It's no longer necessary to maintain the bitmap of noscan objects
since we now use the span metadata to determine that they're noscan
instead of the bitmap.
The combined effect of segregating noscan spans and the follow-on
optimizations is roughly a 1% improvement in performance across the
go1 benchmarks and the x/benchmarks, with no increase in heap size.
Benchmark details: https://perf.golang.org/search?q=upload:
20170420.1
name old time/op new time/op delta
Garbage/benchmem-MB=64-12 2.27ms ± 0% 2.25ms ± 1% -0.96% (p=0.000 n=15+18)
name old time/op new time/op delta
BinaryTree17-12 2.53s ± 2% 2.55s ± 1% +0.68% (p=0.001 n=17+16)
Fannkuch11-12 3.02s ± 0% 3.01s ± 0% -0.15% (p=0.000 n=16+16)
FmtFprintfEmpty-12 47.1ns ± 7% 47.0ns ± 5% ~ (p=0.886 n=20+17)
FmtFprintfString-12 73.6ns ± 3% 73.8ns ± 1% +0.30% (p=0.026 n=19+17)
FmtFprintfInt-12 80.3ns ± 2% 80.2ns ± 1% ~ (p=0.994 n=20+18)
FmtFprintfIntInt-12 124ns ± 0% 124ns ± 0% ~ (all samples are equal)
FmtFprintfPrefixedInt-12 172ns ± 1% 171ns ± 1% -0.72% (p=0.003 n=20+18)
FmtFprintfFloat-12 217ns ± 1% 216ns ± 1% -0.27% (p=0.019 n=18+19)
FmtManyArgs-12 490ns ± 1% 488ns ± 0% -0.36% (p=0.014 n=18+18)
GobDecode-12 6.71ms ± 1% 6.73ms ± 1% +0.42% (p=0.000 n=20+20)
GobEncode-12 5.25ms ± 0% 5.24ms ± 0% -0.20% (p=0.001 n=18+20)
Gzip-12 227ms ± 0% 226ms ± 1% ~ (p=0.107 n=20+19)
Gunzip-12 38.8ms ± 0% 38.8ms ± 0% ~ (p=0.221 n=19+18)
HTTPClientServer-12 75.4µs ± 1% 76.3µs ± 1% +1.26% (p=0.000 n=20+19)
JSONEncode-12 14.7ms ± 0% 14.7ms ± 1% -0.14% (p=0.002 n=18+17)
JSONDecode-12 57.6ms ± 0% 55.2ms ± 0% -4.13% (p=0.000 n=19+19)
Mandelbrot200-12 3.73ms ± 0% 3.73ms ± 0% -0.09% (p=0.000 n=19+17)
GoParse-12 3.18ms ± 1% 3.15ms ± 1% -0.90% (p=0.000 n=18+20)
RegexpMatchEasy0_32-12 73.3ns ± 2% 73.2ns ± 1% ~ (p=0.994 n=20+18)
RegexpMatchEasy0_1K-12 236ns ± 2% 234ns ± 1% -0.70% (p=0.002 n=19+17)
RegexpMatchEasy1_32-12 69.7ns ± 2% 69.9ns ± 2% ~ (p=0.416 n=20+20)
RegexpMatchEasy1_1K-12 366ns ± 1% 365ns ± 1% ~ (p=0.376 n=19+17)
RegexpMatchMedium_32-12 109ns ± 1% 108ns ± 1% ~ (p=0.461 n=17+18)
RegexpMatchMedium_1K-12 35.2µs ± 1% 35.2µs ± 3% ~ (p=0.238 n=19+20)
RegexpMatchHard_32-12 1.77µs ± 1% 1.77µs ± 1% +0.33% (p=0.007 n=17+16)
RegexpMatchHard_1K-12 53.2µs ± 0% 53.3µs ± 0% +0.26% (p=0.001 n=17+17)
Revcomp-12 1.13s ±117% 0.87s ±184% ~ (p=0.813 n=20+19)
Template-12 63.9ms ± 1% 64.6ms ± 1% +1.18% (p=0.000 n=19+20)
TimeParse-12 313ns ± 5% 312ns ± 0% ~ (p=0.114 n=20+19)
TimeFormat-12 336ns ± 0% 333ns ± 0% -0.97% (p=0.000 n=18+16)
[Geo mean] 50.6µs 50.1µs -1.04%
This is a cherry-pick of dev.garbage commit
edb54c300f, with updated
benchmark results.
Change-Id: Ic77faaa15cdac3bfbbb0032dde5c204e05a0fd8e
Reviewed-on: https://go-review.googlesource.com/41253
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Rick Hudson <rlh@golang.org>
}
var scanSize uintptr
- if noscan {
- heapBitsSetTypeNoScan(uintptr(x))
- } else {
+ if !noscan {
// If allocating a defer+arg block, now that we've picked a malloc size
// large enough to hold everything, cut the "asked for" size down to
// just the defer header, so that the GC bitmap will record the arg block
// not checkmarked, and is the dead encoding.
// These properties must be preserved when modifying the encoding.
//
+// The bitmap for noscan spans is not maintained. Code must ensure
+// that an object is scannable before consulting its bitmap by
+// checking either the noscan bit in the span or by consulting its
+// type's information.
+//
// Checkmarks
//
// In a concurrent garbage collector, one worries about failing to mark
}
}
-// heapBitsSetTypeNoScan marks x as noscan by setting the first word
-// of x in the heap bitmap to scalar/dead.
-func heapBitsSetTypeNoScan(x uintptr) {
- h := heapBitsForAddr(uintptr(x))
- *h.bitp &^= (bitPointer | bitScan) << h.shift
-}
-
var debugPtrmask struct {
lock mutex
data *byte