https://jira.whamcloud.com This file is an XML representation of an issue en-us 9.4.14 940014 05-12-2023 https://jira.whamcloud.com/browse/LU-89 Lustre <p>INTERCONNECT=tcp<br/> SERVERIMAGE=/lol/var/cache/cfs/PACKAGE/rpm/lustre/b1_8/18a-012311/sles11sp1/x86_64<br/> CLIENTIMAGE=/lol/var/cache/cfs/PACKAGE/rpm/lustre/b1_8/18a-012311/sles11sp1/i686</p> <p>racer</p> <p>sfire7 (client) syslog:<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.048214&#93;</span> sort invoked oom-killer: gfp_mask=0x201da, order=0,<br/> oom_adj=0<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.055140&#93;</span> sort cpuset=/ mems_allowed=0<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.059162&#93;</span> Pid: 8257, comm: sort Tainted: G N <br/> 2.6.32.19-0.2_lustre.20110123155700-default #1<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.068726&#93;</span> Call Trace:<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.071253&#93;</span> <span class="error">&#91;&lt;c02069e1&gt;&#93;</span> try_stack_unwind+0x1b1/0x1f0<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.076528&#93;</span> <span class="error">&#91;&lt;c02059bf&gt;&#93;</span> dump_trace+0x3f/0xe0<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.081055&#93;</span> <span class="error">&#91;&lt;c02065eb&gt;&#93;</span> show_trace_log_lvl+0x4b/0x60<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.086270&#93;</span> <span class="error">&#91;&lt;c0206618&gt;&#93;</span> show_trace+0x18/0x20<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.090778&#93;</span> <span class="error">&#91;&lt;c05216d9&gt;&#93;</span> dump_stack+0x6d/0x74<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.095338&#93;</span> <span class="error">&#91;&lt;c0299f7f&gt;&#93;</span> oom_kill_process+0x9f/0x2b0<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.100532&#93;</span> <span class="error">&#91;&lt;c029a63e&gt;&#93;</span> __out_of_memory+0x4e/0xb0<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.105550&#93;</span> <span class="error">&#91;&lt;c029a6f4&gt;&#93;</span> out_of_memory+0x54/0xb0<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.110433&#93;</span> <span class="error">&#91;&lt;c029d567&gt;&#93;</span> __alloc_pages_slowpath+0x3a7/0x470<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.116272&#93;</span> <span class="error">&#91;&lt;c029d748&gt;&#93;</span> __alloc_pages_nodemask+0x118/0x120<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.122211&#93;</span> <span class="error">&#91;&lt;c029fa2d&gt;&#93;</span> __do_page_cache_readahead+0xdd/0x1f0<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.128206&#93;</span> <span class="error">&#91;&lt;c029fb67&gt;&#93;</span> ra_submit+0x27/0x40<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.132629&#93;</span> <span class="error">&#91;&lt;c0298242&gt;&#93;</span> filemap_fault+0x382/0x390<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.137586&#93;</span> <span class="error">&#91;&lt;c02af7e6&gt;&#93;</span> __do_fault+0x46/0x470<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.142181&#93;</span> <span class="error">&#91;&lt;c02b09a4&gt;&#93;</span> handle_mm_fault+0x154/0x3d0<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.147295&#93;</span> <span class="error">&#91;&lt;c0526164&gt;&#93;</span> do_page_fault+0x174/0x370<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.152241&#93;</span> <span class="error">&#91;&lt;c0524126&gt;&#93;</span> error_code+0x66/0x70<br/> Jan 23 15:43:05 sfire7 kernel: <span class="error">&#91;16012.156754&#93;</span> <span class="error">&#91;&lt;b7791ec5&gt;&#93;</span> 0xb7791ec5</p> <p><a href="http://lts-head.central.sun.com:8080/display_report.pl?report_id=515817" class="external-link" target="_blank" rel="nofollow noopener">http://lts-head.central.sun.com:8080/display_report.pl?report_id=515817</a></p> LU-89

racer: Oom (both i686 and x86_64)

Bug Major Resolved Fixed Lai Siyao Zhenyu Xu Fri, 18 Feb 2011 19:18:08 +0000 Tue, 28 Jun 2011 15:01:43 +0000 Mon, 14 Mar 2011 08:13:35 +0000 Lustre 1.8.6 Lustre 1.8.6 0 1 <p>According to previous test results this OOM can be triggered in different places, so 'racer' may not be the cause. And I've run 'racer' test several rounds, it looks okay.</p> <p>It seems acceptance test may not trigger this OOM always, I will run full acceptance and try to narrow down the test which triggers it. This will take some time.</p> <p>How much memory do you have on the client side? AFAIK, this problem only shows up in low memory condition (1GB of RAM). The problem is that it used to pass, so i would like to understand why it is failing now.</p> <p>Hmm, I test with 1GB memory, and client and servers on the same host. I am also wondering how and why it will fail, and I've told Bobijam and Niu, if they meet with this OOM in their test, they will let me know.</p> <p>Elena thinks that this is a problem in the racer test. Please check the bugzilla ticket.</p> <p>This is believed be a test script problem: 'racer' is called recursively, and uses up all memory eventually. </p> <p>Peter, can we close this?</p> <p>As per bz this was fixed by correcting the test in 24451</p> Bugzilla ID 24421.0 Development Rank 1|hzw3c7: Rank (Obsolete) 10625 Severity