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-4416 Lustre <p>tracker for 3.12 kernel support</p> <p>now that the kernel used in fc19 and fc20 is 3.12 we will need to support it soon.</p> fc19, fc20 LU-4416

support for 3.12 linux kernel

Improvement Critical Resolved Fixed Yang Sheng Bob Glossman HB patch Fri, 27 Dec 2013 17:00:09 +0000 Fri, 20 Nov 2015 22:34:29 +0000 Thu, 16 Jul 2015 12:56:26 +0000 Lustre 2.6.0 Lustre 2.8.0 0 14 <p>At a minimum there are a few upstream commits from Peng Tao that need to be back ported:</p> <p><a href="https://git.kernel.org/cgit/linux/kernel/git/gregkh/staging.git/commit/drivers/staging/lustre?h=staging-next&amp;id=ea8352c289294e21ee13bdb105f55dc63497acff" class="external-link" target="_blank" rel="nofollow noopener">https://git.kernel.org/cgit/linux/kernel/git/gregkh/staging.git/commit/drivers/staging/lustre?h=staging-next&amp;id=ea8352c289294e21ee13bdb105f55dc63497acff</a> staging/lustre/libcfs: cleanup linux-mem.h</p> <p><a href="https://git.kernel.org/cgit/linux/kernel/git/gregkh/staging.git/commit/drivers/staging/lustre?h=staging-next&amp;id=3bb22ec53e2bd12a241ed84359bffd591a40ab87" class="external-link" target="_blank" rel="nofollow noopener">https://git.kernel.org/cgit/linux/kernel/git/gregkh/staging.git/commit/drivers/staging/lustre?h=staging-next&amp;id=3bb22ec53e2bd12a241ed84359bffd591a40ab87</a> staging/lustre/ptlrpc: convert to new shrinker API</p> <p><a href="https://git.kernel.org/cgit/linux/kernel/git/gregkh/staging.git/commit/drivers/staging/lustre?h=staging-next&amp;id=fe92a0557a6f332119c51fdd2f3d574040989447" class="external-link" target="_blank" rel="nofollow noopener">https://git.kernel.org/cgit/linux/kernel/git/gregkh/staging.git/commit/drivers/staging/lustre?h=staging-next&amp;id=fe92a0557a6f332119c51fdd2f3d574040989447</a> staging/lustre/obdclass: convert lu_object shrinker to count/scan API</p> <p><a href="https://git.kernel.org/cgit/linux/kernel/git/gregkh/staging.git/commit/drivers/staging/lustre?h=staging-next&amp;id=cbc3769ecd74b183d3ba5e11264cf484d8572a00" class="external-link" target="_blank" rel="nofollow noopener">https://git.kernel.org/cgit/linux/kernel/git/gregkh/staging.git/commit/drivers/staging/lustre?h=staging-next&amp;id=cbc3769ecd74b183d3ba5e11264cf484d8572a00</a> staging/lustre/ldlm: convert to shrinkers to count/scan API</p> <p>These upstream mods are only good for the exact kernel version they reside in. Backports will need autoconf support to adapt to different kernel versions as well as 3.12.</p> <p><a href="http://review.whamcloud.com/8799" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/8799</a><br/> <a href="http://review.whamcloud.com/8800" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/8800</a><br/> <a href="http://review.whamcloud.com/8801" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/8801</a></p> <p>another patch is at: <a href="http://review.whamcloud.com/9230" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/9230</a> from <a href="https://jira.whamcloud.com/browse/LU-4614" title="Patch collection from upstream kernels" class="issue-link" data-issue-key="LU-4614"><del>LU-4614</del></a>.</p> <p><a href="https://jira.whamcloud.com/browse/LU-4614" title="Patch collection from upstream kernels" class="issue-link" data-issue-key="LU-4614"><del>LU-4614</del></a> vs. <a href="https://jira.whamcloud.com/browse/LU-4416" title="support for 3.12 linux kernel" class="issue-link" data-issue-key="LU-4416"><del>LU-4416</del></a>, really confusing.</p> <p>Last sanity test result:</p> <p>sanity: FAIL: test_17m e2fsck should not report error upon short/long symlink MDT: rc=4<br/> sanity: FAIL: test_103 permissions failed<br/> sanity: FAIL: test_133e Bad write_bytes sum, expected 1376256, got 0<br/> sanity: FAIL: test_160a User cl1 not found in changelog_users<br/> sanity: FAIL: test_160b User cl2 not found in changelog_users<br/> sanity: FAIL: test_161c flag 0x0 is not 0x1<br/> sanity: FAIL: test_184a swap of file layout failed<br/> sanity: FAIL: test_184c swap of /mnt/lustre/d184c.sanity/184c/file1 and /mnt/lustre/d184c.sanity/184c/file2 failed<br/> sanity: FAIL: test_200 failed to use fallback striping for empty pool<br/> sanity: FAIL: test_200 test_200 failed with 2</p> <p>test_182 dead lock the kernel<br/> test_208 cannot umount<br/> test_228b cannot umount</p> <p>Is this for ZFS? Do you have a shrinker patch?</p> <p>It is ldiskfs. Yes, I'll commit it shortly.</p> <p><a href="http://review.whamcloud.com/9300" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/9300</a> shrinker change.</p> <p>Last sanity status:</p> <p>sanity: FAIL: test_17k rsync failed with xattrs enabled<br/> sanity: FAIL: test_17l lgetxattr_size_check /mnt/lustre/d17l.sanity lustre.lov failed<br/> sanity: FAIL: test_17m e2fsck should not report error upon short/long symlink MDT: rc=4<br/> sanity: FAIL: test_53 can not match last_seq/last_id for <b>OST</b>-osc-MDT0000<br/> sanity: FAIL: test_65k setstripe should have succeeded<br/> sanity: FAIL: test_101b Too many (5632) discarded pages with size (8192)<br/> sanity: FAIL: test_103 permissions failed<br/> sanity: FAIL: test_116b can't create<br/> sanity: FAIL: test_127a Missing read_bytes stats<br/> sanity: FAIL: test_130b FIEMAP on /mnt/lustre/f130b.sanity failed; returned wrong number of luns or wrong len for OST 0001<br/> sanity: FAIL: test_130c FIEMAP on /mnt/lustre/f130c.sanity failed; returned wrong number of luns or wrong len for OST 0001<br/> sanity: FAIL: test_130e FIEMAP on /mnt/lustre/f130e.sanity failed; returned wrong number of luns or wrong len for OST 0001<br/> sanity: FAIL: test_133c The counter for destroy on ost was not incremented<br/> sanity: FAIL: test_133e Bad write_bytes sum, expected 1376256, got 0<br/> sanity: FAIL: test_184c concurrent write on /mnt/lustre/d184c.sanity/184c/file1 failed<br/> sanity: FAIL: test_220 test_220 failed with 6</p> <p>test_209 stuck in shrinker process.</p> <p>Last sanity status:</p> <p>sanity: FAIL: test_17m e2fsck should not report error upon short/long symlink MDT: rc=4<br/> sanity: FAIL: test_103 permissions failed<br/> sanity: FAIL: test_184c concurrent write on /mnt/lustre/d184c.sanity/184c/file1 failed<br/> sanity: FAIL: test_220 test_220 failed with 3<br/> sanity: FAIL: test_231b dd of=/mnt/lustre/d231b.sanity/f231b.sanity seek=510 failed</p> <p>test_209 stuck on shrink.</p> <p>Link with test_103 failed.</p> <p>SLES12 is also 3.12 based, so I can lend a hand here as well.l</p> <p>I have it building against SLES12 Beta5. No testing done yet, but my recipe looks like:</p> <p>Existing commits:<br/> <a href="http://review.whamcloud.com/9300" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/9300</a><br/> <a href="http://review.whamcloud.com/9384" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/9384</a><br/> <a href="http://review.whamcloud.com/7936" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/7936</a><br/> <a href="http://review.whamcloud.com/7934" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/7934</a><br/> <a href="http://review.whamcloud.com/8036" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/8036</a><br/> <a href="http://review.whamcloud.com/8049" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/8049</a></p> <p>New commits:<br/> <a href="http://review.whamcloud.com/10158" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/10158</a><br/> <a href="http://review.whamcloud.com/10159" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/10159</a><br/> <a href="http://review.whamcloud.com/10160" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/10160</a><br/> <a href="http://review.whamcloud.com/10161" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/10161</a><br/> <a href="http://review.whamcloud.com/10162" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/10162</a><br/> <a href="http://review.whamcloud.com/10163" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/10163</a><br/> <a href="http://review.whamcloud.com/10164" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/10164</a><br/> <a href="http://review.whamcloud.com/10165" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/10165</a></p> <p>I'll start some testing in the morning.</p> <p>I think you left out <a href="http://review.whamcloud.com/8010" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/8010</a> from your recipe.</p> <p>Yep, missed that one when pasting. I have it applied in my local repo.</p> <p>Peter can you link this ticket to <a href="https://jira.whamcloud.com/browse/LU-4960" title="Investigate support for linux process namespace on server side" class="issue-link" data-issue-key="LU-4960"><del>LU-4960</del></a> now that Jeff has posted work for process namespace server side.</p> <p>James, I can &amp; will do that.</p> <p>fwiw, I too have been able to do a successful server build following Jeff's recipe including #8010. Build only so far, no actual functional results to report.</p> <p>when building with latest zfs <a href="http://review.whamcloud.com/10064" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/10064</a> is also needed.<br/> if building ldiskfs only, that's a don't care.</p> <p>Welcome back Jeff.</p> <p>I also just changed the recipe. You will now need <a href="http://review.whamcloud.com/#/c/2677" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/2677</a> from <a href="https://jira.whamcloud.com/browse/LU-1330" title="split/cleanup for obdclass/fid/fld modules" class="issue-link" data-issue-key="LU-1330"><del>LU-1330</del></a>. Besides supporting new kernels we have been attempting to sync up the code with what is upstream in the kernel. We are getting pretty close to our goal. Still purging of the cfs_list (<a href="https://jira.whamcloud.com/browse/LU-3963" title="cleanup libcfs wrappers" class="issue-link" data-issue-key="LU-3963"><del>LU-3963</del></a>) is left. There is work from <a href="https://jira.whamcloud.com/browse/LU-4423" title="Tracking of patches from upstream kernel to Lustre client" class="issue-link" data-issue-key="LU-4423"><del>LU-4423</del></a> that is backporting the upstream changes into master as well.</p> <p>As for 3.12 client support only the shrinker change is needed. Everything else is merged <img class="emoticon" src="https://jira.whamcloud.com/images/icons/emoticons/smile.png" height="16" width="16" align="absmiddle" alt="" border="0"/> Yang Sheng reported their was a bug with the shrinker still. Thank you for helping out with pushing forward server side support. One thing I like to recommend is that we create a generic pool of patches for ldiskfs agaisnt the upstream 3.12 kernel. From their we can create distro specific patches. This way the series files can share a lot of the same patches. We also have fedora fc20 support in the works. I have started to look at Ubuntu/debian support as well.</p> <p>Forgot to mention the kernel patch series. The only patches you need to port are raid5-mmp-unplug-dev and bh_lru_size_config.patch. Their are also some quota scaling fixes but I don't know if those have been picked up mainstream and ended up in the SLES12 kernels. Recent test show the block tunable patches might not be worth it anymore. Also dev_read_only kernel hack will be going way. Please try out patch <a href="http://review.whamcloud.com/#/c/7200" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/7200</a> instead. Feed back on that patch would be great.</p> <p>James, for now I have been using the old 3.x-fc18.series for kernel patches. it applies cleanly but still includes the dev_read_only hack. Will look into your alternative.</p> <p>We have a collision with the ext4_map_block patch from <a href="https://jira.whamcloud.com/browse/LU-3373" title="ldiskfs patches for FC19" class="issue-link" data-issue-key="LU-3373"><del>LU-3373</del></a> and the one from Jeff. It seems that the <a href="https://jira.whamcloud.com/browse/LU-3373" title="ldiskfs patches for FC19" class="issue-link" data-issue-key="LU-3373"><del>LU-3373</del></a> patch is the favored but if this is the case then we will run into conflicts with several of the patch Jeff also has pushed. It looks like we are going to have to setup the dependence correctly now. I like to suggest that the ext4_map_block patch be placed last in the dependency tree.</p> <p>After reviewing both, I'd like to perform testing with my version. It's cleaner and ext4_map_blocks is being called correctly. ext4_map_blocks will return the number of blocks mapped and if it returns less than map.m_len, it needs to be called multiple times to properly map the entire range. The version in <a href="https://jira.whamcloud.com/browse/LU-3373" title="ldiskfs patches for FC19" class="issue-link" data-issue-key="LU-3373"><del>LU-3373</del></a> needs general cleanup and also to call ext4_map_blocks properly. I expect that, with the exception of the unmap_underlying_metadata call (which I'd like to see the bug report for), the result would look pretty much like mine.</p> <p>Ok, so I just ran acceptance-small against my recipe and ran into:<br/> ldiskfs_truncate needing i_mutex (WARN_ON)<br/> scheduling while atomic (usermodehelper kmalloc + waiting) due to the upcall cache lock being a rwlock instead of a sleeping lock<br/> procfs warnings from nrs_tbf_quantum not existing during umount<br/> warning from inc_nlink due to I_LINKABLE not being set (introduced in Linux commit f4e0c30c19)</p> <p>All of those are just annoyances and can be fixed pretty easily.</p> <p>But the BUG_ON(de-&gt;name_len != 1); check in dx_get_dx_info is getting triggered as well, which has halted testing for now.</p> <p>I'll dig into these a bit.</p> <p>Jeff, the procfs warnings from nrs_tbf_quantum not existing during umount have already been reported elsewhere, so it's not something new in your patches. see <a href="https://jira.whamcloud.com/browse/LU-4832" title="verbose warnings logged at client umount time" class="issue-link" data-issue-key="LU-4832"><del>LU-4832</del></a></p> <p>Oh, yeah, I'm not expecting that they were introduced by my patches - most of these are checks that have gone into the upstream kernel and haven't been addressed yet.</p> <p>The scheduling while atomic issue was introduced here:<br/> 4b7cbec39 (<a href="https://jira.whamcloud.com/browse/LU-540" title="fix interop issues with lustre_user.h" class="issue-link" data-issue-key="LU-540"><del>LU-540</del></a> misc patch for user identity upcall/downcall)</p> <p>The author claimed that the allocation was unnecessary, but it was necessary to avoid holding the atomic lock across a sleeping operation. Given that the operations using this value aren't performance critical (if they were, we wouldn't be doing call_usermodehelper), we can replace the lock with a sleeping lock and keep the allocations out of it.</p> <p>Oh so that is the source of the upcall backtrace I get. I have been ignoring it thinking it was due to a configuration issue on my part. The patch for the TBF NR is totally broken. When I created the patch I had no docs on how to actually test it. Li has left me some pointers in the gerrit review.</p> <p>Found another scheduling while atomic issue:</p> <p>ll_statahead_interpret takes &amp;lli-&gt;lli_sa_lock<br/> ll_intent_drop_lock<br/> ldlm_lock_decref<br/> ldlm_lock_decref_internal<br/> ldlm_bl_to_thread<br/> kmem_cache_alloc_trace <b>oops</b></p> <p>... this one is a bit more involved than I'm comfortable with.</p> <p>I added a bit of debugging to the dx_get_dx_info BUG_ON and got back the following. AFAICT it's supposed to be "." <img class="emoticon" src="https://jira.whamcloud.com/images/icons/emoticons/smile.png" height="16" width="16" align="absmiddle" alt="" border="0"/><br/> bad name: 0000000200000bd1:00000718:00000000: 0</p> <p>Looks like that's a bug in the ldiskfs patch set.</p> <p>Jeff could you reverse the order of dependency for <a href="http://review.whamcloud.com/#/c/10164" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10164</a> and <a href="http://review.whamcloud.com/#/c/10163" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10163</a>. The reason is 10164 will be much easier to land and 10163 is currently broken which makes 10164 broken. Also we need to investigate to see if a performance difference happens when moving to ext4_map_blocks.</p> <p>Ok, reversed the order and fixed the ext4_map_blocks patch. The entire set builds now.</p> <p>There was a bug in my ext4_map_blocks patch that caused pretty much everything to return zeroes. I have a fixed version that works properly. I also have a patch that's required for any 3.10+ kernel since ext4_truncate will check that i_mutex is held. I'm going to run small-acceptance again and push the fixes.</p> <p>After a quick look over, I think the main performance difference is going to come from the holes case. ext4_map_blocks handles it, but not efficiently. It should be doable to use the FIEMAP code to handle the read-only holes case and use ext4_map_blocks for the write case since the allocations paper over the performance issue AFAICT. Not that I'm volunteering to do it. <img class="emoticon" src="https://jira.whamcloud.com/images/icons/emoticons/smile.png" height="16" width="16" align="absmiddle" alt="" border="0"/></p> <p>Peter can you link <a href="https://jira.whamcloud.com/browse/LU-5058" title="support for linux process namespace is broken" class="issue-link" data-issue-key="LU-5058"><del>LU-5058</del></a> to this ticket as well. Currently a few collisions of patches are happening. What I like to recommend is that the following 3 base patches have no dependency chain so they can land in parallel.</p> <p><a href="http://review.whamcloud.com/#/c/10325" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10325</a> - <a href="https://jira.whamcloud.com/browse/LU-5058" title="support for linux process namespace is broken" class="issue-link" data-issue-key="LU-5058"><del>LU-5058</del></a><br/> <a href="http://review.whamcloud.com/#/c/10160" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10160</a> - <a href="https://jira.whamcloud.com/browse/LU-3953" title="lustre build system improvments" class="issue-link" data-issue-key="LU-3953"><del>LU-3953</del></a><br/> <a href="http://review.whamcloud.com/#/c/10161" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10161</a> - <a href="https://jira.whamcloud.com/browse/LU-4416" title="support for 3.12 linux kernel" class="issue-link" data-issue-key="LU-4416"><del>LU-4416</del></a> - This can be the base for all the osd-ldisk changes. Remove the <br/> <a href="https://jira.whamcloud.com/browse/LU-5058" title="support for linux process namespace is broken" class="issue-link" data-issue-key="LU-5058"><del>LU-5058</del></a> bits.</p> <p>These 3 patches don't have dependency on each other and it is much faster to land patches that lack dependencies. Since time is short we really need to focus on making RHEL7 and SLES12 client support available for Lustre 2.6. We can do the server support for Lustre 2.7. This means focusing on getting 9300, <a href="https://jira.whamcloud.com/browse/LU-3953" title="lustre build system improvments" class="issue-link" data-issue-key="LU-3953"><del>LU-3953</del></a> and <a href="https://jira.whamcloud.com/browse/LU-5058" title="support for linux process namespace is broken" class="issue-link" data-issue-key="LU-5058"><del>LU-5058</del></a> landed ASAP. What do you think Jeff?</p> <p>Works for me, though we've got demand for 2.6 server support on SLE12 AFAIK. So I'll still be plugging away on these (as they pass acceptance except for the namei.c:517 crash).</p> <p>James, I put in the link you asked for.</p> <p>I agree that focusing on the small set of patches needed for client support and without dependencies on each other makes sense. Really want to get at least those landed before 2.6 closes. Don't at all suggest we should slow down or stop progress on all the other patches, just that we do what's needed for clients first.</p> <p>Thank you Bob. Jeff please keep doing the awesome work. </p> <p>Patches needed for RHEL7 client support:</p> <p><a href="http://review.whamcloud.com/#/c/10325" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10325</a> - <a href="https://jira.whamcloud.com/browse/LU-5058" title="support for linux process namespace is broken" class="issue-link" data-issue-key="LU-5058"><del>LU-5058</del></a></p> <p>Additional patches needed for <span class="error">&#91;SuSE12 client &#93;</span> / [ generic 3.12 ] support</p> <p><a href="http://review.whamcloud.com/#/c/10160" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10160</a> - <a href="https://jira.whamcloud.com/browse/LU-3953" title="lustre build system improvments" class="issue-link" data-issue-key="LU-3953"><del>LU-3953</del></a><br/> <a href="http://review.whamcloud.com/#/c/9300" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/9300</a> - <a href="https://jira.whamcloud.com/browse/LU-4416" title="support for 3.12 linux kernel" class="issue-link" data-issue-key="LU-4416"><del>LU-4416</del></a></p> <p>Patches need for ZFS server support include the above plus:</p> <p><a href="http://review.whamcloud.com/#/c/7934" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/7934</a><br/> <a href="http://review.whamcloud.com/#/c/8049" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/8049</a></p> <p>Think there's a typo in your list. don't you mean:</p> <p><a href="http://review.whamcloud.com/#/c/10160" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10160</a> - <a href="https://jira.whamcloud.com/browse/LU-3953" title="lustre build system improvments" class="issue-link" data-issue-key="LU-3953"><del>LU-3953</del></a><br/> <a href="http://review.whamcloud.com/#/c/9300" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/9300</a> - <a href="https://jira.whamcloud.com/browse/LU-4416" title="support for 3.12 linux kernel" class="issue-link" data-issue-key="LU-4416"><del>LU-4416</del></a></p> <p>?</p> <p>fixed.</p> <p>For the latest master all patches needed for client support of 3.12 kernels has been landed. This covers both RHEL7 and SuSE 12 clients.</p> <p>If you want ZFS back end support with 3.12 kernels you will need the following two patches:</p> <p><a href="http://review.whamcloud.com/#/c/7934" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/7934</a> - <a href="https://jira.whamcloud.com/browse/LU-3319" title="Adapt to 3.10 upstream kernel proc_dir_entry change" class="issue-link" data-issue-key="LU-3319"><del>LU-3319</del></a> ZFS lprocfs updates<br/> <a href="http://review.whamcloud.com/#/c/8049" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/8049</a> - <a href="https://jira.whamcloud.com/browse/LU-3319" title="Adapt to 3.10 upstream kernel proc_dir_entry change" class="issue-link" data-issue-key="LU-3319"><del>LU-3319</del></a> mdd/ofd lprocfs updates</p> <p>Currently ldiskfs development is in the early stages for 3.12 kernel supports. The list of patches currently under development can be reviewed with the following link</p> <p><a href="http://review.whamcloud.com/#/q/status:open+message:LU-4416,n,z" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/q/status:open+message:LU-4416,n,z</a></p> <p>In addition for RHEL7 ldiskfs support the following patch needs to be applied:</p> <p><a href="http://review.whamcloud.com/#/c/10249" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10249</a> - <a href="https://jira.whamcloud.com/browse/LU-5022" title="support for 3.10 rhel7 linux kernel" class="issue-link" data-issue-key="LU-5022"><del>LU-5022</del></a></p> <p>Currently clients on newer kernels require you to modprobe lustre before you do a client mount. This is fix in the patch <br/> <a href="http://review.whamcloud.com/#/c/10587" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10587</a> from <a href="https://jira.whamcloud.com/browse/LU-4800" title="no automatic module load in newer kernels" class="issue-link" data-issue-key="LU-4800"><del>LU-4800</del></a>.</p> <p>For people wanted to use an external OFED stack (3.12 or Mellanox) you will need patch <a href="http://review.whamcloud.com/#/c/10571" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10571</a><br/> from <a href="https://jira.whamcloud.com/browse/LU-5140" title="Mellanox backport header conflicts with newer kernels" class="issue-link" data-issue-key="LU-5140"><del>LU-5140</del></a>. This patch also fixes this issue on select SLES11 SP3 platforms (Cray) as well.</p> <p>Time for a update. All the needed <a href="https://jira.whamcloud.com/browse/LU-3319" title="Adapt to 3.10 upstream kernel proc_dir_entry change" class="issue-link" data-issue-key="LU-3319"><del>LU-3319</del></a> patches for ZFS server support has landed. Lustre 2.6 should be able to support ZFS server support on RHEL7 or SuSE12 now. One last cleanup patch will be produced for <a href="https://jira.whamcloud.com/browse/LU-3319" title="Adapt to 3.10 upstream kernel proc_dir_entry change" class="issue-link" data-issue-key="LU-3319"><del>LU-3319</del></a> but it is not necessary to land it for 2.6 to get server support.</p> <p>Currently osd-ldiskfs is still in development but should be ready for 2.7. Patches for that work<br/> can be viewed here <a href="http://review.whamcloud.com/#/q/status:open+message:LU-4416,n,z" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/q/status:open+message:LU-4416,n,z</a></p> <p>For client support the patch for <a href="https://jira.whamcloud.com/browse/LU-4800" title="no automatic module load in newer kernels" class="issue-link" data-issue-key="LU-4800"><del>LU-4800</del></a> has landed. This means you can mount clients without the need to modprobe the lustre modules first. Client support is very well supported at this point. If you are using a external OFED stack you will need patch <a href="http://review.whamcloud.com/#/c/10571" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10571</a> from <a href="https://jira.whamcloud.com/browse/LU-5140" title="Mellanox backport header conflicts with newer kernels" class="issue-link" data-issue-key="LU-5140"><del>LU-5140</del></a>.</p> <p>Update : The patch for <a href="https://jira.whamcloud.com/browse/LU-5140" title="Mellanox backport header conflicts with newer kernels" class="issue-link" data-issue-key="LU-5140"><del>LU-5140</del></a> just landed so clients on newer kernels will build and work with new OFED stacks.</p> <p>I have done some experimenting with the ldiskfs patch for SuSE12 to discover their is only one patch in that series that can't be applied to the 3.12.22 upstream linux kernel trree. Since this is the case I like to purpose we create a 3.12 series file and extend SuSE12 and RHEL7 off of it.The reason for this is so we can start organizing the patches we should be sending upstream to the<br/> ext4 maintainers. I like to create another 3.X-upstream series file as well to sync to every 3.X version that comes out. In the end the goal will be to no longer need ldiskfs.</p> <p>I think the recent landing of fix for <a href="https://jira.whamcloud.com/browse/LU-4906" title="rm -rf triggers too much MDS_READPAGE" class="issue-link" data-issue-key="LU-4906"><del>LU-4906</del></a> has broken the build for 3.12. Can't even build clients anymore, I get build errors from llite/dir.c. I think there was a commit some time ago changing readdir code in osd-ldiskfs. I suspect recent changes to dir.c didn't take into account the HAVE_DIR_CONTEXT case from autoconf wrt readdir code.</p> <p>Looking into it. Can you post what build error you get?</p> <p>added a bit more detail in <a href="https://jira.whamcloud.com/browse/LU-5234" title="lustre builds on 3.12 kernels are broken" class="issue-link" data-issue-key="LU-5234"><del>LU-5234</del></a> for this specific issue</p> <p>As Bob has mentioned a new issue has merged in master that broke client support for RHEL7 and SuSE12. I have a patch to resolve this at <a href="http://review.whamcloud.com/#/c/10761" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10761</a> which is related to <a href="https://jira.whamcloud.com/browse/LU-5234" title="lustre builds on 3.12 kernels are broken" class="issue-link" data-issue-key="LU-5234"><del>LU-5234</del></a>. Please give it a try.</p> <p>As of today all patches needed for client and zfs support has landed. Many patches for ldiskfs has landed but more testing and work needs to be done. The patches left for ldiskfs support are:</p> <p><a href="http://review.whamcloud.com/#/c/8116" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/8116</a> - <a href="https://jira.whamcloud.com/browse/LU-3373" title="ldiskfs patches for FC19" class="issue-link" data-issue-key="LU-3373"><del>LU-3373</del></a> / <a href="https://jira.whamcloud.com/browse/LU-5276" title="ldiskfs patches for FC19" class="issue-link" data-issue-key="LU-5276"><del>LU-5276</del></a> ext4_map_block support<br/> <a href="http://review.whamcloud.com/#/c/10376" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10376</a> - <a href="https://jira.whamcloud.com/browse/LU-4416" title="support for 3.12 linux kernel" class="issue-link" data-issue-key="LU-4416"><del>LU-4416</del></a> limit transaction size in ldiskfs <br/> <a href="http://review.whamcloud.com/#/c/10165" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10165</a> ldiskfs for 3.12 / SuSE12</p> <p><a href="http://review.whamcloud.com/#/c/10249" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10249</a> - <a href="https://jira.whamcloud.com/browse/LU-5022" title="support for 3.10 rhel7 linux kernel" class="issue-link" data-issue-key="LU-5022"><del>LU-5022</del></a> RHEL7 ldiskfs support</p> <p>More patches have landed. The patches left for ldiskfs support are:</p> <p><a href="http://review.whamcloud.com/#/c/10376" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10376</a> - <a href="https://jira.whamcloud.com/browse/LU-4416" title="support for 3.12 linux kernel" class="issue-link" data-issue-key="LU-4416"><del>LU-4416</del></a> limit transaction size in ldiskfs <br/> <a href="http://review.whamcloud.com/#/c/10165" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10165</a> ldiskfs for SuSE12</p> <p><a href="http://review.whamcloud.com/#/c/10249" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10249</a> - <a href="https://jira.whamcloud.com/browse/LU-5022" title="support for 3.10 rhel7 linux kernel" class="issue-link" data-issue-key="LU-5022"><del>LU-5022</del></a> RHEL7 ldiskfs support.</p> <p>Down to two patches.</p> <p><a href="http://review.whamcloud.com/#/c/10165" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10165</a> ldiskfs for SuSE12 support<br/> <a href="http://review.whamcloud.com/#/c/10783" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10783</a> fix for a conf-sanity test so it can pass maloo</p> <p>All that is left to land is <a href="http://review.whamcloud.com/#/c/10165" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10165</a> which covers ldiskfs for SuSE12 support.</p> <p>Jeff I like to discuss how to go about to make a pathless server for SLES12 support. Currently three primary patches are needed:</p> <p>bh_lru_size_config.patch - a simple which might change based on what will go upstream. Andrew Morton discuss just having BH_LRU_SIZE <br/> changes to 16 in the kernel.</p> <p>quota enhancement patches - These have already been merged upstream as the following commits</p> <p> commit b9ba6f94b2382ef832f97122976b73004f714714 <br/> commit 9eb6463f31cf720deaf0e810cacc403d7720b10c <br/> commit 1ea06bec78a128adc995ca32bd906a6c9bb9cf91<br/> commit 606cdcca04a609ed4dfbfe788942de9477da556b<br/> commit d68aab6b8f572406aa93b45ef6483934dd3b54a6</p> <p> It would be really nice to have those merged into your tree.</p> <p>Lastly the work under <a href="https://jira.whamcloud.com/browse/LU-3406" title="Submit raid5-mmp-unplug-dev patch upstream" class="issue-link" data-issue-key="LU-3406"><del>LU-3406</del></a>. That is just starting to get underway and once we have a proper solution then it could also be integrated as well.</p> <p>Hi James, I'm afraid we're too late to incorporate the quota changes. SLE12 GA was released last week. The quota changes would change the kABI so we can't accept them into the release. Unless <a href="https://jira.whamcloud.com/browse/LU-3406" title="Submit raid5-mmp-unplug-dev patch upstream" class="issue-link" data-issue-key="LU-3406"><del>LU-3406</del></a> has changes substantially since I asked Neil Brown to take a look at it last year, we won't be able to accept that one either. He had serious reservations about whether it would end up causing corruption in use. The configurable BH_LRU_SIZE change might be acceptable since it's local to fs/buffer.c</p> <p>Jeff since SLES11SP4 is not out just yet would you consider having the BH_LRU_SIZE and quota improvements merged into your kernel?</p> <p>I can propose it. We're technically past our feature request deadline, but I can present it as a late change request.</p> <p>I think main issue is push <a href="http://review.whamcloud.com/7200" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/7200</a> can be landed asap.</p> <p>Bob Glossman (bob.glossman@intel.com) uploaded a new patch: <a href="http://review.whamcloud.com/14532" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/14532</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-4416" title="support for 3.12 linux kernel" class="issue-link" data-issue-key="LU-4416"><del>LU-4416</del></a> build: add build files for SLES 12 client build<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: 35b55f7f4b2390b4145b6898ccd8e4fb421c7da3</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/14532/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/14532/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-4416" title="support for 3.12 linux kernel" class="issue-link" data-issue-key="LU-4416"><del>LU-4416</del></a> build: add build files for SLES 12 client build<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: 48416b83331778f564986b8c96ee6d362123af76</p> <p>Looks like this ticket can be close after <a href="http://review.whamcloud.com/#/c/10165/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/10165/</a> landed.</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/10165/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/10165/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-4416" title="support for 3.12 linux kernel" class="issue-link" data-issue-key="LU-4416"><del>LU-4416</del></a> ldiskfs: enable support for SLES12<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: 9067f1b50aaeae2a79dfa9f777f96637c3d4bb05</p> <p>Landed for 2.8</p> Related LU-3227 LU-4209 LU-4127 LU-4157 LU-4231 LU-4400 LU-4451 LU-4530 LU-4960 LU-5058 LU-3319 LU-5234 LU-6063 LU-4800 LU-5275 LU-4150 LU-5022 LU-684 LU-6215 LU-4993 LU-5609 LU-4614 LU-5860 Development Rank 1|hzwbwv: Rank (Obsolete) 12130