypePtrSlice 726ns × (0.96,1.08) 760ns × (1.00,1.00) ~ (p=0.152)
SetTypeNode1 14.1ns × (0.94,1.15) 12.0ns × (1.00,1.01) -14.60% (p=0.020)
SetTypeNode1Slice 135ns × (0.96,1.07) 88ns × (1.00,1.00) -34.53% (p=0.000)
SetTypeNode8 20.9ns × (1.00,1.01) 32.6ns × (1.00,1.00) +55.37% (p=0.000) **
SetTypeNode8Slice 414ns × (0.99,1.02) 244ns × (1.00,1.00) -41.09% (p=0.000)
SetTypeNode64 80.0ns × (1.00,1.00) 57.4ns × (1.00,1.00) -28.23% (p=0.000)
SetTypeNode64Slice 2.15µs × (1.00,1.01) 1.56µs × (1.00,1.00) -27.43% (p=0.000)
SetTypeNode124 119ns × (0.99,1.00) 100ns × (1.00,1.00) -16.11% (p=0.000)
SetTypeNode124Slice 3.40µs × (1.00,1.00) 2.93µs × (1.00,1.00) -13.80% (p=0.000)
SetTypeNode126 120ns × (1.00,1.01) 98ns × (1.00,1.00) -18.19% (p=0.000)
SetTypeNode126Slice 3.53µs × (0.98,1.08) 3.02µs × (1.00,1.00) -14.49% (p=0.002)
SetTypeNode1024 726ns × (0.97,1.09) 740ns × (1.00,1.00) ~ (p=0.451)
SetTypeNode1024Slice 24.9µs × (0.89,1.37) 23.1µs × (1.00,1.00) ~ (p=0.476)
Compared to Go 1.4 (** = new atomic)
name old mean new mean delta
SetTypePtr 5.71ns × (0.89,1.19) 14.68ns × (0.93,1.10) +157.24% (p=0.000) **
SetTypePtr8 19.3ns × (0.96,1.10) 18.6ns × (0.81,1.21) ~ (p=0.638)
SetTypePtr16 30.7ns × (0.99,1.03) 22.4ns × (0.90,1.27) -26.88% (p=0.005)
SetTypePtr32 51.5ns × (1.00,1.00) 33.8ns × (0.93,1.24) -34.40% (p=0.001)
SetTypePtr64 83.6ns × (0.94,1.12) 55.1ns × (1.00,1.01) -34.12% (p=0.001)
SetTypePtr126 137ns × (0.87,1.26) 100ns × (1.00,1.00) -27.10% (p=0.028)
SetTypePtrSlice 865ns × (0.80,1.23) 760ns × (1.00,1.00) ~ (p=0.243)
SetTypeNode1 15.2ns × (0.88,1.12) 12.0ns × (1.00,1.01) -20.89% (p=0.014)
SetTypeNode1Slice 156ns × (0.93,1.16) 88ns × (1.00,1.00) -43.57% (p=0.001)
SetTypeNode8 23.8ns × (0.90,1.18) 32.6ns × (1.00,1.00) +36.76% (p=0.003) **
SetTypeNode8Slice 502ns × (0.92,1.10) 244ns × (1.00,1.00) -51.46% (p=0.000)
SetTypeNode64 85.6ns × (0.94,1.11) 57.4ns × (1.00,1.00) -32.89% (p=0.001)
SetTypeNode64Slice 2.36µs × (0.91,1.14) 1.56µs × (1.00,1.00) -33.96% (p=0.002)
SetTypeNode124 130ns × (0.91,1.12) 100ns × (1.00,1.00) -23.49% (p=0.004)
SetTypeNode124Slice 3.81µs × (0.90,1.22) 2.93µs × (1.00,1.00) -23.09% (p=0.025)
There are fewer benchmarks vs Go 1.4 because unrolling directly
into the heap bitmap is not yet implemented, so those would not
be meaningful comparisons.
These benchmarks were not present in Go 1.4 as distributed.
The backport to Go 1.4 is in github.com/rsc/go's go14bench branch,
commit 71d5ee5.
Change-Id: I95ed05a22bf484b0fc9efad549279e766c98d2b6
Reviewed-on: https://go-review.googlesource.com/9704
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-05-04 09:30:10 -06:00
|
|
|
bits := hbits.bits()
|
|
|
|
if i >= 2*ptrSize && bits&bitMarked == 0 {
|
|
|
|
break // no more pointers in this object
|
|
|
|
}
|
|
|
|
if bits&bitPointer == 0 {
|
|
|
|
continue // not a pointer
|
2015-02-19 11:38:46 -07:00
|
|
|
}
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
|
runtime: optimize heapBitsSetType
For the conversion of the heap bitmap from 4-bit to 2-bit fields,
I replaced heapBitsSetType with the dumbest thing that could possibly work:
two atomic operations (atomicand8+atomicor8) per 2-bit field.
This CL replaces that code with a proper implementation that
avoids the atomics whenever possible. Benchmarks vs base CL
(before the conversion to 2-bit heap bitmap) and vs Go 1.4 below.
Compared to Go 1.4, SetTypePtr (a 1-pointer allocation)
is 10ns slower because a race against the concurrent GC requires the
use of an atomicor8 that used to be an ordinary write. This slowdown
was present even in the base CL.
Compared to both Go 1.4 and base, SetTypeNode8 (a 10-word allocation)
is 10ns slower because it too needs a new atomic, because with the
denser representation, the byte on the end of the allocation is now shared
with the object next to it; this was not true with the 4-bit representation.
Excluding these two (fundamental) slowdowns due to the use of atomics,
the new code is noticeably faster than both Go 1.4 and the base CL.
The next CL will reintroduce the ``typeDead'' optimization.
Stats are from 5 runs on a MacBookPro10,2 (late 2012 Core i5).
