Whamcloud Community JIRA https://jira.whamcloud.com This file is an XML representation of an issue en-us 9.4.14 940014 05-12-2023 [LU-3534] async update cross-MDTs https://jira.whamcloud.com/browse/LU-3534 Lustre <p>This bug is for tracking async updates between MDTs.</p> LU-3534 async update cross-MDTs New Feature Minor Resolved Fixed Di Wang Di Wang Sat, 29 Jun 2013 17:44:20 +0000 Thu, 14 Jun 2018 21:41:35 +0000 Thu, 28 Jan 2016 19:10:45 +0000 Lustre 2.8.0 0 9 <p>wangdi (di.wang@intel.com) uploaded a new patch: <a href="http://review.whamcloud.com/13786" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/13786</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-3534" title="async update cross-MDTs" class="issue-link" data-issue-key="LU-3534"><del>LU-3534</del></a> osp: transfer updates with bulk RPC<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: 4432ca911c9bbc17fcd4f38ace16c4a931321b18</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/10794/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/10794/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-3534" title="async update cross-MDTs" class="issue-link" data-issue-key="LU-3534"><del>LU-3534</del></a> osp: move RPC pack from declare to execution phase<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: de8572645d287d17c409b99dabdf176822d91486</p> <p>Newbie alert. I managed to create a file system with the latest patches to test DNE2. So attempting to create a directory I got this error:</p> <p>root@ninja06 scratch]# lfs setdirstripe -c 14 jsimmons<br/> error on LL_IOC_LMV_SETSTRIPE 'jsimmons' (3): Inappropriate ioctl for device<br/> error: setdirstripe: create stripe dir 'jsimmons' failed</p> <p>Did I miss something?</p> <p>Hmm, which build are you using? Could you get me the -1 debug log? Btw: with the current patches, you can only create maximum 16 stripes striped directory, and I am working on a patch to resolve this on <a href="https://jira.whamcloud.com/browse/LU-6602" title="ASSERTION( rec-&gt;lrh_len &lt;= 8192 ) failed" class="issue-link" data-issue-key="LU-6602"><del>LU-6602</del></a>.</p> <p>I was attempting to collect all the patches and piece them together but that didn't work out so well. I grabbed your full DNE2 patch and it seems to work so far. I'm setting up my test system right now to start testing at smaller scale. I will post my results.</p> <p>First issue I'm seeing is that when I create a directory with a specific MDS stripe count that any new directories are not inheriting the new stripe setting.</p> <p>It only inherit default dirstripe, i.e. only stripe setting set by "lfs setdirstripe -D xxx" will be inherited. If that is your case, could you please post the command lines here? thanks</p> <p>Sorry I missed the -D option which explains why it didn't inherit. User error there <img class="emoticon" src="https://jira.whamcloud.com/images/icons/emoticons/smile.png" height="16" width="16" align="absmiddle" alt="" border="0"/> With my DNE2 setup I attempted to start some jobs on our test cluster and the job got stuck for hours attempting to run. So I did testing to see what was breaking. A simple md5sum on files showed the problem very easily. For normal directories md5sum on a file came back very fast. </p> <p><span class="error">&#91;root@ninja06 johndoe&#93;</span># date;md5sum ior;date<br/> Fri May 29 10:08:24 EDT 2015<br/> 4ba1b26f0a4b71dccb237d3fd25f3b67 ior<br/> Fri May 29 10:08:24 EDT 2015</p> <p>But for DNE2 directories I saw this:</p> <p><span class="error">&#91;root@ninja06 jsimmons&#93;</span># date;md5sum simul;date<br/> Fri May 29 10:08:38 EDT 2015<br/> 9fef8669fb0e6669ac646d69062521d3 simul<br/> Fri May 29 10:09:59 EDT 2015</p> <p>This is not a issue for stats. An ls on the file simul comes back very fast. I did this test without your DNE2 patch set and the problem still exist. At this point I think I should open a ticket about this.</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/11909/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/11909/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-3534" title="async update cross-MDTs" class="issue-link" data-issue-key="LU-3534"><del>LU-3534</del></a> mdt: move last_rcvd obj update to LOD<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: c233f39a015943b3df8ddb555765a81b85b31083</p> <p>wangdi (di.wang@intel.com) uploaded a new patch: <a href="http://review.whamcloud.com/15163" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/15163</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-3534" title="async update cross-MDTs" class="issue-link" data-issue-key="LU-3534"><del>LU-3534</del></a> tests: a few tests cases for async update.<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: 0394d9938e655b774d86a4eef15408e7c7e01e3f</p> <p>In my testing I noticed end after a cleanup shut down of the file system when the file system is restarted all the MDS servers go into recovery with each other. The lwp layers reconnect fine without going into recovery but the OSP layer always enters recovery mode. Is this the excepted behavior?</p> <p>Yes, this is expected. LWP(light weight proxy) is not a replayable client, so it will never get into recovery mode. But OSP is a replayable client, which will always enter into recovery mode when required.</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/12825/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/12825/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-3534" title="async update cross-MDTs" class="issue-link" data-issue-key="LU-3534"><del>LU-3534</del></a> osp: send updates by separate thread<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: 2fe22edfe3c365b5c270050fdeed0a86fa74a919</p> <p>wangdi (di.wang@intel.com) uploaded a new patch: <a href="http://review.whamcloud.com/15275" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/15275</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-3534" title="async update cross-MDTs" class="issue-link" data-issue-key="LU-3534"><del>LU-3534</del></a> tests: Add dne-2.5 upgrade test<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: f17fe3836034a2359f53839cd116d08d640c1c31</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/12450/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/12450/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-3534" title="async update cross-MDTs" class="issue-link" data-issue-key="LU-3534"><del>LU-3534</del></a> update: change sync updates to async updates<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: 0136a91b6d629556ef091f5ca210c13772207df9</p> <p>Liang Zhen (liang.zhen@intel.com) uploaded a new patch: <a href="http://review.whamcloud.com/15421" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/15421</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-3534" title="async update cross-MDTs" class="issue-link" data-issue-key="LU-3534"><del>LU-3534</del></a> ptlrpc: mbits is sent within ptlrpc_body<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: b363b70a0c82bccb0d50026ccee756f72f7d3d3d</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/15421/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/15421/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-3534" title="async update cross-MDTs" class="issue-link" data-issue-key="LU-3534"><del>LU-3534</del></a> ptlrpc: mbits is sent within ptlrpc_body<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: d099fdd6cd15d0d00d9b573da5d3bfd3e4bbcb9d</p> <p>wangdi (di.wang@intel.com) uploaded a new patch: <a href="http://review.whamcloud.com/15482" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/15482</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-3534" title="async update cross-MDTs" class="issue-link" data-issue-key="LU-3534"><del>LU-3534</del></a> osp: transfer updates with bulk RPC<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: e1e3d405464b7807f0a016aff8c7df9fb174fc47</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/13786/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/13786/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-3534" title="async update cross-MDTs" class="issue-link" data-issue-key="LU-3534"><del>LU-3534</del></a> osp: transfer updates with bulk RPC<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: 044fbff00b25f127560338d35caa4d89faa4c207</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/15163/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/15163/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-3534" title="async update cross-MDTs" class="issue-link" data-issue-key="LU-3534"><del>LU-3534</del></a> tests: a few tests cases for async update.<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: c2b82ef8a12e6c55f143fbd8986c094425ed667e</p> <p>WangDi since we are near completion of this current work I recommend you open a ticket for continued DNE2 work for 2.9. I see several ticket linked to here to completed for 2.9 and I hate to see them disappear.</p> <p>Right now, all DNE2 works are linked under lu-6831, I will move unfinished tickets there.</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/15275/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/15275/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-3534" title="async update cross-MDTs" class="issue-link" data-issue-key="LU-3534"><del>LU-3534</del></a> tests: Add dne-2.5 upgrade test<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: 38d45a59d8a29bc60d690620e9bcc3eaba108d9b</p> <p>All sub-tasks have now landed for 2.8.</p> Duplicate LU-5302 Related LU-5222 LU-6663 LU-6262 LU-6297 LU-6380 LU-5571 LU-7102 LU-6287 LU-6288 LU-6289 LU-6290 LU-6291 LU-6292 LU-6293 LU-6294 LU-6295 LU-6296 LU-6328 LU-6329 LU-6330 LU-4583 LU-6362 LU-3541 LU-4837 LU-3535 LU-3536 LU-3537 LU-3538 LU-3539 LU-3540 LU-3541 LU-4076 LU-4837 Development End date Mon, 14 Dec 2015 18:07:07 +0000 Rank 1|hzvudr: Rank (Obsolete) 8898 Severity Start date Mon, 1 Jul 2013 18:07:07 +0000