benchmark

[David Relson]

On 12 Feb 2004 01:44:37 -0500
Tom Anderson wrote:

> On Wed, 2004-02-11 at 19:10, David Relson wrote:
> > You indicate a problem but don't give much info about your
> > environment or what you're doing.  In order to fix anything I need
> > more info about what is (or might be) wrong.
> 
> model name      : AMD-K6(tm) 3D processor
> stepping        : 12
> cpu MHz         : 448.220
> cache size      : 64 KB
> 
> linux 2.2.16
> gcc 2.95.2

Oldish kernel.  Have you access to a newer environment?  Maybe you could
boot Knoppix (or another LiveCD environment) and get numbers from
that...

> This is average usage:
> 12:29am  up 138 days,  8:41,  4 users,  load average: 1.11, 1.28, 1.04
> 59 processes: 55 sleeping, 3 running, 0 zombie, 1 stopped
> CPU states:  9.4% user, 32.4% system,  0.0% nice, 58.0% idle
> Mem:  257644K av, 250872K used,   6772K free, 112248K shrd,  76348K
> buff Swap: 131536K av,  15540K used, 115996K free  122924K cached

Plenty of system ram - 256MB.  When bfproxy and bogofilter are running,
does top show unusual states for either?  I'd consider R and S to be
"normal" and D to be "unusual".  You might also want to run vmstat which
will show disk i/o.

> > How big is the mailbox you're registering?  How
> > big is your wordlist?  What other factors do you think relate to
> > the... You can expect to see a size reduction.  You may also see a
> > performance improvement.

Rereading your message I saw the "448 words, 1 messages" line, which
told me you were processing a single message rather than a multi-message
mailbox.

> Ok, I did the optimization, and this is the result of registering the
> same 53 emails via bfproxy both before and after:

...[snip]...

Sounds like database size isn't the issue.  You've explored that
thoroughly.

> Although your and my example systems are both around 500MHz, I notice
> yours is a PIII while mine is a K6.  Are there any Intel optimizations
> made in the code or make files?  I think we've essentially eliminated
> memory problems, right?

Bogofilter builds with "-O2".  You can edit src/Makefile to remove that
if wish.  That will increase user time a small amount.  However you're
seeing large amounts of system time.

Assuming you're building your own binaries, compiler options should be
appropriate for your CPU.  Given that I create the binary rpms on my
Mandrake 9.2 system and Mandrake is for i586 and up, the code _might_ be
not be optimal for your K6.  I don't know if that would explain the
ratio of user to system time.

Sorry, but that's all I know :-<

David