Compared to base CL (** = new atomic)
name old mean new mean delta
SetTypePtr 14.1ns × (0.99,1.02) 14.7ns × (0.93,1.10) ~ (p=0.175)
SetTypePtr8 18.4ns × (1.00,1.01) 18.6ns × (0.81,1.21) ~ (p=0.866)
SetTypePtr16 28.7ns × (1.00,1.00) 22.4ns × (0.90,1.27) -21.88% (p=0.015)
SetTypePtr32 52.3ns × (1.00,1.00) 33.8ns × (0.93,1.24) -35.37% (p=0.001)
SetTypePtr64 79.2ns × (1.00,1.00) 55.1ns × (1.00,1.01) -30.43% (p=0.000)
SetTypePtr126 118ns × (1.00,1.00) 100ns × (1.00,1.00) -15.97% (p=0.000)
SetTypePtr128 130ns × (0.92,1.19) 98ns × (1.00,1.00) -24.36% (p=0.008)
SetTypePtrSlice 726ns × (0.96,1.08) 760ns × (1.00,1.00) ~ (p=0.152)
SetTypeNode1 14.1ns × (0.94,1.15) 12.0ns × (1.00,1.01) -14.60% (p=0.020)
SetTypeNode1Slice 135ns × (0.96,1.07) 88ns × (1.00,1.00) -34.53% (p=0.000)
SetTypeNode8 20.9ns × (1.00,1.01) 32.6ns × (1.00,1.00) +55.37% (p=0.000) **
SetTypeNode8Slice 414ns × (0.99,1.02) 244ns × (1.00,1.00) -41.09% (p=0.000)
SetTypeNode64 80.0ns × (1.00,1.00) 57.4ns × (1.00,1.00) -28.23% (p=0.000)
SetTypeNode64Slice 2.15µs × (1.00,1.01) 1.56µs × (1.00,1.00) -27.43% (p=0.000)
SetTypeNode124 119ns × (0.99,1.00) 100ns × (1.00,1.00) -16.11% (p=0.000)
SetTypeNode124Slice 3.40µs × (1.00,1.00) 2.93µs × (1.00,1.00) -13.80% (p=0.000)
SetTypeNode126 120ns × (1.00,1.01) 98ns × (1.00,1.00) -18.19% (p=0.000)
SetTypeNode126Slice 3.53µs × (0.98,1.08) 3.02µs × (1.00,1.00) -14.49% (p=0.002)
SetTypeNode1024 726ns × (0.97,1.09) 740ns × (1.00,1.00) ~ (p=0.451)
SetTypeNode1024Slice 24.9µs × (0.89,1.37) 23.1µs × (1.00,1.00) ~ (p=0.476)
Compared to Go 1.4 (** = new atomic)
name old mean new mean delta
SetTypePtr 5.71ns × (0.89,1.19) 14.68ns × (0.93,1.10) +157.24% (p=0.000) **
SetTypePtr8 19.3ns × (0.96,1.10) 18.6ns × (0.81,1.21) ~ (p=0.638)
SetTypePtr16 30.7ns × (0.99,1.03) 22.4ns × (0.90,1.27) -26.88% (p=0.005)
SetTypePtr32 51.5ns × (1.00,1.00) 33.8ns × (0.93,1.24) -34.40% (p=0.001)
SetTypePtr64 83.6ns × (0.94,1.12) 55.1ns × (1.00,1.01) -34.12% (p=0.001)
SetTypePtr126 137ns × (0.87,1.26) 100ns × (1.00,1.00) -27.10% (p=0.028)
SetTypePtrSlice 865ns × (0.80,1.23) 760ns × (1.00,1.00) ~ (p=0.243)
SetTypeNode1 15.2ns × (0.88,1.12) 12.0ns × (1.00,1.01) -20.89% (p=0.014)
SetTypeNode1Slice 156ns × (0.93,1.16) 88ns × (1.00,1.00) -43.57% (p=0.001)
SetTypeNode8 23.8ns × (0.90,1.18) 32.6ns × (1.00,1.00) +36.76% (p=0.003) **
SetTypeNode8Slice 502ns × (0.92,1.10) 244ns × (1.00,1.00) -51.46% (p=0.000)
SetTypeNode64 85.6ns × (0.94,1.11) 57.4ns × (1.00,1.00) -32.89% (p=0.001)
SetTypeNode64Slice 2.36µs × (0.91,1.14) 1.56µs × (1.00,1.00) -33.96% (p=0.002)
SetTypeNode124 130ns × (0.91,1.12) 100ns × (1.00,1.00) -23.49% (p=0.004)
SetTypeNode124Slice 3.81µs × (0.90,1.22) 2.93µs × (1.00,1.00) -23.09% (p=0.025)
There are fewer benchmarks vs Go 1.4 because unrolling directly
into the heap bitmap is not yet implemented, so those would not
be meaningful comparisons.
These benchmarks were not present in Go 1.4 as distributed.
The backport to Go 1.4 is in github.com/rsc/go's go14bench branch,
commit 71d5ee5.
Change-Id: I95ed05a22bf484b0fc9efad549279e766c98d2b6
Reviewed-on: https://go-review.googlesource.com/9704
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-05-04 09:30:10 -06:00
|
|
|
// Work here is duplicated in scanblock and above.
|
|
|
|
// If you make changes here, make changes there too.
|
2015-02-19 11:38:46 -07:00
|
|
|
obj := *(*uintptr)(unsafe.Pointer(b + i))
|
|
|
|
|
|
|
|
// At this point we have extracted the next potential pointer.
|
runtime: add fast check for self-loop pointer in scanobject
Addresses a problem reported on the mailing list.
This will come up mainly in programs custom allocators that batch allocations,
but it still helps in our programs, which mainly do not have such allocations.
