great information, I disabled s/g on one cluster and didnt have any crashed since then.<br>Is it enough to disconnect the resources and change that settings or do I have to completely shutdown<br>drbddevice and xen VM?<br>
<br>big thnx<br><br>.r<br><br><div class="gmail_quote">On Thu, Jul 30, 2009 at 11:29 PM, Maros Timko <span dir="ltr"><<a href="mailto:timkom@gmail.com">timkom@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div>No,</div>
<div> </div>
<div>I meant:</div>
<div><a href="http://www.gossamer-threads.com/lists/drbd/users/17212" target="_blank">http://www.gossamer-threads.com/lists/drbd/users/17212</a></div>
<div><a href="http://www.gossamer-threads.com/lists/drbd/users/17356" target="_blank">http://www.gossamer-threads.com/lists/drbd/users/17356</a></div>
<div><a href="http://www.gossamer-threads.com/lists/drbd/users/16962" target="_blank">http://www.gossamer-threads.com/lists/drbd/users/16962</a></div><div><div></div><div class="h5">
<div> </div>
<div>Tino<br><br></div>
<div class="gmail_quote">2009/7/30 Rupert <span dir="ltr"><<a href="mailto:rupertt@gmail.com" target="_blank">rupertt@gmail.com</a>></span><br>
<blockquote style="border-left: 1px solid rgb(204, 204, 204); margin: 0px 0px 0px 0.8ex; padding-left: 1ex;" class="gmail_quote">Maros Timko wrote:<br>
<blockquote style="border-left: 1px solid rgb(204, 204, 204); margin: 0px 0px 0px 0.8ex; padding-left: 1ex;" class="gmail_quote">
<div>Rupertt,<br> TOE - TCP Offloading Engine is HW support of network card to improve performance. It is usually enabled by default on your network card.<br>Check "ethtool -k" option and search on this list.<br>
Tino<br></div>2009/7/30 Rupert <<a href="mailto:rupertt@gmail.com" target="_blank">rupertt@gmail.com</a> <mailto:<a href="mailto:rupertt@gmail.com" target="_blank">rupertt@gmail.com</a>>>
<div><br><br> Maros Timko wrote:<br><br> Heiko,<br> whhich machine crashes? Primary only, both?<br> I think it is primary but only in case xen VM is running on<br> top of DRBD. You can prevent crashes by disabling TOE. Or use<br>
DRBD 8.3.2, AFAIK there should be a parameter that should help<br> in such setups.<br> Check older posts in this list.<br> Tino<br><br></div></blockquote>Hello tino,<br><br>you mean this post?<br>
<br><a href="http://archives.free.net.ph/message/20071214.134353.11ba93b1.de.html" target="_blank">http://archives.free.net.ph/message/20071214.134353.11ba93b1.de.html</a><br><br>this is what ethtool show me:<br>ethtool -k eth0<br>
Offload parameters for eth0:<br>Cannot get device rx csum settings: Operation not supported<br>Cannot get device udp large send offload settings: Operation not supported<br>rx-checksumming: off<br>tx-checksumming: on<br>
scatter-gather: on<br>
tcp segmentation offload: on<br>udp fragmentation offload: off<br>generic segmentation offload: off<br><br>will disabling tx have any affect on traffic over this device?<br>there are 3 other VM that use that device, so i hesitate to just change this setting.<br>
<br><br>cheers<br><br><br>.r<br><br>
<blockquote style="border-left: 1px solid rgb(204, 204, 204); margin: 0px 0px 0px 0.8ex; padding-left: 1ex;" class="gmail_quote">
<div> Hello Tino,<br><br> in one case I have a primary on each machine, means 2 drbd devices.<br> In the other case we have only 1 drbd device, and there only the<br> primary crashed.<br> What means TOE, havent found anything about that yet?<br>
Someone on this list suggested that I should use protocol A, but<br> we dont want to loose<br> any data, so we cant use that.<br> I am thinking about updating, but I first have to test if these<br> packages work with our system,<br>
CentOS 5.x.<br><br> so long<br><br> 2009/7/27 Heiko <<a href="mailto:rupertt@gmail.com" target="_blank">rupertt@gmail.com</a> <mailto:<a href="mailto:rupertt@gmail.com" target="_blank">rupertt@gmail.com</a>><br>
</div> <mailto:<a href="mailto:rupertt@gmail.com" target="_blank">rupertt@gmail.com</a> <mailto:<a href="mailto:rupertt@gmail.com" target="_blank">rupertt@gmail.com</a>>>>
<div><br><br><br><br><br> On Mon, Jul 27, 2009 at 2:18 PM, Martin Gombac<br> <<a href="mailto:martin@isg.si" target="_blank">martin@isg.si</a> <mailto:<a href="mailto:martin@isg.si" target="_blank">martin@isg.si</a>><br>
</div>
<div>
<div></div>
<div> <mailto:<a href="mailto:martin@isg.si" target="_blank">martin@isg.si</a> <mailto:<a href="mailto:martin@isg.si" target="_blank">martin@isg.si</a>>>> wrote:<br><br> In my humble opinion, drbd does't crash if you loose<br>
