Mailing-List: contact users-help@httpd.apache.org; run by ezmlm
Precedence: bulk
Reply-To: users@httpd.apache.org
Date: Wed, 19 May 2004 11:52:40 +0100 (BST)
From: Nick Kew <nick@webthing.com>
To: users@httpd.apache.org
In-Reply-To: <1084956896.3370.5.camel@daubian>
Message-ID: <Pine.LNX.4.53.0405191145310.2810@hugin.webthing.com>
References: <20040519083334.CB46D46BA@midgard.webthing.com>
 <Pine.LNX.4.53.0405190943150.2446@hugin.webthing.com>
 <1084956896.3370.5.camel@daubian>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=ISO-8859-1
Content-Transfer-Encoding: QUOTED-PRINTABLE
Subject: Re: [users@httpd] High load average problem

On Wed, 19 May 2004, Aur=E9lien DEHAY wrote:

> Furthermore, he is already using prefork env: he has a RH 9, then with
> the NPTL patch applied, and if he is using the worker model, he wouldn't
> see all that httpd but only a few.

I was guessing based on seeing several listed "httpd"s of exactly
the same size.  That's typical of linux's ps listing different
threads "as if" they are processes under kernel 2.4.

They're also huge - presumably due to something running locally and
perhaps leaking memory badly - and in state D.  The latter could
be down to a number of causes: heavy thrashing (bloated processes)
or threading trouble and deadlock.  I'd be looking at what's causing
the httpd size to spiral out of control.  Especially if it's prefork,
so that no process is handling more than one client!

--=20
Nick Kew

---------------------------------------------------------------------
The official User-To-User support forum of the Apache HTTP Server Project.
See <URL:http://httpd.apache.org/userslist.html> for more info.
To unsubscribe, e-mail: users-unsubscribe@httpd.apache.org
   "   from the digest: users-digest-unsubscribe@httpd.apache.org
For additional commands, e-mail: users-help@httpd.apache.org