[distcc] speedup with >2 hosts
Dan Kegel
dank at kegel.com
Tue Apr 6 03:46:21 GMT 2004
SCHMID Stefan wrote:
> i'm using a system of five dual-CPU distcc-hosts for distributed
> compilation. with all my projects, one additional host is very useful
> but the third to fifth hardly contribute anything at all. moreover,
> there is quite some variation in the execution time although all hosts
> do nothing else besides compilation (maybe because of the sleeping times
> when hosts are locked?). it is therefore also hard to tell which
> -j-option is the best for a given number of hosts...
>
> all in all, with 5 hosts (10 cpu's) i hardly get any speedups greater
> than 2 (compared to one host, i.e. 2 cpu's). do you have an idea where i
> do something wrong?
>
> my test results (secs for execution) for two projects (see
> http://pool.cern.ch/ and http://cobra.web.cern.ch/cobra/)
Are all 5 hosts equal performance? What kind of systems are they?
What does your DISTCC_HOSTS list look like?
Looks like you're using a strange build system written
in Python called SCRAM. Are you quite sure that's not
the bottleneck? None of us, I suspect, have ever heard
of it.
Do check out the notes Benjamin Meyer just posted,
http://www.csh.rit.edu/~benjamin/articles/distcc.php
- Dan
--
My technical stuff: http://kegel.com
My politics: see http://www.misleader.org for examples of why I'm for regime change
More information about the distcc
mailing list