Return-Path: <designrw@bellatlantic.net>
Mailing-List: contact tomcat-dev-help@jakarta.apache.org; run by ezmlm
Delivered-To: mailing list tomcat-dev@jakarta.apache.org
Received: (qmail 10540 invoked from network); 2 Mar 2001 18:59:30 -0000
Received: from smtp4vepub.gte.net (HELO smtp4ve.mailsrvcs.net) (206.46.170.25)
  by h31.sny.collab.net with SMTP; 2 Mar 2001 18:59:30 -0000
Received: from alfred.bear.com (adsl-141-151-136-122.bellatlantic.net
 [141.151.136.122])
	by smtp4ve.mailsrvcs.net (8.9.1/8.9.1) with SMTP id TAA6279913
	for <tomcat-dev@jakarta.apache.org>; Fri, 2 Mar 2001 19:05:56 GMT
From: Roy Wilson <designrw@bellatlantic.net>
Date: Fri, 02 Mar 2001 19:00:50 GMT
Message-ID: <20010302.19005000@alfred.bear.com>
Subject: RE: Just another Benchmark
To: tomcat-dev@jakarta.apache.org
In-Reply-To: <NEBBJGMDILNMFBIJAMCPGEOACBAA.ron.pitts@claripoint.com>
References: <NEBBJGMDILNMFBIJAMCPGEOACBAA.ron.pitts@claripoint.com>
X-Mailer: Mozilla/3.0 (compatible; StarOffice/5.2;Linux)
X-Priority: 3 (Normal)
MIME-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable
X-Spam-Rating: h31.sny.collab.net 1.6.2 0/1000/N

Hi,

See below.

Roy

<snip>



> -----Original Message-----
> From: Thomas Bezdicek [mailto:t.bezdicek@lgsoft.at]
> Sent: 02 March 2001 09:50
> To: tomcat-dev@jakarta.apache.org
> Subject: Just another Benchmark


> Hi,

> we tried the apachebench on our solaris system, to check out
> differences between architectures and thereby we found a quite
> interesting behaviour.

> When serving a static page, apache uses the whole machine
> resources while tomcat isn't (CPU usage 100% to 20%) and for
> maybe this reason isn't serving at the same speed as apache.
> Is there a limit somewhere in the java net or in tomcat?

Just curious: you say "CPU usage 100%". I guess what I'm asking is=20
whether you assume that Apache keeps the CPU busy 100% of the time based=
=20
on the ratio of the throughputs (requests per second) or whether you=20
measured CPU busy using sar (or something like it). FWIW, in measurement=
s=20
of Apache I've done, I've rarely seen CPU utilization above about 75%.

Roy