Mailing-List: contact dev-help@httpd.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@httpd.apache.org
Mime-Version: 1.0 (Apple Message framework v609)
In-Reply-To: <4002CF3E.70503@apache.org>
References: <sffc1c76.034@prv-mail20.provo.novell.com>
 <4002CF3E.70503@apache.org>
Content-Type: text/plain; charset=US-ASCII; format=flowed
Message-Id: <E23EAEEA-5222-11D8-8133-000A95891440@slamb.org>
Content-Transfer-Encoding: 7bit
From: Scott Lamb <slamb@slamb.org>
Subject: Re: 2.0.48 worker mpm on RH3 NPTL results
Date: Thu, 29 Jan 2004 00:17:58 -0600
To: dev@httpd.apache.org

On Jan 12, 2004, at 10:45 AM, gregames@apache.org wrote:
> What did you use for ThreadsPerChild?  The default?  It's 25.  The 
> reason I ask is I did some scalability measurements maybe a year ago 
> and saw a lot of CPU usage in linuxthreads with a high number (maybe 
> 1000) for ThreadsPerChild.  It was in some pthread mutex unlock 
> function, doing a serial search for the highest priority thread to 
> wake up.  This is pointless in our case because all the worker threads 
> are the same priority.  I'm hoping that this problem is fixed in the 
> new pthread library, but haven't verified it.

NPTL, for better or for worse, does not honor priorities. Quoting from 
<http://people.redhat.com/drepper/nptl-design.pdf>:

Realtime support is mostly missing from the library implementation. The 
system calls to select scheduling parameters are available but they 
have not effects. The reason for this is that large parts of the kernel 
do not follow the rules for realtime scheduling. Waking one of the 
threads waiting for a futex is not done by looking at the priorities of 
the waiters.

Scott Lamb