From mboxrd@z Thu Jan 1 00:00:00 1970 From: Lucas Meneghel Rodrigues Subject: Re: just a dump Date: Thu, 28 May 2009 10:39:31 -0300 Message-ID: <1243517971.2976.1059.camel@localhost.localdomain> References: <4A09E620.3040300@xs4all.nl> <4A09F62A.8010203@xs4all.nl> <20090515144923.GA6304@amt.cnet> <4A0E7B81.6070203@xs4all.nl> <1242913886.12727.5.camel@localhost.localdomain> <4A1CEF05.6010203@xs4all.nl> Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit Cc: Marcelo Tosatti , kvm@vger.kernel.org To: Hans de Bruin Return-path: Received: from mx2.redhat.com ([66.187.237.31]:57586 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757682AbZE1Njc (ORCPT ); Thu, 28 May 2009 09:39:32 -0400 In-Reply-To: <4A1CEF05.6010203@xs4all.nl> Sender: kvm-owner@vger.kernel.org List-ID: On Wed, 2009-05-27 at 09:43 +0200, Hans de Bruin wrote: > > [09:09:47 INFO ] Test finished after 1 iterations. > Memory test passed. > [09:09:48 DEBUG] Running 'grep MemTotal /proc/meminfo' > [09:09:48 DEBUG] Running 'rpm -qa' > [09:09:49 INFO ] GOOD dma_memtest dma_memtest > timestamp=1243408189 localtime=May 27 09:09:49 completed > successfully > [09:09:49 DEBUG] Persistent state variable __group_level now set to 1 > [09:09:49 INFO ] END GOOD dma_memtest dma_memtest > timestamp=1243408189 localtime=May 27 09:09:49 > [09:09:49 DEBUG] Dropping caches > [09:09:49 DEBUG] Running 'sync' > [09:09:51 DEBUG] Running 'sync' > [09:09:51 DEBUG] Running 'echo 3 > /proc/sys/vm/drop_caches' > [09:09:52 DEBUG] Persistent state variable __group_level now set to 0 > [09:09:52 INFO ] END GOOD ---- ---- timestamp=1243408192 > localtime=May 27 09:09:52 > > Well that looks good. The web page talks about forcing the system to > swap. That never happend swap usage is still 0 bytes. I installed > autotest on the same lv (3 disk stripe) as the vmdisks. Interesting, about that I made some tests and just realized that in some cases both mine and the original shell implementation are failing on forcing the system to go to swap (the tests I made when the test was firstly implemented did manage to make the machines swap, but in conditions where the system had a significantly higher initial memory usage). I will work on a better heuristic to force swap. Thanks for pointing this out, -- Lucas Meneghel Rodrigues Software Engineer (QE) Red Hat - Emerging Technologies