name old mean new mean delta
BinaryTree17 5.95s × (0.97,1.03) 5.93s × (0.97,1.04) ~ (p=0.613)
Fannkuch11 4.46s × (0.98,1.04) 4.33s × (0.99,1.01) -2.93% (p=0.000)
FmtFprintfEmpty 86.6ns × (0.98,1.03) 86.8ns × (0.98,1.02) ~ (p=0.523)
FmtFprintfString 290ns × (0.98,1.05) 287ns × (0.98,1.03) ~ (p=0.061)
FmtFprintfInt 271ns × (0.98,1.04) 286ns × (0.99,1.01) +5.54% (p=0.000)
FmtFprintfIntInt 495ns × (0.98,1.04) 489ns × (0.99,1.01) -1.24% (p=0.015)
FmtFprintfPrefixedInt 391ns × (0.99,1.02) 407ns × (0.99,1.01) +4.00% (p=0.000)
FmtFprintfFloat 578ns × (0.99,1.01) 559ns × (0.99,1.01) -3.35% (p=0.000)
FmtManyArgs 1.96µs × (0.98,1.05) 1.94µs × (0.99,1.01) -1.33% (p=0.030)
GobDecode 15.9ms × (0.97,1.05) 15.7ms × (0.99,1.01) -1.35% (p=0.044)
GobEncode 11.4ms × (0.97,1.05) 11.3ms × (0.98,1.03) ~ (p=0.141)
Gzip 658ms × (0.98,1.05) 648ms × (0.99,1.01) -1.59% (p=0.009)
Gunzip 144ms × (0.99,1.03) 144ms × (0.99,1.01) ~ (p=0.867)
HTTPClientServer 92.1µs × (0.97,1.05) 90.3µs × (0.99,1.01) -1.89% (p=0.005)
JSONEncode 31.0ms × (0.96,1.07) 30.2ms × (0.98,1.03) -2.66% (p=0.001)
JSONDecode 110ms × (0.97,1.04) 107ms × (0.99,1.01) -2.59% (p=0.000)
Mandelbrot200 6.15ms × (0.98,1.04) 6.07ms × (0.99,1.02) -1.32% (p=0.045)
GoParse 6.79ms × (0.97,1.04) 6.74ms × (0.97,1.04) ~ (p=0.242)
RegexpMatchEasy0_32 158ns × (0.98,1.05) 155ns × (0.99,1.01) -1.64% (p=0.010)
RegexpMatchEasy0_1K 548ns × (0.97,1.04) 540ns × (0.99,1.01) -1.34% (p=0.042)
RegexpMatchEasy1_32 133ns × (0.97,1.04) 132ns × (0.97,1.05) ~ (p=0.466)
RegexpMatchEasy1_1K 899ns × (0.96,1.05) 878ns × (0.99,1.01) -2.32% (p=0.002)
RegexpMatchMedium_32 250ns × (0.96,1.03) 243ns × (0.99,1.01) -2.90% (p=0.000)
RegexpMatchMedium_1K 73.4µs × (0.98,1.04) 73.0µs × (0.98,1.04) ~ (p=0.411)
RegexpMatchHard_32 3.87µs × (0.97,1.07) 3.84µs × (0.98,1.04) ~ (p=0.273)
RegexpMatchHard_1K 120µs × (0.97,1.08) 117µs × (0.99,1.01) -2.06% (p=0.010)
Revcomp 940ms × (0.96,1.07) 924ms × (0.97,1.07) ~ (p=0.071)
Template 128ms × (0.96,1.05) 128ms × (0.99,1.01) ~ (p=0.502)
TimeParse 632ns × (0.96,1.07) 616ns × (0.99,1.01) -2.58% (p=0.001)
TimeFormat 671ns × (0.97,1.06) 657ns × (0.99,1.02) -2.10% (p=0.002)
In contrast to the one in test/bench/go1 (above), the binarytree program on the
shootout site uses more goroutines, batches allocations, and sets GOMAXPROCS
to runtime.NumCPU()*2.
Using that version, before vs after:
name old mean new mean delta
BinaryTree20 18.6s × (0.96,1.05) 11.3s × (0.98,1.02) -39.46% (p=0.000)
And Go 1.4 vs after:
name old mean new mean delta
BinaryTree20 13.0s × (0.97,1.02) 11.3s × (0.98,1.02) -13.21% (p=0.000)
There is still a scheduling problem - the raw run times are hiding the fact that
this chews up 2x the CPU - but we'll take care of that separately.
Change-Id: I3f5da879b24ae73a0d06745381ffb88c3744948b
Reviewed-on: https://go-review.googlesource.com/10220
Reviewed-by: Austin Clements <austin@google.com>
2015-05-18 09:40:29 -06:00
|
|
|
// Check if it points into heap and not back at the current object.
|
|
|
|
if obj != 0 && arena_start <= obj && obj < arena_used && obj-b >= n {
|
cmd/internal/gc, runtime: use 1-bit bitmap for stack frames, data, bss
The bitmaps were 2 bits per pointer because we needed to distinguish
scalar, pointer, multiword, and we used the leftover value to distinguish
uninitialized from scalar, even though the garbage collector (GC) didn't care.
Now that there are no multiword structures from the GC's point of view,
cut the bitmaps down to 1 bit per pointer, recording just live pointer vs not.
The GC assumes the same layout for stack frames and for the maps
describing the global data and bss sections, so change them all in one CL.
The code still refers to 4-bit heap bitmaps and 2-bit "type bitmaps", since
the 2-bit representation lives (at least for now) in some of the reflect data.
Because these stack frame bitmaps are stored directly in the rodata in
the binary, this CL reduces the size of the 6g binary by about 1.1%.
Performance change is basically a wash, but using less memory,
and smaller binaries, and enables other bitmap reductions.
name old mean new mean delta
BenchmarkBinaryTree17 13.2s × (0.97,1.03) 13.0s × (0.99,1.01) -0.93% (p=0.005)
BenchmarkBinaryTree17-2 9.69s × (0.96,1.05) 9.51s × (0.96,1.03) -1.86% (p=0.001)
BenchmarkBinaryTree17-4 10.1s × (0.97,1.05) 10.0s × (0.96,1.05) ~ (p=0.141)
BenchmarkFannkuch11 4.35s × (0.99,1.01) 4.43s × (0.98,1.04) +1.75% (p=0.001)
BenchmarkFannkuch11-2 4.31s × (0.99,1.03) 4.32s × (1.00,1.00) ~ (p=0.095)
