> > gig-e acenic in each node. A while back the acenic driver had some > > problems and would silently fail after a while; the arp reponse behavior > > allowed the cluster to remain 'up' long enough to finish the jobs we > > assigned to it (although performance sucked since all traffic went over > > the eepros). After we were done, we could ifdown/ifup the interfaces and > > all was good. > I'm still seeing this problem with 2.4.3 on netgear acenic gige cards. > Do you know anything else about it? Garzik tells me that there are > acenic changes in the 2.4.4-pre series, but I haven't checked them yet. I'm afraid not; we're using Alteon (now 3Com?) AceNICs here on 2.2.18 (with 'hidden'). A while back there was a new release of the driver and the problem just went away, I didn't ask questions. It could be the driver, it could be that I discovered 'hidden', it could be that we moved our group behind a new firewall. The problems you're seeing could be due to networking changes between 2.2 and 2.4 the driver doesn't expect, which can be pretty subtle, or faulty firmware code (we're running some homebrew here for our research). Lots of possibilities, but no answers ;( All I can suggest is to check the homepage http://jes.home.cern.ch/jes/gige/acenic.html and see if your driver/firmware version is at least as new as the one there, and contact Jes Sørensen at (jes@linuxcare.com, the driver author) with any specific bug reports. -Eric -------------------------------------------- Eric H. Weigle CCS-1, RADIANT team ehw@lanl.gov Los Alamos National Lab (505) 665-4937 http://home.lanl.gov/ehw/ -------------------------------------------- - : send the line "unsubscribe linux-net" in the body of a message to majordomo@vger.kernel.org
