Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 10 Mar 2005 19:30:15 -0800
From:      ray@redshift.com
To:        Joseph Koshy <joseph.koshy@gmail.com>
Cc:        freebsd-performance@freebsd.org
Subject:   Re: performance modifications
Message-ID:  <3.0.1.32.20050310193015.00a7e908@pop.redshift.com>
In-Reply-To: <84dead7205031019235f37f5cc@mail.gmail.com>
References:  <3.0.1.32.20050310180051.00a7e908@pop.redshift.com> <3.0.1.32.20050310180051.00a7e908@pop.redshift.com>

next in thread | previous in thread | raw e-mail | index | archive | help
| > I'm wondering if anyone on the list has a good source for 
| > the major sysctl settings and/or kernel settings that can be 
| > modified in order to bring up the performance level on a 
| > FreeBSD 5.3 machine that is used with apache under heavy
| > load.
| 
| There is the tuning(7) manual page.

Yes, have read those from start to finish.  Just wondering if there are other
areas to look into that may not be covered there.
 
| There are better web servers than Apache for demanding loads;
| ones that used a non-forking, event-driven I/O model.  
| Aolserver and thttpd come to mind.

I tried thttpd a number of years ago, but due to its limited cgi support (at
least at the time) I didn't do too much with it.  It did seem fast, however.
 
| Yaoping Ruan and Vivek Pai from Princeton have reported 
| excellent results with their "Flash" [1] web server.  While
| many of their recommended changes to FreeBSD have been folded
| into the base source, I'm not sure how many popular web-servers
| are using these speedups.
| 
| [1] Making the "Box" Transparent: System Call Performance as a
|     First-class Result
|     Yaoping Ruan, Vivek Pai
|     http://www.cs.princeton.edu/~yruan/debox/debox.pdf

Okay, great, thanks.  I'll check into that area.  My biggest problem right now
is that PHP brings down the speed of everything.  I may have to go back to Perl
and use mod_perl or look into some other alternatives.  The main thing I wanted
to do was get the OS running at it's best, so the benchmarks were not being
affected by some area of FreeBSD.  

Anyway, thanks very much for the info!

Ray



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?3.0.1.32.20050310193015.00a7e908>