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-15695 Lustre <p>We saw this OSS LBUG yesterday following the use of <tt>lfs ladvise</tt>. Both 2.12.8 -based clients and servers (we have a <a href="https://github.com/stanford-rc/lustre/commits/b2_12_8_oak_server" class="external-link" target="_blank" rel="nofollow noopener">few patches</a> on top).</p> <p>The command that triggered this from a client as root was:</p> <div class="preformatted panel" style="border-width: 1px;"><div class="preformattedContent panelContent"> <pre>touch testladvise lfs ladvise -a dontneed -s 0 -e 1048576000 testladvise </pre> </div></div> <p>Result on the OSS:</p> <div class="preformatted panel" style="border-width: 1px;"><div class="preformattedContent panelContent"> <pre>Mar 24 18:53:55 oak-io7-s1 kernel: LustreError: 3782:0:(dt_object.h:2507:dt_ladvise()) ASSERTION( dt-&gt;do_body_ops-&gt;dbo_ladvise ) failed:  Mar 24 18:53:55 oak-io7-s1 kernel: LustreError: 3782:0:(dt_object.h:2507:dt_ladvise()) LBUG Mar 24 18:53:55 oak-io7-s1 kernel: Pid: 3782, comm: ll_ost_io00_111 3.10.0-1160.6.1.el7_lustre.pl1.x86_64 #1 SMP Mon Dec 14 21:25:04 PST 2020 Mar 24 18:53:55 oak-io7-s1 kernel: Call Trace: Mar 24 18:53:55 oak-io7-s1 kernel:  [&lt;ffffffffc085c7cc&gt;] libcfs_call_trace+0x8c/0xc0 [libcfs] Mar 24 18:53:55 oak-io7-s1 kernel:  [&lt;ffffffffc085c87c&gt;] lbug_with_loc+0x4c/0xa0 [libcfs] Mar 24 18:53:55 oak-io7-s1 kernel:  [&lt;ffffffffc15e12ce&gt;] ofd_ladvise_hdl+0xdee/0xf10 [ofd] Mar 24 18:53:55 oak-io7-s1 kernel:  [&lt;ffffffffc1235f1a&gt;] tgt_request_handle+0xada/0x1570 [ptlrpc] Mar 24 18:53:55 oak-io7-s1 kernel:  [&lt;ffffffffc11dabfb&gt;] ptlrpc_server_handle_request+0x24b/0xab0 [ptlrpc] Mar 24 18:53:55 oak-io7-s1 kernel:  [&lt;ffffffffc11de564&gt;] ptlrpc_main+0xb34/0x1470 [ptlrpc] Mar 24 18:53:55 oak-io7-s1 kernel:  [&lt;ffffffffac0c5c21&gt;] kthread+0xd1/0xe0 Mar 24 18:53:55 oak-io7-s1 kernel:  [&lt;ffffffffac794ddd&gt;] ret_from_fork_nospec_begin+0x7/0x21 Mar 24 18:53:55 oak-io7-s1 kernel:  [&lt;ffffffffffffffff&gt;] 0xffffffffffffffff </pre> </div></div> <p>However, I can't seem to reproduce on a test system. It is not time sensitive for us. Just wanted to open a ticket as I didn't find this LBUG on the Jira.</p> CentOS 7.9 LU-15695

dt_ladvise(): ASSERTION( dt->do_body_ops->dbo_ladvise )

Bug Minor Resolved Duplicate Peter Jones Stephane Thiell Fri, 25 Mar 2022 15:49:48 +0000 Tue, 19 Dec 2023 20:17:31 +0000 Tue, 19 Dec 2023 04:07:56 +0000 Lustre 2.12.8 Lustre 2.16.0 0 6 <p>Looking at the code in 2.12.8 (and master) I see that "<tt>.dbo_ladvise = osd_ladvise</tt>" is set in the object methods, so this assertion is very strange. I was likewise unable to reproduce this issue on my test system, even with a directory or symlink, or with a PFL file that had an uninstantiated layout in the "advice" range.</p> <p>There is <a href="https://jira.whamcloud.com/browse/LU-15139" title="sanity test_160h: dt_record_write() ASSERTION( dt-&gt;do_body_ops-&gt;dbo_write ) failed" class="issue-link" data-issue-key="LU-15139"><del>LU-15139</del></a>, which is a similar <tt>LASSERT()</tt> for missing object operations that is unexplained so far.</p> <p>PS: you should fork your lustre github repo from <a href="https://github.com/lustre/lustre-release" class="external-link" target="_blank" rel="nofollow noopener">lustre/lustre-release</a>, which is the clone that I maintain from the whamcloud.com repo.</p> <p>Interesting, ok I'm now watching <a href="https://jira.whamcloud.com/browse/LU-15139" title="sanity test_160h: dt_record_write() ASSERTION( dt-&gt;do_body_ops-&gt;dbo_write ) failed" class="issue-link" data-issue-key="LU-15139"><del>LU-15139</del></a>.</p> <p>And very cool, I didn't know about the clone repo on Github, this is going to be useful, thanks!</p> <p> </p> <p>Wouldn't be possible to ignore ladvise requests if the object is not fully initialised? it is an optional hint, not a real read request as in <a href="https://jira.whamcloud.com/browse/LU-15139" title="sanity test_160h: dt_record_write() ASSERTION( dt-&gt;do_body_ops-&gt;dbo_write ) failed" class="issue-link" data-issue-key="LU-15139"><del>LU-15139</del></a>.</p> <p>Zam, I agree. The ladvise request could be dropped in this case, rather than taking the system down. </p> <p>This should be fixed with <a href="https://review.whamcloud.com/c/fs/lustre-release/+/48080" class="external-link" target="_blank" rel="nofollow noopener">https://review.whamcloud.com/c/fs/lustre-release/+/48080</a></p> <p><a href="https://jira.whamcloud.com/browse/LU-16057" title="OBD_MD_FLGROUP not set for ladvise rpc" class="issue-link" data-issue-key="LU-16057"><del>LU-16057</del></a> obdclass: set OBD_MD_FLGROUP for ladvise RPC</p> <p><del>"Andriy Skulysh &lt;andriy.skulysh@hpe.com&gt;" uploaded a new patch:</del> <a href="https://review.whamcloud.com/c/fs/lustre-release/+/53161" class="external-link" target="_blank" rel="nofollow noopener">https://review.whamcloud.com/c/fs/lustre-release/+/53161</a><br/> <del>Subject: <a href="https://jira.whamcloud.com/browse/LU-15695" title="dt_ladvise(): ASSERTION( dt-&gt;do_body_ops-&gt;dbo_ladvise )" class="issue-link" data-issue-key="LU-15695"><del>LU-15695</del></a> osd: dt_ladvise(): ASSERTION( dt</del>&gt;do_body_ops-&gt;dbo_ladvise)-<br/> <del>Project: fs/lustre-release</del><br/> <del>Branch: master</del><br/> <del>Current Patch Set: 1</del><br/> <del>Commit: e2c5a0faaa6e2405e27575935fc8a96b8510bf8c</del></p> <p>The <a href="https://jira.whamcloud.com/browse/LU-16057" title="OBD_MD_FLGROUP not set for ladvise rpc" class="issue-link" data-issue-key="LU-16057"><del>LU-16057</del></a> patch was included in 2.15.53.</p> Cloners Related LU-15139 LU-16057 Development Rank 1|i02ls7: Rank (Obsolete) 9223372036854775807 Severity