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-3580 Lustre <p>I was running lustre-rsync-test test_8 repeatedly without umount/remount to reproduce <a href="https://jira.whamcloud.com/browse/LU-3573" title="lustre-rsync-test test_8: @@@@@@ FAIL: Failure in replication; differences found. " class="issue-link" data-issue-key="LU-3573"><del>LU-3573</del></a>, when my MDS hit an LBUG:</p> <div class="preformatted panel" style="border-width: 1px;"><div class="preformattedContent panelContent"> <pre>LustreError: 48946:0:(sec_null.c:318:null_alloc_rs()) ASSERTION( rs-&gt;rs_size &gt;= rs_size ) failed: LustreError: 48946:0:(sec_null.c:318:null_alloc_rs()) LBUG Kernel panic - not syncing: LBUG Pid: 48946, comm: mdt00_002 Tainted: P --------------- 2.6.32-358.11.1.el6_lustre.g3b657b6.x86_64 #1 Call Trace: [&lt;ffffffff8150d8f8&gt;] ? panic+0xa7/0x16f [&lt;ffffffffa0629eeb&gt;] ? lbug_with_loc+0x9b/0xb0 [libcfs] [&lt;ffffffffa0979632&gt;] ? null_alloc_rs+0x272/0x390 [ptlrpc] [&lt;ffffffffa0967dd9&gt;] ? sptlrpc_svc_alloc_rs+0x1d9/0x2a0 [ptlrpc] [&lt;ffffffffa093d533&gt;] ? lustre_pack_reply_v2+0x93/0x280 [ptlrpc] [&lt;ffffffffa093d7ce&gt;] ? lustre_pack_reply_flags+0xae/0x1f0 [ptlrpc] [&lt;ffffffffa093d921&gt;] ? lustre_pack_reply+0x11/0x20 [ptlrpc] [&lt;ffffffffa09654e3&gt;] ? req_capsule_server_pack+0x53/0x100 [ptlrpc] [&lt;ffffffffa0d37f1e&gt;] ? mdt_get_info+0xae/0x19b0 [mdt] [&lt;ffffffffa0d29fbd&gt;] ? mdt_unpack_req_pack_rep+0x4d/0x4d0 [mdt] [&lt;ffffffffa093e52c&gt;] ? lustre_msg_get_version+0x8c/0x100 [ptlrpc] [&lt;ffffffffa0d33cf7&gt;] ? mdt_handle_common+0x647/0x16d0 [mdt] [&lt;ffffffffa0d6d155&gt;] ? mds_regular_handle+0x15/0x20 [mdt] [&lt;ffffffffa094d978&gt;] ? ptlrpc_server_handle_request+0x398/0xc60 [ptlrpc] [&lt;ffffffffa062a54e&gt;] ? cfs_timer_arm+0xe/0x10 [libcfs] [&lt;ffffffffa063ba9f&gt;] ? lc_watchdog_touch+0x6f/0x170 [libcfs] [&lt;ffffffffa0944d99&gt;] ? ptlrpc_wait_event+0xa9/0x290 [ptlrpc] [&lt;ffffffff81063310&gt;] ? default_wake_function+0x0/0x20 [&lt;ffffffffa094ecfd&gt;] ? ptlrpc_main+0xabd/0x1700 [ptlrpc] [&lt;ffffffffa094e240&gt;] ? ptlrpc_main+0x0/0x1700 [ptlrpc] [&lt;ffffffff81096936&gt;] ? kthread+0x96/0xa0 [&lt;ffffffff8100c0ca&gt;] ? child_rip+0xa/0x20 [&lt;ffffffff810968a0&gt;] ? kthread+0x0/0xa0 [&lt;ffffffff8100c0c0&gt;] ? child_rip+0x0/0x20 </pre> </div></div> 1 OSS (2 osts), 1 MDS, 1 Client (all running lustre-master build 1546), MDS and OSS using ZFS LU-3580

Panic in ptlrpc when rerunning lustre-rsync-test/8 without remount

Bug Minor Resolved Low Priority WC Triage Nathaniel Clark zfs Fri, 12 Jul 2013 15:55:36 +0000 Thu, 9 Jan 2020 07:06:26 +0000 Thu, 9 Jan 2020 07:06:26 +0000 Lustre 2.5.0 0 4 <p>Shadow, I wonder if you have an opinion on this?</p> <p>Thee was a class of bugs in the past that you worked on where a missing OST led to some smaller allocations and then everything came down once we realized we had more OSTs in the system.</p> <p>Nathaniel, why is the OST down?</p> <p>Oleg, The OST wasn't down. lustre-rsync-test/8 builds a directory tree with createmany and some nested Gfor loops for directories, and then does a lustre_rsync to a local directory (on the client). I had been running that in a loop to try to recreate the bug I was looking for when the MDT went down, it's pretty reproducable, you just have to keep the filesystem mounted between runs. I can reproduce if you want cleaner logs.</p> <p>Oleg,</p> <p>it's looks new bug in sptlrpc code, and don't related to the MDC&lt;&gt;MDT exchange.<br/> OSC have an own pool for requests - where it's preallocted with messages - but looks some reply`s need more size then set in preallocate time or it's related to the early reply.<br/> as i see lustre_pack_reply may called more then one time - first for early reply second for the real reply - in that case we will have different request format and size for </p> <div class="code panel" style="border-width: 1px;"><div class="codeContent panelContent"> <pre class="code-java">rc = sptlrpc_svc_alloc_rs(req, msg_len); </pre> </div></div> <p>did we have a crashdump ?</p> <p>Close old bug</p> Related LU-3573 Development Rank 1|hzvv9b: Rank (Obsolete) 9068 Severity