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-721 Lustre <p>this is in an MPI environment.</p> <p>Total (customer) is running MPI(SGI-MPT, actually) processes on different compute<br/> nodes writing to the same file in pararallel would result in the file<br/> contain zeros. this doesn't happen all the time, but enough to be a severe<br/> issue.</p> Compute node:<br/> - SLES 11 kernel 2.6.32.29-0.3-default<br/> - lustre 1.8.25 build 1.8.5-20110509165255-PRISTINE-2.6.32.29-0.3-default<br/> OSS:<br/> - SLES 10 SP2 kernerl 2.6.16.60-0.42.8_default<br/> - lustre 1.8.4<br/> LU-721

Parallel writes to same file results in a file of zeroes

Bug Blocker Resolved Fixed Zhenyu Xu Zhenyu Xu Sun, 25 Sep 2011 23:05:11 +0000 Tue, 10 Jan 2012 17:41:04 +0000 Mon, 10 Oct 2011 09:59:23 +0000 Lustre 1.8.6 Lustre 2.2.0 Lustre 2.1.1 Lustre 1.8.7 0 4 <p>quote from <a href="https://bugzilla.lustre.org/show_bug.cgi?id=24548#c23" class="external-link" target="_blank" rel="nofollow noopener">https://bugzilla.lustre.org/show_bug.cgi?id=24548#c23</a></p> <p>The following scenario seems to lead to wrong data in a file:</p> <p>One client writes data under a lock, it completes the write and runs file closing.<br/> Another client wants to write the file, requests a lock, server sees a conflict and sends blocking<br/> AST to first client.<br/> First client handles blocking AST (sending data protected by a lock to OST), the lock has<br/> LDLM_FL_CANCELING flag set.</p> <p>In the meantime, file close runs concurrently and enters dcache.c:ll_ddelete(), which contains the<br/> following lines:</p> <p> /* if not ldlm lock for this inode, set i_nlink to 0 so that</p> <ul> <li>this inode can be recycled later b=20433 */<br/> LASSERT(atomic_read(&amp;de-&gt;d_count) == 0);<br/> if (de-&gt;d_inode &amp;&amp; !find_cbdata(de-&gt;d_inode))<br/> de-&gt;d_inode-&gt;i_nlink = 0;</li> </ul> <p>dcache.c:find_cbdata() checks if there are any locks associated with the file using<br/> dcache.c:return_if_equal() which currently does not count lock with LDLM_FL_CANCELING as such<br/> locks. So, inode gets nlink set to 0, and delete_inode invalidates pages which have not been sent<br/> to OST yet.</p> <p>The proposed quick fix changes return_if_equal() to respect locks which are being canceled but<br/> whose data are to be sent to servers.</p> <p>b18 patch tracking at <a href="http://review.whamcloud.com/1422" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/1422</a><br/> master patch tracking at <a href="http://review.whamcloud.com/1423" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/1423</a></p> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-master/./arch=i686,build_type=client,distro=el6,ib_stack=inkernel/284/" class="external-link" target="_blank" rel="nofollow noopener">lustre-master » i686,client,el6,inkernel #284</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> llite: Parallel writes to same file results in zero file</p> <p>Oleg Drokin : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/master&amp;a=commit&amp;h=0356a2376375020abb861423ce557767dadf593e" class="external-link" target="_blank" rel="nofollow noopener">0356a2376375020abb861423ce557767dadf593e</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-master/./arch=x86_64,build_type=server,distro=el6,ib_stack=inkernel/284/" class="external-link" target="_blank" rel="nofollow noopener">lustre-master » x86_64,server,el6,inkernel #284</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> llite: Parallel writes to same file results in zero file</p> <p>Oleg Drokin : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/master&amp;a=commit&amp;h=0356a2376375020abb861423ce557767dadf593e" class="external-link" target="_blank" rel="nofollow noopener">0356a2376375020abb861423ce557767dadf593e</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-master/./arch=i686,build_type=client,distro=el5,ib_stack=ofa/284/" class="external-link" target="_blank" rel="nofollow noopener">lustre-master » i686,client,el5,ofa #284</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> llite: Parallel writes to same file results in zero file</p> <p>Oleg Drokin : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/master&amp;a=commit&amp;h=0356a2376375020abb861423ce557767dadf593e" class="external-link" target="_blank" rel="nofollow noopener">0356a2376375020abb861423ce557767dadf593e</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-master/./arch=x86_64,build_type=client,distro=el5,ib_stack=inkernel/284/" class="external-link" target="_blank" rel="nofollow noopener">lustre-master » x86_64,client,el5,inkernel #284</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> llite: Parallel writes to same file results in zero file</p> <p>Oleg Drokin : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/master&amp;a=commit&amp;h=0356a2376375020abb861423ce557767dadf593e" class="external-link" target="_blank" rel="nofollow noopener">0356a2376375020abb861423ce557767dadf593e</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-master/./arch=i686,build_type=server,distro=el5,ib_stack=inkernel/284/" class="external-link" target="_blank" rel="nofollow noopener">lustre-master » i686,server,el5,inkernel #284</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> llite: Parallel writes to same file results in zero file</p> <p>Oleg Drokin : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/master&amp;a=commit&amp;h=0356a2376375020abb861423ce557767dadf593e" class="external-link" target="_blank" rel="nofollow noopener">0356a2376375020abb861423ce557767dadf593e</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-master/./arch=i686,build_type=server,distro=el6,ib_stack=inkernel/284/" class="external-link" target="_blank" rel="nofollow noopener">lustre-master » i686,server,el6,inkernel #284</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> llite: Parallel writes to same file results in zero file</p> <p>Oleg Drokin : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/master&amp;a=commit&amp;h=0356a2376375020abb861423ce557767dadf593e" class="external-link" target="_blank" rel="nofollow noopener">0356a2376375020abb861423ce557767dadf593e</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-master/./arch=x86_64,build_type=client,distro=sles11,ib_stack=inkernel/284/" class="external-link" target="_blank" rel="nofollow noopener">lustre-master » x86_64,client,sles11,inkernel #284</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> llite: Parallel writes to same file results in zero file</p> <p>Oleg Drokin : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/master&amp;a=commit&amp;h=0356a2376375020abb861423ce557767dadf593e" class="external-link" target="_blank" rel="nofollow noopener">0356a2376375020abb861423ce557767dadf593e</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-master/./arch=x86_64,build_type=client,distro=el6,ib_stack=inkernel/284/" class="external-link" target="_blank" rel="nofollow noopener">lustre-master » x86_64,client,el6,inkernel #284</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> llite: Parallel writes to same file results in zero file</p> <p>Oleg Drokin : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/master&amp;a=commit&amp;h=0356a2376375020abb861423ce557767dadf593e" class="external-link" target="_blank" rel="nofollow noopener">0356a2376375020abb861423ce557767dadf593e</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-master/./arch=i686,build_type=client,distro=el5,ib_stack=inkernel/284/" class="external-link" target="_blank" rel="nofollow noopener">lustre-master » i686,client,el5,inkernel #284</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> llite: Parallel writes to same file results in zero file</p> <p>Oleg Drokin : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/master&amp;a=commit&amp;h=0356a2376375020abb861423ce557767dadf593e" class="external-link" target="_blank" rel="nofollow noopener">0356a2376375020abb861423ce557767dadf593e</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-master/./arch=x86_64,build_type=server,distro=el5,ib_stack=inkernel/284/" class="external-link" target="_blank" rel="nofollow noopener">lustre-master » x86_64,server,el5,inkernel #284</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> llite: Parallel writes to same file results in zero file</p> <p>Oleg Drokin : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/master&amp;a=commit&amp;h=0356a2376375020abb861423ce557767dadf593e" class="external-link" target="_blank" rel="nofollow noopener">0356a2376375020abb861423ce557767dadf593e</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-master/./arch=x86_64,build_type=client,distro=ubuntu1004,ib_stack=inkernel/284/" class="external-link" target="_blank" rel="nofollow noopener">lustre-master » x86_64,client,ubuntu1004,inkernel #284</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> llite: Parallel writes to same file results in zero file</p> <p>Oleg Drokin : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/master&amp;a=commit&amp;h=0356a2376375020abb861423ce557767dadf593e" class="external-link" target="_blank" rel="nofollow noopener">0356a2376375020abb861423ce557767dadf593e</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-master/./arch=x86_64,build_type=server,distro=el5,ib_stack=ofa/284/" class="external-link" target="_blank" rel="nofollow noopener">lustre-master » x86_64,server,el5,ofa #284</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> llite: Parallel writes to same file results in zero file</p> <p>Oleg Drokin : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/master&amp;a=commit&amp;h=0356a2376375020abb861423ce557767dadf593e" class="external-link" target="_blank" rel="nofollow noopener">0356a2376375020abb861423ce557767dadf593e</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-master/./arch=i686,build_type=server,distro=el5,ib_stack=ofa/284/" class="external-link" target="_blank" rel="nofollow noopener">lustre-master » i686,server,el5,ofa #284</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> llite: Parallel writes to same file results in zero file</p> <p>Oleg Drokin : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/master&amp;a=commit&amp;h=0356a2376375020abb861423ce557767dadf593e" class="external-link" target="_blank" rel="nofollow noopener">0356a2376375020abb861423ce557767dadf593e</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-master/./arch=x86_64,build_type=client,distro=el5,ib_stack=ofa/284/" class="external-link" target="_blank" rel="nofollow noopener">lustre-master » x86_64,client,el5,ofa #284</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> llite: Parallel writes to same file results in zero file</p> <p>Oleg Drokin : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/master&amp;a=commit&amp;h=0356a2376375020abb861423ce557767dadf593e" class="external-link" target="_blank" rel="nofollow noopener">0356a2376375020abb861423ce557767dadf593e</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> </ul> <p>got kernel panic when running conf-sanity test 22, 23a on build <a href="http://build.whamcloud.com/job/lustre-reviews/2387/" class="external-link" target="_blank" rel="nofollow noopener">http://build.whamcloud.com/job/lustre-reviews/2387/</a> rhel5-x86_64</p> <p>Lustre: DEBUG MARKER: == test 22: start a client before osts (should return errs) == 15:54:17<br/> Lustre: DEBUG MARKER: ost now in FULL state<br/> LustreError: 152-6: Ignoring deprecated mount option 'acl'.<br/> Lustre: MGC192.168.4.2@o2ib: Reactivating import<br/> Lustre: Client lustre-client has started<br/> Lustre: 25423:0:(client.c:1487:ptlrpc_expire_one_request()) @@@ Request x1381780714160180 sent from lustre-OST0000-osc-ffff810326f68800 to NID 192.168.4.131@o2ib 5s ago has timed out (5s prior to deadline).