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-4852 Lustre <p>&gt; 19:39:34 LustreError: 18612:0:(osc_cache.c:933:osc_extent_truncate()) ASSERTION( !ext-&gt;oe_urgent ) failed:<br/> &gt; 19:39:34 LustreError: 18612:0:(osc_cache.c:933:osc_extent_truncate()) LBUG<br/> &gt; 19:39:34 Pid: 18612, comm: iozone<br/> &gt; 19:39:34 Call Trace:<br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffff81005eb9&gt;&#93;</span> try_stack_unwind+0x169/0x1b0<br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffff81004919&gt;&#93;</span> dump_trace+0x89/0x450<br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffffa02388d7&gt;&#93;</span> libcfs_debug_dumpstack+0x57/0x80 <span class="error">&#91;libcfs&#93;</span><br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffffa0238e37&gt;&#93;</span> lbug_with_loc+0x47/0xc0 <span class="error">&#91;libcfs&#93;</span><br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffffa071f7ed&gt;&#93;</span> osc_cache_truncate_start+0x204d/0x2320 <span class="error">&#91;osc&#93;</span><br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffffa070e972&gt;&#93;</span> osc_io_setattr_start+0x212/0x460 <span class="error">&#91;osc&#93;</span><br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffffa038dea2&gt;&#93;</span> cl_io_start+0x72/0x140 <span class="error">&#91;obdclass&#93;</span><br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffffa079f047&gt;&#93;</span> lov_io_call+0x87/0x130 <span class="error">&#91;lov&#93;</span><br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffffa07a26e5&gt;&#93;</span> lov_io_start+0x115/0x180 <span class="error">&#91;lov&#93;</span><br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffffa038dea2&gt;&#93;</span> cl_io_start+0x72/0x140 <span class="error">&#91;obdclass&#93;</span><br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffffa0392134&gt;&#93;</span> cl_io_loop+0xb4/0x1b0 <span class="error">&#91;obdclass&#93;</span><br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffffa086f8f0&gt;&#93;</span> cl_setattr_ost+0x260/0x300 <span class="error">&#91;lustre&#93;</span><br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffffa0843aaa&gt;&#93;</span> ll_setattr_raw+0xa4a/0x10a0 <span class="error">&#91;lustre&#93;</span><br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffffa0844157&gt;&#93;</span> ll_setattr+0x57/0x100 <span class="error">&#91;lustre&#93;</span><br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffff8116faf0&gt;&#93;</span> notify_change+0x120/0x310<br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffff81154451&gt;&#93;</span> do_truncate+0x61/0x90<br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffff81162ec1&gt;&#93;</span> do_last+0x5d1/0x7d0<br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffff81163c08&gt;&#93;</span> path_openat+0xc8/0x3d0<br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffff81164038&gt;&#93;</span> do_filp_open+0x48/0xa0<br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffff81154c4e&gt;&#93;</span> do_sys_open+0x16e/0x240<br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffff81154d60&gt;&#93;</span> sys_open+0x20/0x30<br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffff81154d85&gt;&#93;</span> sys_creat+0x15/0x20<br/> &gt; 19:39:34 <span class="error">&#91;&lt;ffffffff8145512b&gt;&#93;</span> system_call_fastpath+0x16/0x1b<br/> &gt; 19:39:34 <span class="error">&#91;&lt;00000000201d2e60&gt;&#93;</span> 0x201d2e60<br/> &gt; 19:39:34 Kernel panic - not syncing: LBUG</p> LU-4852

osc_extent_truncate()) ASSERTION( !ext->oe_urgent ) failed

Bug Critical Resolved Fixed Lai Siyao Andriy Skulysh patch Wed, 2 Apr 2014 10:47:48 +0000 Wed, 11 Jun 2014 22:05:49 +0000 Wed, 11 Jun 2014 22:05:49 +0000 Lustre 2.5.2 0 8 <p>The bug was caused by race between truncate &amp; fsync. The problem is in osc_extent_wait().<br/> There are 2 flags used for changing state : oe_trunc_pending and oe_urgent.<br/> osc_cache_truncate_start() waits for all oe_urgent extents written.<br/> But osc_extent_wait() doesn't takes into account oe_trunc_pending when sets oe_urgent.<br/> The race arises after osc_object_unlock().</p> <p>patch: <a href="http://review.whamcloud.com/9866" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/9866</a></p> <p>Lai,<br/> Could you please keep an eye on this patch?<br/> Thank you!</p> <p>Hi Andriy,</p> <p>Did you see this issue in b2_4 or master?</p> <p>Jinshan - We saw this in 2.5, I believe. Possibly 2.4 as well. Not master, but we don't do much testing with master (yet).</p> <p>patch for b2_5: <a href="http://review.whamcloud.com/#/c/10204/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10204/</a></p> <p>Fixed in master by other means so only needed in 2.5.2</p> Development Rank 1|hzwj3z: Rank (Obsolete) 13384 Severity