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-1629 Lustre <p>Hyperion clustre, 100+ mounted clients. <br/> Powered off entire clustre. Upon restart, MDS is in recovery waiting for 0 clients. <br/> Example message: Jul 13 07:01:06 ehyperion-rst6 kernel: Lustre: lustre-MDT0000: Denying connection for new client 192.168.117.50@o2ib1 (at 11e711ab-a329-f07a-8312-6a40af7fc5a4), waiting for 0 clients in recovery for 2:38<br/> At the end of the recovery timeout, clients mount</p> <p>Lustre: lustre-MDT0000: recovery is timed out, evict stale exports<br/> Lustre: lustre-MDT0000: disconnecting 112 stale clients<br/> Lustre: lustre-MDT0000: Recovery over after 5:00, of 112 clients 0 recovered and 112 were evicted.</p> Hyperion LU-1629

MDS waiting for 0 clients in recovery

Bug Blocker Closed Fixed Li Wei Cliff White Fri, 13 Jul 2012 10:06:06 +0000 Wed, 1 Aug 2012 23:43:40 +0000 Wed, 1 Aug 2012 23:43:30 +0000 Lustre 2.3.0 Lustre 2.3.0 0 2 <p>System log from MGS/MDS for the recovery</p> <p>I thought I saw a very similar bug report a week or two ago. Did you do a search for this first? I believe there was already a patch for it. </p> <p>The same as ORI-668, there is discussion about that issue</p> <p>This is not recovery issue but reporting, we are reporting currently just number of clients in recovery, that is why there is 0. There is no patch for this yet.</p> <p>Mike,<br/> Would you be able to look into this one or assign to someone that could?<br/> Thank you!</p> <p>Li Wei - Mikhail is swamped with rebase. Can you please work on this? He says fix should be to change message and output slightly different values.</p> <p>Message can be changed like the following:</p> <div class="code panel" style="border-width: 1px;"><div class="codeContent panelContent"> <pre class="code-java"> LCONSOLE_WARN(<span class="code-quote">"%s: Denying connection <span class="code-keyword">for</span> <span class="code-keyword">new</span> client "</span> <span class="code-quote">"%s (at %s), total clients to recover %d,"</span> <span class="code-quote">" %d clients in recovery <span class="code-keyword">for</span> %d:%.02d\n"</span>, target-&gt;obd_name, libcfs_nid2str(req-&gt;rq_peer.nid), cluuid.uuid, target-&gt;obd_max_recoverable_clients, cfs_atomic_read(&amp;target-&gt; \ obd_lock_replay_clients), (<span class="code-object">int</span>)t / 60, (<span class="code-object">int</span>)t % 60); </pre> </div></div> <p>It outputs obd_max_recoverable_clients as total expected number of client to recover and uses obd_lock_replay_clients counter to show how many of them are already participating in recovery</p> <p><a href="http://review.whamcloud.com/3485" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/3485</a></p> <p>The patch has landed to master.</p> Duplicate Related Development Rank 1|hzv613: Rank (Obsolete) 4511 Severity