<br/> req@ffff810325487400 x1381780714160180/t0 o8-&gt;lustre-OST0000_UUID@192.168.4.131@o2ib:28/4 lens 368/584 e 0 to 1 dl 1317768871 ref 1 fl Rpc:N/0/0 rc 0/0<br/> LustreError: 30513:0:(ldlm_request.c:1039:ldlm_cli_cancel_req()) Got rc -108 from cancel RPC: canceling anyway<br/> LustreError: 30513:0:(ldlm_request.c:1039:ldlm_cli_cancel_req()) Skipped 2 previous similar messages<br/> LustreError: 30513:0:(ldlm_request.c:1597:ldlm_cli_cancel_list()) ldlm_cli_cancel_list: -108<br/> LustreError: 30513:0:(ldlm_request.c:1597:ldlm_cli_cancel_list()) Skipped 2 previous similar messages<br/> Lustre: client ffff810326f68800 umount complete<br/> LustreError: 152-6: Ignoring deprecated mount option 'acl'.<br/> Lustre: MGC192.168.4.2@o2ib: Reactivating import<br/> Lustre: Client lustre-client has started<br/> LustreError: 30629:0:(ldlm_request.c:1039:ldlm_cli_cancel_req()) Got rc -108 from cancel RPC: canceling anyway<br/> LustreError: 30629:0:(ldlm_request.c:1039:ldlm_cli_cancel_req()) Skipped 1 previous similar message<br/> LustreError: 30629:0:(ldlm_request.c:1597:ldlm_cli_cancel_list()) ldlm_cli_cancel_list: -108<br/> LustreError: 30629:0:(ldlm_request.c:1597:ldlm_cli_cancel_list()) Skipped 1 previous similar message<br/> Lustre: client ffff81033eaf8c00 umount complete<br/> LustreError: 152-6: Ignoring deprecated mount option 'acl'.<br/> Lustre: MGC192.168.4.2@o2ib: Reactivating import<br/> LustreError: 11-0: an error occurred while communicating with 192.168.4.2@o2ib. The mds_connect operation failed with -11<br/> Lustre: Client lustre-client has started<br/> Lustre: setting import lustre-MDT0000_UUID INACTIVE by administrator request<br/> Lustre: setting import lustre-OST0000_UUID INACTIVE by administrator request<br/> LustreError: 31531:0:(ldlm_request.c:1039:ldlm_cli_cancel_req()) Got rc -108 from cancel RPC: canceling anyway<br/> LustreError: 31531:0:(ldlm_request.c:1597:ldlm_cli_cancel_list()) ldlm_cli_cancel_list: -108<br/> Lustre: 31531:0:(client.c:1487:ptlrpc_expire_one_request()) @@@ Request x1381780836843537 sent from MGC192.168.4.2@o2ib to NID 192.168.4.2@o2ib 6s ago has timed out (6s prior to deadline).<br/> req@ffff810326cbc800 x1381780836843537/t0 o251-&gt;MGS@MGC192.168.4.2@o2ib_0:26/25 lens 192/384 e 0 to 1 dl 1317768914 ref 1 fl Rpc:N/0/0 rc 0/0<br/> Lustre: client ffff8103263fb000 umount complete<br/> LustreError: 152-6: Ignoring deprecated mount option 'acl'.<br/> Lustre: MGC192.168.4.2@o2ib: Reactivating import<br/> LustreError: 11-0: an error occurred while communicating with 192.168.4.2@o2ib. The mds_connect operation failed with -16<br/> LustreError: 31583:0:(lov_obd.c:1009:lov_cleanup()) lov tgt 0 not cleaned! deathrow=0, lovrc=1<br/> LustreError: 31583:0:(ldlm_resource.c:636:ldlm_namespace_free_post()) ASSERTION(list_empty(&amp;ns-&gt;ns_list_chain)) failed<br/> LustreError: 31583:0:(ldlm_resource.c:636:ldlm_namespace_free_post()) LBUG<br/> Pid: 31583, comm: mount.lustre</p> <p>Call Trace:<br/> <span class="error">&#91;&lt;ffffffff8007725f&gt;&#93;</span> do_flush_tlb_all+0x0/0x6a<br/> <span class="error">&#91;&lt;ffffffff887af6a1&gt;&#93;</span> libcfs_debug_dumpstack+0x51/0x60 <span class="error">&#91;libcfs&#93;</span><br/> <span class="error">&#91;&lt;ffffffff887afbda&gt;&#93;</span> lbug_with_loc+0x7a/0xd0 <span class="error">&#91;libcfs&#93;</span><br/> <span class="error">&#91;&lt;ffffffff887b7fc0&gt;&#93;</span> tracefile_init+0x0/0x110 <span class="error">&#91;libcfs&#93;</span><br/> <span class="error">&#91;&lt;ffffffff888ddc08&gt;&#93;</span> ldlm_namespace_free_post+0x2f8/0x3f0 <span class="error">&#91;ptlrpc&#93;</span><br/> <span class="error">&#91;&lt;ffffffff888e473c&gt;&#93;</span> client_obd_cleanup+0x6c/0x100 <span