DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Richardson, Bruce" <bruce.richardson@intel.com>
To: Sunil Bojanapally <sunil.bojanapally@ericsson.com>,
	"Liu, Jijiang" <jijiang.liu@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] VMDq + DCB: 128 Tx queues
Date: Fri, 1 Aug 2014 17:38:46 +0000	[thread overview]
Message-ID: <59AF69C657FD0841A61C55336867B5B0343D47C5@IRSMSX103.ger.corp.intel.com> (raw)
In-Reply-To: <2093D5E48464CB43A02B12483F758F7A1A3BB243@ESESSMB105.ericsson.se>

> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Sunil Bojanapally
> Sent: Friday, August 01, 2014 9:13 AM
> To: Liu, Jijiang
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] VMDq + DCB: 128 Tx queues
> 
> Thanks Liu for the pointer to function implemented in testpmd.c
> 
> Just want to know in RX configured pools, what scheduling method is used in
> polling the  queues.

How the queues are polled when in vmdq+dcb mode is entirely up to the application, as the queue id passed into the rx_burst function will refer directly to one of the hardware queues to be read. There is no behind-the-scenes magic and prioritization of packets being done, the app knows best what way it wants the packets to be read and processed.

Regards,
/Bruce

> 
> -Sunil
> 
> On Fri, Aug 01, 2014 at 1:11 PM, Liu, Jijiang
> <jijiang.liu@intel.com<mailto:jijiang.liu@intel.com>> wrote:
> 
> 
> Yes, if you hope TX is configured DCB mode, and 128 TX queues are needed. In
> testpmd codes, there is an example how to use 128 RX queue and 128 TX queue
> simultaneously in vmdq+dcb mode.
> The example function is get_eth_dcb_conf() in testpmd.c file.
> 
> BRs,
> Jijiang Liu
> 
> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Sunil Bojanapally
> Sent: Friday, August 01, 2014 1:13 PM
> To: dev@dpdk.org
> Subject: [dpdk-dev] VMDq + DCB: 128 Tx queues
> 
> Hi team,
> 
> As per dpdk programming guide on VMDq+DCB will configure each Ethernet port
> to 16 pools with 8 queues each. Which means per port will have 128 Rx & Tx
> queues.
> 
> The question is, in order to have end 2 end QoS support the port should get
> configured with 128 Rx as well as 128 Tx queues ?
> 
> Note: I am considering same port for Rx & Tx.
> 
> Thanks,
> Sunil

      reply	other threads:[~2014-08-01 17:37 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-08-01  5:13 Sunil Bojanapally
2014-08-01  7:41 ` Liu, Jijiang
2014-08-01 16:12   ` Sunil Bojanapally
2014-08-01 17:38     ` Richardson, Bruce [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=59AF69C657FD0841A61C55336867B5B0343D47C5@IRSMSX103.ger.corp.intel.com \
    --to=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    --cc=jijiang.liu@intel.com \
    --cc=sunil.bojanapally@ericsson.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).