Commit fbf27325 authored by Austin Clements's avatar Austin Clements

runtime: perform mark 2 root re-scanning in GC workers

This moves another root scanning task out of the GC coordinator and
parallelizes it on the GC workers.

This has negligible effect on the go1 benchmarks and the garbage
benchmark.

name              old time/op  new time/op  delta
XBenchGarbage-12  5.24ms ± 1%  5.26ms ± 1%  +0.30%  (p=0.007 n=18+17)

name                      old time/op    new time/op    delta
BinaryTree17-12              3.20s ± 5%     3.21s ± 5%    ~     (p=0.264 n=20+18)
Fannkuch11-12                2.46s ± 1%     2.54s ± 2%  +3.09%  (p=0.000 n=18+20)
FmtFprintfEmpty-12          49.9ns ± 4%    50.0ns ± 5%    ~     (p=0.356 n=20+20)
FmtFprintfString-12          170ns ± 1%     170ns ± 2%    ~     (p=0.815 n=19+20)
FmtFprintfInt-12             160ns ± 1%     159ns ± 1%  -0.63%  (p=0.003 n=18+19)
FmtFprintfIntInt-12          270ns ± 1%     267ns ± 1%  -1.00%  (p=0.000 n=19+18)
FmtFprintfPrefixedInt-12     238ns ± 1%     232ns ± 1%  -2.28%  (p=0.000 n=19+19)
FmtFprintfFloat-12           310ns ± 2%     313ns ± 2%  +0.93%  (p=0.000 n=19+19)
FmtManyArgs-12              1.06µs ± 1%    1.04µs ± 1%  -1.93%  (p=0.000 n=20+19)
GobDecode-12                8.63ms ± 1%    8.70ms ± 1%  +0.81%  (p=0.001 n=20+19)
GobEncode-12                6.52ms ± 1%    6.56ms ± 1%  +0.66%  (p=0.000 n=20+19)
Gzip-12                      318ms ± 1%     319ms ± 1%    ~     (p=0.405 n=17+18)
Gunzip-12                   42.1ms ± 2%    42.0ms ± 1%    ~     (p=0.771 n=20+19)
HTTPClientServer-12         62.6µs ± 1%    62.9µs ± 1%  +0.41%  (p=0.038 n=20+20)
JSONEncode-12               16.9ms ± 1%    16.9ms ± 1%    ~     (p=0.077 n=18+20)
JSONDecode-12               60.7ms ± 1%    62.3ms ± 1%  +2.73%  (p=0.000 n=20+20)
Mandelbrot200-12            3.86ms ± 1%    3.85ms ± 1%    ~     (p=0.084 n=19+20)
GoParse-12                  3.75ms ± 2%    3.73ms ± 1%    ~     (p=0.107 n=20+19)
RegexpMatchEasy0_32-12       100ns ± 2%     101ns ± 2%  +0.97%  (p=0.001 n=20+19)
RegexpMatchEasy0_1K-12       342ns ± 2%     332ns ± 2%  -2.86%  (p=0.000 n=19+19)
RegexpMatchEasy1_32-12      83.2ns ± 2%    82.8ns ± 2%    ~     (p=0.108 n=19+20)
RegexpMatchEasy1_1K-12       495ns ± 2%     490ns ± 2%  -1.04%  (p=0.000 n=18+19)
RegexpMatchMedium_32-12      130ns ± 2%     131ns ± 2%    ~     (p=0.291 n=20+20)
RegexpMatchMedium_1K-12     39.3µs ± 1%    39.9µs ± 1%  +1.54%  (p=0.000 n=18+20)
RegexpMatchHard_32-12       2.02µs ± 1%    2.05µs ± 2%  +1.19%  (p=0.000 n=19+19)
RegexpMatchHard_1K-12       60.9µs ± 1%    61.5µs ± 1%  +0.99%  (p=0.000 n=18+18)
Revcomp-12                   535ms ± 1%     531ms ± 1%  -0.82%  (p=0.000 n=17+17)
Template-12                 73.0ms ± 1%    74.1ms ± 1%  +1.47%  (p=0.000 n=20+20)
TimeParse-12                 356ns ± 2%     348ns ± 1%  -2.30%  (p=0.000 n=20+20)
TimeFormat-12                347ns ± 1%     353ns ± 1%  +1.68%  (p=0.000 n=19+20)
[Geo mean]                  62.3µs         62.4µs       +0.12%

