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-1423 Lustre <p>Mounting a lustre2.1.1 filesystem on a 1.8.6 client doing a ls will fail with the following error on the client logs.</p> <p>LustreError: 2551436:0:(mdc_request.c:983:mdc_readpage()) Unexpected # bytes transferred: 4096 (16384 expected)<br/> LustreError: 2556239:0:(mdc_request.c:983:mdc_readpage()) Unexpected # bytes transferred: 4096 (16384 expected)<br/> LustreError: 2556239:0:(dir.c:949:ll_readdir_20()) error reading dir <span class="error">&#91;0x12480001:0xc1bc1b0c:0x0&#93;</span> at 0: rc -71</p> clients = ia64 (16Kpagesize) lustre-1.8.6.81-5.1nas<br/> server = x86(4kpagesize) lustre-2.1.1 LU-1423

16K pagesize clients error during ls

Bug Minor Resolved Fixed Yang Sheng Mahmoud Hanafi Fri, 18 May 2012 15:15:34 +0000 Mon, 23 Jul 2012 06:52:52 +0000 Mon, 23 Jul 2012 06:52:52 +0000 Lustre 2.1.1 Lustre 1.8.6 Lustre 2.3.0 Lustre 2.1.3 0 6 <p>YangSheng</p> <p>Could you please look into this one?</p> <p>Thanks</p> <p>Peter</p> <p>Could I get an update on this.<br/> Thanks,<br/> Mahmoud</p> <p>The kernel in the IA64 system is a sles10sp2 kernel 2.6.16.60-0.77.1-default.<br/> The kernel config set CONFIG_IA64_PAGE_SIZE_16KB=y.</p> <p>We also mounted a lustre 1.8.6 server on the IA64 client and it worked. So, it appears the problem was at the 2.1.1 server.</p> <p>This likely relates to the changes made for 1MB readdir RPCs on 2.x, but the compatibility code on 1.8 was not updated correctly. Possibly the server needs to reply with the requested RPC size for old clients that do not handle OBD_CONNECT_BRW_SIZE, rather than hard-coding the 4096-byte lu_page size.</p> <p>In the case that server and client have different page size, should they be settled with the higher value or lower value?</p> <p>Hi, Jay, Could you tell me what net type is used between client&amp;server.</p> <p>We use IB. ipoib on ib0 and rdma on ib1.</p> <p>This issue related to change: <a href="http://review.whamcloud.com/#change,604" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#change,604</a></p> <p>For the fix, We need to check OBD_CONNECT_BRW_SIZE on server and return single page for old client. So looks like we need restore some codes that removed from above change.</p> <p>Patch unload to: <a href="http://review.whamcloud.com/3014" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/3014</a></p> <p>We installed the patch. Got a LBUG!</p> <p>Lustre: 3692:0:(sec.c:1474:sptlrpc_import_sec_adapt()) import MGS-&gt;NET_0x500000a9719cf_UUID netid 50000: select flavor null^M<br/> Lustre: 3692:0:(sec.c:1474:sptlrpc_import_sec_adapt()) Skipped 37 previous similar messages^M<br/> LustreError: 3761:0:(mdt_handler.c:1247:mdt_sendpage()) ASSERTION(desc-&gt;bd_nob == nob) failed^M<br/> LustreError: 3761:0:(mdt_handler.c:1247:mdt_sendpage()) LBUG^M<br/> Pid: 3761, comm: mdt_rdpg_01^M<br/> ^M<br/> Call Trace:^M<br/> <span class="error">&#91;&lt;ffffffffa05e3855&gt;&#93;</span> libcfs_debug_dumpstack+0x55/0x80 <span class="error">&#91;libcfs&#93;</span>^M<br/> <span class="error">&#91;&lt;ffffffffa05e3e95&gt;&#93;</span> lbug_with_loc+0x75/0xe0 <span class="error">&#91;libcfs&#93;</span>^M<br/> ^M<br/> Entering kdb (current=0xffff880c1f4fa0c0, pid 3761) on processor 0 Oops: (null)^M</p> <p>Patch update, Please retry, sorry for the inconvenient.</p> <p>The latest patch seemed working for us. Mahmoud tested it.</p> <p>Hi, Jay, Cloud we close this ticket? Please advice.</p> <p>The patch was landed to b2_1 tree 3 days ago. So, please close this ticket.</p> <p>Patch landed. close bug.</p> Development Rank 1|hzv6bj: Rank (Obsolete) 4558 Severity