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-4755 Lustre <p>After ran "lctl set_param osc.*.max_pages_per_rpc=4M", we ran 4k random write test with IOR and easily hit this problem.</p> <p>After some test, we found that the biggest value of msgsize is 16384 for bulk write, while req-&gt;rq_reqbuf_len is only 8192.</p> LU-4755

ASSERTION( req->rq_reqbuf_len >= msgsize ) failed when using 4MB RPC

Bug Minor Resolved Fixed Cliff White Li Xi patch Wed, 12 Mar 2014 11:23:18 +0000 Thu, 17 Sep 2015 23:17:51 +0000 Wed, 16 Jul 2014 14:42:10 +0000 Lustre 2.7.0 Lustre 2.5.3 0 7 <p>With following patch, this problem won't be reproduced.</p> <p><a href="http://review.whamcloud.com/9599" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/9599</a></p> <p>However, I am wondering whether there is any automatic way to calculate the proper value of OST_MAXREQSIZE at compile time rather than doing guesswork or manual caculation.</p> <p>Cliff</p> <p>Could you please take care of this patch?</p> <p>Thanks</p> <p>Peter</p> <p>Actually, before I dismiss the patch to increase the request size, it is worthwhile to ask if there is any performance improvement from sending 4096 random pages in one RPC compared to 16 x 256 random pages in separate RPCs? It might even be faster to send parallel RPCs due to checksums running on separate cores and being handled in parallel on the OST. If there is no improvement from many random pages in one RPC, it is better to just limit the number of niobufs that the client sends in one RPC.</p> <p>The patch is failing sanity test at this time. Is it possible to submit a new patch?</p> <p>Patch landed to Master.</p> Related LU-7181 Development Rank 1|hzwhhr: Rank (Obsolete) 13084 Severity