On Wed, Jan 11, 2017 at 10:51 AM, Wiles, Keith <keith.wi...@intel.com>
wrote:
>
> > On Jan 11, 2017, at 12:08 PM, Vincent Li <vincent.mc...@gmail.com>
> wrote:
> >
> > Hi,
> >
> > I have direct two cable connections between Pktgen DPDK box and BIGIP
> >
> > this is a problem I am not sure if it Pktgen, or the DPDK net bonding
> mode
> > 4 LACP, or the BIGIP trunk with LACP enabled issue, I am hoping someone
> > here have more clue and give me some direction on how to trouble shoot
> > this. I am suspecting there might some issue between DPDK net bonding
> > 8023ad mode 4 and BIGIP trunk LACP mode. I turned
> > on CONFIG_RTE_LOG_LEVEL=RTE_LOG_DEBUG and
> > defined RTE_LIBRTE_BOND_DEBUG_8023AD
> > in drivers/net/bonding/rte_eth_bond_8023ad.c hoping getting more debug
> > output in Pktgen, I could not see any debug output for 8023ad protocol.
>
> I am not going to be much help as I do not and have not used BIGIP.
>
> I assume you have the Pktgen that supports bonding mode 4. The previous
> Pktgen version would not call tx_burst() unless it had something to send,
> which the bonding driver requires tx_burst() with zero packets at least at
> a given interval. The latest versions do call tx_burst() with zero pkts at
> least within the needed timing.
>
> Yes, I am using latest Pktgen with latest DPDK and run Pktgen like:
# ./app/app/x86_64-native-linuxapp-gcc/pktgen -c 0xff
--vdev=net_bonding0,mode=4,xmit_policy=l34,slave=0000:04:00.1,slave=0000:04:00.0
-- -P -m [0:1-7].2
also I am not sure where net bonding debug log goes as I added
#define RTE_LIBRTE_BOND_DEBUG_8023AD 1
in drivers/net/bonding/rte_eth_bond_8023ad.c and the code has following
#ifdef RTE_LIBRTE_BOND_DEBUG_8023AD
#define MODE4_DEBUG(fmt, ...) RTE_LOG(DEBUG, PMD, "%6u [Port %u: %s] " fmt,
\
bond_dbg_get_time_diff_ms(), slave_id, \
__func__, ##__VA_ARGS__)