BenchmarkFannkuch11-4 4.32s × (0.99,1.02) 4.38s × (0.98,1.04) +1.38% (p=0.008)
BenchmarkFmtFprintfEmpty 83.5ns × (0.97,1.10) 87.3ns × (0.92,1.11) +4.55% (p=0.014)
BenchmarkFmtFprintfEmpty-2 81.8ns × (0.98,1.04) 82.5ns × (0.97,1.08) ~ (p=0.364)
BenchmarkFmtFprintfEmpty-4 80.9ns × (0.99,1.01) 82.6ns × (0.97,1.08) +2.12% (p=0.010)
BenchmarkFmtFprintfString 320ns × (0.95,1.04) 322ns × (0.97,1.05) ~ (p=0.368)
BenchmarkFmtFprintfString-2 303ns × (0.97,1.04) 304ns × (0.97,1.04) ~ (p=0.484)
BenchmarkFmtFprintfString-4 305ns × (0.97,1.05) 306ns × (0.98,1.05) ~ (p=0.543)
BenchmarkFmtFprintfInt 311ns × (0.98,1.03) 319ns × (0.97,1.03) +2.63% (p=0.000)
BenchmarkFmtFprintfInt-2 297ns × (0.98,1.04) 301ns × (0.97,1.04) +1.19% (p=0.023)
BenchmarkFmtFprintfInt-4 302ns × (0.98,1.02) 304ns × (0.97,1.03) ~ (p=0.126)
BenchmarkFmtFprintfIntInt 554ns × (0.96,1.05) 554ns × (0.97,1.03) ~ (p=0.975)
BenchmarkFmtFprintfIntInt-2 520ns × (0.98,1.03) 517ns × (0.98,1.02) ~ (p=0.153)
BenchmarkFmtFprintfIntInt-4 524ns × (0.98,1.02) 525ns × (0.98,1.03) ~ (p=0.597)
BenchmarkFmtFprintfPrefixedInt 433ns × (0.97,1.06) 434ns × (0.97,1.06) ~ (p=0.804)
BenchmarkFmtFprintfPrefixedInt-2 413ns × (0.98,1.04) 413ns × (0.98,1.03) ~ (p=0.881)
BenchmarkFmtFprintfPrefixedInt-4 420ns × (0.97,1.03) 421ns × (0.97,1.03) ~ (p=0.561)
BenchmarkFmtFprintfFloat 620ns × (0.99,1.03) 636ns × (0.97,1.03) +2.57% (p=0.000)
BenchmarkFmtFprintfFloat-2 601ns × (0.98,1.02) 617ns × (0.98,1.03) +2.58% (p=0.000)
BenchmarkFmtFprintfFloat-4 613ns × (0.98,1.03) 626ns × (0.98,1.02) +2.15% (p=0.000)
BenchmarkFmtManyArgs 2.19µs × (0.96,1.04) 2.23µs × (0.97,1.02) +1.65% (p=0.000)
BenchmarkFmtManyArgs-2 2.08µs × (0.98,1.03) 2.10µs × (0.99,1.02) +0.79% (p=0.019)
BenchmarkFmtManyArgs-4 2.10µs × (0.98,1.02) 2.13µs × (0.98,1.02) +1.72% (p=0.000)
BenchmarkGobDecode 21.3ms × (0.97,1.05) 21.1ms × (0.97,1.04) -1.36% (p=0.025)
BenchmarkGobDecode-2 20.0ms × (0.97,1.03) 19.2ms × (0.97,1.03) -4.00% (p=0.000)
BenchmarkGobDecode-4 19.5ms × (0.99,1.02) 19.0ms × (0.99,1.01) -2.39% (p=0.000)
BenchmarkGobEncode 18.3ms × (0.95,1.07) 18.1ms × (0.96,1.08) ~ (p=0.305)
BenchmarkGobEncode-2 16.8ms × (0.97,1.02) 16.4ms × (0.98,1.02) -2.79% (p=0.000)
BenchmarkGobEncode-4 15.4ms × (0.98,1.02) 15.4ms × (0.98,1.02) ~ (p=0.465)
BenchmarkGzip 650ms × (0.98,1.03) 655ms × (0.97,1.04) ~ (p=0.075)
BenchmarkGzip-2 652ms × (0.98,1.03) 655ms × (0.98,1.02) ~ (p=0.337)
BenchmarkGzip-4 656ms × (0.98,1.04) 653ms × (0.98,1.03) ~ (p=0.291)
BenchmarkGunzip 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.507)
BenchmarkGunzip-2 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.313)
BenchmarkGunzip-4 143ms × (1.00,1.01) 143ms × (1.00,1.01) ~ (p=0.312)
BenchmarkHTTPClientServer 110µs × (0.98,1.03) 109µs × (0.99,1.02) -1.40% (p=0.000)
BenchmarkHTTPClientServer-2 154µs × (0.90,1.08) 149µs × (0.90,1.08) -3.43% (p=0.007)
BenchmarkHTTPClientServer-4 138µs × (0.97,1.04) 138µs × (0.96,1.04) ~ (p=0.670)
BenchmarkJSONEncode 40.2ms × (0.98,1.02) 40.2ms × (0.98,1.05) ~ (p=0.828)
BenchmarkJSONEncode-2 35.1ms × (0.99,1.02) 35.2ms × (0.98,1.03) ~ (p=0.392)
BenchmarkJSONEncode-4 35.3ms × (0.98,1.03) 35.3ms × (0.98,1.02) ~ (p=0.813)
BenchmarkJSONDecode 119ms × (0.97,1.02) 117ms × (0.98,1.02) -1.80% (p=0.000)
BenchmarkJSONDecode-2 115ms × (0.99,1.02) 114ms × (0.98,1.02) -1.18% (p=0.000)
BenchmarkJSONDecode-4 116ms × (0.98,1.02) 114ms × (0.98,1.02) -1.43% (p=0.000)
BenchmarkMandelbrot200 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.985)
BenchmarkMandelbrot200-2 6.03ms × (1.00,1.01) 6.02ms × (1.00,1.01) ~ (p=0.320)
BenchmarkMandelbrot200-4 6.03ms × (1.00,1.01) 6.03ms × (1.00,1.01) ~ (p=0.799)
BenchmarkGoParse 8.63ms × (0.89,1.10) 8.58ms × (0.93,1.09) ~ (p=0.667)
BenchmarkGoParse-2 8.20ms × (0.97,1.04) 8.37ms × (0.97,1.04) +1.96% (p=0.001)
BenchmarkGoParse-4 8.00ms × (0.98,1.02) 8.14ms × (0.99,1.02) +1.75% (p=0.000)
BenchmarkRegexpMatchEasy0_32 162ns × (1.00,1.01) 164ns × (0.98,1.04) +1.35% (p=0.011)
BenchmarkRegexpMatchEasy0_32-2 161ns × (1.00,1.01) 161ns × (1.00,1.00) ~ (p=0.185)
BenchmarkRegexpMatchEasy0_32-4 161ns × (1.00,1.00) 161ns × (1.00,1.00) -0.19% (p=0.001)
BenchmarkRegexpMatchEasy0_1K 540ns × (0.99,1.02) 566ns × (0.98,1.04) +4.98% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-2 540ns × (0.99,1.01) 557ns × (0.99,1.01) +3.21% (p=0.000)
BenchmarkRegexpMatchEasy0_1K-4 541ns × (0.99,1.01) 559ns × (0.99,1.01) +3.26% (p=0.000)
BenchmarkRegexpMatchEasy1_32 139ns × (0.98,1.04) 139ns × (0.99,1.03) ~ (p=0.979)
BenchmarkRegexpMatchEasy1_32-2 139ns × (0.99,1.04) 139ns × (0.99,1.02) ~ (p=0.777)
