<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
<meta name="Generator" content="Microsoft Exchange Server">
<!-- converted from text --><style><!-- .EmailQuote { margin-left: 1pt; padding-left: 4pt; border-left: #800000 2px solid; } --></style>
</head>
<body>
<meta content="text/html; charset=UTF-8">
<style type="text/css" style="">
<!--
p
{margin-top:0;
margin-bottom:0}
-->
</style>
<div dir="ltr">
<div id="x_divtagdefaultwrapper" dir="ltr" style="font-size:12pt; color:#000000; font-family:Calibri,Helvetica,sans-serif">
<p>Brian,</p>
<br>
<p>What is the actual crash? Null pointer, failed assertion/LBUG...? Probably just a few more lines back in the log would show that.</p>
<p><br>
</p>
<p>Also, Lustre 2.10 has been released, you might benefit from switching to that. There are almost certainly more bugs in this pre-2.10 development version you're running than in the release.
</p>
<p><br>
</p>
<p>- Patrick<br>
</p>
</div>
<hr tabindex="-1" style="display:inline-block; width:98%">
<div id="x_divRplyFwdMsg" dir="ltr"><font face="Calibri, sans-serif" color="#000000" style="font-size:11pt"><b>From:</b> lustre-discuss <lustre-discuss-bounces@lists.lustre.org> on behalf of Brian Andrus <toomuchit@gmail.com><br>
<b>Sent:</b> Friday, August 4, 2017 12:12:59 PM<br>
<b>To:</b> lustre-discuss@lists.lustre.org<br>
<b>Subject:</b> [lustre-discuss] nodes crash during ior test</font>
<div> </div>
</div>
</div>
<font size="2"><span style="font-size:10pt;">
<div class="PlainText">All,<br>
<br>
I am trying to run some ior benchmarking on a small system.<br>
<br>
It only has 2 OSSes.<br>
I have been having some trouble where one of the clients will reboot and <br>
do a crash dump somewhat arbitrarily. The runs will work most of the <br>
time, but every 5 or so times, a client reboots and it is not always the <br>
same client.<br>
<br>
The call trace seems to point to lnet:<br>
<br>
<br>
72095.973865] Call Trace:<br>
[72095.973892] [<ffffffffa070e856>] ? cfs_percpt_unlock+0x36/0xc0 [libcfs]<br>
[72095.973936] [<ffffffffa0779851>] <br>
lnet_return_tx_credits_locked+0x211/0x480 [lnet]<br>
[72095.973973] [<ffffffffa076c770>] lnet_msg_decommit+0xd0/0x6c0 [lnet]<br>
[72095.974006] [<ffffffffa076d0f9>] lnet_finalize+0x1e9/0x690 [lnet]<br>
[72095.974037] [<ffffffffa06baf45>] ksocknal_tx_done+0x85/0x1c0 [ksocklnd]<br>
[72095.974068] [<ffffffffa06c3277>] ksocknal_handle_zcack+0x137/0x1e0 <br>
[ksocklnd]<br>
[72095.974101] [<ffffffffa06becf1>] <br>
ksocknal_process_receive+0x3a1/0xd90 [ksocklnd]<br>
[72095.974134] [<ffffffffa06bfa6e>] ksocknal_scheduler+0xee/0x670 <br>
[ksocklnd]<br>
[72095.974165] [<ffffffff810b1b20>] ? wake_up_atomic_t+0x30/0x30<br>
[72095.974193] [<ffffffffa06bf980>] ? ksocknal_recv+0x2a0/0x2a0 [ksocklnd]<br>
[72095.974222] [<ffffffff810b0a4f>] kthread+0xcf/0xe0<br>
[72095.974244] [<ffffffff810b0980>] ? kthread_create_on_node+0x140/0x140<br>
[72095.974272] [<ffffffff81697758>] ret_from_fork+0x58/0x90<br>
[72095.974296] [<ffffffff810b0980>] ? kthread_create_on_node+0x140/0x140<br>
<br>
I am currently using lustre 2.9.59_15_g107b2cb built for kmod<br>
<br>
Is there something I can do to track this down and hopefully remedy it?<br>
<br>
Brian Andrus<br>
<br>
_______________________________________________<br>
lustre-discuss mailing list<br>
lustre-discuss@lists.lustre.org<br>
<a href="http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org">http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org</a><br>
</div>
</span></font>
</body>
</html>