name                      old speed      new speed      delta
GobDecode-12              88.9MB/s ± 1%  88.2MB/s ± 1%  -0.81%  (p=0.001 n=20+19)
GobEncode-12               118MB/s ± 1%   117MB/s ± 1%  -0.66%  (p=0.000 n=20+19)
Gzip-12                   60.9MB/s ± 1%  60.8MB/s ± 1%    ~     (p=0.409 n=17+18)
Gunzip-12                  461MB/s ± 2%   462MB/s ± 1%    ~     (p=0.765 n=20+19)
JSONEncode-12              115MB/s ± 1%   115MB/s ± 1%    ~     (p=0.078 n=18+20)
JSONDecode-12             32.0MB/s ± 1%  31.1MB/s ± 1%  -2.65%  (p=0.000 n=20+20)
GoParse-12                15.5MB/s ± 2%  15.5MB/s ± 1%    ~     (p=0.111 n=20+19)
RegexpMatchEasy0_32-12     318MB/s ± 2%   314MB/s ± 2%  -1.27%  (p=0.000 n=20+19)
RegexpMatchEasy0_1K-12    2.99GB/s ± 1%  3.08GB/s ± 2%  +2.94%  (p=0.000 n=19+19)
RegexpMatchEasy1_32-12     385MB/s ± 2%   386MB/s ± 2%    ~     (p=0.105 n=19+20)
RegexpMatchEasy1_1K-12    2.07GB/s ± 1%  2.09GB/s ± 2%  +1.06%  (p=0.000 n=18+19)
RegexpMatchMedium_32-12   7.64MB/s ± 2%  7.61MB/s ± 1%    ~     (p=0.179 n=20+20)
RegexpMatchMedium_1K-12   26.1MB/s ± 1%  25.7MB/s ± 1%  -1.52%  (p=0.000 n=18+20)
RegexpMatchHard_32-12     15.8MB/s ± 1%  15.6MB/s ± 2%  -1.18%  (p=0.000 n=19+19)
RegexpMatchHard_1K-12     16.8MB/s ± 2%  16.6MB/s ± 1%  -0.90%  (p=0.000 n=19+18)
Revcomp-12                 475MB/s ± 1%   479MB/s ± 1%  +0.83%  (p=0.000 n=17+17)
Template-12               26.6MB/s ± 1%  26.2MB/s ± 1%  -1.45%  (p=0.000 n=20+20)
[Geo mean]                99.0MB/s       98.7MB/s       -0.32%

Change-Id: I6ea44d7a59aaa6851c64695277ab65645ff9d32e
Reviewed-on: https://go-review.googlesource.com/16070Reviewed-by: 's avatarRick Hudson <rlh@golang.org>
Run-TryBot: Austin Clements <austin@google.com>
parent 82d14d77
......@@ -1055,11 +1055,6 @@ func gc(mode gcMode) {
// objects reachable from global roots since they don't have write
// barriers. Rescan some roots and flush work caches.
systemstack(func() {
// rescan global data and bss.
for i := fixedRootCount; i < fixedRootCount+work.nDataRoots+work.nBSSRoots; i++ {
markroot(nil, uint32(i))
}
// Disallow caching workbufs.
gcBlackenPromptly = true
......@@ -1069,6 +1064,12 @@ func gc(mode gcMode) {
forEachP(func(_p_ *p) {
_p_.gcw.dispose()
})
// Rescan global data and BSS. Bump "jobs"
// down before "next" so workers won't try
// running root jobs until we set "next".
atomicstore(&work.markrootJobs, uint32(fixedRootCount+work.nDataRoots+work.nBSSRoots))
atomicstore(&work.markrootNext, fixedRootCount)
})
// Wait for this more aggressive background mark to complete.
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment