<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=Windows-1252">
</head>
<body dir="auto">
Based on the messages on the client, this isn’t related to mmap() or writes done by the client, since the data has the same checksum from before it was sent and after it got the checksum error returned from the server. That means the pages did not change on
the client.
<div><br>
</div>
<div>Possible causes include the client network card, server network card, memory, or possibly the OFED driver? It could of course be something in Lustre/LNet, though we haven’t had any reports of anything similar. </div>
<div><br>
</div>
<div>When the checksum code was first written, it was motivated by a faulty Ethernet NIC that had TCP checksum offload, but bad onboard cache, and the data was corrupted when copied onto the NIC but the TCP checksum was computed on the bad data and the checksum
was “correct” when received by the server, so it didn’t cause TCP resends. </div>
<div><br>
</div>
<div>Are you seeing this on multiple servers? The client log only shows one server, while the server log shows multiple clients. If it is only happening on one server it might point to hardware. </div>
<div><br>
</div>
<div>Did you also upgrade the kernel and OFED at the same time as Lustre? You could try building Lustre 2.10.1 on the old 2.9.0 kernel and OFED to see if that works properly. <br>
<br>
<div id="AppleMailSignature">Cheers, Andreas</div>
<div><br>
On Dec 9, 2017, at 11:09, Hans Henrik Happe <<a href="mailto:happe@nbi.dk">happe@nbi.dk</a>> wrote:<br>
<br>
</div>
<blockquote type="cite">
<div><span></span><br>
<span></span><br>
<span>On 09-12-2017 18:57, Hans Henrik Happe wrote:</span><br>
<blockquote type="cite"><span>On 07-12-2017 21:36, Dilger, Andreas wrote:</span><br>
</blockquote>
<blockquote type="cite">
<blockquote type="cite"><span>On Dec 7, 2017, at 10:37, Hans Henrik Happe <<a href="mailto:happe@nbi.dk">happe@nbi.dk</a>> wrote:</span><br>
</blockquote>
</blockquote>
<blockquote type="cite">
<blockquote type="cite">
<blockquote type="cite"><span>Hi,</span><br>
</blockquote>
</blockquote>
</blockquote>
<blockquote type="cite">
<blockquote type="cite">
<blockquote type="cite"><span></span><br>
</blockquote>
</blockquote>
</blockquote>
<blockquote type="cite">
<blockquote type="cite">
<blockquote type="cite"><span>Can an application cause BAD CHECKSUM errors in Lustre logs by somehow</span><br>
</blockquote>
</blockquote>
</blockquote>
<blockquote type="cite">
<blockquote type="cite">
<blockquote type="cite"><span>overwriting memory while being DMA'ed to network?</span><br>
</blockquote>
</blockquote>
</blockquote>
<blockquote type="cite">
<blockquote type="cite">
<blockquote type="cite"><span></span><br>
</blockquote>
</blockquote>
</blockquote>
<blockquote type="cite">
<blockquote type="cite">
<blockquote type="cite"><span>After upgrading to 2.10.1 on the server side we started seeing this from</span><br>
</blockquote>
</blockquote>
</blockquote>
<blockquote type="cite">
<blockquote type="cite">
<blockquote type="cite"><span>a user's application (MPI I/O). Both 2.9.0 and 2.10.1 clients emit these</span><br>
</blockquote>
</blockquote>
</blockquote>
<blockquote type="cite">
<blockquote type="cite">
<blockquote type="cite"><span>errors. We have not yet established weather the application is doing</span><br>
</blockquote>
</blockquote>
</blockquote>
<blockquote type="cite">
<blockquote type="cite">
<blockquote type="cite"><span>things correctly.</span><br>
</blockquote>
</blockquote>
</blockquote>
<blockquote type="cite">
<blockquote type="cite"><span>If applications are using mmap IO it is possible for the page to become inconsistent after the checksum has been computed. However, mmap IO is</span><br>
</blockquote>
</blockquote>
<blockquote type="cite">
<blockquote type="cite"><span>normally detected by the client and no message should be printed.</span><br>
</blockquote>
</blockquote>
<blockquote type="cite">
<blockquote type="cite"><span></span><br>
</blockquote>
</blockquote>
<blockquote type="cite">
<blockquote type="cite"><span>There isn't anything that the application needs to do, since the client will resend the data if there is a checksum error, but the resends do slow down the IO. If the inconsistency is on the client, there is no cause for concern
(though it would be good to figure out the root cause).</span><br>
</blockquote>
</blockquote>
<blockquote type="cite">
<blockquote type="cite"><span></span><br>
</blockquote>
</blockquote>
<blockquote type="cite">
<blockquote type="cite"><span>It would be interesting to see what the exact error message is, since that will say whether the data became inconsistent on the client, or over the network. If the inconsistency is over the network or on the server, then that
may point to hardware issues.</span><br>
</blockquote>
</blockquote>
<blockquote type="cite"><span>I've attached logs from a server and a client.</span><br>
</blockquote>
<span></span><br>
<span>There was a cut n' paste error in the first set of files. This should be</span><br>
<span>better.</span><br>
<span></span><br>
<span>Looks like a something goes wrong over the network.</span><br>
<span></span><br>
<span>Cheers,</span><br>
<span>Hans Henrik</span><br>
<span></span><br>
</div>
</blockquote>
<blockquote type="cite">
<div><client.log></div>
</blockquote>
<blockquote type="cite">
<div><server.log></div>
</blockquote>
<blockquote type="cite">
<div><span>_______________________________________________</span><br>
<span>lustre-discuss mailing list</span><br>
<span><a href="mailto:lustre-discuss@lists.lustre.org">lustre-discuss@lists.lustre.org</a></span><br>
<span><a href="http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org">http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org</a></span><br>
</div>
</blockquote>
</div>
</body>
</html>