Return-Path: Delivered-To: apmail-directory-dev-archive@www.apache.org Received: (qmail 11939 invoked from network); 27 Mar 2007 14:56:34 -0000 Received: from hermes.apache.org (HELO mail.apache.org) (140.211.11.2) by minotaur.apache.org with SMTP; 27 Mar 2007 14:56:34 -0000 Received: (qmail 36736 invoked by uid 500); 27 Mar 2007 14:56:41 -0000 Delivered-To: apmail-directory-dev-archive@directory.apache.org Received: (qmail 36695 invoked by uid 500); 27 Mar 2007 14:56:41 -0000 Mailing-List: contact dev-help@directory.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: "Apache Directory Developers List" Delivered-To: mailing list dev@directory.apache.org Received: (qmail 36681 invoked by uid 99); 27 Mar 2007 14:56:41 -0000 Received: from herse.apache.org (HELO herse.apache.org) (140.211.11.133) by apache.org (qpsmtpd/0.29) with ESMTP; Tue, 27 Mar 2007 07:56:41 -0700 X-ASF-Spam-Status: No, hits=2.0 required=10.0 tests=HTML_MESSAGE,SPF_PASS X-Spam-Check-By: apache.org Received-SPF: pass (herse.apache.org: domain of akarasulu@gmail.com designates 66.249.82.232 as permitted sender) Received: from [66.249.82.232] (HELO wx-out-0506.google.com) (66.249.82.232) by apache.org (qpsmtpd/0.29) with ESMTP; Tue, 27 Mar 2007 07:56:32 -0700 Received: by wx-out-0506.google.com with SMTP id h31so2501975wxd for ; Tue, 27 Mar 2007 07:56:11 -0700 (PDT) DKIM-Signature: a=rsa-sha1; c=relaxed/relaxed; d=gmail.com; s=beta; h=domainkey-signature:received:received:message-id:date:from:sender:to:subject:in-reply-to:mime-version:content-type:references:x-google-sender-auth; b=KrT31Ij36ghuQQDVruT5yesOX863INCJdyxbFZ3hiirUanqWiyrcROaQ+E3wDq2cB1dBT5uXOtJB5sKTkz5J+J7AzmJOKOiEhRDKck1F3Z9Dkup/KVxL7d+ni21ckJJGsMSJKRujP1hXZSHOLCZpQfC8WqIxEgVURCDxOu60hls= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:sender:to:subject:in-reply-to:mime-version:content-type:references:x-google-sender-auth; b=AaMp9OYnlCvdwkGELD6mv0qrTofwlIdmFE+DnBk1Me3r27NslK1MrydtqkE2Q2TTHm7Q0O/64/BP9MyWYQi5+o8vkYf23vSRrLlHEUn0KMwIM9S9aV1In5uJDvn8SpVLkM2FQmusi33/ChyqkftjXoTmRoghqSlZ7Fn9k1/fFIo= Received: by 10.70.90.12 with SMTP id n12mr12948483wxb.1175007371527; Tue, 27 Mar 2007 07:56:11 -0700 (PDT) Received: by 10.70.78.18 with HTTP; Tue, 27 Mar 2007 07:56:11 -0700 (PDT) Message-ID: Date: Tue, 27 Mar 2007 10:56:11 -0400 From: "Alex Karasulu" Sender: akarasulu@gmail.com To: "Apache Directory Developers List" , elecharny@iktek.com Subject: Re: Benchmarks feedback In-Reply-To: MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----=_Part_3597_5272222.1175007371473" References: <460832A9.10806@gmail.com> X-Google-Sender-Auth: 56b3ff6cb386a0b8 X-Virus-Checked: Checked by ClamAV on apache.org ------=_Part_3597_5272222.1175007371473 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: quoted-printable Content-Disposition: inline I think we need to use load injectors and SLAMD with this thing. Really having the clients on the same machine is causing issues. I highly recommend setting up some other machines as client injectors. I can do this with some machines. Also Emmanuel we need to use SLAMD instead of inventing our own means to measure performance. The SUN guys really put a lot of work into SLAMD and we should use it. Perhaps we can build our own custom tests if need be. SLAMD should be the default tool we use otherwise the measurments and techniques used are questionable. If we use matt's machine as the server I can setup several machines on the internet to be used as the load injectors. Yes this is a bit crazy across the open internet but if we can generate enough load with a few machines across several sites we should be able to peak the server. Alex On 3/27/07, Emmanuel Lecharny wrote: > > Hi Matt, > > I wasn't sure you subscribed, sorry for the duplicated mails :( > > > On 3/27/07, Matt Hogstrom < matt@hogstrom.org> wrote: > > > > I subscribed to your list so you won't have to copy me. > > > > I'd do a couple of things. The system is Hyperthreaded so you have > > "16" CPUs. I'll reboot the system and go back to 8 real cores just > > to make sure hyperthreading isn't a cause. I'll do that tonight if > > no one is on the system. > > > Ok, np. I don't exactly know what 'tonite' means in UTC, FYI, I'm UTC + 2= . > (this mail has been sent at 09h05UTC) > I'm not sure that HyperThreading could be the cause of bad performance I'= m > having... > > > Next, I've used the IBM VM for this kind of analysis as it has a Java > > Lock monitor built in that will help to identify hot locks that might > > be causing the scaling problem. > > > I will install IBM JVM today. I have tested the server with IBM, SUN and > BEA jvms last year, and it was my intention to do so. > > > The next thing we can do is I have a hardware profiler on the system > > that is similar to VTune that is most excellent at tracking CPU, time > > in method, etc. I need to recompile the kernel so this will take a > > few days. > > > Oh, that would be great ! I feel like been totally blind when doing perf > tests, just guessing about what could be the bottlenecks... > > > So if you want to take this baby for another spin around the block, > > let me know. I'll get some instructions on setting up the lock monitor= . > > > Yeah, sure. I'm working full time on ADS for a little while, so anytime > you want will be ok for me. > > > Nice to know my basement is getting warmed for good reason :) > > > yeah, I'm not sure it helps figth against global warming...At least, it's > not using gazoline to run ! > > > Matt > > > > -- > Cordialement, > Emmanuel L=E9charny > www.iktek.com ------=_Part_3597_5272222.1175007371473 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Content-Disposition: inline
I think we need to use load injectors and SLAMD with this thing. = Really having the clients on the same machine
is causing issues.  I highly recommend setting up some other mach= ines as client injectors.  I can do this with
some machines.
 
