All of lore.kernel.org
 help / color / mirror / Atom feed
From: Leon Romanovsky <leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
To: Jason Gunthorpe
	<jgunthorpe-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>,
	Moni Shoua <monis-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Cc: Doug Ledford <dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
	linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	yonatanc <yonatanc-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Subject: Re: [PATCH rdma-next 2/2] IB/rxe: Cache dst in QP instead of getting it for each send
Date: Thu, 20 Apr 2017 21:43:48 +0300	[thread overview]
Message-ID: <20170420184348.GT14088@mtr-leonro.local> (raw)
In-Reply-To: <20170420180114.GA6763-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>

[-- Attachment #1: Type: text/plain, Size: 888 bytes --]

On Thu, Apr 20, 2017 at 12:01:14PM -0600, Jason Gunthorpe wrote:
> On Thu, Apr 20, 2017 at 08:55:56PM +0300, Leon Romanovsky wrote:
> > From: yonatanc <yonatanc-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
> >
> > In RC QP there is no need to resolve the outgoing interface
> > for each packet, as this does not change during QP life cycle.
>
> At first blush that seems wonky, shouldn't a QP act like a TCP socket
> and be able to migrate around when things are reconfigured?

I didn't find any support for it in the code. If I don't miss anything,
the RXE will shutdown QP and create it again.

Moni, am I right?

>
> IIRC there is some kind of dst cache scheme you should use instead?

It depends on the answer to the previous question. Let's assume that I'm wrong,
so yes, dst_set_expires will be the way to go. However the code assumes
that RC QP doesn't reconfigure.

Thanks

>
> Jason

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

  parent reply	other threads:[~2017-04-20 18:43 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-04-20 17:55 [PATCH rdma-next 1/2] IB/rxe: Offload CRC calculation when possible Leon Romanovsky
     [not found] ` <20170420175556.8573-1-leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
2017-04-20 17:55   ` [PATCH rdma-next 2/2] IB/rxe: Cache dst in QP instead of getting it for each send Leon Romanovsky
     [not found]     ` <20170420175556.8573-2-leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
2017-04-20 18:01       ` Jason Gunthorpe
     [not found]         ` <20170420180114.GA6763-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
2017-04-20 18:43           ` Leon Romanovsky [this message]
2017-04-23  7:00           ` Moni Shoua
2017-04-20 19:28       ` Steve Wise
2017-04-24 16:19   ` [PATCH rdma-next 1/2] IB/rxe: Offload CRC calculation when possible Doug Ledford

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=20170420184348.GT14088@mtr-leonro.local \
    --to=leon-dgejt+ai2ygdnm+yrofe0a@public.gmane.org \
    --cc=dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
    --cc=jgunthorpe-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org \
    --cc=linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
    --cc=monis-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org \
    --cc=yonatanc-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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.