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-13001 Lustre <p>Historically, check_routers_before_use would cause LNet<br/> initialization to pause until all routers had been ping'd once.</p> <p>This behavior was changed in commit<br/> fe17e9b8370affe063769b880f02b9190584baaa from <a href="https://jira.whamcloud.com/browse/LU-11298" title="LNet: Router peer instead of Router Peer NI" class="issue-link" data-issue-key="LU-11298"><del>LU-11298</del></a>. Now, LNet<br/> will wait indefinitely until discovery completes on all routers.<br/> This is problematic, because if even one router is down then LNet<br/> will stall forever.</p> LU-13001

check_routers_before_use causes LNet to hang indefinitely if any router is down

Bug Major Resolved Fixed Chris Horn Chris Horn Fri, 22 Nov 2019 20:26:59 +0000 Wed, 6 Jan 2021 01:18:17 +0000 Sat, 14 Dec 2019 13:48:07 +0000 Lustre 2.13.0 Lustre 2.14.0 Lustre 2.14.0 0 5 <p>Chris Horn (hornc@cray.com) uploaded a new patch: <a href="https://review.whamcloud.com/36820" class="external-link" target="_blank" rel="nofollow noopener">https://review.whamcloud.com/36820</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-13001" title="check_routers_before_use causes LNet to hang indefinitely if any router is down" class="issue-link" data-issue-key="LU-13001"><del>LU-13001</del></a> lnet: Wait for single discovery attempt of routers<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: 9282b4f0c0198407d285bfa4c05f4dc5fa82b60c</p> <p>Oleg Drokin (green@whamcloud.com) merged in patch <a href="https://review.whamcloud.com/36820/" class="external-link" target="_blank" rel="nofollow noopener">https://review.whamcloud.com/36820/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-13001" title="check_routers_before_use causes LNet to hang indefinitely if any router is down" class="issue-link" data-issue-key="LU-13001"><del>LU-13001</del></a> lnet: Wait for single discovery attempt of routers<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: d45a032d9a5c6929f62e00e75d8fb0103cc0fbb4</p> <p>Landed for 2.14</p> <p>I believe this can be hit on 2.12.x Is there any plan to backport to b2_12?</p> <p>2.13.0 was affected.</p> <p>Can we get a backport to 2.12</p> <p> </p> Development Rank 1|i00ptr: Rank (Obsolete) 9223372036854775807 Severity