Re: [squid-users] Benchmark of compiler options on Squid?

Henrik is correct.

Squid compiled -O and -O3 results in nearly immeasurably small
differences (around 3%--I wouldn't even call it statistically
significant), as does compiling for a specific compiler. The slowdowns
in Squid, it seems, are not of the 'tight loop' sort that compiler
optimizations can sometimes help.

Henrik Nordstrom wrote:

> I don't think the compiler optimizations will make much of a difference
> from Squid. The bottlenecks in Squid is mostly on other levels.
>
> Regards
> Henrik Nordström
> Squid Hacker
>
>
> Steve Snyder wrote:
>
>>Has anyone benchmarked various GCC compiler optimizations used when
>>building Squid?
>>
>>I'm building for a Pentium3 box, using the compiler included in RedHat's
>>v7.1 release. I understand that there's some environment-specific
>>variables (CPU L2 cache size, etc.), but I'm hoping that some industrious
>>person has tested differing compiler options when compiling for for the
>>i686 processor.
>>
>>Any info on this? Thanks.

                                   --
                      Joe Cooper <joe@swelltech.com>
                  Affordable Web Caching Proxy Appliances
                         http://www.swelltech.com
Received on Sat Sep 29 2001 - 10:15:20 MDT