<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">This only adds a checksum to the NSD wire protocol. The question was about detecting data corruption at rest.<div class=""><br class=""><div class="">
<div style="color: rgb(0, 0, 0); letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px; word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class="">-- <br class="">Stephen<br class=""><br class=""><br class=""></div>
</div>
<div><br class=""><blockquote type="cite" class=""><div class="">On Jun 2, 2022, at 1:01 PM, Achim Rehor <<a href="mailto:Achim.Rehor@de.ibm.com" class="">Achim.Rehor@de.ibm.com</a>> wrote:</div><br class="Apple-interchange-newline"><div class="">
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" class="">
<div class="">
<div class="">hi Stephan, </div>
<div class=""><br class="">
</div>
<div class="">there is, see mmchconfig man page : <br class="">
<br class="">
</div>
<div class="">nsdCksumTraditional</div>
<div class="">This attribute enables checksum data-integrity checking between a traditional NSD client node and its NSD server. Valid values are yes and no. The default value is no.</div>
<div class="">(Traditional in this context means that the NSD client and server are configured with IBM Spectrum Scale rather than with IBM Spectrum Scale RAID. </div>
<div class="">The latter is a component of IBM Elastic Storage Server (ESS) and of IBM GPFS Storage Server (GSS).)</div>
<div class=""><br class="">
</div>
<div class="">The checksum procedure detects any corruption by the network of the data in the NSD RPCs that are exchanged between the NSD client and the </div>
<div class="">server. A checksum error triggers a request to retransmit the message.</div>
<div class=""><br class="">
</div>
<div class="">When this attribute is enabled on a client node, the client indicates in each of its requests to the server that it is using checksums. The server uses checksums only in</div>
<div class="">response to client requests in which the indicator is set. A client node that accesses a file system that belongs to another cluster can use checksums in the same way.</div>
<div class=""><br class="">
</div>
<div class="">You can change the value of the this attribute for an entire cluster without shutting down the mmfsd daemon, or for one or more nodes without restarting the nodes.</div>
<div class=""><br class="">
</div>
<div class="">Note:</div>
<div class="">* Enabling this feature can result in significant I/O performance degradation and a considerable increase in CPU usage.</div>
<div class=""><br class="">
</div>
<div class="">* To enable checksums for a subset of the nodes in a cluster, issue a command like the following one:</div>
<div class=""> mmchconfig nsdCksumTraditional=yes -i -N <subset-of-nodes></div>
<div class=""><br class="">
</div>
<div class=""> The -N flag is valid for this attribute.</div>
<div class=""><br class="">
</div>
<div class=""><span class="">
<pre class="">-- <br class=""></pre>
<div data-evo-paragraph="" class="" style="width: 71ch;" data-evo-signature-plain-text-mode="">
Mit freundlichen Grüßen / Kind regards</div>
<div data-evo-paragraph="" class="" style="width: 71ch;"><br class="">
</div>
<div data-evo-paragraph="" class="" style="width: 71ch;">Achim Rehor</div>
<div data-evo-paragraph="" class="" style="width: 71ch;"><br class="">
</div>
<div data-evo-paragraph="" class="" style="width: 71ch;">Technical Support Specialist Spectrum Scale and ESS (SME)</div>
<div data-evo-paragraph="" class="" style="width: 71ch;">Advisory Product Services Professional</div>
<div data-evo-paragraph="" class="" style="width: 71ch;">IBM Systems Storage Support - EMEA</div>
<div data-evo-paragraph="" class="" style="width: 71ch;"><br class="">
</div>
<div data-evo-paragraph="" class="" style="width: 71ch;"><a href="mailto:Achim.Rehor@de.ibm.com" class="">Achim.Rehor@de.ibm.com</a>
<span class="Apple-tab-span" style="white-space:pre"></span>+49-170-4521194<span class="Apple-tab-span" style="white-space:pre">
</span> <span class="Apple-tab-span" style="white-space:pre"> </span><span class="Apple-tab-span" style="white-space:pre"></span><span class="Apple-tab-span" style="white-space:pre"></span><span class="Apple-tab-span" style="white-space:pre"></span><span class="Apple-tab-span" style="white-space: pre;"></span><span class="Apple-tab-span" style="white-space: pre;"></span><span class="Apple-tab-span" style="white-space: pre;"></span></div>
<div data-evo-paragraph="" class="" style="width: 71ch;">IBM Deutschland GmbH </div>
<div data-evo-paragraph="" class="" style="width: 71ch;">Vorsitzender des Aufsichtsrats: Sebastian Krause</div>
<div data-evo-paragraph="" class="" style="width: 71ch;">Geschäftsführung: Gregor Pillen (Vorsitzender), Nicole Reimer, </div>
<div data-evo-paragraph="" class="" style="width: 71ch;">Gabriele Schwarenthorer, Christine Rupp, Frank Theisen</div>
<div data-evo-paragraph="" class="" style="width: 71ch;">Sitz der Gesellschaft: Ehningen / Registergericht: Amtsgericht<span data-hidden-space="" class=""></span><br class="-x-evo-wrap-br">
Stuttgart, HRB 14562 / WEEE-Reg.-Nr. DE 99369940</div>
<div data-evo-paragraph="" class="" style="width: 71ch;"><br class="">
</div>
</span></div>
<div class=""><br class="">
</div>
<div class="">-----Original Message-----</div>
<div class=""><b class="">From</b>: Stephan Graf <<a href="mailto:Stephan%20Graf%20%3cst.graf@fz-juelich.de%3e" class="">st.graf@fz-juelich.de</a>></div>
<div class=""><b class="">Reply-To</b>: gpfsug main discussion list <<a href="mailto:gpfsug%20main%20discussion%20list%20%3cgpfsug-discuss@gpfsug.org%3e" class="">gpfsug-discuss@gpfsug.org</a>></div>
<div class=""><b class="">To</b>: gpfsug-discuss <<a href="mailto:gpfsug-discuss%20%3cgpfsug-discuss@gpfsug.org%3e" class="">gpfsug-discuss@gpfsug.org</a>></div>
<div class=""><b class="">Subject</b>: [EXTERNAL] [gpfsug-discuss] Protection against silent data corruption</div>
<div class=""><b class="">Date</b>: Thu, 02 Jun 2022 16:31:43 +0200</div>
<div class=""><br class="">
</div>
<div class="">Hi,<br class="">
</div>
<div class=""><br class="">
</div>
<div class="">I am wondering if there is an option in SS to enable some checking to <br class="">
</div>
<div class="">detect silent data corruption.<br class="">
</div>
<div class=""><br class="">
</div>
<div class="">Form GNR I know that there is End-to-End integrity. So a checksum is <br class="">
</div>
<div class="">stored in addition.<br class="">
</div>
<div class=""><br class="">
</div>
<div class="">The background is that we are facing an issue where in some files (which <br class="">
</div>
<div class="">have data replication = 2) the mmrestripefile is reporting, that one <br class="">
</div>
<div class="">block is mismatching it's copy (the storage cluster is running SS <br class="">
</div>
<div class="">without GNR).<br class="">
</div>
<div class="">We have validated that the copied block is fine, but the original one is <br class="">
</div>
<div class="">broken (and this is what is returned on read access).<br class="">
</div>
<div class="">SS right now in our installation is unable to determine which is the <br class="">
</div>
<div class="">correct one.<br class="">
</div>
<div class="">Is there any option to enable this kind of feature in SS? If not, does <br class="">
</div>
<div class="">it make sense to create an "IDEA" for it?<br class="">
</div>
<div class=""><br class="">
</div>
<div class="">Stephan<br class="">
</div>
<div class=""><br class="">
</div>
<div class="">_______________________________________________<br class="">
</div>
<div class="">gpfsug-discuss mailing list<br class="">
</div>
<div class="">gpfsug-discuss at <a href="http://gpfsug.org" class="">gpfsug.org</a><br class="">
</div>
<div class=""><a href="http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org" class="">http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org</a><br class="">
</div>
</div>
_______________________________________________<br class="">gpfsug-discuss mailing list<br class="">gpfsug-discuss at <a href="http://gpfsug.org" class="">gpfsug.org</a><br class=""><a href="http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org" class="">http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org</a><br class=""></div></blockquote></div><br class=""></div></body></html>