On 01/26/2011 11:35 AM, Scooter Morris wrote: > We're seeing lots of these messages on a single node in our 3 node RHEL > 5.6 cluster (but never on the other nodes). According to previous > posts, this is indicative of lost packets and openais should recover > just fine. On the other hand, it's really disconcerting that we're > losing packets (we've been fighting gfs2 glock issues also). Is this a > "normal" message, or should we really be concerned about losing > packets? We're not logging any errors on the private ethernet > interfaces of any of the nodes, so I'm not really sure what might be > going on. > We implemented a workaround in 5.6 for a delayed multicast situation that occurs on many switch vendor's hardware in openais-0.80.6-27.el5. The workaround should solve the problem unless indeed there are lost packets or there is a build error. Which openais rpm are you using? Regards -steve > -- scooter > > -- > Linux-cluster mailing list > Linux-cluster@xxxxxxxxxx > https://www.redhat.com/mailman/listinfo/linux-cluster -- Linux-cluster mailing list Linux-cluster@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/linux-cluster
