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-3583 Lustre <p>During inspection of <a href="https://jira.whamcloud.com/browse/LU-2869" title="extended attribute cache for Lustre" class="issue-link" data-issue-key="LU-2869"><del>LU-2869</del></a> I was asked to file a ticket to track this problem in the future.</p> <p>The issue is that client-side LDLM does not have support for atomic match_or_enqueue operations. This may cause several lock enqueue requests being issued in parallel by a single client causing lock ping-pongs.</p> <p>It looks like different parts of Lustre code either ignore this problem or solve it in a specific way. For example, ll_layout_refresh() implements the atomic operation by serializing requests with lli_layout_mutex. The extended attribute cache patch uses the same technique with lli_xattrs_enq_lock().</p> LU-3583

LDLM support for atomic match_or_enqueue operation

Improvement Minor Open Unresolved WC Triage Andrew Perepechko Sun, 14 Jul 2013 19:14:51 +0000 Mon, 15 Jul 2013 15:28:34 +0000 Lustre 2.5.0 0 2 <p>It should probably be implemented as part of LDLM API.</p> Related LU-2869 Development Rank 1|hzvvbz: Rank (Obsolete) 9080