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-3851 Lustre <p>Running iorfpp, scaling from 1-64 clients, had page_allocation failures </p> <div class="code panel" style="border-width: 1px;"><div class="codeContent panelContent"> <pre class="code-java">Aug 27 15:40:56 iwc1 kernel: ptlrpcd_8: page allocation failure. order:1, mode:0x40 Aug 27 15:40:56 iwc1 kernel: ptlrpcd_10: page allocation failure. order:1, mode:0x40 Aug 27 15:40:56 iwc1 kernel: Pid: 5769, comm: ptlrpcd_10 Not tainted 2.6.32-358.14.1.el6.x86_64 #1 Aug 27 15:40:56 iwc1 kernel: Call Trace: Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffff8112c197&gt;] ? __alloc_pages_nodemask+0x757/0x8d0 Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffff81166b42&gt;] ? kmem_getpages+0x62/0x170 Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffff8116775a&gt;] ? fallback_alloc+0x1ba/0x270 Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffff811671af&gt;] ? cache_grow+0x2cf/0x320 Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffff811674d9&gt;] ? ____cache_alloc_node+0x99/0x160 Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffffa0842a98&gt;] ? ptlrpc_new_bulk+0x48/0x270 [ptlrpc] Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffff811682a9&gt;] ? __kmalloc+0x189/0x220 Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffffa0842a98&gt;] ? ptlrpc_new_bulk+0x48/0x270 [ptlrpc] Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffffa0842d18&gt;] ? ptlrpc_prep_bulk_imp+0x58/0x190 [ptlrpc] Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffffa09f0084&gt;] ? osc_brw_prep_request+0x294/0x11e0 [osc] Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffffa0a0446c&gt;] ? osc_req_attr_set+0x16c/0x5b0 [osc] Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffffa0717941&gt;] ? cl_req_attr_set+0xd1/0x230 [obdclass] Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffffa09f6210&gt;] ? osc_build_rpc+0x870/0x1840 [osc] Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffffa0a1052d&gt;] ? osc_io_unplug0+0x16ad/0x1f20 [osc] Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffff812811d6&gt;] ? vsnprintf+0x336/0x5e0 Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffffa0a12aa1&gt;] ? osc_io_unplug+0x11/0x20 [osc] Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffffa09e4286&gt;] ? brw_queue_work+0x36/0xd0 [osc] Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffffa083be77&gt;] ? work_interpreter+0x27/0x90 [ptlrpc] Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffffa0844c5c&gt;] ? ptlrpc_check_set+0x2ac/0x1b20 [ptlrpc] Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffffa087006b&gt;] ? ptlrpcd_check+0x53b/0x560 [ptlrpc] Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffffa08704f0&gt;] ? ptlrpcd+0x190/0x380 [ptlrpc] Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffff81063330&gt;] ? default_wake_function+0x0/0x20 Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffffa0870360&gt;] ? ptlrpcd+0x0/0x380 [ptlrpc] Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffff81096956&gt;] ? kthread+0x96/0xa0 Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffff8100c0ca&gt;] ? child_rip+0xa/0x20 Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffff810968c0&gt;] ? kthread+0x0/0xa0 Aug 27 15:40:56 iwc1 kernel: [&lt;ffffffff8100c0c0&gt;] ? child_rip+0x0/0x20 Aug 27 15:40:56 iwc1 kernel: Mem-Info: Aug 27 15:40:56 iwc1 kernel: Node 0 DMA per-cpu: Aug 27 15:40:56 iwc1 kernel: CPU 0: hi: 0, btch: 1 usd: 0 Aug 27 15:40:56 iwc1 kernel: CPU 1: hi: 0, btch: 1 usd: 0 Aug 27 15:40:56 iwc1 kernel: CPU 2: hi: 0, btch: 1 usd: 0 Aug 27 15:40:56 iwc1 kernel: CPU 3: hi: 0, btch: 1 usd: 0 Aug 27 15:40:56 iwc1 kernel: CPU 4: hi: 0, btch: 1 usd: 0 Aug 27 15:40:56 iwc1 kernel: CPU 5: hi: 0, btch: 1 usd: 0 </pre> </div></div> Hyperion/LLNL LU-3851

Single-client scale test: ptlrpcd page allocation failure

Bug Critical Resolved Duplicate WC Triage Cliff White Wed, 28 Aug 2013 16:02:42 +0000 Mon, 2 Jun 2014 16:50:36 +0000 Thu, 13 Feb 2014 22:01:06 +0000 Lustre 2.5.0 0 5 <p>Cliff can you attach the whole console log? These errors are ok it themselves but it sounded like there was a crash soon after? I didn't see a vmcore from today for iwc1. </p> <p>Also, information from /proc/slabinfo and /proc/meminfo.</p> <p>This will be fixed in <a href="https://jira.whamcloud.com/browse/LU-4357" title="page allocation failure. mode:0x40 caused by missing __GFP_WAIT flag" class="issue-link" data-issue-key="LU-4357"><del>LU-4357</del></a>. It is definitely the same problem, since it is showing the "0x40" allocation flag, which is only __GFP_IO.</p> <p>Shows mode:0x40 == __GFP_IO, but missing __GFP_WAIT from <a href="https://jira.whamcloud.com/browse/LU-4357" title="page allocation failure. mode:0x40 caused by missing __GFP_WAIT flag" class="issue-link" data-issue-key="LU-4357"><del>LU-4357</del></a>.</p> Duplicate LU-4357 Development Rank 1|hzvziv: Rank (Obsolete) 9971 Severity