They have been the same error messages I've received previously during the locking crashes I posted about last year. The trace always goes back to skb_ring_handler(). (I would post the traces, but it's a fairly major hassle to hook something up to the serial port to get the dumps). Essentially, there is some strange bug with the ring_mgmt lock where situations like clustering or running more than one app on the same PF_RING interface under heavy load cause a kernel panic. Others had reported no problems, but I experienced it on several different hardware architectures, kernel versions, and PF_RING versions.
On a separate topic, Ken had asked about the setsockop filtering last night, would this have something to do with the new parse_pkt() function Luca has added? --Martin -----Original Message----- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Michael Stiller Sent: Wednesday, January 31, 2007 12:59 AM To: [email protected] Subject: RE: [Ntop-misc] Get PF_RING to work with bonding? Sounds very interesting indeed, but i have not used it. > However, I have not been able to get clustering to work properly as it > is fairly buggy in adding and removing rings from the cluster. It also > has a tendency to crash the system. I am wondering if anyone else has > been able to use or has attempted to use the clustering feature. If you get crashes with error messages, i think you should post them here. -Michael _______________________________________________ Ntop-misc mailing list [email protected] http://listgateway.unipi.it/mailman/listinfo/ntop-misc _______________________________________________ Ntop-misc mailing list [email protected] http://listgateway.unipi.it/mailman/listinfo/ntop-misc