BenchmarkRegexpMatchEasy1_32-4 139ns × (0.98,1.04) 139ns × (0.99,1.04) ~ (p=0.771)
BenchmarkRegexpMatchEasy1_1K 890ns × (0.99,1.03) 885ns × (1.00,1.01) -0.50% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-2 888ns × (0.99,1.01) 885ns × (0.99,1.01) -0.37% (p=0.004)
BenchmarkRegexpMatchEasy1_1K-4 890ns × (0.99,1.02) 884ns × (1.00,1.00) -0.70% (p=0.000)
BenchmarkRegexpMatchMedium_32 252ns × (0.99,1.01) 251ns × (0.99,1.01) ~ (p=0.081)
BenchmarkRegexpMatchMedium_32-2 254ns × (0.99,1.04) 252ns × (0.99,1.01) -0.78% (p=0.027)
BenchmarkRegexpMatchMedium_32-4 253ns × (0.99,1.04) 252ns × (0.99,1.01) -0.70% (p=0.022)
BenchmarkRegexpMatchMedium_1K 72.9µs × (0.99,1.01) 72.7µs × (1.00,1.00) ~ (p=0.064)
BenchmarkRegexpMatchMedium_1K-2 74.1µs × (0.98,1.05) 72.9µs × (1.00,1.01) -1.61% (p=0.001)
BenchmarkRegexpMatchMedium_1K-4 73.6µs × (0.99,1.05) 72.8µs × (1.00,1.00) -1.13% (p=0.007)
BenchmarkRegexpMatchHard_32 3.88µs × (0.99,1.03) 3.92µs × (0.98,1.05) ~ (p=0.143)
BenchmarkRegexpMatchHard_32-2 3.89µs × (0.99,1.03) 3.93µs × (0.98,1.09) ~ (p=0.278)
BenchmarkRegexpMatchHard_32-4 3.90µs × (0.99,1.05) 3.93µs × (0.98,1.05) ~ (p=0.252)
BenchmarkRegexpMatchHard_1K 118µs × (0.99,1.01) 117µs × (0.99,1.02) -0.54% (p=0.003)
BenchmarkRegexpMatchHard_1K-2 118µs × (0.99,1.01) 118µs × (0.99,1.03) ~ (p=0.581)
BenchmarkRegexpMatchHard_1K-4 118µs × (0.99,1.02) 117µs × (0.99,1.01) -0.54% (p=0.002)
BenchmarkRevcomp 991ms × (0.95,1.10) 989ms × (0.94,1.08) ~ (p=0.879)
BenchmarkRevcomp-2 978ms × (0.95,1.11) 962ms × (0.96,1.08) ~ (p=0.257)
BenchmarkRevcomp-4 979ms × (0.96,1.07) 974ms × (0.96,1.11) ~ (p=0.678)
BenchmarkTemplate 141ms × (0.99,1.02) 145ms × (0.99,1.02) +2.75% (p=0.000)
BenchmarkTemplate-2 135ms × (0.98,1.02) 138ms × (0.99,1.02) +2.34% (p=0.000)
BenchmarkTemplate-4 136ms × (0.98,1.02) 140ms × (0.99,1.02) +2.71% (p=0.000)
BenchmarkTimeParse 640ns × (0.99,1.01) 622ns × (0.99,1.01) -2.88% (p=0.000)
BenchmarkTimeParse-2 640ns × (0.99,1.01) 622ns × (1.00,1.00) -2.81% (p=0.000)
BenchmarkTimeParse-4 640ns × (1.00,1.01) 622ns × (0.99,1.01) -2.82% (p=0.000)
BenchmarkTimeFormat 730ns × (0.98,1.02) 731ns × (0.98,1.03) ~ (p=0.767)
BenchmarkTimeFormat-2 709ns × (0.99,1.02) 707ns × (0.99,1.02) ~ (p=0.347)
BenchmarkTimeFormat-4 717ns × (0.98,1.01) 718ns × (0.98,1.02) ~ (p=0.793)
Change-Id: Ie779c47e912bf80eb918bafa13638bd8dfd6c2d9
Reviewed-on: https://go-review.googlesource.com/9406
Reviewed-by: Rick Hudson <rlh@golang.org>
2015-04-27 20:45:57 -06:00
|
|
|
// Mark the object.
|
|
|
|
if obj, hbits, span := heapBitsForObject(obj); obj != 0 {
|
|
|
|
greyobject(obj, b, i, hbits, span, gcw)
|
|
|
|
}
|
2015-02-19 11:38:46 -07:00
|
|
|
}
|
|
|
|
}
|
2015-03-12 14:53:57 -06:00
|
|
|
gcw.bytesMarked += uint64(n)
|
2015-05-04 13:40:58 -06:00
|
|
|
gcw.scanWork += int64(i)
|
2015-02-19 11:38:46 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
// Shade the object if it isn't already.
|
|
|
|
// The object is not nil and known to be in the heap.
|
runtime: replace per-M workbuf cache with per-P gcWork cache
Currently, each M has a cache of the most recently used *workbuf. This
is used primarily by the write barrier so it doesn't have to access
the global workbuf lists on every write barrier. It's also used by
stack scanning because it's convenient.
This cache is important for write barrier performance, but this
particular approach has several downsides. It's faster than no cache,
but far from optimal (as the benchmarks below show). It's complex:
access to the cache is sprinkled through most of the workbuf list
operations and it requires special care to transform into and back out
of the gcWork cache that's actually used for scanning and marking. It
requires atomic exchanges to take ownership of the cached workbuf and
to return it to the M's cache even though it's almost always used by
only the current M. Since it's per-M, flushing these caches is O(# of
Ms), which may be high. And it has some significant subtleties: for
example, in general the cache shouldn't be used after the
harvestwbufs() in mark termination because it could hide work from
mark termination, but stack scanning can happen after this and *will*
use the cache (but it turns out this is okay because it will always be
followed by a getfull(), which drains the cache).
This change replaces this cache with a per-P gcWork object. This
gcWork cache can be used directly by scanning and marking (as long as
preemption is disabled, which is a general requirement of gcWork).