class="error">&#91;ptlrpc&#93;</span><br/> <span class="error">&#91;&lt;ffffffff88a02bc5&gt;&#93;</span> osc_cleanup+0x255/0x2d0 <span class="error">&#91;osc&#93;</span><br/> <span class="error">&#91;&lt;ffffffff8887157c&gt;&#93;</span> class_decref+0x5dc/0x730 <span class="error">&#91;obdclass&#93;</span><br/> <span class="error">&#91;&lt;ffffffff88859962&gt;&#93;</span> obd_zombie_impexp_cull+0x82/0xa0 <span class="error">&#91;obdclass&#93;</span><br/> <span class="error">&#91;&lt;ffffffff8887285d&gt;&#93;</span> class_detach+0x2bd/0x350 <span class="error">&#91;obdclass&#93;</span><br/> <span class="error">&#91;&lt;ffffffff8885da89&gt;&#93;</span> class_name2obd+0x9/0x30 <span class="error">&#91;obdclass&#93;</span><br/> <span class="error">&#91;&lt;ffffffff8887662e&gt;&#93;</span> class_process_config+0x1dae/0x3180 <span class="error">&#91;obdclass&#93;</span><br/> <span class="error">&#91;&lt;ffffffff88878547&gt;&#93;</span> class_manual_cleanup+0xb47/0xe10 <span class="error">&#91;obdclass&#93;</span><br/> <span class="error">&#91;&lt;ffffffff8885f66f&gt;&#93;</span> class_devices_in_group+0x4f/0xa0 <span class="error">&#91;obdclass&#93;</span><br/> <span class="error">&#91;&lt;ffffffff88b1c06d&gt;&#93;</span> ll_put_super+0x1bd/0x2f0 <span class="error">&#91;lustre&#93;</span><br/> <span class="error">&#91;&lt;ffffffff88b1e33a&gt;&#93;</span> ll_fill_super+0x219a/0x2370 <span class="error">&#91;lustre&#93;</span><br/> <span class="error">&#91;&lt;ffffffff888e469e&gt;&#93;</span> client_connect_import+0x4ee/0x520 <span class="error">&#91;ptlrpc&#93;</span><br/> <span class="error">&#91;&lt;ffffffff8888ab50&gt;&#93;</span> lustre_fill_super+0x1770/0x1970 <span class="error">&#91;obdclass&#93;</span><br/> <span class="error">&#91;&lt;ffffffff800ef592&gt;&#93;</span> get_filesystem+0x12/0x3b<br/> <span class="error">&#91;&lt;ffffffff800e6298&gt;&#93;</span> sget+0x365/0x377<br/> <span class="error">&#91;&lt;ffffffff800e69fd&gt;&#93;</span> set_anon_super+0x0/0xab<br/> <span class="error">&#91;&lt;ffffffff888893e0&gt;&#93;</span> lustre_fill_super+0x0/0x1970 <span class="error">&#91;obdclass&#93;</span><br/> <span class="error">&#91;&lt;ffffffff800e6c77&gt;&#93;</span> get_sb_nodev+0x4f/0x97<br/> <span class="error">&#91;&lt;ffffffff800e654f&gt;&#93;</span> vfs_kern_mount+0x93/0x11a<br/> <span class="error">&#91;&lt;ffffffff800e6618&gt;&#93;</span> do_kern_mount+0x36/0x4d<br/> <span class="error">&#91;&lt;ffffffff800f0ec1&gt;&#93;</span> do_mount+0x6a9/0x719<br/> <span class="error">&#91;&lt;ffffffff8000d044&gt;&#93;</span> do_lookup+0x65/0x1e6<br/> <span class="error">&#91;&lt;ffffffff8002cc16&gt;&#93;</span> mntput_no_expire+0x19/0x89<br/> <span class="error">&#91;&lt;ffffffff8000a81a&gt;&#93;</span> __link_path_walk+0xf79/0xfb9<br/> <span class="error">&#91;&lt;ffffffff8002cc16&gt;&#93;</span> mntput_no_expire+0x19/0x89<br/> <span class="error">&#91;&lt;ffffffff8000eb94&gt;&#93;</span> link_path_walk+0xa6/0xb2<br/> <span class="error">&#91;&lt;ffffffff800ce6ab&gt;&#93;</span> zone_statistics+0x3e/0x6d<br/> <span class="error">&#91;&lt;ffffffff8000f41e&gt;&#93;</span> __alloc_pages+0x78/0x308<br/> <span class="error">&#91;&lt;ffffffff8004c76c&gt;&#93;</span> sys_mount+0x8a/0xcd<br/> <span class="error">&#91;&lt;ffffffff8005d28d&gt;&#93;</span> tracesys+0xd5/0xe0</p> <p>Message fromLustreError: dumping log to /tmp/lustre-log.1317768920.31583<br/> syslogd@ at Tue Oct 4 15:55:20 2011 ...<br/> client-15 kernel: LustreError: 31583:0:(ldlm_resource.c:636:ldlm_namespace_free_post()) ASSERTION(list_empty(&amp;ns-&gt;ns_list_chain)) failed</p> <p>Message from syslogd@ at Tue Oct 4 15:55:20 2011 ...