pprof: improve sampling for heap profiling

The current heap sampling introduces some bias that interferes
with unsampling, producing unexpected heap profiles.
The solution is to use a Poisson process to generate the
sampling points, using the formulas described at
https://en.wikipedia.org/wiki/Poisson_process

This fixes #12620

Change-Id: If2400809ed3c41de504dd6cff06be14e476ff96c
Reviewed-on: https://go-review.googlesource.com/14590
Reviewed-by: Keith Randall <khr@golang.org>
Reviewed-by: Minux Ma <minux@golang.org>
Run-TryBot: Minux Ma <minux@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
This commit is contained in:
Raul Silvera 2015-09-14 14:03:45 -07:00 committed by Minux Ma
parent 0357c38adf
commit 27ee719fb3
9 changed files with 361 additions and 28 deletions

View file

@ -69,16 +69,7 @@ func allocmcache() *mcache {
for i := 0; i < _NumSizeClasses; i++ {
c.alloc[i] = &emptymspan
}
// Set first allocation sample size.
rate := MemProfileRate
if rate > 0x3fffffff { // make 2*rate not overflow
rate = 0x3fffffff
}
if rate != 0 {
c.next_sample = int32(int(fastrand1()) % (2 * rate))
}
c.next_sample = nextSample()
return c
}