Also Emmanuel we need to use SLAMD instead of inventing our own means = to measure performance.  The SUN
guys really put a lot of work into SLAMD and we should use it.  P= erhaps we can build our own custom tests if need
be.  SLAMD should be the default tool we use otherwise the measur= ments and techniques used are questionable.
 
If we use matt's machine as the server I can setup several machine= s on the internet to be used as the load
injectors.  Yes this is a bit crazy across the open internet but = if we can generate enough load with a few
machines across several sites we should be able to peak the server.
Alex
 
On 3/27/07, = Emmanuel Lecharny <elecharny@= gmail.com> wrote:
Hi Matt,

I wasn't sur= e you subscribed, sorry for the duplicated mails :(


On 3/27/07, Matt Hogstrom < matt@hogstrom.org > wrote:=20
I subscribed to your= list so you won't have to copy me.

I'd do a couple of thin= gs.  The system is Hyperthreaded so you have
"16" CPUs.  I'll reboot the system and go back = to 8 real cores just
to make sure hyperthreading isn't a cause. = ; I'll do that tonight if
no one is on the system.

Ok, np. I don't exactly know what 'tonite' means in UT= C, FYI, I'm UTC + 2. (this mail has been sent at 09h05UTC)
I'm n= ot sure that HyperThreading could be the cause of bad performance I'm h= aving...=20
 

Next, I've used = the IBM VM for this kind of analysis as it has a Java
Lock monitor built= in that will help to identify hot locks that might=20
be causing the scaling problem.

I will install IBM JVM today. I have tested the server with IBM, S= UN and BEA jvms last year, and it was my intention to do so.
 
The next thing we ca= n do is I have a hardware profiler on the system
that is similar to VTun= e that is most excellent at tracking CPU, time
in method, etc.  I need to recompile the kernel so this will = take a
few days.

Oh, that would be great ! I feel like been totally blind when doin= g perf tests, just guessing about what could be the bottlenecks...
&nbs= p;

So if you want to ta= ke this baby for another spin around the block,
let me know.  = I'll get some instructions on setting up the lock monitor.

Yeah, sure. I'm working full time on ADS for a little while, s= o anytime you want will be ok for me.
 
Nice to know my base= ment is getting warmed for good reason :)

yeah, I'm not sure it helps figth against global warming...At = least, it's not using gazoline to run !
 

Matt

 
--
Cordialement,
Emmanuel L=E9charny
<= a onclick=3D"return top.js.OpenExtLink(window,event,this)" href=3D"http://w= ww.iktek.com/" target=3D"_blank">www.iktek.com

------=_Part_3597_5272222.1175007371473--