Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 19 May 2006 09:03:07 +0100 (BST)
From:      Robert Watson <rwatson@FreeBSD.org>
To:        Vlad GALU <vladgalu@gmail.com>
Cc:        freebsd-performance@freebsd.org
Subject:   Re: (Another) simple benchmark
Message-ID:  <20060519090031.F49041@fledge.watson.org>
In-Reply-To: <79722fad0605182319o2eefa538i8505631f8802d5d@mail.gmail.com>
References:  <446CCE1C.1050200@fer.hr> <446CD873.9080903@stevehodgson.co.uk> <446CE6CE.50009@fer.hr> <BBF811FC-8BD3-4081-8922-50128C7C7E45@shire.net> <79722fad0605182319o2eefa538i8505631f8802d5d@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help

On Fri, 19 May 2006, Vlad GALU wrote:

> On 5/19/06, Chad Leigh -- Shire.Net LLC <chad@shire.net> wrote:
>> 
>> On May 18, 2006, at 3:27 PM, Ivan Voras wrote:
>> 
>> >
>> > Using lighttpd or ab on other host is not really applicable - I
>> > wasn't trying to configure the box for production, only ran the
>> > benchmarks out of curiosity. Apache *should* work ok out of the box
>> > on FreeBSD :)
>> > (btw. apache was installed from binary package)
>> 
>> You were not testing apache.  You were testing apache and ab.  It very well 
>> could be that ab is the culprit, not apache.  We'll never know unless you 
>> can retest with ab on another box.
>
> Still, the fact that a simple program, regardless of its nature, runs a lot 
> faster on Linux than it does on FreeBSD is a problem, isn't it ?

I don't think anyone is debating the simple output of the benchmark, what's 
being asked for is an exploration of the source of the problem.  By placing ab 
on a second machine with a static configuration taretting an apache box with a 
variable configuration, we can explore whether it's the cost of web serving 
that is having problems or the cost of running the benchmark and the web 
server that is having problems.  We can also more easily profile the behavior 
of the individual applications.  When it comes to figuring out the cause and 
properly understanding the benchmark results, there's a big difference between 
"ab runs 40% slower" and "apache runs 40% slower".

Robert N M Watson



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20060519090031.F49041>