Since it's per-P, it doesn't require synchronization, which simplifies
things and means the only atomic operations in the write barrier are
occasionally fetching new work buffers and setting a mark bit if the
object isn't already marked. This cache can be flushed in O(# of Ps),
which is generally small. It follows a simple flushing rule: the cache
can be used during any phase, but during mark termination it must be
flushed before allowing preemption. This also makes the dispose during
mutator assist no longer necessary, which eliminates the vast majority
of gcWork dispose calls and reduces contention on the global workbuf
lists. And it's a lot faster on some benchmarks:
benchmark old ns/op new ns/op delta
BenchmarkBinaryTree17 11963668673 11206112763 -6.33%
BenchmarkFannkuch11 2643217136 2649182499 +0.23%
BenchmarkFmtFprintfEmpty 70.4 70.2 -0.28%
BenchmarkFmtFprintfString 364 307 -15.66%
BenchmarkFmtFprintfInt 317 282 -11.04%
BenchmarkFmtFprintfIntInt 512 483 -5.66%
BenchmarkFmtFprintfPrefixedInt 404 380 -5.94%
BenchmarkFmtFprintfFloat 521 479 -8.06%
BenchmarkFmtManyArgs 2164 1894 -12.48%
BenchmarkGobDecode 30366146 22429593 -26.14%
BenchmarkGobEncode 29867472 26663152 -10.73%
BenchmarkGzip 391236616 396779490 +1.42%
BenchmarkGunzip 96639491 96297024 -0.35%
BenchmarkHTTPClientServer 100110 70763 -29.31%
BenchmarkJSONEncode 51866051 52511382 +1.24%
BenchmarkJSONDecode 103813138 86094963 -17.07%
BenchmarkMandelbrot200 4121834 4120886 -0.02%
BenchmarkGoParse 16472789 5879949 -64.31%
BenchmarkRegexpMatchEasy0_32 140 140 +0.00%
BenchmarkRegexpMatchEasy0_1K 394 394 +0.00%
BenchmarkRegexpMatchEasy1_32 120 120 +0.00%
BenchmarkRegexpMatchEasy1_1K 621 614 -1.13%
BenchmarkRegexpMatchMedium_32 209 202 -3.35%
BenchmarkRegexpMatchMedium_1K 54889 55175 +0.52%
BenchmarkRegexpMatchHard_32 2682 2675 -0.26%
BenchmarkRegexpMatchHard_1K 79383 79524 +0.18%
BenchmarkRevcomp 584116718 584595320 +0.08%
BenchmarkTemplate 125400565 109620196 -12.58%
BenchmarkTimeParse 386 387 +0.26%
BenchmarkTimeFormat 580 447 -22.93%
(Best out of 10 runs. The delta of averages is similar.)
This also puts us in a good position to flush these caches when
nearing the end of concurrent marking, which will let us increase the
size of the work buffers while still controlling mark termination
pause time.
Change-Id: I2dd94c8517a19297a98ec280203cccaa58792522
Reviewed-on: https://go-review.googlesource.com/9178
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
2015-04-19 13:22:20 -06:00
|
|
|
// Preemption must be disabled.
|
2015-02-19 11:38:46 -07:00
|
|
|
//go:nowritebarrier
|
|
|
|
func shade(b uintptr) {
|
2015-03-12 14:53:57 -06:00
|
|
|
if obj, hbits, span := heapBitsForObject(b); obj != 0 {
|
runtime: replace per-M workbuf cache with per-P gcWork cache
Currently, each M has a cache of the most recently used *workbuf. This
is used primarily by the write barrier so it doesn't have to access
the global workbuf lists on every write barrier. It's also used by
stack scanning because it's convenient.
This cache is important for write barrier performance, but this
particular approach has several downsides. It's faster than no cache,
but far from optimal (as the benchmarks below show). It's complex:
access to the cache is sprinkled through most of the workbuf list
operations and it requires special care to transform into and back out
of the gcWork cache that's actually used for scanning and marking. It
requires atomic exchanges to take ownership of the cached workbuf and
to return it to the M's cache even though it's almost always used by
only the current M. Since it's per-M, flushing these caches is O(# of
Ms), which may be high. And it has some significant subtleties: for
example, in general the cache shouldn't be used after the
harvestwbufs() in mark termination because it could hide work from
mark termination, but stack scanning can happen after this and *will*
use the cache (but it turns out this is okay because it will always be
followed by a getfull(), which drains the cache).
This change replaces this cache with a per-P gcWork object. This
gcWork cache can be used directly by scanning and marking (as long as
preemption is disabled, which is a general requirement of gcWork).
Since it's per-P, it doesn't require synchronization, which simplifies
things and means the only atomic operations in the write barrier are
occasionally fetching new work buffers and setting a mark bit if the
object isn't already marked. This cache can be flushed in O(# of Ps),
which is generally small. It follows a simple flushing rule: the cache
can be used during any phase, but during mark termination it must be
flushed before allowing preemption. This also makes the dispose during
mutator assist no longer necessary, which eliminates the vast majority
of gcWork dispose calls and reduces contention on the global workbuf
lists. And it's a lot faster on some benchmarks:
benchmark old ns/op new ns/op delta
BenchmarkBinaryTree17 11963668673 11206112763 -6.33%
BenchmarkFannkuch11 2643217136 2649182499 +0.23%
BenchmarkFmtFprintfEmpty 70.4 70.2 -0.28%
BenchmarkFmtFprintfString 364 307 -15.66%
BenchmarkFmtFprintfInt 317 282 -11.04%
BenchmarkFmtFprintfIntInt 512 483 -5.66%
BenchmarkFmtFprintfPrefixedInt 404 380 -5.94%
BenchmarkFmtFprintfFloat 521 479 -8.06%
BenchmarkFmtManyArgs 2164 1894 -12.48%
BenchmarkGobDecode 30366146 22429593 -26.14%
BenchmarkGobEncode 29867472 26663152 -10.73%
BenchmarkGzip 391236616 396779490 +1.42%
BenchmarkGunzip 96639491 96297024 -0.35%
BenchmarkHTTPClientServer 100110 70763 -29.31%
BenchmarkJSONEncode 51866051 52511382 +1.24%
BenchmarkJSONDecode 103813138 86094963 -17.07%
BenchmarkMandelbrot200 4121834 4120886 -0.02%
BenchmarkGoParse 16472789 5879949 -64.31%
BenchmarkRegexpMatchEasy0_32 140 140 +0.00%
BenchmarkRegexpMatchEasy0_1K 394 394 +0.00%
BenchmarkRegexpMatchEasy1_32 120 120 +0.00%
BenchmarkRegexpMatchEasy1_1K 621 614 -1.13%
BenchmarkRegexpMatchMedium_32 209 202 -3.35%
BenchmarkRegexpMatchMedium_1K 54889 55175 +0.52%
BenchmarkRegexpMatchHard_32 2682 2675 -0.26%
BenchmarkRegexpMatchHard_1K 79383 79524 +0.18%
BenchmarkRevcomp 584116718 584595320 +0.08%
BenchmarkTemplate 125400565 109620196 -12.58%
BenchmarkTimeParse 386 387 +0.26%
BenchmarkTimeFormat 580 447 -22.93%
(Best out of 10 runs. The delta of averages is similar.)
This also puts us in a good position to flush these caches when
nearing the end of concurrent marking, which will let us increase the
size of the work buffers while still controlling mark termination
pause time.
