I would look to characterize some sampling of those queries. For example, are there a large volume of arp requests with no answers (e.g. conserver spinning on trying to reach nonexistant or misconfigured service processors)? Are there a significant number of arp replies with no requests (e.g. gratuitous arps)? Are arp requests seemingly replaying?
I might be able to look at a pcap dump of the situation if you wanted to send it to me. From: "Baker D.J." <[email protected]> To: xCAT Users Mailing list <[email protected]>, Date: 03/27/2012 10:25 AM Subject: [xcat-user] ARP traffic Hello, We’re running xcat Version 2.6.10 on our cluster, and I’ve been taking a look at the network with tcpdump recently. We have in the region of 1000 compute nodes on the network, and they’re all managed by xcat. The volume of ARP related traffic on the network (I ran tcpdump on the xcat master) seems very high to me, however I’m no expert in these things and so the level of ARP activity may be reasonable. I ran tcpdump for just 1 minute, and recorded in the region of 7,000 ARP transactions. Is this reasonable for a cluster of 1000 compute nodes? If anyone can please advise us in this respect then that would be appreciated. Best regards – David. ------------------------------------------------------------------------------ This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure _______________________________________________ xCAT-user mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/xcat-user
<<inline: graycol.gif>>
------------------------------------------------------------------------------ This SF email is sponsosred by: Try Windows Azure free for 90 days Click Here http://p.sf.net/sfu/sfd2d-msazure
_______________________________________________ xCAT-user mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/xcat-user