<br/> client-15 kernel: LustreError: 31583:0:(ldlm_resource.c:636:ldlm_namespace_free_post()) LBUG<br/> general protection fault: 0000 <span class="error">&#91;1&#93;</span> SMP <br/> last sysfs file: /devices/pci0000:00/0000:00:00.0/irq<br/> CPU 2 <br/> Modules linked in: mgc(U) lustre(U) lov(U) mdc(U) lquota(U) osc(U) ksocklnd(U) ko2iblnd(U) ptlrpc(U) obdclass(U) lnet(U) lvfs(U) libcfs(U) autofs4 hidp rfcomm l2cap bluetooth lockd sunrpc cpufreq_ondemand acpi_cpufreq freq_table mperf be2iscsi iscsi_tcp bnx2i cnic uio cxgb3i iw_cxgb3 cxgb3 libiscsi_tcp ib_iser libiscsi2 scsi_transport_iscsi2 scsi_transport_iscsi ib_srp rds ib_sdp ib_ipoib ipoib_helper ipv6 xfrm_nalgo crypto_api rdma_ucm rdma_cm ib_ucm ib_uverbs ib_umad ib_cm iw_cm ib_addr ib_sa loop dm_mirror dm_multipath scsi_dh video backlight sbs power_meter hwmon i2c_ec dell_wmi wmi button battery asus_acpi acpi_memhotplug ac parport_pc lp parport mlx4_ib ib_mad ib_core mlx4_en joydev sg igb 8021q shpchp dca mlx4_core i2c_i801 i2c_core tpm_tis tpm i7core_edac edac_mc serio_raw tpm_bios pcspkr dm_raid45 dm_message dm_region_hash dm_log dm_mod dm_mem_cache ahci libata sd_mod scsi_mod ext3 jbd uhci_hcd ohci_hcd ehci_hcd<br/> Pid: 31592, comm: ldlm_poold Tainted: G 2.6.18-238.12.1.el5 #1<br/> RIP: 0010:<span class="error">&#91;&lt;ffffffff8890325f&gt;&#93;</span> <span class="error">&#91;&lt;ffffffff8890325f&gt;&#93;</span> :ptlrpc:ldlm_pool_recalc+0xdf/0x130<br/> RSP: 0000:ffff8103271a5e20 EFLAGS: 00010246<br/> RAX: 5a5a5a5a5a5a5a5a RBX: 0000000000000000 RCX: ffff810336983e40<br/> RDX: ffffffff8898c6f0 RSI: ffff810336983e40 RDI: ffff810325bb452c<br/> RBP: ffff810325bb44c0 R08: ffff8103271a4000 R09: 000000000000003e<br/> R10: ffff81010b7e4038 R11: 0000000000000246 R12: 0000000000000002<br/> R13: ffffffff88998660 R14: 0000000000000002 R15: 0000000000000002<br/> FS: 00002b798882e6e0(0000) GS:ffff81010b763ec0(0000) knlGS:0000000000000000<br/> CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b<br/> CR2: 00002b7fcca2a500 CR3: 00000003283af000 CR4: 00000000000006e0<br/> Process ldlm_poold (pid: 31592, threadinfo ffff8103271a4000, task ffff8103255b57e0)<br/> Stack: ffff810325bb4400 ffffffff88998660 0000000000000002 ffffffff88998660<br/> 0000000000000002 ffffffff889040bf 000000010008d605 ffffffff8005bbcb<br/> 000000010008d605 ffffffff80063893 0000000000000000 0000000000200200<br/> Call Trace:<br/> <span class="error">&#91;&lt;ffffffff889040bf&gt;&#93;</span> :ptlrpc:ldlm_pools_recalc+0x2bf/0x2f0<br/> <span class="error">&#91;&lt;ffffffff8005bbcb&gt;&#93;</span> del_timer_sync+0xc/0x16<br/> <span class="error">&#91;&lt;ffffffff80063893&gt;&#93;</span> schedule_timeout+0x92/0xad<br/> <span class="error">&#91;&lt;ffffffff88906226&gt;&#93;</span> :ptlrpc:ldlm_pools_thread_main+0x106/0x2cf<br/> <span class="error">&#91;&lt;ffffffff8008e430&gt;&#93;</span> default_wake_function+0x0/0xe<br/> <span class="error">&#91;&lt;ffffffff8005dfb1&gt;&#93;</span> child_rip+0xa/0x11<br/> <span class="error">&#91;&lt;ffffffff88906120&gt;&#93;</span> :ptlrpc:ldlm_pools_thread_main+0x0/0x2cf<br/> <span class="error">&#91;&lt;ffffffff8005dfa7&gt;&#93;</span> child_rip+0x0/0x11</p> <p>Code: 48 8b 00 48 85 c0 74 1b 48 89 ef ff d0 48 8b bd c0 00 00 00 <br/> RIP <span class="error">&#91;&lt;ffffffff8890325f&gt;&#93;</span> :ptlrpc:ldlm_pool_recalc+0xdf/0x130<br/> RSP &lt;ffff8103271a5e20&gt;<br/> &lt;0&gt;Kernel panic - not syncing: Fatal exception</p> <p>Sarah, this panic is due to <a href="https://jira.whamcloud.com/browse/LU-607" title="port bz24419 (ldlm namespace lock contention during oom)" class="issue-link" data-issue-key="LU-607"><del>LU-607</del></a>, while latest b1_8 codebase had reverted the wrong patch, which should solve the panic.</p> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/red.