Change-Id: I2dd94c8517a19297a98ec280203cccaa58792522
Reviewed-on: https://go-review.googlesource.com/9178
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
2015-04-19 13:22:20 -06:00
|
|
|
gcw := &getg().m.p.ptr().gcw
|
|
|
|
greyobject(obj, 0, 0, hbits, span, gcw)
|
2015-02-19 11:38:46 -07:00
|
|
|
if gcphase == _GCmarktermination {
|
runtime: replace per-M workbuf cache with per-P gcWork cache
Currently, each M has a cache of the most recently used *workbuf. This
is used primarily by the write barrier so it doesn't have to access
the global workbuf lists on every write barrier. It's also used by
stack scanning because it's convenient.
This cache is important for write barrier performance, but this
particular approach has several downsides. It's faster than no cache,
but far from optimal (as the benchmarks below show). It's complex:
access to the cache is sprinkled through most of the workbuf list
operations and it requires special care to transform into and back out
of the gcWork cache that's actually used for scanning and marking. It
requires atomic exchanges to take ownership of the cached workbuf and
to return it to the M's cache even though it's almost always used by
only the current M. Since it's per-M, flushing these caches is O(# of
Ms), which may be high. And it has some significant subtleties: for
example, in general the cache shouldn't be used after the
harvestwbufs() in mark termination because it could hide work from
mark termination, but stack scanning can happen after this and *will*
use the cache (but it turns out this is okay because it will always be
followed by a getfull(), which drains the cache).
This change replaces this cache with a per-P gcWork object. This
gcWork cache can be used directly by scanning and marking (as long as
preemption is disabled, which is a general requirement of gcWork).
Since it's per-P, it doesn't require synchronization, which simplifies
things and means the only atomic operations in the write barrier are
occasionally fetching new work buffers and setting a mark bit if the
object isn't already marked. This cache can be flushed in O(# of Ps),
which is generally small. It follows a simple flushing rule: the cache
can be used during any phase, but during mark termination it must be
flushed before allowing preemption. This also makes the dispose during
mutator assist no longer necessary, which eliminates the vast majority
of gcWork dispose calls and reduces contention on the global workbuf
lists. And it's a lot faster on some benchmarks:
benchmark old ns/op new ns/op delta
BenchmarkBinaryTree17 11963668673 11206112763 -6.33%
BenchmarkFannkuch11 2643217136 2649182499 +0.23%
BenchmarkFmtFprintfEmpty 70.4 70.2 -0.28%
BenchmarkFmtFprintfString 364 307 -15.66%
BenchmarkFmtFprintfInt 317 282 -11.04%
BenchmarkFmtFprintfIntInt 512 483 -5.66%
BenchmarkFmtFprintfPrefixedInt 404 380 -5.94%
BenchmarkFmtFprintfFloat 521 479 -8.06%
BenchmarkFmtManyArgs 2164 1894 -12.48%
BenchmarkGobDecode 30366146 22429593 -26.14%
BenchmarkGobEncode 29867472 26663152 -10.73%
BenchmarkGzip 391236616 396779490 +1.42%
BenchmarkGunzip 96639491 96297024 -0.35%
BenchmarkHTTPClientServer 100110 70763 -29.31%
BenchmarkJSONEncode 51866051 52511382 +1.24%
BenchmarkJSONDecode 103813138 86094963 -17.07%
BenchmarkMandelbrot200 4121834 4120886 -0.02%
BenchmarkGoParse 16472789 5879949 -64.31%
BenchmarkRegexpMatchEasy0_32 140 140 +0.00%
BenchmarkRegexpMatchEasy0_1K 394 394 +0.00%
BenchmarkRegexpMatchEasy1_32 120 120 +0.00%
BenchmarkRegexpMatchEasy1_1K 621 614 -1.13%
BenchmarkRegexpMatchMedium_32 209 202 -3.35%
BenchmarkRegexpMatchMedium_1K 54889 55175 +0.52%
BenchmarkRegexpMatchHard_32 2682 2675 -0.26%
BenchmarkRegexpMatchHard_1K 79383 79524 +0.18%
BenchmarkRevcomp 584116718 584595320 +0.08%
BenchmarkTemplate 125400565 109620196 -12.58%
BenchmarkTimeParse 386 387 +0.26%
BenchmarkTimeFormat 580 447 -22.93%
(Best out of 10 runs. The delta of averages is similar.)
This also puts us in a good position to flush these caches when
nearing the end of concurrent marking, which will let us increase the
size of the work buffers while still controlling mark termination
pause time.
Change-Id: I2dd94c8517a19297a98ec280203cccaa58792522
Reviewed-on: https://go-review.googlesource.com/9178
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>
2015-04-19 13:22:20 -06:00
|
|
|
// Ps aren't allowed to cache work during mark
|
|
|
|
// termination.
|
2015-02-19 11:38:46 -07:00
|
|
|
gcw.dispose()
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// obj is the start of an object with mark mbits.
|
2015-04-27 13:42:45 -06:00
|
|
|
// If it isn't already marked, mark it and enqueue into gcw.
|
2015-02-19 11:38:46 -07:00
|
|
|
// base and off are for debugging only and could be removed.
|
|
|
|
//go:nowritebarrier
|
2015-03-12 14:53:57 -06:00
|
|
|
func greyobject(obj, base, off uintptr, hbits heapBits, span *mspan, gcw *gcWork) {
|
2015-02-19 11:38:46 -07:00
|
|
|
// obj should be start of allocation, and so must be at least pointer-aligned.
|
|
|
|
if obj&(ptrSize-1) != 0 {
|
|
|
|
throw("greyobject: obj not pointer-aligned")
|
|
|
|
}
|
|
|
|
|
2015-02-19 14:43:27 -07:00
|
|
|
if useCheckmark {
|
2015-02-19 11:38:46 -07:00
|
|
|
if !hbits.isMarked() {
|
2015-03-12 12:26:04 -06:00
|
|
|
printlock()
|
2015-02-19 11:38:46 -07:00
|
|
|
print("runtime:greyobject: checkmarks finds unexpected unmarked object obj=", hex(obj), "\n")
|
|
|
|
print("runtime: found obj at *(", hex(base), "+", hex(off), ")\n")
|
|
|
|
|
|
|
|
// Dump the source (base) object
|
2015-03-12 12:26:04 -06:00
|
|
|
gcDumpObject("base", base, off)
|
2015-02-19 11:38:46 -07:00
|
|
|
|
|
|
|
// Dump the object
|
2015-03-12 12:26:04 -06:00
|
|
|
gcDumpObject("obj", obj, ^uintptr(0))
|
2015-02-19 11:38:46 -07:00
|
|
|
|
|
|
|
throw("checkmark found unmarked object")
|
|
|
|
}
|
2015-05-04 08:19:24 -06:00
|
|
|
if hbits.isCheckmarked(span.elemsize) {
|
2015-02-19 11:38:46 -07:00
|
|
|
return
|
|
|
|
}
|
2015-05-04 08:19:24 -06:00
|
|
|
hbits.setCheckmarked(span.elemsize)
|
|
|
|
if !hbits.isCheckmarked(span.elemsize) {
|
2015-02-19 11:38:46 -07:00
|
|
|
throw("setCheckmarked and isCheckmarked disagree")
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
// If marked we have nothing to do.
