I think I answered my own question: you cannot rename your Ethernet device in /etc/udev/rules.d/70-persistent-net.rules. In the dmesg output above you'll notice I'm renaming dna0 to data. When I left the interface as dna0, it's receiving packets now.
On Tue, May 7, 2013 at 4:17 PM, Cliff Burdick <[email protected]> wrote: > Hi, I'm trying to test out DNA mode on the pfdnacluster_master example > program to see if it works, and I'm getting a floating point exception when > the program starts. I compiled the ixgbe DNA driver, as well as copied the > .a from the libs/ directory into lib/ to get the architecture-specific > file. I loaded the ixgbe driver as follows: > > insmod pf_ring.ko > insmod ./ixgbe.ko RSS=1,1,1,1 > > ./pfdnacluster_master -i data -c 1 -n 2 -a > Capturing from data > Using PF_RING v.5.5.2 > Hashing packets per-IP Address > Floating point exception > > gdb shows the following: > Hashing packets per-IP Address > > Program received signal SIGFPE, Arithmetic exception. > 0x0000000000410fa9 in dna_cluster_enable () > (gdb) backtrace > #0 0x0000000000410fa9 in dna_cluster_enable () > #1 0x0000000000407d4b in main () > > > Lastly, dmesg shows: > > [PF_RING] Welcome to PF_RING 5.5.2 ($Revision: $) > (C) 2004-13 ntop.org > [PF_RING] registered /proc/net/pf_ring/ > NET: Registered protocol family 27 > [PF_RING] Min # ring slots 4096 > [PF_RING] Slot version 14 > [PF_RING] Capture TX Yes [RX+TX] > [PF_RING] Transparent Mode 0 > [PF_RING] IP Defragment No > [PF_RING] Initialized correctly > Intel(R) 10 Gigabit PCI Express Network Driver - version 3.10.16-DNA > Copyright (c) 1999-2012 Intel Corporation. > ixgbe 0000:0e:00.0: PCI INT A -> GSI 16 (level, low) -> IRQ 16 > ixgbe 0000:0e:00.0: setting latency timer to 64 > ixgbe: Receive-Side Scaling (RSS) set to 1 > ixgbe 0000:0e:00.0: irq 37 for MSI/MSI-X > ixgbe 0000:0e:00.0: irq 38 for MSI/MSI-X > [DNA] Hardware filtering rule not supported (no 82599) > ixgbe 0000:0e:00.0: (PCI Express:2.5GT/s:Width x8) 00:00:50:87:7e:e0 > ixgbe 0000:0e:00.0: data: MAC: 1, PHY: 0, PBA No: 010613-031 > ixgbe 0000:0e:00.0: data: Enabled Features: RxQ: 1 TxQ: 1 LRO > ixgbe 0000:0e:00.0: data: Intel(R) 10 Gigabit Network Connection > ixgbe 0000:0e:00.1: PCI INT B -> GSI 17 (level, low) -> IRQ 17 > ixgbe 0000:0e:00.1: setting latency timer to 64 > ixgbe: Receive-Side Scaling (RSS) set to 1 > udev: renamed network interface dna0 to data > [DNA] MTU resize at runtime is not YET supported on DNA > ixgbe 0000:0e:00.1: irq 39 for MSI/MSI-X > ixgbe 0000:0e:00.1: irq 40 for MSI/MSI-X > ADDRCONF(NETDEV_UP): data: link is not ready > [DNA] Hardware filtering rule not supported (no 82599) > ixgbe 0000:0e:00.1: (PCI Express:2.5GT/s:Width x8) 00:00:50:87:7e:e1 > ixgbe 0000:0e:00.1: rtm10g: MAC: 1, PHY: 0, PBA No: 010613-031 > ixgbe 0000:0e:00.1: rtm10g: Enabled Features: RxQ: 1 TxQ: 1 LRO > ixgbe 0000:0e:00.1: rtm10g: Intel(R) 10 Gigabit Network Connection > udev: renamed network interface dna0 to rtm10g > [DNA] MTU resize at runtime is not YET supported on DNA > ADDRCONF(NETDEV_UP): rtm10g: link is not ready > ixgbe 0000:0e:00.0: data: NIC Link is Up 10 Gbps, Flow Control: None > ADDRCONF(NETDEV_CHANGE): data: link becomes ready > ixgbe 0000:0e:00.1: rtm10g: NIC Link is Up 10 Gbps, Flow Control: None > ADDRCONF(NETDEV_CHANGE): rtm10g: link becomes ready > rtm10g: no IPv6 routers present > data: no IPv6 routers present > device data entered promiscuous mode > pfdnacluster_ma[1768] trap divide error ip:410fa9 sp:7fff78cd7950 error:0 > in pfdnacluster_master[400000+50000] > > > Anyone know what could be wrong? I'm running this on a 64-bit 6-core Xeon > E5645 processor. >
_______________________________________________ Ntop-misc mailing list [email protected] http://listgateway.unipi.it/mailman/listinfo/ntop-misc
