Commit 4fffc50c authored by Russ Cox's avatar Russ Cox

runtime: correct accounting of scan work and bytes marked

(1) Count pointer-free objects found during scanning roots
as marked bytes, by not zeroing the mark total after scanning roots.

(2) Don't count the bytes for the roots themselves, by not adding
them to the mark total in scanblock (the zeroing removed by (1)
was aimed at that add but hitting more).

Combined, (1) and (2) fix the calculation of the marked heap size.
This makes the GC trigger much less often in the Go 1 benchmarks,
which have a global []byte pointing at 256 MB of data.
That 256 MB allocation was not being included in the heap size
in the current code, but was included in Go 1.4.
This is the source of much of the relative slowdown in that directory.

(3) Count the bytes for the roots as scanned work, by not zeroing
the scan total after scanning roots. There is no strict justification
for this, and it probably doesn't matter much either way,
but it was always combined with another buggy zeroing
(removed in (1)), so guilty by association.

Austin noticed this.

name                                    old mean                new mean        delta
BenchmarkBinaryTree17              13.1s × (0.97,1.03)      5.9s × (0.97,1.05)  -55.19% (p=0.000)
BenchmarkFannkuch11                4.35s × (0.99,1.01)     4.37s × (1.00,1.01)  +0.47% (p=0.032)
BenchmarkFmtFprintfEmpty          84.6ns × (0.95,1.14)    85.7ns × (0.94,1.05)  ~ (p=0.521)
BenchmarkFmtFprintfString          320ns × (0.95,1.06)     283ns × (0.99,1.02)  -11.48% (p=0.000)
BenchmarkFmtFprintfInt             311ns × (0.98,1.03)     288ns × (0.99,1.02)  -7.26% (p=0.000)
BenchmarkFmtFprintfIntInt          554ns × (0.96,1.05)     478ns × (0.99,1.02)  -13.70% (p=0.000)
BenchmarkFmtFprintfPrefixedInt     434ns × (0.96,1.06)     393ns × (0.98,1.04)  -9.60% (p=0.000)
BenchmarkFmtFprintfFloat           620ns × (0.99,1.03)     584ns × (0.99,1.01)  -5.73% (p=0.000)
BenchmarkFmtManyArgs              2.19µs × (0.98,1.03)    1.94µs × (0.99,1.01)  -11.62% (p=0.000)
BenchmarkGobDecode                21.2ms × (0.97,1.06)    15.2ms × (0.99,1.01)  -28.17% (p=0.000)
BenchmarkGobEncode                18.1ms × (0.94,1.06)    11.8ms × (0.99,1.01)  -35.00% (p=0.000)
BenchmarkGzip                      650ms × (0.98,1.01)     649ms × (0.99,1.02)  ~ (p=0.802)
BenchmarkGunzip                    143ms × (1.00,1.01)     143ms × (1.00,1.01)  ~ (p=0.438)
BenchmarkHTTPClientServer          110µs × (0.98,1.04)     101µs × (0.98,1.02)  -8.79% (p=0.000)
BenchmarkJSONEncode               40.3ms × (0.97,1.03)    31.8ms × (0.98,1.03)  -20.92% (p=0.000)
BenchmarkJSONDecode                119ms × (0.97,1.02)     108ms × (0.99,1.02)  -9.15% (p=0.000)
BenchmarkMandelbrot200            6.03ms × (1.00,1.01)    6.03ms × (0.99,1.01)  ~ (p=0.750)
BenchmarkGoParse                  8.58ms × (0.89,1.10)    6.80ms × (1.00,1.00)  -20.71% (p=0.000)
BenchmarkRegexpMatchEasy0_32       162ns × (1.00,1.01)     162ns × (0.99,1.02)  ~ (p=0.131)
BenchmarkRegexpMatchEasy0_1K       540ns × (0.99,1.02)     559ns × (0.99,1.02)  +3.58% (p=0.000)
BenchmarkRegexpMatchEasy1_32       139ns × (0.98,1.04)     139ns × (1.00,1.00)  ~ (p=0.466)
BenchmarkRegexpMatchEasy1_1K       889ns × (0.99,1.01)     885ns × (0.99,1.01)  -0.50% (p=0.022)
BenchmarkRegexpMatchMedium_32      252ns × (0.99,1.02)     252ns × (0.99,1.01)  ~ (p=0.469)
BenchmarkRegexpMatchMedium_1K     72.9µs × (0.99,1.01)    73.6µs × (0.99,1.03)  ~ (p=0.168)
BenchmarkRegexpMatchHard_32       3.87µs × (1.00,1.01)    3.86µs × (1.00,1.00)  ~ (p=0.055)
BenchmarkRegexpMatchHard_1K        118µs × (0.99,1.01)     117µs × (0.99,1.00)  ~ (p=0.133)
BenchmarkRevcomp                   995ms × (0.94,1.10)     949ms × (0.99,1.01)  -4.64% (p=0.000)
BenchmarkTemplate                  141ms × (0.97,1.02)     127ms × (0.99,1.01)  -10.00% (p=0.000)
BenchmarkTimeParse                 641ns × (0.99,1.01)     623ns × (0.99,1.01)  -2.79% (p=0.000)
BenchmarkTimeFormat                729ns × (0.98,1.03)     679ns × (0.99,1.00)  -6.93% (p=0.000)

