Linux RDMA and InfiniBand development
 help / color / mirror / Atom feed
From: "Håkon Bugge" <haakon.bugge@oracle.com>
To: Christopher Lameter <cl@linux.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>,
	Mark Haywood <mark.haywood@oracle.com>,
	OFED mailing list <linux-rdma@vger.kernel.org>
Subject: Re: Is there a working cache for path record and lids etc for librdmacm?
Date: Sun, 22 Nov 2020 16:50:24 +0100	[thread overview]
Message-ID: <801AE4A1-7AE8-4756-8F32-5F3BFD189E2B@oracle.com> (raw)
In-Reply-To: <alpine.DEB.2.22.394.2011221246230.261606@www.lameter.com>



> On 22 Nov 2020, at 13:49, Christopher Lameter <cl@linux.com> wrote:
> 
> On Fri, 20 Nov 2020, Håkon Bugge wrote:
>>> Oh great. I did not know. Will work with them to get things sorted out.
>> Inside Oracle, we're only using it for resolving IB routes. A cache for
>> address resolution already exists in the kernel. There is a config
>> option to disable address resolution from user-space
>> (acme_plus_kernel_only).
> 
> The app that we have runs in user space. Can it use the cache? Is the
> cache only in Mellanox OFED? I heard that it was removed.

An app in user space can use the ibacm cache. If you use the default configuration that comes with rdma-core, both address and route resolution will be from librdmacm directly to ibacm, i.e., no kernel involved. The ibacm options are by default installed in /etc/rdma/ibacm_opts.cfg

If you set acme_plus_kernel_only to one in said config file, you app will resolve the address using the kernel neighbour cache and the route resolution will go into the kernel and then "bounce" back  to user space and ibacm through NetLink.

I do not know if ibacm is present in Mellanox OFED, but it is easy to find out:

# rpm -q ibacm


> This is an an option while building ibacm?

Nop, runtime config option as depicted above.

> And yes we need it to resolve IB routes.

Then the above will work.

> Can you share a working config?

The default provided by rdma-core should work, possible requiring the option above.


Thxs, Håkon


  reply	other threads:[~2020-11-22 15:50 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-17  2:57 Is there a working cache for path record and lids etc for librdmacm? Christopher Lameter
2020-11-17  8:46 ` Jens Domke
2020-11-17 14:20   ` Christopher Lameter
2020-11-17 19:33 ` Jason Gunthorpe
2020-11-20 18:05   ` Christopher Lameter
2020-11-20 18:34     ` Håkon Bugge
2020-11-22 12:49       ` Christopher Lameter
2020-11-22 15:50         ` Håkon Bugge [this message]
2020-11-22 19:22           ` Christopher Lameter
2020-11-23 12:50             ` Christopher Lameter
2020-11-23 19:01               ` Håkon Bugge
2020-11-24 19:01                 ` Christopher Lameter
2020-11-25  8:10                   ` Honggang LI
2020-11-25 16:43                     ` Christopher Lameter
2020-11-27 14:52                       ` Håkon Bugge
2020-11-30  8:24                         ` Christopher Lameter
2020-12-04 11:17                           ` Håkon Bugge
2020-12-05 11:50                             ` Christoph Lameter
2020-12-07 10:28                             ` Christoph Lameter
2020-12-07 21:08                               ` Mark Haywood
2020-12-08  8:59                                 ` Christoph Lameter

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=801AE4A1-7AE8-4756-8F32-5F3BFD189E2B@oracle.com \
    --to=haakon.bugge@oracle.com \
    --cc=cl@linux.com \
    --cc=jgg@ziepe.ca \
    --cc=linux-rdma@vger.kernel.org \
    --cc=mark.haywood@oracle.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