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-8548 Lustre <p>I attached the kern log that captured the OOM that happened while running mdtest with the directory striped across 16 MDTs.</p> Power8 clients running 2.8.56 and back end servers running the same. This OOM happened while running mdtest with the directory striped across 16 MDTs. LU-8548

MDS crash during DNE2 testing with Lustre 2.9

Bug Major Closed Cannot Reproduce Lai Siyao James A Simmons Fri, 26 Aug 2016 01:08:58 +0000 Fri, 26 Aug 2016 21:48:43 +0000 Fri, 26 Aug 2016 21:48:43 +0000 Lustre 2.9.0 0 3 <p>Hi Lai,</p> <p>Could you please help to investigate this issue?</p> <p>Thanks.<br/> Joe</p> <p>The backtrace shows it's a soft lockup in mdt_lock_root_xattr()-&gt;mdt_remote_object_lock(), which is introduced in <a href="https://jira.whamcloud.com/browse/LU-7660" title="FS default striping settings only honored on MDT 0" class="issue-link" data-issue-key="LU-7660"><del>LU-7660</del></a>, however this root XATTR lock is not held (i.e., decref-ed right after taken), I don't see why it will cause soft lockup. Could you get backtraces of the MDS where the soft lockup occurs? and are all MDT locked up?</p> <p>BTW, do you think it's happens with Power8 clients only?</p> <p>I updated the server side up to the latest master since it was over a month old and when I attempted to reproduce this problem it went away. So it looks like a version mismatch in version of pre-2.9 caused this issue.</p> Development Rank 1|hzym4f: Rank (Obsolete) 9223372036854775807 Severity