Hi- I've had lustre running happily for some time over a single 10g ethernet NIC per node. After switching to dual 10g and creating a new filesystem (1.6.4.2), I'm seeing nothing but keep-alive packets with bad checksums.
What is the current "correct" way to do this now? The manual suggest not using bonding, but several list postings now reccommend it. Without bonding, do I need to have my 2 switches stacked, or will Lustre recognize the division in my subnet? LNET module options I've tried are: 1) networks="tcp0(eth2,eth3)" 2) ip2nets="tcp(eth2,eth3); tcp(eth2) 10.9.[1-4].*; tcp(eth3) 10.9.[5-8].*;" and many other variations All other services are functional on both interfaces. Thanks in advance, J Bower-Cooley Scientific Systems Engineer Las Cumbres Observatory Global Telescope _______________________________________________ Lustre-discuss mailing list [email protected] http://lists.lustre.org/mailman/listinfo/lustre-discuss
