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-7756 Lustre <p>When submitting read IOs from lustre clients to oss which uses 6 OSTs, we see in iostat that the number of IO requests in progress on each lun does not go beyond 86.</p> <p>The result is that throughput per lun is limited to ~600 MB/s.</p> <p>To be able to get the most out of the pun we need at least 100 requests at once. </p> <p>This is due to the max number of <tt>oss_num_threads</tt> being limited by <tt>OSS_NTHRS_MAX</tt> (512 / 6 = ~86).</p> <p>Raising the limit to 1024 by patching the code allowed to get enough I/Os at once on each lun and get up to 900MB/s per OST.</p> LU-7756

oss_num_threads max value is sometimes too low to feed disk controllers

Bug Minor Resolved Fixed Bob Glossman Gregoire Pichon patch performance Mon, 8 Feb 2016 15:50:12 +0000 Thu, 9 Feb 2017 16:57:35 +0000 Mon, 14 Mar 2016 03:05:42 +0000 Lustre 2.5.3 Lustre 2.9.0 0 9 <p>Grégoire Pichon (gregoire.pichon@bull.net) uploaded a new patch: <a href="http://review.whamcloud.com/18350" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/18350</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-7756" title="oss_num_threads max value is sometimes too low to feed disk controllers" class="issue-link" data-issue-key="LU-7756"><del>LU-7756</del></a> oss: allow larger number of OSS service threads<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: 208ba9b329834bd09ed9f33cdbaf0220c15fe887</p> <p>Have you tried increasing the RPC size to 4MB so that fewer IOS are needed to keep the backend busy?</p> <p>Hi Bob,<br/> can you have a look at the patch?<br/> Thanks.<br/> Joe</p> <p>I see that the patch does what it says, adds a module param in place of a hard coded limit. However I can't speak to if this is a good change or not. I believe in the past having too many service threads actually reduced performance in some cases.</p> <p>I would tend to agree, and I wouldn't want to allow the number of threads to increase by default, but since this is a module parameter that explicitly needs to be set by the admin I think it is fairly safe. </p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/18350/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/18350/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-7756" title="oss_num_threads max value is sometimes too low to feed disk controllers" class="issue-link" data-issue-key="LU-7756"><del>LU-7756</del></a> oss: allow larger number of OSS service threads<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: aa84d188641fa95b0e66ada438c2ba79f164c0d0</p> <p>Gregoire, your patch has landed for 2.9.0. Does it need to be backported to an EE release, or are you applying this locally?</p> <p>Yes, we would need to have the patch backported to b2_7_fe and IEEL 3.0 if possible.<br/> thanks.</p> <p>b2_7_fe port: <a href="http://review.whamcloud.com/#/c/22391/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/22391/</a><br/> b2_8_fe port: <a href="http://review.whamcloud.com/#/c/22882/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/22882/</a></p> Related Development Rank 1|hzy0n3: Rank (Obsolete) 9223372036854775807 Severity