From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from sog-mx-2.v43.ch3.sourceforge.com ([172.29.43.192] helo=mx.sourceforge.net) by sfs-ml-2.v29.ch3.sourceforge.com with esmtp (Exim 4.76) (envelope-from ) id 1URaTm-0004Jw-3v for ltp-list@lists.sourceforge.net; Mon, 15 Apr 2013 03:53:18 +0000 Received: from mx1.redhat.com ([209.132.183.28]) by sog-mx-2.v43.ch3.sourceforge.com with esmtp (Exim 4.76) id 1URaTi-0001tH-Fi for ltp-list@lists.sourceforge.net; Mon, 15 Apr 2013 03:53:18 +0000 Message-ID: <516B7911.7040403@redhat.com> Date: Mon, 15 Apr 2013 11:50:41 +0800 From: Zhouping Liu MIME-Version: 1.0 References: <3bc25be7511978a5ccb9faad218e397743d1820b.1365411883.git.zliu@redhat.com> <516B52DB.2000004@cn.fujitsu.com> <516B7077.1000001@redhat.com> <516B7420.5010002@cn.fujitsu.com> In-Reply-To: <516B7420.5010002@cn.fujitsu.com> Subject: Re: [LTP] [PATCH v2 1/3] mm/thp: new case thp04.c List-Id: Linux Test Project General Discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: ltp-list-bounces@lists.sourceforge.net To: gaowanlong@cn.fujitsu.com Cc: LTP List On 04/15/2013 11:29 AM, Wanlong Gao wrote: > On 04/15/2013 11:13 AM, Zhouping Liu wrote: >> depending on your system's memory info: >> >> free reports: >> total used free shared buffers cached >> Mem: 8025000 7563668 461332 0 730920 4891316 >> -/+ buffers/cache: 1941432 6083568 >> Swap: 4194300 16212 4178088 >> >> your system has 8Gb RAM and there's 460Mb memory left when you start to test thp04 serial cases. >> I guess the cases failed because of the low memory. >> >> can you re-test them on the system with enough memory? and provide the value of /proc/sys/vm/min_free_kbytes, >> I think 1Gb memory left is enough to test the new THP case. >> >> also I'm very confused why the above case didn't get any THPs, maybe there's some performance issues... > Yes, that's passed after my reboot. Thanks again for your tests :) the case needs most memory is 'thp0[4|5]_3 -n 1 -N 300', which require 300 huge pages(600Mb memory) at least, also there's some memory limitation, such as /proc/sys/vm/min_free_kbytes, so I think 1Gb free memory is enough to test the serial cases, it's better to give some kind comments when memory is low, what I can think of is to print out the MemFree when starting to test: e.g: memfree= read_meminfo("MemFree:"); tst_resm(TINFO, "The system has %ld memory left before starting", memfree); if (memfree < 1G) tst_resm(TINFO, "The system has low memory, which will cause the case fail"); I'll send v3 to include it. Thanks, Zhouping ------------------------------------------------------------------------------ Precog is a next-generation analytics platform capable of advanced analytics on semi-structured data. The platform includes APIs for building apps and a phenomenal toolset for data science. Developers can use our toolset for easy data analysis & visualization. Get a free account! http://www2.precog.com/precogplatform/slashdotnewsletter _______________________________________________ Ltp-list mailing list Ltp-list@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ltp-list