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-17 Lustre <p>While testing iozone, a client hit this LBUG:</p> <p>Nov 18 15:43:53 psana0107 kernel: LustreError: 28278:0:(socklnd_cb.c:550:ksocknal_process_transmit()) ASSERTION(rc &lt; 0) failed<br/> Nov 18 15:43:53 psana0107 kernel: LustreError: 28278:0:(socklnd_cb.c:550:ksocknal_process_transmit()) LBUG<br/> Nov 18 15:43:53 psana0107 kernel: Pid: 28278, comm: socknal_sd01<br/> Nov 18 15:43:53 psana0107 kernel: <br/> Nov 18 15:43:53 psana0107 kernel: Call Trace:<br/> Nov 18 15:43:53 psana0107 kernel: <span class="error">&#91;&lt;ffffffff884b56a1&gt;&#93;</span> libcfs_debug_dumpstack+0x51/0x60 <span class="error">&#91;libcfs&#93;</span><br/> Nov 18 15:43:53 psana0107 kernel: <span class="error">&#91;&lt;ffffffff884b5bda&gt;&#93;</span> lbug_with_loc+0x7a/0xd0 <span class="error">&#91;libcfs&#93;</span><br/> Nov 18 15:43:53 psana0107 kernel: <span class="error">&#91;&lt;ffffffff884bdf40&gt;&#93;</span> tracefile_init+0x0/0x110 <span class="error">&#91;libcfs&#93;</span><br/> Nov 18 15:43:53 psana0107 kernel: <span class="error">&#91;&lt;ffffffff886a582a&gt;&#93;</span> ksocknal_process_transmit+0x33a/0x640 <span class="error">&#91;ksocklnd&#93;</span><br/> Nov 18 15:43:53 psana0107 kernel: <span class="error">&#91;&lt;ffffffff886a75cb&gt;&#93;</span> ksocknal_scheduler+0x38b/0x640 <span class="error">&#91;ksocklnd&#93;</span><br/> Nov 18 15:43:53 psana0107 kernel: <span class="error">&#91;&lt;ffffffff800a0abe&gt;&#93;</span> autoremove_wake_function+0x0/0x2e<br/> Nov 18 15:43:53 psana0107 kernel: <span class="error">&#91;&lt;ffffffff8005dfb1&gt;&#93;</span> child_rip+0xa/0x11<br/> Nov 18 15:43:53 psana0107 kernel: <span class="error">&#91;&lt;ffffffff886a7240&gt;&#93;</span> ksocknal_scheduler+0x0/0x640 <span class="error">&#91;ksocklnd&#93;</span><br/> Nov 18 15:43:53 psana0107 kernel: <span class="error">&#91;&lt;ffffffff8005dfa7&gt;&#93;</span> child_rip+0x0/0x11</p> <p>Liang Zhen posted this patch in <a href="https://jira.whamcloud.com/browse/LU-15" title="strange slow IO messages and bad performance " class="issue-link" data-issue-key="LU-15"><del>LU-15</del></a> originally:<br/> <a href="http://review.whamcloud.com/#change,127" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#change,127</a></p> <p>This bug is to track work on that.</p> LU-17

LBUG in ksocklnd

Bug Minor Resolved Fixed Liang Zhen Kit Westneat Mon, 22 Nov 2010 07:41:06 +0000 Thu, 3 Feb 2011 15:12:13 +0000 Thu, 3 Feb 2011 15:12:13 +0000 0 1 <p>Thanks Kit. I assigned to Liang as he is working on this. </p> <p>Liang, please post the patch to a new bugzilla bug and request an inspection from Isaac.</p> <p>Cross referencing Liang's comment in bug <a href="https://jira.whamcloud.com/browse/LU-15" title="strange slow IO messages and bad performance " class="issue-link" data-issue-key="LU-15"><del>LU-15</del></a>, which Kit opened this <a href="https://jira.whamcloud.com/browse/LU-17" title="LBUG in ksocklnd" class="issue-link" data-issue-key="LU-17"><del>LU-17</del></a> bug up for:</p> <p>Liang Zhen added a comment - 18/Nov/10 8:06 PM<br/> I've posted patch on <a href="http://review.whamcloud.com/#change,127" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#change,127</a><br/> (description of the patch should be "fix contention on ksock_tx_t)</p> <p>Description of the problem:</p> <p>If the connection is closed before ksocknal_transmit() returns to ksocknal_process_transmit(), then nobody has refcount on conn::ksnc_sock and all pending ZC requests will be finalized by ksocknal_connsock_decref-&gt;ksocknal_finalize_zcreq<br/> ksocknal_finalize_zcreq will mark not-acked ZC request as error by setting tx::tx_reside = -1.<br/> This is race because ksocknal_process_transmit() will check tx::tx_resid right after calling ksocknal_transmit(), and it can get<br/> both tx-&gt;tx_resid != 0 and rc == 0 then hit later LASSERT(rc &lt; 0).<br/> I've added Jay and Lai as reviewer, also, I will file a bug on bugzilla and try to push it into mainstream.</p> <p>but this bug is not reason of bad performance, so we still need to survey on performance issue.</p> <p>Regards<br/> Liang</p> <p>I've filed a bug on BZ and try to push it into mainstream<br/> <a href="https://bugzilla.lustre.org/show_bug.cgi?id=24218" class="external-link" target="_blank" rel="nofollow noopener">https://bugzilla.lustre.org/show_bug.cgi?id=24218</a></p> <p>Regards<br/> Liang</p> <p>Patch landed on 2.x, still pending on test for 1.8</p> <p>Patch landed on both 1.8.* and 2.*, mark it as resolved</p> Bugzilla ID 24218.0 Development Rank 1|hzw033: Rank (Obsolete) 10093 Severity