Re: [svnbench] Revision: 1447108 compiled Feb 18 2013, 00:21:45 on x86_64-unknown-linux-gnu

On Mon, 18 Feb 2013 00:55:07 +0000
neels_at_apache.org wrote:

> Charts of this data are available at
> http://svn-qavm.apache.org/charts/

Looking at

http://svn-qavm.apache.org/charts/compare_1.7.0_trunk@last12.svg

I notice that somewhere between r1439212 and r1441993, 'update' got a
lot slower. The dip is visible in evenly-spread and flat WCs, the very
deep WC test is not affected.

The slowness is consistent over the last three benchmarked revisions,
that's why I'm noticing it as a probable actual code inefficiency,
instead of just a freak test run.

I leave the investigation up to ... Bert? ;) We'll see, but I am too
darn busy, unfortunately. I could trigger a few bisecting benchmarks if
I'm asked, best with specific revision numbers.

Again the reminder that the benchmark shows only ra_local, so the
network can't be the cause of the slowdown.

~Neels