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-5957 Lustre <p>The following operations sequence eventually fails with EBADF (let fstripe be a striped file, fnostripeX unstriped files):</p> <p>1) swap_layouts fstripe fnostripe1<br/> 2) I/O into fstripe<br/> 3) swap_layouts fstripe fnostripe2<br/> 4) I/O into fstripe # Fails with EBADF</p> <p>Please find a reproducer attached. This seems to affect current master as well as older versions of that provide layout swap.</p> <p>The file remains unavailable, also after a client umount/remount or from another client.</p> <p>It seems that lov_conf_set() doesn't call lov_layout_change() in the second case, leading to lov_io_init_empty() being called eventually on the write...</p> LU-5957

Broken layout after swapping layouts with unstriped files

Bug Minor Resolved Fixed Bruno Faccini Henri Doreau cea patch Wed, 26 Nov 2014 09:12:15 +0000 Thu, 1 Sep 2016 12:42:33 +0000 Tue, 3 Feb 2015 18:20:36 +0000 Lustre 2.4.1 Lustre 2.7.0 Lustre 2.5.3 Lustre 2.7.0 0 5 <p>"unstriped" is probably poorly chosen, I mean files with no LOV EA.</p> <p>I wonder if this could be related to <a href="https://jira.whamcloud.com/browse/LU-2766" title="lov_object.c:635:lov_layout_change()) ASSERTION( atomic_read(&amp;lov-&gt;lo_active_ios) == 0 ) failed" class="issue-link" data-issue-key="LU-2766"><del>LU-2766</del></a>, with a new symptom ?</p> <p>I don't think so, according to our analysis (which just ended) this is a server-side issue. It comes from a missing clear of a MDT flag after a swap layout that removes LOV. We will provide a patch.</p> <p>Ah ok, so I wonder if this could be in mdd_swap_layouts() after the swap has been re-ordered to start by the no layout file ??</p> <p>Henri Doreau (henri.doreau@cea.fr) uploaded a new patch: <a href="http://review.whamcloud.com/12877" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/12877</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-5957" title="Broken layout after swapping layouts with unstriped files" class="issue-link" data-issue-key="LU-5957"><del>LU-5957</del></a> mdt: Update MDT flags after layout swap<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: dcebecc7d669e71c45597d07715faed4e49885e9</p> <p>Bruno, as you might see in the patch above it's an mdt issue: an I/O on a non-striped file invokes mdt_create_data, which creates the LOV and set MOF_LOV_CREATED on the object. If you "destripe" this object again an re-do an I/O this flag will prevent the LOV from being re-created as expected.</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/12877/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/12877/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-5957" title="Broken layout after swapping layouts with unstriped files" class="issue-link" data-issue-key="LU-5957"><del>LU-5957</del></a> mdt: Update MDT flags after layout swap<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: 1d3ee3ed2b56d73f392e1b2a033f7d274f5202d9</p> <p>Landed for 2.7</p> <p>Could this be considered for 2.5?</p> <p>Henri Doreau (henri.doreau@cea.fr) uploaded a new patch: <a href="http://review.whamcloud.com/14255" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/14255</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-5957" title="Broken layout after swapping layouts with unstriped files" class="issue-link" data-issue-key="LU-5957"><del>LU-5957</del></a> mdt: Update MDT flags after layout swap<br/> Project: fs/lustre-release<br/> Branch: b2_5<br/> Current Patch Set: 1<br/> Commit: 6032c1e646942169d73ea3763c0399c5d663e498</p> <p>Here is a 2.5 backport: <a href="http://review.whamcloud.com/14255" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/14255</a></p> Development Rank 1|hzx1kv: Rank (Obsolete) 16639 Severity