Change-Id: I839bd7356630d18377989a0748763414e15ed057
Reviewed-on: https://go-review.googlesource.com/9602Reviewed-by: default avatarAustin Clements <austin@google.com>
parent 4d0f3a1c
...@@ -161,10 +161,6 @@ func markroot(desc *parfor, i uint32) { ...@@ -161,10 +161,6 @@ func markroot(desc *parfor, i uint32) {
} }
} }
// Root aren't part of the heap, so don't count them toward
// marked heap bytes.
gcw.bytesMarked = 0
gcw.scanWork = 0
gcw.dispose() gcw.dispose()
} }
...@@ -314,8 +310,6 @@ func scanstack(gp *g) { ...@@ -314,8 +310,6 @@ func scanstack(gp *g) {
} }
gcw := &getg().m.p.ptr().gcw gcw := &getg().m.p.ptr().gcw
origBytesMarked := gcw.bytesMarked
origScanWork := gcw.scanWork
scanframe := func(frame *stkframe, unused unsafe.Pointer) bool { scanframe := func(frame *stkframe, unused unsafe.Pointer) bool {
// Pick up gcw as free variable so gentraceback and friends can // Pick up gcw as free variable so gentraceback and friends can
// keep the same signature. // keep the same signature.
...@@ -324,10 +318,6 @@ func scanstack(gp *g) { ...@@ -324,10 +318,6 @@ func scanstack(gp *g) {
} }
gentraceback(^uintptr(0), ^uintptr(0), 0, gp, 0, nil, 0x7fffffff, scanframe, nil, 0) gentraceback(^uintptr(0), ^uintptr(0), 0, gp, 0, nil, 0x7fffffff, scanframe, nil, 0)
tracebackdefers(gp, scanframe, nil) tracebackdefers(gp, scanframe, nil)
// Stacks aren't part of the heap, so don't count them toward
// marked heap bytes.
gcw.bytesMarked = origBytesMarked
gcw.scanWork = origScanWork
if gcphase == _GCmarktermination { if gcphase == _GCmarktermination {
gcw.dispose() gcw.dispose()
} }
...@@ -578,7 +568,6 @@ func scanblock(b0, n0 uintptr, ptrmask *uint8, gcw *gcWork) { ...@@ -578,7 +568,6 @@ func scanblock(b0, n0 uintptr, ptrmask *uint8, gcw *gcWork) {
} }
} }
gcw.bytesMarked += uint64(n)
gcw.scanWork += scanWork gcw.scanWork += scanWork
} }
......
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