From: Yuanhan Liu <yuanhan.liu@linux.intel.com>
To: Pankaj Chauhan <pankaj.chauhan@nxp.com>
Cc: "Tan, Jianfeng" <jianfeng.tan@intel.com>,
dev@dpdk.org, hemant.agrawal@nxp.com, maxime.coquelin@redhat.com
Subject: Re: [dpdk-dev] [RFC][PATCH V2 1/3] examples/vhost: Add vswitch (generic switch) framework
Date: Tue, 27 Sep 2016 20:10:45 +0800 [thread overview]
Message-ID: <20160927121045.GN25823@yliu-dev.sh.intel.com> (raw)
In-Reply-To: <2d3dbd38-7dba-3af4-ab0e-52bc48f861d6@nxp.com>
On Tue, Sep 27, 2016 at 05:05:41PM +0530, Pankaj Chauhan wrote:
> >Hi Pankaj,
> >
> >Again, apologize for late response: you see I was busy ;) Besides, I
> >need some time to think about it.
> >
>
> Hi YLiu,
>
> No issues with delayed response :)
Thanks!
>
> >Generally, I think your ideal proposal looks good to me (well, I don't
> >see the need of port mask):
>
> The idea of port mask was to give ability to the caller to choose which type
> of port to do rx from, Physical port or vhost port.
What's the need of it? If you register a port, don't you need pull
packets from it?
And you don't have to distinguish whether it's a physical port or vhost
port or not. If a port is registered, just pull it. Simple, right?
> >
> > switch_worker() {
> > rx_port = vs_sched_rx_port(vswit_dev_g, core_id)
> > rx_q = rx_port->get_rxq(vs_port, vdev, code_id);
> > rx_port->do_rx(rx_port, rxq, NULL, pktss, MAX_PKT_BURST);
> >
> > vs_lookup_n_fwd(rx_port, pkts, rx_count, rxq);
> > }
> >
> >The issue is, as you stated, VMDq it's bit tricky to handle. How about
> >the following proposal then?
> >
> >We don't have to register the nic queues while VMDq is used, since a
> >phys queue is bond to a virtio queue in this mode. That means only
> >virtio queues will be scheduled.
> >
> >The virtio do_rx might look like below then:
> >
> > vmdq_rx() {
> > rte_eth_rx_burst(port, queue_bond_to_this_virtio_queue, ...);
> > rte_vhost_enqueue_burst(...) if any;
> >
> > rte_vhost_dequeue_burst(...);
> > }
> >
>
> Okay so in that case, we won't do any rte_eth_rx_burst() when
> physical_port->do_rx is called, Correct?.
The physical port do_rx will not be called at all, since it will
not registered. In the VMDq case, only virtio port will be registered
(by your vs_add_port function).
> If yes then in vmdq.c we'll
> overwrite vs_port->do_rx of physical port with a vmdq_do_rx_phys() which
> does nothing. Or we can even have an option that vmdq.c doesn't return the
> physical port when vs_sched_rx_port() is called,
As stated, if you don't register it, then vs_sched_rx_port will return no
physical port.
--yliu
> i think this later option
> is better to save some CPU cycles.
>
> I think it is possible but i would prefer to overwrite vs_port->do_rx() for
> vmdq (in vmdq.c) with the implementation that you suggested. The framework
> provides this option, i.e the switch implementation can overwrite the
> vs_port->do_rx/do_tx if required to handle any special cases for example the
> case of vmdq <> vdev boding.
>
> Thanks,
> Pankaj
> > --yliu
> >
>
next prev parent reply other threads:[~2016-09-27 12:10 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-09-05 10:54 [dpdk-dev] [RFC][PATCH V2 0/3] example/vhost: Introduce Vswitch Framework Pankaj Chauhan
2016-09-05 10:54 ` [dpdk-dev] [RFC][PATCH V2 1/3] examples/vhost: Add vswitch (generic switch) framework Pankaj Chauhan
2016-09-09 8:56 ` Tan, Jianfeng
2016-09-12 10:55 ` Pankaj Chauhan
2016-09-13 6:51 ` Tan, Jianfeng
2016-09-15 9:00 ` Pankaj Chauhan
2016-09-19 12:42 ` Tan, Jianfeng
2016-09-27 11:26 ` Pankaj Chauhan
2016-09-19 14:43 ` Yuanhan Liu
2016-09-20 8:58 ` Pankaj Chauhan
2016-09-26 3:56 ` Yuanhan Liu
2016-09-27 11:35 ` Pankaj Chauhan
2016-09-27 12:10 ` Yuanhan Liu [this message]
2016-09-11 12:21 ` Yuanhan Liu
2016-09-12 10:59 ` Pankaj Chauhan
2016-09-26 4:12 ` Yuanhan Liu
2016-09-27 11:44 ` Pankaj Chauhan
2016-09-27 12:03 ` Yuanhan Liu
2016-09-05 10:54 ` [dpdk-dev] [RFC][PATCH V2 2/3] examples/vhost: Add vswitch command line options Pankaj Chauhan
2016-09-13 12:14 ` Yuanhan Liu
2016-09-15 9:11 ` Pankaj Chauhan
2016-09-05 10:54 ` [dpdk-dev] [RFC][PATCH V2 3/3] examples/vhost: Add VMDQ vswitch device Pankaj Chauhan
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=20160927121045.GN25823@yliu-dev.sh.intel.com \
--to=yuanhan.liu@linux.intel.com \
--cc=dev@dpdk.org \
--cc=hemant.agrawal@nxp.com \
--cc=jianfeng.tan@intel.com \
--cc=maxime.coquelin@redhat.com \
--cc=pankaj.chauhan@nxp.com \
/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).