network<br> connections. :-)<br> Would be a first in history.<br> Maybe heartbeat puts both sources to primary and when they<br> join you got split brain.<br> In this case you didn't set up heartbeat correctly.<br>
<br> Hello M.,<br><br> i had some people here that confirmed a bug in protocol C that<br> causes these crashes.<br> I also thought of heartbeat, but I now have 2 ucast devices<br> and we<br>
still have crashes and<br> no entries in the logfile that say it does a reboot on purpose:<br><br> only these messages:<br><br> heartbeat[2880]: 2009/07/27_11:59:37 ERROR: glib: Unable to<br>
send<br> [-1] ucast packet: No such device<br> heartbeat[2880]: 2009/07/27_11:59:37 ERROR: write_child: write<br> failure on ucast eth0.: No such device<br><br><br><br><br> my ha config looks like this<br>
<br> #use_logd on<br> logfile /var/log/ha-log<br> debugfile /var/log/ha-debug<br> logfacility local0<br> keepalive 2<br> deadtime 10<br> warntime 3<br> initdead 20<br>
udpport 694<br> ucast eth0 172.17.8.201<br> ucast eth0 172.17.8.202<br> ucast eth1 172.31.0.1<br> ucast eth1 172.31.0.2<br> node xen-a1.fra1<br> node xen-b1.fra1<br>
auto_failback on<br><br> haresources:<br><br> xen-a1.fra1 drbddisk::blrg xen::blrg-vm1<br> <br> thnx a lot<br><br><br> .r<br><br><br> Regards,<br> M.<br>
<br><br> On 27, Jul2009, at 1:47 PM, Heiko wrote:<br><br> Hello,<br><br> i have to convince my boss that our server crashes i<br> reported on this list are due<br>
to a non exsiting dedicated line! We have all our drbd<br> traffic routed through switches<br> and they often just crash.<br><br> Now I have to create a test setup to show them that<br>
when I<br> plug the corg/shutdown the networkdevice<br> the machines tend to crash.<br> Since I dont have any spare machines I would like<br> to use<br> loopback devices,<br>
are these supported by now? I found some list<br> entries that<br> say this is not supported by drbd!<br> would this be enough to get the machines crashing?<br> We use drbd8.0 and 8.2 and have on both these crashes.<br>
<br><br> cheers.<br> _______________________________________________<br> drbd-user mailing list<br> <a href="mailto:drbd-user@lists.linbit.com" target="_blank">drbd-user@lists.linbit.com</a><br>
<mailto:<a href="mailto:drbd-user@lists.linbit.com" target="_blank">drbd-user@lists.linbit.com</a>><br> <mailto:<a href="mailto:drbd-user@lists.linbit.com" target="_blank">drbd-user@lists.linbit.com</a><br>
<mailto:<a href="mailto:drbd-user@lists.linbit.com" target="_blank">drbd-user@lists.linbit.com</a>>><br><br> <a href="http://lists.linbit.com/mailman/listinfo/drbd-user" target="_blank">http://lists.linbit.com/mailman/listinfo/drbd-user</a><br>
<br><br><br><br> _______________________________________________<br> drbd-user mailing list<br> <a href="mailto:drbd-user@lists.linbit.com" target="_blank">drbd-user@lists.linbit.com</a><br> <mailto:<a href="mailto:drbd-user@lists.linbit.com" target="_blank">drbd-user@lists.linbit.com</a>><br>
<mailto:<a href="mailto:drbd-user@lists.linbit.com" target="_blank">drbd-user@lists.linbit.com</a><br> <mailto:<a href="mailto:drbd-user@lists.linbit.com" target="_blank">drbd-user@lists.linbit.com</a>>><br>
<br> <a href="http://lists.linbit.com/mailman/listinfo/drbd-user" target="_blank">http://lists.linbit.com/mailman/listinfo/drbd-user</a><br><br><br> ------------------------------------------------------------------------<br>
<br> _______________________________________________<br> drbd-user mailing list<br> <a href="mailto:drbd-user@lists.linbit.com" target="_blank">drbd-user@lists.linbit.com</a> <mailto:<a href="mailto:drbd-user@lists.linbit.com" target="_blank">drbd-user@lists.linbit.com</a>><br>
<a href="http://lists.linbit.com/mailman/listinfo/drbd-user" target="_blank">http://lists.linbit.com/mailman/listinfo/drbd-user</a><br> <br><br><br>------------------------------------------------------------------------<br>
<br>_______________________________________________<br>drbd-user mailing list<br><a href="mailto:drbd-user@lists.linbit.com" target="_blank">drbd-user@lists.linbit.com</a><br><a href="http://lists.linbit.com/mailman/listinfo/drbd-user" target="_blank">http://lists.linbit.com/mailman/listinfo/drbd-user</a><br>
<br></div></div></blockquote><br></blockquote></div><br>
</div></div><br>_______________________________________________<br>
drbd-user mailing list<br>
<a href="mailto:drbd-user@lists.linbit.com">drbd-user@lists.linbit.com</a><br>
<a href="http://lists.linbit.com/mailman/listinfo/drbd-user" target="_blank">http://lists.linbit.com/mailman/listinfo/drbd-user</a><br>
<br></blockquote></div><br>