mirror of
https://github.com/golang/go.git
synced 2025-12-08 06:10:04 +00:00
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>
This commit is contained in:
Russ Cox
parent
e9ab343f0e
commit
4d0f3a1c95
10 changed files with 236 additions and 237 deletions
|
|
@ -237,18 +237,10 @@ type childInfo struct {
|
|||
// dump kinds & offsets of interesting fields in bv
|
||||
func dumpbv(cbv *bitvector, offset uintptr) {
|
||||
bv := gobv(*cbv)
|
||||
for i := uintptr(0); i < uintptr(bv.n); i += typeBitsWidth {
|
||||
switch bv.bytedata[i/8] >> (i % 8) & typeMask {
|
||||
default:
|
||||
throw("unexpected pointer bits")
|
||||
case typeDead:
|
||||
// typeDead has already been processed in makeheapobjbv.
|
||||
// We should only see it in stack maps, in which case we should continue processing.
|
||||
case typeScalar:
|
||||
// ok
|
||||
case typePointer:
|
||||
for i := uintptr(0); i < uintptr(bv.n); i++ {
|
||||
if bv.bytedata[i/8]>>(i%8)&1 == 1 {
|
||||
dumpint(fieldKindPtr)
|
||||
dumpint(uint64(offset + i/typeBitsWidth*ptrSize))
|
||||
dumpint(uint64(offset + i*ptrSize))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -278,7 +270,7 @@ func dumpframe(s *stkframe, arg unsafe.Pointer) bool {
|
|||
var bv bitvector
|
||||
if stkmap != nil && stkmap.n > 0 {
|
||||
bv = stackmapdata(stkmap, pcdata)
|
||||
dumpbvtypes(&bv, unsafe.Pointer(s.varp-uintptr(bv.n/typeBitsWidth*ptrSize)))
|
||||
dumpbvtypes(&bv, unsafe.Pointer(s.varp-uintptr(bv.n*ptrSize)))
|
||||
} else {
|
||||
bv.n = -1
|
||||
}
|
||||
|
|
@ -326,7 +318,7 @@ func dumpframe(s *stkframe, arg unsafe.Pointer) bool {
|
|||
} else if stkmap.n > 0 {
|
||||
// Locals bitmap information, scan just the pointers in
|
||||
// locals.
|
||||
dumpbv(&bv, s.varp-uintptr(bv.n)/typeBitsWidth*ptrSize-s.sp)
|
||||
dumpbv(&bv, s.varp-uintptr(bv.n)*ptrSize-s.sp)
|
||||
}
|
||||
dumpint(fieldKindEol)
|
||||
|
||||
|
|
@ -651,7 +643,7 @@ func dumpmemprof() {
|
|||
}
|
||||
}
|
||||
|
||||
var dumphdr = []byte("go1.4 heap dump\n")
|
||||
var dumphdr = []byte("go1.5 heap dump\n")
|
||||
|
||||
func mdump() {
|
||||
// make sure we're done sweeping
|
||||
|
|
@ -720,18 +712,21 @@ func dumpbvtypes(bv *bitvector, base unsafe.Pointer) {
|
|||
func makeheapobjbv(p uintptr, size uintptr) bitvector {
|
||||
// Extend the temp buffer if necessary.
|
||||
nptr := size / ptrSize
|
||||
if uintptr(len(tmpbuf)) < nptr*typeBitsWidth/8+1 {
|
||||
if uintptr(len(tmpbuf)) < nptr/8+1 {
|
||||
if tmpbuf != nil {
|
||||
sysFree(unsafe.Pointer(&tmpbuf[0]), uintptr(len(tmpbuf)), &memstats.other_sys)
|
||||
}
|
||||
n := nptr*typeBitsWidth/8 + 1
|
||||
n := nptr/8 + 1
|
||||
p := sysAlloc(n, &memstats.other_sys)
|
||||
if p == nil {
|
||||
throw("heapdump: out of memory")
|
||||
}
|
||||
tmpbuf = (*[1 << 30]byte)(p)[:n]
|
||||
}
|
||||
// Convert heap bitmap to type bitmap.
|
||||
// Convert heap bitmap to pointer bitmap.
|
||||
for i := uintptr(0); i < nptr/8+1; i++ {
|
||||
tmpbuf[i] = 0
|
||||
}
|
||||
i := uintptr(0)
|
||||
hbits := heapBitsForAddr(p)
|
||||
for ; i < nptr; i++ {
|
||||
|
|
@ -740,8 +735,9 @@ func makeheapobjbv(p uintptr, size uintptr) bitvector {
|
|||
break // end of object
|
||||
}
|
||||
hbits = hbits.next()
|
||||
tmpbuf[i*typeBitsWidth/8] &^= (typeMask << ((i * typeBitsWidth) % 8))
|
||||
tmpbuf[i*typeBitsWidth/8] |= bits << ((i * typeBitsWidth) % 8)
|
||||
if bits == typePointer {
|
||||
tmpbuf[i/8] |= 1 << (i % 8)
|
||||
}
|
||||
}
|
||||
return bitvector{int32(i * typeBitsWidth), &tmpbuf[0]}
|
||||
return bitvector{int32(i), &tmpbuf[0]}
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue