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-5888 Lustre <p>This issue was created by maloo for Andreas Dilger &lt;andreas.dilger@intel.com&gt;</p> <p>I noticed that the automatic tuning of max_sectors_kb by mount.lustre is going badly at mount time: </p> <div class="preformatted panel" style="border-width: 1px;"><div class="preformattedContent panelContent"> <pre>mount.lustre: set /sys/block/dm-0/queue/max_sectors_kb to 2147483647 </pre> </div></div> <p>This looks like and overflow, but even if it is not then we don't need to set this higher than PTLRPC_MAX_BRW_SIZE, or maybe 16MB or 32MB if that #define is not available in userspace. </p> <p>This issue relates to the following test suite run: <a href="https://testing.hpdd.intel.com/test_sets/169fa0cc-6627-11e4-8c86-5254006e85c2" class="external-link" target="_blank" rel="nofollow noopener">https://testing.hpdd.intel.com/test_sets/169fa0cc-6627-11e4-8c86-5254006e85c2</a>.</p> LU-5888

mount.lustre: set max_sectors_kb to 2147483647

Bug Major Resolved Fixed Dmitry Eremin Maloo mq115 Sun, 9 Nov 2014 17:04:41 +0000 Thu, 27 Apr 2017 17:34:38 +0000 Mon, 3 Aug 2015 05:40:40 +0000 Lustre 2.7.0 Lustre 2.8.0 0 6 <p> <a href="http://review.whamcloud.com/12723" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/12723</a></p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/12723/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/12723/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-5888" title="mount.lustre: set max_sectors_kb to 2147483647" class="issue-link" data-issue-key="LU-5888"><del>LU-5888</del></a> utils: limit max_sectors_kb tunable setting<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: 73bd456e8965e3c3e7ccab0f7850fc50355d9cec</p> <p>James Simmons (uja.ornl@gmail.com) uploaded a new patch: <a href="http://review.whamcloud.com/12940" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/12940</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-5888" title="mount.lustre: set max_sectors_kb to 2147483647" class="issue-link" data-issue-key="LU-5888"><del>LU-5888</del></a> utils: limit max_sectors_kb tunable setting<br/> Project: fs/lustre-release<br/> Branch: b2_5<br/> Current Patch Set: 1<br/> Commit: 917ea4f04572451dc7c43d96436707d22a3701c4</p> <p>Andreas Dilger (andreas.dilger@intel.com) uploaded a new patch: <a href="http://review.whamcloud.com/13240" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/13240</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-5888" title="mount.lustre: set max_sectors_kb to 2147483647" class="issue-link" data-issue-key="LU-5888"><del>LU-5888</del></a> utils: limit max_sectors_kb tunable setting<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: e2e89380f0366c102c3db203f03730c4075f1bb4</p> <p>Seems my first patch didn't completely fix the problem for newer kernels that allow a huge max_sectors_kb. I've pushed a second patch to resolve the remaining problem.</p> <p>Strangely, the new patch fails with a BUG in the DM layer now that it is actually limiting the max request size to 32MB. For example, in the autotest and MDS console log of <a href="https://testing.hpdd.intel.com/test_sets/05b9a226-a6c8-11e4-ad11-5254006e85c2:" class="external-link" target="_blank" rel="nofollow noopener">https://testing.hpdd.intel.com/test_sets/05b9a226-a6c8-11e4-ad11-5254006e85c2:</a></p> <div class="preformatted panel" style="border-width: 1px;"><div class="preformattedContent panelContent"> <pre>07:19:32:CMD: onyx-33vm3 mkdir -p /mnt/mds1; mount -t lustre /dev/lvm-Role_MDS/P1 /mnt/mds1 07:19:33:onyx-33vm3: mount.lustre: increased /sys/block/dm-0/queue/max_sectors_kb from 1024 to 32768 07:19:33:onyx-33vm3: mount.lustre: increased /sys/block/vda/queue/max_sectors_kb from 1024 to 32768 </pre> </div></div> <div class="preformatted panel" style="border-width: 1px;"><div class="preformattedContent panelContent"> <pre>07:19:14:LDISKFS-fs (dm-0): mounted filesystem with ordered data mode. quota=on. Opts: 07:19:14:BUG: unable to handle kernel NULL pointer dereference at (null) 07:19:14:IP: [&lt;ffffffff811ca1b0&gt;] mpage_end_io_read+0x30/0x90 07:19:14:Oops: 0002 [#1] SMP 07:19:14:Pid: 2832, comm: modprobe Not tainted 2.6.32-431.29.2.el6_lustre.gffd1fc2.x86_64 #1 Red Hat KVM 07:19:14:RIP: 0010:[&lt;ffffffff811ca1b0&gt;] [&lt;ffffffff811ca1b0&gt;] mpage_end_io_read+0x30/0x90 07:19:15:Process modprobe (pid: 2832, threadinfo ffff88005916a000, task ffff880079ae554 07:19:16:Call Trace: 07:19:16: &lt;IRQ&gt; 07:19:16: [&lt;ffffffff811c314d&gt;] bio_endio+0x1d/0x40 07:19:16: [&lt;ffffffff812661fb&gt;] req_bio_endio+0x9b/0xe0 07:19:16: [&lt;ffffffff81267777&gt;] blk_update_request+0x117/0x490 07:19:16: [&lt;ffffffff81267b17&gt;] blk_update_bidi_request+0x27/0xa0 07:19:16: [&lt;ffffffff812698be&gt;] __blk_end_request_all+0x2e/0x60 07:19:16: [&lt;ffffffffa005a22a&gt;] blk_done+0x4a/0x110 [virtio_blk] 07:19:16: [&lt;ffffffffa004e2ac&gt;] vring_interrupt+0x3c/0xd0 [virtio_ring] 07:19:16: [&lt;ffffffff810e7090&gt;] handle_IRQ_event+0x60/0x170 07:19:16: [&lt;ffffffff810e99ee&gt;] handle_edge_irq+0xde/0x180 07:19:16: [&lt;ffffffff8100faf9&gt;] handle_irq+0x49/0xa0 07:19:16: [&lt;ffffffff81532dbc&gt;] do_IRQ+0x6c/0xf0 07:19:16: [&lt;ffffffff8100b9d3&gt;] ret_from_intr+0x0/0x11 07:19:16: &lt;EOI&gt; 07:19:16: [&lt;ffffffff811c4f3e&gt;] bio_alloc_bioset+0x3e/0xf0 07:19:17: [&lt;ffffffff811c5095&gt;] bio_alloc+0x15/0x30 07:19:17: [&lt;ffffffff811ca065&gt;] mpage_alloc+0x35/0xa0 07:19:17: [&lt;ffffffff811ca5de&gt;] do_mpage_readpage+0x35e/0x5f0 07:19:17: [&lt;ffffffff811ca9c9&gt;] mpage_readpages+0xe9/0x130 07:19:18: [&lt;ffffffffa0089ccd&gt;] ext3_readpages+0x1d/0x20 [ext3] 07:19:18: [&lt;ffffffff81135795&gt;] __do_page_cache_readahead+0x185/0x210 07:19:18: [&lt;ffffffff81135841&gt;] ra_submit+0x21/0x30 07:19:18: [&lt;ffffffff81135bb5&gt;] ondemand_readahead+0x115/0x240 07:19:18: [&lt;ffffffff81135dd3&gt;] page_cache_sync_readahead+0x33/0x50 07:19:18: [&lt;ffffffff81121868&gt;] generic_file_aio_read+0x558/0x700 07:19:19: [&lt;ffffffff811890ba&gt;] do_sync_read+0xfa/0x140 07:19:19: [&lt;ffffffff81189a75&gt;] vfs_read+0xb5/0x1a0 07:19:19: [&lt;ffffffff81189bb1&gt;] sys_read+0x51/0x90 </pre> </div></div> <p>Dmitry</p> <p>Andreas is too busy to complete the remaining work on this. Could you please take this to completion?</p> <p>Thanks</p> <p>Peter</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/13240/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/13240/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-5888" title="mount.lustre: set max_sectors_kb to 2147483647" class="issue-link" data-issue-key="LU-5888"><del>LU-5888</del></a> utils: limit max_sectors_kb tunable setting<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: 0484a16883a951f27c30ee926c9a1c305f7cf489</p> <p>landed to master</p> Duplicate Related LU-4810 LU-6974 Development Rank 1|hzx0jb: Rank (Obsolete) 16462 Severity