DPDK usage discussions
 help / color / mirror / Atom feed
From: Vincent Li <vincent.mc.li@gmail.com>
To: "Wiles, Keith" <keith.wiles@intel.com>
Cc: "users@dpdk.org" <users@dpdk.org>, "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-users] Pktgen DPDK net bonding mode 4 802.3AD (LACP) not working with BIGIP trunk with LACP enabled
Date: Wed, 11 Jan 2017 11:08:45 -0800	[thread overview]
Message-ID: <CAK3+h2z7A6Vy1q3x+tmDH2VuMP9WShWHV+A2FCbApd5Ms1mbjQ@mail.gmail.com> (raw)
In-Reply-To: <57835675-A430-40D9-83EC-6B5ADE66D247@intel.com>

On Wed, Jan 11, 2017 at 10:51 AM, Wiles, Keith <keith.wiles@intel.com>
wrote:

>
> > On Jan 11, 2017, at 12:08 PM, Vincent Li <vincent.mc.li@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__)

      reply	other threads:[~2017-01-11 19:08 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-01-11 18:08 Vincent Li
2017-01-11 18:51 ` Wiles, Keith
2017-01-11 19:08   ` Vincent Li [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CAK3+h2z7A6Vy1q3x+tmDH2VuMP9WShWHV+A2FCbApd5Ms1mbjQ@mail.gmail.com \
    --to=vincent.mc.li@gmail.com \
    --cc=dev@dpdk.org \
    --cc=keith.wiles@intel.com \
    --cc=users@dpdk.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).