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-b1_8/./arch=i686,build_type=client,distro=el5,ib_stack=ofa/136/" class="external-link" target="_blank" rel="nofollow noopener">lustre-b1_8 » i686,client,el5,ofa #136</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> Parallel writes to same file results in a file of zeroes</p> <p>Johann Lombardi : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/b1_8&amp;a=commit&amp;h=0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68" class="external-link" target="_blank" rel="nofollow noopener">0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> <li>lustre/tests/conf-sanity.sh</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-b1_8/./arch=x86_64,build_type=client,distro=el5,ib_stack=inkernel/136/" class="external-link" target="_blank" rel="nofollow noopener">lustre-b1_8 » x86_64,client,el5,inkernel #136</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> Parallel writes to same file results in a file of zeroes</p> <p>Johann Lombardi : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/b1_8&amp;a=commit&amp;h=0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68" class="external-link" target="_blank" rel="nofollow noopener">0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68</a><br/> Files : </p> <ul> <li>lustre/tests/conf-sanity.sh</li> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/red.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-b1_8/./arch=x86_64,build_type=client,distro=el5,ib_stack=ofa/136/" class="external-link" target="_blank" rel="nofollow noopener">lustre-b1_8 » x86_64,client,el5,ofa #136</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> Parallel writes to same file results in a file of zeroes</p> <p>Johann Lombardi : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/b1_8&amp;a=commit&amp;h=0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68" class="external-link" target="_blank" rel="nofollow noopener">0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68</a><br/> Files : </p> <ul> <li>lustre/tests/conf-sanity.sh</li> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/red.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-b1_8/./arch=x86_64,build_type=server,distro=el5,ib_stack=ofa/136/" class="external-link" target="_blank" rel="nofollow noopener">lustre-b1_8 » x86_64,server,el5,ofa #136</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> Parallel writes to same file results in a file of zeroes</p> <p>Johann Lombardi : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/b1_8&amp;a=commit&amp;h=0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68" class="external-link" target="_blank" rel="nofollow noopener">0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68</a><br/> Files : </p> <ul> <li>lustre/tests/conf-sanity.sh</li> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-b1_8/./arch=x86_64,build_type=client,distro=el6,ib_stack=inkernel/136/" class="external-link" target="_blank" rel="nofollow noopener">lustre-b1_8 » x86_64,client,el6,inkernel #136</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> Parallel writes to same file results in a file of zeroes</p> <p>Johann Lombardi : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/b1_8&amp;a=commit&amp;h=0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68" class="external-link" target="_blank" rel="nofollow noopener">0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> <li>lustre/tests/conf-sanity.sh</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-b1_8/./arch=x86_64,build_type=server,distro=el5,ib_stack=inkernel/136/" class="external-link" target="_blank" rel="nofollow noopener">lustre-b1_8 » x86_64,server,el5,inkernel #136</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> Parallel writes to same file results in a file of zeroes</p> <p>Johann Lombardi : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/b1_8&amp;a=commit&amp;h=0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68" class="external-link" target="_blank" rel="nofollow noopener">0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> <li>lustre/tests/conf-sanity.sh</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-b1_8/./arch=i686,build_type=client,distro=el5,ib_stack=inkernel/136/" class="external-link" target="_blank" rel="nofollow