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-6941 Lustre <p>This issue was created by maloo for Bob Glossman &lt;bob.glossman@intel.com&gt;</p> <p>This issue relates to the following test suite run: <a href="https://testing.hpdd.intel.com/test_sets/81d99640-38ea-11e5-8dec-5254006e85c2" class="external-link" target="_blank" rel="nofollow noopener">https://testing.hpdd.intel.com/test_sets/81d99640-38ea-11e5-8dec-5254006e85c2</a>.</p> <p>The sub-test test_209 failed with the following error:</p> <div class="preformatted panel" style="border-width: 1px;"><div class="preformattedContent panelContent"> <pre>open/close requests are not freed </pre> </div></div> <p>Looks like <a href="https://jira.whamcloud.com/browse/LU-4270" title="Interop 2.5.0&lt;-&gt;2.6 failure on test suite sanity test_209: open/close requests are not freed" class="issue-link" data-issue-key="LU-4270"><del>LU-4270</del></a>, but that is marked Closed.</p> <p>Info required for matching: sanity 209</p> LU-6941

sanity test_209: open/close requests are not freed

Bug Major Resolved Cannot Reproduce Hongchao Zhang Maloo p4hc Sun, 2 Aug 2015 19:51:16 +0000 Wed, 8 Apr 2020 05:21:21 +0000 Wed, 8 Apr 2020 05:21:21 +0000 Lustre 2.7.0 Lustre 2.8.0 0 12 <p>more on master:<br/> <a href="https://testing.hpdd.intel.com/test_sets/72f0624c-3e05-11e5-8300-5254006e85c2" class="external-link" target="_blank" rel="nofollow noopener">https://testing.hpdd.intel.com/test_sets/72f0624c-3e05-11e5-8300-5254006e85c2</a><br/> <a href="https://testing.hpdd.intel.com/test_sets/450d6c92-3e39-11e5-a492-5254006e85c2" class="external-link" target="_blank" rel="nofollow noopener">https://testing.hpdd.intel.com/test_sets/450d6c92-3e39-11e5-a492-5254006e85c2</a></p> <p>By searching on Maloo, I found since 2015-02-13 all of the failure instances occurred on IB network (nodes onyx-[64-67]-ib) .</p> <p>Hongchao</p> <p>Could you please look into this issue as a priority?</p> <p>Thanks</p> <p>Peter</p> <p>as per the logs, there are only about 130 ptlrpc requests sent to MDT to open the file (LDLM_ENQUEUE), and there are about 470<br/> (LDLM_CANCEL) ptlrpc requests sent to the MDT, then the test script should be improved to adapt it.</p> <p>More failure instance on master branch:<br/> <a href="https://testing.hpdd.intel.com/test_sets/2e32e524-428a-11e5-9941-5254006e85c2" class="external-link" target="_blank" rel="nofollow noopener">https://testing.hpdd.intel.com/test_sets/2e32e524-428a-11e5-9941-5254006e85c2</a></p> <p>Hongchao Zhang (hongchao.zhang@intel.com) uploaded a new patch: <a href="http://review.whamcloud.com/16001" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/16001</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-6941" title="sanity test_209: open/close requests are not freed" class="issue-link" data-issue-key="LU-6941"><del>LU-6941</del></a> mdc: debug patch<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: e7004c63c85041923082a95ece5e55a6931ba557</p> <p>Another failure on master:<br/> 2015-08-17 14:31:06 - review-zfs-part-1 - <a href="https://testing.hpdd.intel.com/test_sets/23814aac-4524-11e5-a64b-5254006e85c2" class="external-link" target="_blank" rel="nofollow noopener">https://testing.hpdd.intel.com/test_sets/23814aac-4524-11e5-a64b-5254006e85c2</a></p> <p>Another on master, review-zfs at<br/> 2015-09-10 01:57:56 - <a href="https://testing.hpdd.intel.com/test_sets/7d8651c8-57b7-11e5-a084-5254006e85c2" class="external-link" target="_blank" rel="nofollow noopener">https://testing.hpdd.intel.com/test_sets/7d8651c8-57b7-11e5-a084-5254006e85c2</a></p> <p>Failure today on master:<br/> <a href="https://testing.hpdd.intel.com/test_sessions/0a6e7516-6050-11e5-b0a3-5254006e85c2" class="external-link" target="_blank" rel="nofollow noopener">https://testing.hpdd.intel.com/test_sessions/0a6e7516-6050-11e5-b0a3-5254006e85c2</a></p> <p>status update:<br/> debug patch <a href="http://review.whamcloud.com/#/c/16001/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/16001/</a> run "sanity" 3 times without this problem.<br/> have retriggered it to test more times.</p> <p>+1 on master at <a href="https://testing.hpdd.intel.com/test_sets/c3b65a8e-7888-11e5-a98c-5254006e85c2" class="external-link" target="_blank" rel="nofollow noopener">https://testing.hpdd.intel.com/test_sets/c3b65a8e-7888-11e5-a98c-5254006e85c2</a></p> <p>Another on master at <a href="https://testing.hpdd.intel.com/test_sets/1f89e264-7829-11e5-9072-5254006e85c2" class="external-link" target="_blank" rel="nofollow noopener">https://testing.hpdd.intel.com/test_sets/1f89e264-7829-11e5-9072-5254006e85c2</a></p> <p>hit this after upgrade system from 2.5.5 RHEL6.6 to master/3264 RHEL6.7</p> <div class="preformatted panel" style="border-width: 1px;"><div class="preformattedContent panelContent"> <pre>onyx-28: == sanity test 209: read-only open/close requests should be freed promptly == 18:35:49 (1449714949) onyx-28: before: 39, after: 360 onyx-28: sanity test_209: @@@@@@ FAIL: open/close requests are not freed onyx-28: Trace dump: onyx-28: = /usr/lib64/lustre/tests/test-framework.sh:4822:error_noexit() onyx-28: = /usr/lib64/lustre/tests/test-framework.sh:4853:error() onyx-28: = /usr/lib64/lustre/tests/sanity.sh:11943:test_209() onyx-28: = /usr/lib64/lustre/tests/test-framework.sh:5100:run_one() onyx-28: = /usr/lib64/lustre/tests/test-framework.sh:5137:run_one_logged() onyx-28: = /usr/lib64/lustre/tests/test-framework.sh:5002:run_test() onyx-28: = /usr/lib64/lustre/tests/sanity.sh:11946:main() </pre> </div></div> <p>status update:<br/> no new occurrence since Jan 12, 2016</p> <p>Hongchao Zhang (hongchao.zhang@intel.com) uploaded a new patch: <a href="http://review.whamcloud.com/22808" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/22808</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-6941" title="sanity test_209: open/close requests are not freed" class="issue-link" data-issue-key="LU-6941"><del>LU-6941</del></a> test: use multiop to trigger open/close<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: 3b718c8cf201f94d16344ae11886fa58bda9214e</p> <p>By investigating the recent occurrences, this issue could be triggered by the ptlrpc_request history cache of "ldlm_cbd" service.<br/> the corresponding patch is tracked at <a href="http://review.whamcloud.com/22808" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/22808</a></p> <p>the patch has been rebased to the latest master</p> <p>Close old issue that has not been seen in a long time.</p> Related Development Rank 1|hzxjjb: Rank (Obsolete) 9223372036854775807 Severity