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-1231 Lustre <p><a href="https://maloo.whamcloud.com/test_sessions/0a6e15b6-7126-11e1-a89e-5254004bbbd3" class="external-link" target="_blank" rel="nofollow noopener">https://maloo.whamcloud.com/test_sessions/0a6e15b6-7126-11e1-a89e-5254004bbbd3</a></p> <p>total: 9000 creates in 28.71 seconds: 313.44 creates/second<br/> llite.lustre-ffff88005e131800.statahead_max=0<br/> 10001</p> <p>real 0m55.864s<br/> user 0m0.140s<br/> sys 0m28.882s<br/> ls 10000 files without statahead: 56 sec<br/> llite.lustre-ffff88005e131800.statahead_max=32<br/> 32<br/> 10001</p> <p>real 0m59.101s<br/> user 0m0.180s<br/> sys 0m24.130s<br/> ls 10000 files with statahead: 59 sec<br/> statahead total: 4<br/> statahead wrong: 0<br/> agl total: 4</p> LU-1231

statahead/agl is slower on sles11 client

Bug Minor Resolved Won't Fix nasf Minh Diep Sun, 18 Mar 2012 16:31:31 +0000 Tue, 24 Jul 2012 22:03:58 +0000 Tue, 24 Jul 2012 22:03:58 +0000 Lustre 2.2.0 0 1 <p>Fanyong</p> <p>Could you please give an initial assessment of this issue?</p> <p>Thanks</p> <p>Peter</p> <p>Such case is reasonable, because "statahead + AGL" needs to start two threads at background for pre-fetching. That requires powerful CPU to schedule those pre-fetching threads in time. But above tests are done under virtual machines: four VMs share the same physical node, which only have 4-cores. That means each VM only has 1-core. So it is possible that those pre-fetching threads cannot be scheduled in time. And then the "statahead + AGL" mode is slower than w/o cases.</p> <p>How do we explain that the issue only seen in sles11 clients, not in rhel5 nor rhel6. Not even in rhel6 1.8.7-wc1 client.</p> <p>In fact, I have also met the same issue in my local VM environment, mine is RHEL6 based, with 2-cores shared by MDS + OSTs + client.</p> <p>On the other hand, is it true that all test_123a failed for lustre-2.x on sles11 client?</p> <p>Statahead performance under VM environment is incredible because of less CPU power and schedule delay.</p> <p>On the other hand, we found some performance degression caused by security getxattr RPC. Related issues have been fixed in <a href="https://jira.whamcloud.com/browse/LU-549" title="Add xattr list/value cache on client" class="issue-link" data-issue-key="LU-549"><del>LU-549</del></a>.</p> Development Rank 1|hzvh67: Rank (Obsolete) 6431 Severity