noopener">lustre-b1_8 » i686,client,el5,inkernel #136</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> Parallel writes to same file results in a file of zeroes</p> <p>Johann Lombardi : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/b1_8&amp;a=commit&amp;h=0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68" class="external-link" target="_blank" rel="nofollow noopener">0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> <li>lustre/tests/conf-sanity.sh</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-b1_8/./arch=i686,build_type=client,distro=el6,ib_stack=inkernel/136/" class="external-link" target="_blank" rel="nofollow noopener">lustre-b1_8 » i686,client,el6,inkernel #136</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> Parallel writes to same file results in a file of zeroes</p> <p>Johann Lombardi : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/b1_8&amp;a=commit&amp;h=0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68" class="external-link" target="_blank" rel="nofollow noopener">0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> <li>lustre/tests/conf-sanity.sh</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/red.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-b1_8/./arch=i686,build_type=server,distro=el5,ib_stack=ofa/136/" class="external-link" target="_blank" rel="nofollow noopener">lustre-b1_8 » i686,server,el5,ofa #136</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> Parallel writes to same file results in a file of zeroes</p> <p>Johann Lombardi : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/b1_8&amp;a=commit&amp;h=0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68" class="external-link" target="_blank" rel="nofollow noopener">0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68</a><br/> Files : </p> <ul> <li>lustre/tests/conf-sanity.sh</li> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-b1_8/./arch=x86_64,build_type=client,distro=ubuntu1004,ib_stack=inkernel/136/" class="external-link" target="_blank" rel="nofollow noopener">lustre-b1_8 » x86_64,client,ubuntu1004,inkernel #136</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> Parallel writes to same file results in a file of zeroes</p> <p>Johann Lombardi : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/b1_8&amp;a=commit&amp;h=0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68" class="external-link" target="_blank" rel="nofollow noopener">0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68</a><br/> Files : </p> <ul> <li>lustre/tests/conf-sanity.sh</li> <li>lustre/llite/dcache.c</li> </ul> <p>Integrated in <span class="image-wrap" style=""><img src="http://build.whamcloud.com/images/16x16/blue.png" style="border: 0px solid black" /></span> <a href="http://build.whamcloud.com/job/lustre-b1_8/./arch=i686,build_type=server,distro=el5,ib_stack=inkernel/136/" class="external-link" target="_blank" rel="nofollow noopener">lustre-b1_8 » i686,server,el5,inkernel #136</a><br/> <a href="https://jira.whamcloud.com/browse/LU-721" title="Parallel writes to same file results in a file of zeroes" class="issue-link" data-issue-key="LU-721"><del>LU-721</del></a> Parallel writes to same file results in a file of zeroes</p> <p>Johann Lombardi : <a href="http://git.whamcloud.com/gitweb?p=fs/lustre-release.git;a=shortlog;h=refs/heads/b1_8&amp;a=commit&amp;h=0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68" class="external-link" target="_blank" rel="nofollow noopener">0f7efbe4dcc8c78fcf73660ded113bcaa6d5ae68</a><br/> Files : </p> <ul> <li>lustre/llite/dcache.c</li> <li>lustre/tests/conf-sanity.sh</li> </ul> <p>Fixed for 1.8.7 and 2.2</p> Bugzilla ID 24548.0 Development Rank 1|hzv8fr: Rank (Obsolete) 4901 Severity