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-5872 Lustre <p>This issue was created by maloo for John Hammond &lt;john.hammond@intel.com&gt;</p> <p>This issue relates to the following test suite run: <a href="https://testing.hpdd.intel.com/test_sets/27a469b2-6513-11e4-ab6d-5254006e85c2" class="external-link" target="_blank" rel="nofollow noopener">https://testing.hpdd.intel.com/test_sets/27a469b2-6513-11e4-ab6d-5254006e85c2</a>.</p> <p>The sub-test test_6 failed with the following error:</p> <div class="preformatted panel" style="border-width: 1px;"><div class="preformattedContent panelContent"> <pre>dd not finished in 240 secs </pre> </div></div> <p>Please provide additional information about the failure here.</p> <p>Info required for matching: sanity-quota 6</p> LU-5872

sanity-quota test_6: dd not finished in 240 secs

Bug Minor Resolved Cannot Reproduce WC Triage Maloo Wed, 5 Nov 2014 19:14:28 +0000 Tue, 23 Nov 2021 08:11:28 +0000 Wed, 13 Oct 2021 01:39:56 +0000 0 7 <p>When approaching hard limit, client turns to sync write (page by page), so the write will be extremely slow. I checked the test log, there is no errors, the dd was still in progress after 240 seconds.</p> <p>Looks 240 seconds isn't enough for 2M bytes sync write (4k per OST write) to finish on current autotest system. Given that test script checks if file is growing every 30 seconds to avoid waiting too long when dd is hung, I think we can safely bump the 240 to a larger value.</p> <p>Even better would be to make the test run more quickly, if possible, rather than accepting that it will take more time to complete. 2MB in 4KB chunks is 512 sync writes. With a real disk this should only take about 5s to complete, so it is sad that it takes so much longer.</p> <p>Looks the OSTs were quit busy on handling statfs &amp; ping requests, and each OST_WRITE took very long time, for example:</p> <div class="code panel" style="border-width: 1px;"><div class="codeContent panelContent"> <pre class="code-java">00000100:00100000:1.0:1415181131.383051:0:583:0:(service.c:2116:ptlrpc_server_handle_request()) Handled RPC pname:cluuid+ref:pid:xid:nid:opc ll_ost_io00_042:c453fba3-d5c5-1944-5f99-be5cc0651185+7:29501:x1483920018695096:12345-10.1.5.70@tcp:4 Request procesed in 1869583us (1869643us total) trans 90194313389 rc 0/0 </pre> </div></div> <p>Another instance: <a href="https://testing.hpdd.intel.com/test_sets/f878df9a-2661-11e5-8b33-5254006e85c2" class="external-link" target="_blank" rel="nofollow noopener">https://testing.hpdd.intel.com/test_sets/f878df9a-2661-11e5-8b33-5254006e85c2</a><br/> BTW, both test_1 and test_3 failed due to <a href="https://jira.whamcloud.com/browse/LU-5245" title="sanity-quota test_1: user write success, but expect EDQUOT " class="issue-link" data-issue-key="LU-5245"><del>LU-5245</del></a> in this test.</p> <p>+1 <a href="https://testing.whamcloud.com/test_sets/5a5c171b-264f-4d1d-a843-60df8e84db41" class="external-link" target="_blank" rel="nofollow noopener">https://testing.whamcloud.com/test_sets/5a5c171b-264f-4d1d-a843-60df8e84db41</a></p> Development Rank 1|hzx0bb: Rank (Obsolete) 16423 Severity