linux-rdma.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jason Gunthorpe <jgunthorpe-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
To: Erez Shitrit <erezsh-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org>
Cc: Leon Romanovsky <leonro-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>,
	Erez Shitrit <erezsh-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>,
	Doug Ledford <dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
	"linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org"
	<linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	valex-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org
Subject: Re: [RFC v2 for accelerated IPoIB 00/6] Enhanced mode for IPoIB driver
Date: Sun, 26 Mar 2017 14:42:37 -0600	[thread overview]
Message-ID: <20170326204237.GB3113@obsidianresearch.com> (raw)
In-Reply-To: <CAAk-MO_7LVUQS_8+h9shFEXkjT6NHkzXeYRH+_8Wcjr0P+dHAw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>

On Sun, Mar 26, 2017 at 07:17:13PM +0300, Erez Shitrit wrote:

> > be computed once instead of computed for every split packet. The
> > downside here is that it may be very complicated to store a kref in a
> > skb pseudo header and properly unref it at all the right times..
> 
> It is an optimization, and still we need to get the ah even at the
> middle of GSO, for each skb, or to keep it somewhere, also will need
> to keep more space in the skb, more processing.

GSO is done in a way where the pseudo header is retained but not
recomputed for every fragment, much like for ethernet.

Does mlx5 even need a 'AH'? Maybe allowing the driver to provide some
bytes in the pseudo header that match the HW SQE is an overall more
efficient direction.

> > The other is to factor out the AH extraction from ipoib_start_xmit
> > into a helper function and have all the rn drivers call it to get the
> > AH.
> 
> We will pay with performance degradation for each send.

Eh? Having ndo->ipoib->driver or ndo->driver->ipoib as a call chain
doesn't really matter one bit.

Jason
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

  parent reply	other threads:[~2017-03-26 20:42 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-03-20 19:08 [RFC v2 for accelerated IPoIB 00/6] Enhanced mode for IPoIB driver Erez Shitrit
     [not found] ` <1490036908-12528-1-git-send-email-erezsh-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
2017-03-20 19:08   ` [RFC v2 for accelerated IPoIB 01/6] IB/ipoib: Separate control and data related initializations Erez Shitrit
2017-03-20 19:08   ` [RFC v2 for accelerated IPoIB 02/6] IB/ipoib: separate control from HW operation on ipoib_open/stop ndo Erez Shitrit
2017-03-20 19:08   ` [RFC v2 for accelerated IPoIB 03/6] IB/ipoib: Rename qpn to dqpn in ipoib_send and post_send functions Erez Shitrit
2017-03-20 19:08   ` [RFC v2 for accelerated IPoIB 04/6] IB/verb: Add ipoib_options struct and API Erez Shitrit
2017-03-20 19:08   ` [RFC v2 for accelerated IPoIB 05/6] IB/ipoib: Support ipoib acceleration options callbacks Erez Shitrit
2017-03-20 19:08   ` [RFC v2 for accelerated IPoIB 6/6] mlx5_ib: skeleton for mlx5_ib to support ipoib_ops Erez Shitrit
2017-03-20 20:59   ` [RFC v2 for accelerated IPoIB 00/6] Enhanced mode for IPoIB driver Jason Gunthorpe
     [not found]     ` <20170320205927.GA17225-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2017-03-21 11:49       ` Leon Romanovsky
     [not found]         ` <20170321114955.GB2079-U/DQcQFIOTAAJjI8aNfphQ@public.gmane.org>
2017-03-21 16:15           ` Jason Gunthorpe
     [not found]             ` <20170321161530.GB22216-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2017-03-21 16:49               ` Leon Romanovsky
     [not found]                 ` <20170321164952.GE2079-U/DQcQFIOTAAJjI8aNfphQ@public.gmane.org>
2017-03-22 11:18                   ` Erez Shitrit
     [not found]                     ` <CAAk-MO_KEV9MA5Dcaz8SZagMeC4hQX456Cu8To-YRBNMeNu3pg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2017-03-22 16:52                       ` Jason Gunthorpe
     [not found]                         ` <20170322165238.GA26589-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2017-03-26 16:17                           ` Erez Shitrit
     [not found]                             ` <CAAk-MO_7LVUQS_8+h9shFEXkjT6NHkzXeYRH+_8Wcjr0P+dHAw-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2017-03-26 20:42                               ` Jason Gunthorpe [this message]
     [not found]                                 ` <20170326204237.GB3113-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2017-03-28 11:40                                   ` Erez Shitrit
     [not found]                                     ` <CAAk-MO8Z7wKGFU5empgHGpN73cGMkKMi+ijnTHpfXBD5oZ+cGQ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2017-03-29 13:46                                       ` Jason Gunthorpe

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=20170326204237.GB3113@obsidianresearch.com \
    --to=jgunthorpe-epgobjl8dl3ta4ec/59zmfatqe2ktcn/@public.gmane.org \
    --cc=dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
    --cc=erezsh-LDSdmyG8hGV8YrgS2mwiifqBs+8SCbDb@public.gmane.org \
    --cc=erezsh-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org \
    --cc=leonro-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org \
    --cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=valex-VPRAkNaXOzVWk0Htik3J/w@public.gmane.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).