From: Jason Gunthorpe <jgg@nvidia.com>
To: Haakon Bugge <haakon.bugge@oracle.com>
Cc: "dledford@redhat.com" <dledford@redhat.com>,
"leon@kernel.org" <leon@kernel.org>,
"valentinef@mellanox.com" <valentinef@mellanox.com>,
"gustavoars@kernel.org" <gustavoars@kernel.org>,
OFED mailing list <linux-rdma@vger.kernel.org>,
Manjunath Patil <manjunath.b.patil@oracle.com>
Subject: Re: [PATCH] IB/ipoib: improve latency in ipoib/cm connection formation
Date: Tue, 26 Jan 2021 20:16:42 -0400 [thread overview]
Message-ID: <20210127001642.GJ4147@nvidia.com> (raw)
In-Reply-To: <6F3F22D0-2E85-4505-9179-2D2699EA2E2E@oracle.com>
On Tue, Jan 26, 2021 at 08:28:18PM +0000, Haakon Bugge wrote:
> >>> @@ -1122,7 +1123,8 @@ static int ipoib_cm_modify_tx_init(struct
> >> net_device *dev,
> >>> struct ipoib_dev_priv *priv = ipoib_priv(dev);
> >>> struct ib_qp_attr qp_attr;
> >>> int qp_attr_mask, ret;
> >>> - ret = ib_find_pkey(priv->ca, priv->port, priv->pkey,
> >> &qp_attr.pkey_index);
> >>> + ret = ib_find_cached_pkey(priv->ca, priv->port, priv->pkey,
> >>> + &qp_attr.pkey_index);
> >>
> >> ipoib interfaces are locked to a single pkey, you should be able to get the
> >> pkey index that was determined at link up time and use it here instead of
> >> searching anything
>
> Isn't possible to:
>
> # ip link add DEVICE name NAME type ipoib [ pkey PKEY ]
>
> ?
Yes, and each new netdev that spawns has a fixed pkey that doesn't
change for the life of the netdev
Jason
prev parent reply other threads:[~2021-01-27 4:22 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-21 17:50 [PATCH] IB/ipoib: improve latency in ipoib/cm connection formation Manjunath Patil
2021-01-21 18:16 ` Jason Gunthorpe
2021-01-25 18:49 ` Manjunath Patil
2021-01-26 20:01 ` Haakon Bugge
2021-01-26 20:28 ` Haakon Bugge
2021-01-27 0:16 ` Jason Gunthorpe [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=20210127001642.GJ4147@nvidia.com \
--to=jgg@nvidia.com \
--cc=dledford@redhat.com \
--cc=gustavoars@kernel.org \
--cc=haakon.bugge@oracle.com \
--cc=leon@kernel.org \
--cc=linux-rdma@vger.kernel.org \
--cc=manjunath.b.patil@oracle.com \
--cc=valentinef@mellanox.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).