DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Dumitrescu, Cristian" <cristian.dumitrescu@intel.com>
To: Stephen Hemminger <stephen@networkplumber.org>
Cc: Kevin Yan <Kevin.Yan@mavenir.com>, "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] DPDK qos support for 40G port
Date: Fri, 18 Aug 2017 18:05:19 +0000	[thread overview]
Message-ID: <3EB4FA525960D640B5BDFFD6A3D891267BA9C95D@IRSMSX108.ger.corp.intel.com> (raw)
In-Reply-To: <20170818102158.1d5f7d0f@xeon-e3>



> -----Original Message-----
> From: Stephen Hemminger [mailto:stephen@networkplumber.org]
> Sent: Friday, August 18, 2017 6:22 PM
> To: Dumitrescu, Cristian <cristian.dumitrescu@intel.com>
> Cc: Kevin Yan <Kevin.Yan@mavenir.com>; dev@dpdk.org
> Subject: Re: [dpdk-dev] DPDK qos support for 40G port
> 
> On Fri, 18 Aug 2017 11:24:12 +0000
> "Dumitrescu, Cristian" <cristian.dumitrescu@intel.com> wrote:
> 
> > Hi Kevin,
> >
> > > Hi Cristian,
> > > Sorry to bother again, could you give suggestions/hints of code change to
> > > support single 40G port?  Because  in our setup, we will use single 40G
> port
> > > (Intel XL710) as the network interface.
> > >
> > > Or is there any workaround to bypass the limitation?(we are not willing to
> > > use 4*10G setup)
> > >
> > > Thanks.
> > >
> >
> > Probably the easiest thing to do as workaround to support single port of
> 40GbE rate is to change the code so that each credit is equivalent to 2 bytes
> instead of one. This is likely to result in some scheduling accuracy loss, but it
> can be implemented relatively quickly while avoiding complex code changes.
> >
> > Regards,
> > Cristian
> >
> 
> Maybe it is time to deprecate existing QoS since it has so many fixed limits
> and start a new version which supports up to 400G and many more classes.
> 
> Something that integrated better with your new QoS framework.

s/deprecate/improve

I am working to push some updates to librte_meter library, librte_sched to follow.

  reply	other threads:[~2017-08-18 18:05 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-08-04  1:54 Kevin Yan
2017-08-04  9:57 ` Dumitrescu, Cristian
2017-08-07  4:42   ` Kevin Yan
2017-08-18 11:24     ` Dumitrescu, Cristian
2017-08-18 17:21       ` Stephen Hemminger
2017-08-18 18:05         ` Dumitrescu, Cristian [this message]
2017-08-23  5:37       ` Kevin Yan

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=3EB4FA525960D640B5BDFFD6A3D891267BA9C95D@IRSMSX108.ger.corp.intel.com \
    --to=cristian.dumitrescu@intel.com \
    --cc=Kevin.Yan@mavenir.com \
    --cc=dev@dpdk.org \
    --cc=stephen@networkplumber.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).