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-7578 Lustre <p>There have been a few gnilnd changes since the last time we sync'd up. I'll be pushing up the latest commits.</p> LU-7578

Push latest gnilnd changes

Task Minor Resolved Fixed Chris Horn Chris Horn Thu, 17 Dec 2015 19:49:16 +0000 Fri, 5 Feb 2016 15:31:43 +0000 Fri, 5 Feb 2016 15:31:43 +0000 Lustre 2.8.0 0 6 <p>Chris Horn (hornc@cray.com) uploaded a new patch: <a href="http://review.whamcloud.com/17663" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/17663</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-7578" title="Push latest gnilnd changes" class="issue-link" data-issue-key="LU-7578"><del>LU-7578</del></a> gnilnd: Modify allocator flags to prevent waiting<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: d172877a683e8f0a980265c96edccf8f214fd674</p> <p>Chris Horn (hornc@cray.com) uploaded a new patch: <a href="http://review.whamcloud.com/17664" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/17664</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-7578" title="Push latest gnilnd changes" class="issue-link" data-issue-key="LU-7578"><del>LU-7578</del></a> gnilnd: Add module parameter reg_fail_timeout<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: a1909655ff47f5276ca789dad6e88b6bc167fd3f</p> <p>Chris Horn (hornc@cray.com) uploaded a new patch: <a href="http://review.whamcloud.com/17665" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/17665</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-7578" title="Push latest gnilnd changes" class="issue-link" data-issue-key="LU-7578"><del>LU-7578</del></a> gnilnd: Handle new return code in gni_mem_register()<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: 237a4857ae42ef2fb569664a1e5f24398ae53687</p> <p>Chris Horn (hornc@cray.com) uploaded a new patch: <a href="http://review.whamcloud.com/17666" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/17666</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-7578" title="Push latest gnilnd changes" class="issue-link" data-issue-key="LU-7578"><del>LU-7578</del></a> gnilnd: Return correct error on GNI_RC_ERROR_NOMEM<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: b2d35706d02c0cf16ef404f865211e7fde14cfb1</p> <p>Chris Horn (hornc@cray.com) uploaded a new patch: <a href="http://review.whamcloud.com/17667" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/17667</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-7578" title="Push latest gnilnd changes" class="issue-link" data-issue-key="LU-7578"><del>LU-7578</del></a> gnilnd: Revert max_immediate setting<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: a382968a06574400bd48e2e0beb848ad1ba81304</p> <p>Chris one of these patches is causing a regression in my testing. I'm seeing an increase in memory pressure that is causing jobs to fail under pressure.</p> <p>James, I've passed along your comments to our gnilnd engineers and asked them to weigh in on this ticket.</p> <p>James, are you saying that gnilnd is now using more memory or that allocations are failing when the node is under high memory pressure?<br/> Also, I assume this is on compute nodes that you are seeing this issue. Is that true?<br/> I don't see that these changes would cause gnilnd to use more memory.<br/> <a href="http://review.whamcloud.com/17663" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/17663</a> changed the vmalloc allocation flags so an allocation will fail instead of waiting forever to allocate memory. <br/> We have seen heartbeat failures when a node needs to allocate memory to establish a connection in the case where Lustre is trying to write to disk in order to free memory.</p> <p>Just did another round of testing and I didn't see problems this time. Strange some unrelated change must of landed that fix the problem the latest Gemini changes must of been exposing.</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/17667/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/17667/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-7578" title="Push latest gnilnd changes" class="issue-link" data-issue-key="LU-7578"><del>LU-7578</del></a> gnilnd: Revert max_immediate setting<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: 928c5050f7d2a8a2cabb6eeb3993b29166fdaf1e</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/17663/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/17663/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-7578" title="Push latest gnilnd changes" class="issue-link" data-issue-key="LU-7578"><del>LU-7578</del></a> gnilnd: Modify allocator flags to prevent waiting<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: 4e7994f45811e66f50a5d174b1b5dfc20c65269b</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/17664/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/17664/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-7578" title="Push latest gnilnd changes" class="issue-link" data-issue-key="LU-7578"><del>LU-7578</del></a> gnilnd: Add module parameter reg_fail_timeout<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: 5b787cb7a375372c7a4f3c405d38137a7a867677</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/17665/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/17665/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-7578" title="Push latest gnilnd changes" class="issue-link" data-issue-key="LU-7578"><del>LU-7578</del></a> gnilnd: Handle new return code in gni_mem_register()<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: 37e5f21ee4db9cb3df063d5537511ec15c1196b3</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/17666/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/17666/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-7578" title="Push latest gnilnd changes" class="issue-link" data-issue-key="LU-7578"><del>LU-7578</del></a> gnilnd: Return correct error on GNI_RC_ERROR_NOMEM<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: 919b8968d84d0d6ad57e2e6e5e1a8ccb02a1bd2c</p> <p>All outstanding patches have landed.</p> <p>Patches have landed for 2.8</p> Development Rank 1|hzxw73: Rank (Obsolete) 9223372036854775807