[rrd-developers] performance under 1.3 beta

[Dave Plonka]

Hi Richard,

On Thu, Nov 15, 2007 at 01:39:51PM -0500, Richard A Steenbergen wrote:
> So, I think you guys might want to do some performance tests on a wider 
> range of platforms before 1.3 is released. I just tried running a few 
> comparison tests between 1.3 (with various settings) and some older 1.2 
> rrdupdate code, and got significantly worse performance on the newer 
> "better" code.
<snip>
> Haven't had free time to tinker with turning off some of the prodigious 
> madvise()'s or anything else, but clearly on some platforms this is not 
> working out so well.

I'm curious to see how 1.2.24 or 1.2.25 performs if your platform
has a working posix_fadvise(RANDOM) call.  Tobi cut rrdtool-1.2.25
to coincide with a LISA talk, and that has the fadvise performance
optimization but without all the mmap changes, thus is a useful point
of comparison.

This is pretty much the configuration I'm having
good performance with as reported in this paper:
   http://www.usenix.org/events/lisa07/tech/plonka.html

Dave

-- 
plonka at doit.wisc.edu  http://net.doit.wisc.edu/~plonka/  Madison, WI