Whamcloud Community JIRA

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-6705] MDT hung at umount under DNE mode https://jira.whamcloud.com/browse/LU-6705 Lustre <p>It can be reproduced via the following steps:<br/> 1) create some files cross multiple MDTs.<br/> 2) umount the MDTs<br/> 3) mount the MDTs<br/> 4) umount the MDTs<br/> 5) mount the MDTs<br/> 6) umount the MDTs</p> <p>Then hung at the last umount.</p> LU-6705

MDT hung at umount under DNE mode

Bug Major Resolved Fixed Di Wang nasf Wed, 10 Jun 2015 08:18:13 +0000 Tue, 14 Jul 2015 22:55:31 +0000 Tue, 14 Jul 2015 22:55:31 +0000 Lustre 2.8.0 Lustre 2.8.0 0 3 <p>Just discussed with Fan Yong, it seems umount thread is blocked because it can not stop the recovery update thread. And the recovery update thread is trying to retrieve the update records from the remote MDT. and that MDT has been shutdown.</p> <p>update recovery thread</p> <div class="preformatted panel" style="border-width: 1px;"><div class="preformattedContent panelContent"> <pre>[<ffffffffa0526c18>] ? ptlrpc_set_wait+0x188/0x900 [ptlrpc] [<ffffffffa051c5b0>] ? ptlrpc_interrupted_set+0x0/0x110 [ptlrpc] [<ffffffffa051da74>] ? ptlrpc_request_pack+0x24/0x70 [ptlrpc] [<ffffffffa0527411>] ? ptlrpc_queue_wait+0x81/0x220 [ptlrpc] [<ffffffffa073655b>] ? fld_client_rpc+0x15b/0x510 [fld] [<ffffffffa073c42e>] ? fld_server_lookup+0x14e/0x330 [fld] [<ffffffffa0c804ff>] ? lod_fld_lookup+0x34f/0x520 [lod] [<ffffffff8116fef2>] ? kmem_cache_alloc+0x182/0x190 [<ffffffffa0c958e3>] ? lod_object_init+0x103/0x3c0 [lod] [<ffffffffa1294298>] ? lu_object_alloc+0xd8/0x320 [obdclass] [<ffffffffa12957a1>] ? lu_object_find_try+0x151/0x260 [obdclass] [<ffffffffa1295961>] ? lu_object_find_at+0xb1/0xe0 [obdclass] [<ffffffffa0d06fc2>] ? dt_update_request_destroy+0x1c2/0x270 [osp] [<ffffffffa1296ebc>] ? dt_locate_at+0x1c/0xa0 [obdclass] [<ffffffffa125346f>] ? llog_osd_open+0xdf/0xde0 [obdclass] [<ffffffffa124a375>] ? llog_open+0x145/0x470 [obdclass] [<ffffffffa0caa82e>] ? lod_sub_prep_llog+0x19e/0x7a0 [lod] [<ffffffffa0c8088e>] ? lod_sub_recovery_thread+0x1be/0x980 [lod] [<ffffffff81061c62>] ? default_wake_function+0x12/0x20 [<ffffffffa0c806d0>] ? lod_sub_recovery_thread+0x0/0x980 [lod] [<ffffffff8109ab46>] ? kthread+0x96/0xa0 [<ffffffff8100c20a>] ? child_rip+0xa/0x20 [<ffffffff8109aab0>] ? kthread+0x0/0xa0 [<ffffffff8100c200>] ? child_rip+0x0/0x20 </pre> </div></div> <p>So we need to stop the recovery thread during umount, </p> <div class="preformatted panel" style="border-width: 1px;"><div class="preformattedContent panelContent"> <pre>static void mdt_fini() { ..... target_recovery_fini(obd); ping_evictor_stop(); mdt_stack_pre_fini(env, m, md2lu_dev(m->mdt_child)); ...... </pre> </div></div> <p>Simply, if we move mdt_stack_pre_fini before target_recovery_fini, the problem should go away, but that will cause other problem. </p> <p>wangdi (di.wang@intel.com) uploaded a new patch: <a href="http://review.whamcloud.com/15210" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/15210</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-6705" title="MDT hung at umount under DNE mode" class="issue-link" data-issue-key="LU-6705"><del>LU-6705</del></a> lod: re-order lodsub recovery cleanup<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: 1<br/> Commit: eee8fdfd69dc66e4224507ce9284022f3a1758a9</p> <p>Oleg Drokin (oleg.drokin@intel.com) merged in patch <a href="http://review.whamcloud.com/15210/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/15210/</a><br/> Subject: <a href="https://jira.whamcloud.com/browse/LU-6705" title="MDT hung at umount under DNE mode" class="issue-link" data-issue-key="LU-6705"><del>LU-6705</del></a> lod: re-order lodsub recovery cleanup<br/> Project: fs/lustre-release<br/> Branch: master<br/> Current Patch Set: <br/> Commit: 8299bdd484ad44d3ed25dcc68e8440242c155c80</p> Related LU-6720 Development Rank 1|hzxfdb: Rank (Obsolete) 9223372036854775807 Severity