DPDK patches and discussions
 help / color / mirror / Atom feed
From: Bruce Richardson <bruce.richardson@intel.com>
To: "Walukiewicz, Miroslaw" <Miroslaw.Walukiewicz@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCHv2 0/5] ethdev: add new API to retrieve RX/TX queue information
Date: Thu, 18 Jun 2015 15:13:03 +0100	[thread overview]
Message-ID: <20150618141303.GB5344@bricha3-MOBL3> (raw)
In-Reply-To: <7C4248CAE043B144B1CD242D27562653454ABDA5@IRSMSX104.ger.corp.intel.com>

On Thu, Jun 18, 2015 at 02:56:52PM +0100, Walukiewicz, Miroslaw wrote:
> Yes, really I need a high performance function - it is especially useful on TX path.
> 
> Which queue query function are you talking here to be enhanced?
> 

There are already functions for querying the RX queue - so as to enable power
management/frequency scaling.

rte_eth_rx_queue_count()
rte_eth_rX_descriptor_done()

You could write equivalents for the TX side that only do the minimum needed.
Descriptor-done is probably the simplest and most useful for you, as in you can
query if you have enough space for a single operation, rather than having the
code scan arbitrarily far ahead.

/Bruce

> Mirek
> 
> > -----Original Message-----
> > From: Richardson, Bruce
> > Sent: Thursday, June 18, 2015 3:39 PM
> > To: Walukiewicz, Miroslaw
> > Cc: Ananyev, Konstantin; dev@dpdk.org
> > Subject: Re: [dpdk-dev] [PATCHv2 0/5] ethdev: add new API to retrieve RX/TX
> > queue information
> > 
> > On Thu, Jun 18, 2015 at 01:30:33PM +0000, Walukiewicz, Miroslaw wrote:
> > > Konstantin,
> > >
> > > Is there a possibility to read information about available space in NIC queue
> > for TX.
> > >
> > > It is quite easy to compute (or even available directly)  and very useful
> > especially for application sending multi-descriptor packets like TCP TSO.
> > >
> > > Now there is no access to such information and the transmit packet function
> > must be called to
> > > be sure that there is available space.
> > >
> > > Mirek
> > >
> > 
> > Hi Mirek,
> > 
> > I'm not sure this function is the right place for such a query. It seems that
> > a function like you require needs to be used on the datapath, while this API
> > is not planned to be high-performance. I think that it might be better to
> > add an equivalent function to the existing RX descriptor querying function.
> > 
> > /Bruce
> > 
> > > > -----Original Message-----
> > > > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Konstantin
> > Ananyev
> > > > Sent: Thursday, June 18, 2015 3:19 PM
> > > > To: dev@dpdk.org
> > > > Subject: [dpdk-dev] [PATCHv2 0/5] ethdev: add new API to retrieve RX/TX
> > > > queue information
> > > >
> > > > Add the ability for the upper layer to query RX/TX queue information.
> > > > Right now supported for:
> > > > ixgbe, i40e, e1000 PMDs.
> > > >
> > > > Konstantin Ananyev (5):
> > > >   ethdev: add new API to retrieve RX/TX queue information
> > > >   i40e: add support for eth_(rxq|txq)_info_get
> > > >   ixgbe: add support for eth_(rxq|txq)_info_get
> > > >   e1000: add support for eth_(rxq|txq)_info_get
> > > >   testpmd: add new command to display RX/TX queue information
> > > >
> > > >  app/test-pmd/cmdline.c           | 48 +++++++++++++++++++++++++
> > > >  app/test-pmd/config.c            | 67
> > > > ++++++++++++++++++++++++++++++++++
> > > >  app/test-pmd/testpmd.h           |  2 ++
> > > >  drivers/net/e1000/e1000_ethdev.h | 12 +++++++
> > > >  drivers/net/e1000/em_ethdev.c    |  2 ++
> > > >  drivers/net/e1000/em_rxtx.c      | 38 ++++++++++++++++++++
> > > >  drivers/net/e1000/igb_ethdev.c   |  4 +++
> > > >  drivers/net/e1000/igb_rxtx.c     | 36 +++++++++++++++++++
> > > >  drivers/net/i40e/i40e_ethdev.c   |  2 ++
> > > >  drivers/net/i40e/i40e_ethdev.h   |  5 +++
> > > >  drivers/net/i40e/i40e_rxtx.c     | 42 ++++++++++++++++++++++
> > > >  drivers/net/ixgbe/ixgbe_ethdev.c |  4 +++
> > > >  drivers/net/ixgbe/ixgbe_ethdev.h |  6 ++++
> > > >  drivers/net/ixgbe/ixgbe_rxtx.c   | 42 ++++++++++++++++++++++
> > > >  lib/librte_ether/rte_ethdev.c    | 54 ++++++++++++++++++++++++++++
> > > >  lib/librte_ether/rte_ethdev.h    | 77
> > > > +++++++++++++++++++++++++++++++++++++++-
> > > >  16 files changed, 440 insertions(+), 1 deletion(-)
> > > >
> > > > --
> > > > 1.8.5.3
> > >

  reply	other threads:[~2015-06-18 14:13 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-06-17 16:54 [dpdk-dev] [PATCH " Konstantin Ananyev
2015-06-17 16:54 ` [dpdk-dev] [PATCH 1/5] " Konstantin Ananyev
2015-06-18 13:18   ` [dpdk-dev] [PATCHv2 0/5] " Konstantin Ananyev
2015-06-18 13:18     ` [dpdk-dev] [PATCHv2 1/5] " Konstantin Ananyev
2015-07-20  0:12       ` Thomas Monjalon
2015-07-20  9:52         ` Ananyev, Konstantin
2015-06-18 13:18     ` [dpdk-dev] [PATCHv2 2/5] i40e: add support for eth_(rxq|txq)_info_get Konstantin Ananyev
2015-06-18 13:18     ` [dpdk-dev] [PATCHv2 3/5] ixgbe: " Konstantin Ananyev
2015-06-18 13:18     ` [dpdk-dev] [PATCHv2 4/5] e1000: " Konstantin Ananyev
2015-06-18 13:18     ` [dpdk-dev] [PATCHv2 5/5] testpmd: add new command to display RX/TX queue information Konstantin Ananyev
2015-06-18 13:30     ` [dpdk-dev] [PATCHv2 0/5] ethdev: add new API to retrieve " Walukiewicz, Miroslaw
2015-06-18 13:39       ` Bruce Richardson
2015-06-18 13:56         ` Walukiewicz, Miroslaw
2015-06-18 14:13           ` Bruce Richardson [this message]
2015-06-18 14:17       ` Ananyev, Konstantin
2015-06-18 14:37         ` Walukiewicz, Miroslaw
2015-06-18 13:58     ` Bruce Richardson
2015-06-19  3:18     ` Zhang, Helin
2015-06-23 12:35     ` David Harton (dharton)
2015-06-17 16:54 ` [dpdk-dev] [PATCH 2/5] i40e: add support for eth_(rx|tx)_qinfo_get Konstantin Ananyev
2015-06-17 16:54 ` [dpdk-dev] [PATCH 3/5] ixgbe: " Konstantin Ananyev
2015-06-17 16:54 ` [dpdk-dev] [PATCH 4/5] e1000: " Konstantin Ananyev
2015-06-17 16:54 ` [dpdk-dev] [PATCH 5/5] testpmd: add new command to display RX/TX queue information Konstantin Ananyev

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=20150618141303.GB5344@bricha3-MOBL3 \
    --to=bruce.richardson@intel.com \
    --cc=Miroslaw.Walukiewicz@intel.com \
    --cc=dev@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).