Re: First bench of 2.4-HEAD branch...

Henrik Nordstrom wrote:
>
> Adrian Chadd wrote:
>
> > Have you thought about trying diskd under Linux?
>
> I have tried it in my limited testing environment, but it wasn't very
> sucessful. When stressed it aborted with an assertion failure in
> storeDiskdShmGet(). Unfortunately I have not had the time to dig any
> deeper into this yet, but it looks like a fairly generic diskd problem.
>
> /Henrik

I tried it in the DEVEL2 release but could only get DiskD to segfault.
Will try again periodically on HEAD.

I've finished up the four runs I planned for this configuration of
HEAD. Out of curiosity I'm doing one more at an even lower req rate,
after that I'll start on other configurations in a couple of hours. The
first four runs are posted on my site:

http://www.swelltech.com/pengies/joe/index.html#benchmarks

(The Squid-CVS runs are at the bottom of the page.)

The slower runs proved to allow higher hit ratios, but even as slow as
40 reqs/sec the hit ratio is well below ideal. I'll try with more
threads later. Adrian hinted that it might allow more reqs before
starting to drop the swaps to disk.

Questions, comments, and requests, are always welcome.
                                 --
                    Joe Cooper <joe@swelltech.com>
                Affordable Web Caching Proxy Appliances
                       http://www.swelltech.com
Received on Sun Jun 11 2000 - 08:36:44 MDT