From: Jason Gunthorpe <jgg@nvidia.com>
To: Jinpu Wang <jinpu.wang@cloud.ionos.com>
Cc: <linux-rdma@vger.kernel.org>,
Bart Van Assche <bvanassche@acm.org>,
Leon Romanovsky <leon@kernel.org>,
Doug Ledford <dledford@redhat.com>,
Gioh Kim <gi-oh.kim@cloud.ionos.com>
Subject: Re: [PATCH] RDMA/ipoib: distribute cq completion vector better
Date: Wed, 28 Oct 2020 10:59:29 -0300 [thread overview]
Message-ID: <20201028135929.GX1523783@nvidia.com> (raw)
In-Reply-To: <CAMGffE=9j+yWXhWj+X2XVYm018GBwOw4ZZxQ5GYs-rwrW4q3Kg@mail.gmail.com>
On Wed, Oct 28, 2020 at 02:57:57PM +0100, Jinpu Wang wrote:
> On Wed, Oct 28, 2020 at 2:53 PM Jason Gunthorpe <jgg@nvidia.com> wrote:
> >
> > On Wed, Oct 28, 2020 at 02:48:01PM +0100, Jinpu Wang wrote:
> > > On Wed, Oct 28, 2020 at 2:44 PM Jason Gunthorpe <jgg@nvidia.com> wrote:
> > > >
> > > > On Tue, Oct 13, 2020 at 09:43:42AM +0200, Jack Wang wrote:
> > > > > Currently ipoib choose cq completion vector based on port number,
> > > > > when HCA only have one port, all the interface recv queue completion
> > > > > are bind to cq completion vector 0.
> > > > >
> > > > > To better distribute the load, use same method as __ib_alloc_cq_any
> > > > > to choose completion vector, with the change, each interface now use
> > > > > different completion vectors.
> > > > >
> > > > > Signed-off-by: Jack Wang <jinpu.wang@cloud.ionos.com>
> > > > > Reviewed-by: Gioh Kim <gi-oh.kim@cloud.ionos.com>
> > > > > drivers/infiniband/ulp/ipoib/ipoib_verbs.c | 4 ++--
> > > > > 1 file changed, 2 insertions(+), 2 deletions(-)
> > > >
> > > > If you care about IPoIB performance you should be using the
> > > > accelerated IPoIB stuff, the drivers implementing that all provide
> > > > much better handling of CQ affinity.
> > > >
> > > > What scenario does this patch make a difference?
> > >
> > > AFAIK the enhance mode is only for datagram mode, we are using connected mode.
> >
> > And you are using child interfaces or multiple cards?
> we are using multiple child interfaces on Connect x5 HCA
> (MCX556A-ECAT)
Ok.. Do you think it would be better to change IPoIB to use the new
shared CQ pool API?
Jason
next prev parent reply other threads:[~2020-10-29 0:22 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-13 7:43 [PATCH] RDMA/ipoib: distribute cq completion vector better Jack Wang
2020-10-28 13:44 ` Jason Gunthorpe
2020-10-28 13:48 ` Jinpu Wang
2020-10-28 13:53 ` Jason Gunthorpe
2020-10-28 13:57 ` Jinpu Wang
2020-10-28 13:59 ` Jason Gunthorpe [this message]
2020-10-28 14:08 ` Jinpu Wang
2020-11-20 20:28 ` 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=20201028135929.GX1523783@nvidia.com \
--to=jgg@nvidia.com \
--cc=bvanassche@acm.org \
--cc=dledford@redhat.com \
--cc=gi-oh.kim@cloud.ionos.com \
--cc=jinpu.wang@cloud.ionos.com \
--cc=leon@kernel.org \
--cc=linux-rdma@vger.kernel.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).