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-13923 Lustre <p>Steps to reproduce:</p> <p>Configure 3 nodes: PeerA (tcp), PeerB (tcp1) and GW1 (tcp, tcp1).</p> <p>Configure GW1 to act as a router and add corresponding routes to PeerA/PeerB.</p> <p>Verify connectivity between PeerA and PeerB by executing "lnetctl ping" back and forth.</p> <p>Execute "lnetctl lnet unconfigure" on GW1. The command hangs.</p> <p>The issue affects tag 2.13.55 </p> LU-13923

LNet: lnetctl "lnet unconfigure" or "net del" hangs if executed on a gateway

Bug Minor Closed Duplicate Serguei Smirnov Serguei Smirnov Tue, 25 Aug 2020 22:03:01 +0000 Thu, 24 Mar 2022 16:19:44 +0000 Thu, 24 Mar 2022 16:19:44 +0000 0 2 <p>The issue has been introduced by <a href="https://jira.whamcloud.com/browse/LU-13606" title="Poor performance with routed clients to multi-rail servers when single server interface fails" class="issue-link" data-issue-key="LU-13606"><del>LU-13606</del></a>: </p> <p><a href="https://review.whamcloud.com/38798" class="external-link" target="_blank" rel="nofollow noopener">https://review.whamcloud.com/38798</a></p> <p>The change added a call to lnet_nid2peerni_locked which is incrementing a reference on a peer_ni object which is never decremented. This results in LNet being unable to cleanup properly on "unconfigure" or "net del" operation, causing lnetctl to hang.</p> <p>Serguei Smirnov (ssmirnov@whamcloud.com) uploaded a new patch: <a href="https://review.whamcloud.com/39731" class="external-link" target="_blank" rel="nofollow noopener">https://review.whamcloud.com/39731</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-13923" title="LNet: lnetctl &quot;lnet unconfigure&quot; or &quot;net del&quot; hangs if executed on a gateway" class="issue-link" data-issue-key="LU-13923"><del>LU-13923</del></a> lnet: Add missing lnet_peer_ni_decref call<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: 8564e47bc2d37102e742f8e688d87291ff39780a</p> <p>This ticket is a duplicate of <a href="https://jira.whamcloud.com/browse/LU-13896" title="Reference leak in check for mr_forwarding" class="issue-link" data-issue-key="LU-13896"><del>LU-13896</del></a>.</p> Duplicate LU-13896 Development Epic/Theme lnet Rank 1|i018cf: Rank (Obsolete) 9223372036854775807 Severity