|
|
|
|
if hbits.isMarked() {
|
|
|
|
return
|
|
|
|
}
|
|
|
|
hbits.setMarked()
|
|
|
|
|
2015-02-27 10:41:20 -07:00
|
|
|
// If this is a noscan object, fast-track it to black
|
|
|
|
// instead of greying it.
|
2015-05-04 08:19:24 -06:00
|
|
|
if !hbits.hasPointers(span.elemsize) {
|
2015-03-12 14:53:57 -06:00
|
|
|
gcw.bytesMarked += uint64(span.elemsize)
|
2015-02-27 10:41:20 -07:00
|
|
|
return
|
|
|
|
}
|
2015-02-19 11:38:46 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
// Queue the obj for scanning. The PREFETCH(obj) logic has been removed but
|
|
|
|
// seems like a nice optimization that can be added back in.
|
|
|
|
// There needs to be time between the PREFETCH and the use.
|
|
|
|
// Previously we put the obj in an 8 element buffer that is drained at a rate
|
|
|
|
// to give the PREFETCH time to do its work.
|
|
|
|
// Use of PREFETCHNTA might be more appropriate than PREFETCH
|
|
|
|
|
|
|
|
gcw.put(obj)
|
|
|
|
}
|
|
|
|
|
2015-03-12 12:26:04 -06:00
|
|
|
// gcDumpObject dumps the contents of obj for debugging and marks the
|
|
|
|
// field at byte offset off in obj.
|
|
|
|
func gcDumpObject(label string, obj, off uintptr) {
|
2015-04-29 13:15:43 -06:00
|
|
|
if obj < mheap_.arena_start || obj >= mheap_.arena_used {
|
|
|
|
print(label, "=", hex(obj), " is not a heap object\n")
|
|
|
|
return
|
|
|
|
}
|
2015-03-12 12:26:04 -06:00
|
|
|
k := obj >> _PageShift
|
|
|
|
x := k
|
|
|
|
x -= mheap_.arena_start >> _PageShift
|
|
|
|
s := h_spans[x]
|
|
|
|
print(label, "=", hex(obj), " k=", hex(k))
|
|
|
|
if s == nil {
|
|
|
|
print(" s=nil\n")
|
|
|
|
return
|
|
|
|
}
|
|
|
|
print(" s.start*_PageSize=", hex(s.start*_PageSize), " s.limit=", hex(s.limit), " s.sizeclass=", s.sizeclass, " s.elemsize=", s.elemsize, "\n")
|
|
|
|
for i := uintptr(0); i < s.elemsize; i += ptrSize {
|
|
|
|
print(" *(", label, "+", i, ") = ", hex(*(*uintptr)(unsafe.Pointer(obj + uintptr(i)))))
|
|
|
|
if i == off {
|
|
|
|
print(" <==")
|
|
|
|
}
|
|
|
|
print("\n")
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-02-19 11:38:46 -07:00
|
|
|
// When in GCmarkterminate phase we allocate black.
|
|
|
|
//go:nowritebarrier
|
2015-03-12 14:53:57 -06:00
|
|
|
func gcmarknewobject_m(obj, size uintptr) {
|
2015-02-19 11:38:46 -07:00
|
|
|
if gcphase != _GCmarktermination {
|
|
|
|
throw("marking new object while not in mark termination phase")
|
|
|
|
}
|
2015-02-19 14:43:27 -07:00
|
|
|
if useCheckmark { // The world should be stopped so this should not happen.
|
2015-02-19 11:38:46 -07:00
|
|
|
throw("gcmarknewobject called while doing checkmark")
|
|
|
|
}
|
|
|
|
|
|
|
|
heapBitsForAddr(obj).setMarked()
|
2015-03-12 14:53:57 -06:00
|
|
|
xadd64(&work.bytesMarked, int64(size))
|
2015-02-19 11:38:46 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
// Checkmarking
|
|
|
|
|
|
|
|
// To help debug the concurrent GC we remark with the world
|
|
|
|
// stopped ensuring that any object encountered has their normal
|
|
|
|
// mark bit set. To do this we use an orthogonal bit
|
|
|
|
// pattern to indicate the object is marked. The following pattern
|
|
|
|
// uses the upper two bits in the object's bounday nibble.
|
|
|
|
// 01: scalar not marked
|
|
|
|
// 10: pointer not marked
|
|
|
|
// 11: pointer marked
|
|
|
|
// 00: scalar marked
|
|
|
|
// Xoring with 01 will flip the pattern from marked to unmarked and vica versa.
|
|
|
|
// The higher bit is 1 for pointers and 0 for scalars, whether the object
|
|
|
|
// is marked or not.
|
|
|
|
// The first nibble no longer holds the typeDead pattern indicating that the
|
|
|
|
// there are no more pointers in the object. This information is held
|
|
|
|
// in the second nibble.
|
|
|
|
|
2015-02-19 14:43:27 -07:00
|
|
|
// If useCheckmark is true, marking of an object uses the
|
|
|
|
// checkmark bits (encoding above) instead of the standard
|
|
|
|
// mark bits.
|
|
|
|
var useCheckmark = false
|
2015-02-19 11:38:46 -07:00
|
|
|
|
|
|
|
//go:nowritebarrier
|
|
|
|
func initCheckmarks() {
|
2015-02-19 14:43:27 -07:00
|
|
|
useCheckmark = true
|
2015-02-19 11:38:46 -07:00
|
|
|
for _, s := range work.spans {
|
|
|
|
if s.state == _MSpanInUse {
|
|
|
|
heapBitsForSpan(s.base()).initCheckmarkSpan(s.layout())
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
func clearCheckmarks() {
|
2015-02-19 14:43:27 -07:00
|
|
|
useCheckmark = false
|
2015-02-19 11:38:46 -07:00
|
|
|
for _, s := range work.spans {
|
|
|
|
if s.state == _MSpanInUse {
|
|
|
|
heapBitsForSpan(s.base()).clearCheckmarkSpan(s.layout())
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|