[Ofa_boardplus] Logo Program Discussion

Fri Sep 1 07:51:39 PDT 2017

Christoph Lameter wrote,

>Which companies are participating in the IWG? It seems that Mellanox is at this point the overwhelming provider of most of the InfiniBand technology with just minor niches >occupied by others. Our own experience with trying to use technology from Qlogic on a single system (2011) failed miserably. Intel is moving to Omnipath. Others simply focus on >Ethernet to have a vendor neutral shared standard.

>It seems to us therefore (Jump Trading) that there is a trend for interconnect technology to become vendor specific whereas the APIs to access the interconnect (RDMA subsystem >in the kernel) provide a common way of using these fabrics by essentially providing a hardware abstraction layer for fabrics in the Linux Kernel.

>Given this I would like to see a list of participants in the IWG and if its is as dominated as I think it is by Mellanox then we should slowly shut down the program and focus on the >software layer while continuing to provide a forum for the exchange of innovative ideas about fabrics.

Since this discussion has moved to a new thread… Adding my comment here too…

There are actually a number of new RDMA devices coming on the market recently, such as the new Cavium and Broadcom Roce adapters and the new Intel iWarp NIC that is integrated into the chipset of the recently released Xeon (skylake) platform. I know that Intel is still interested in interop testing between the new i40 NIC and the Chelsio iWarp NICs.

I believe that Cavium has also been participating in various debug events. Not sure about Broadcom. Check with Paul Bowden and/or Rupert Dance. They would have the details on who is most active in the events.

From: Ofa_boardplus [mailto:ofa_boardplus-bounces at lists.openfabrics.org] On Behalf Of Jim Ryan
Sent: Thursday, August 31, 2017 8:48 PM
To: Jason Gunthorpe <jgunthorpe at obsidianresearch.com>
Cc: ofa_boardplus at lists.openfabrics.org, <ofa_boardplus at lists.openfabrics.org>
Subject: Re: [Ofa_boardplus] Logo Program Discussion

Jason, because of my idiot gmail  system, I have to copy/paste your comments below. I apologize for the redundancy this will likely present:
> IBTA. We view interop as a program of value to participants who make the biz
> decision to fund it.

> actual components are, AFAIK, left behind after testing. I have requested
> another call for donations but, for whatever reason, that hasn't happened.

Ignoring donations, a logo program that pretty much exclusively
certifies discontinued equipment has deeply malfunctioned.

>>>[JR] if that were the case, I'd have to agree, and I hope it's not. My best info is there are new devices coming in for testing. If that's not the case, I have no defense or further arguments.

> I *do* have to ask you to not use terms along the lines of "membership
> funding"; there is no such thing.

When I use that term, I am refering to the direct funding from the
membership of the OFA to the OFA treasury in the form of general dues,
IWG particpation fees, special contributions, and sponsorship
opportunities. There certainly is such a thing :)

>>>[JR] I'm sorry, but I continue to disagree. OFA members make a specific decision to pay dues and they make a separate decision as to whether to pay logo/interop participation fees. I'm asking you to respect that and I'm perplexed as to why you want to remove that option from them

> Re the quality of testing, that's a challenge for the IWG. One of, if not *the*
> most important thing they're responsible for is quality of testing. If
> something is broken there, I'm not aware of it, and we need to come to
> understand this.

As far as granting logos to the submitted devices, it could be
fine.

As far as testing the OFED software and the open source stack around
it, it is vastly inadequate. I can say that confidently just from the
list of hardware being tested: It simply does not cover a very useful
(to end users) portion of the stack any longer.

So, again, I would like to see the OFA refocus this funding on better
testing. Scrap the logo program and ask the participating membership
to redirect the funding to direct software stack testing. Test the
software stack. Figure out how to directly buy modern hardware if
donations are not forthcoming. I hope this is the shape of the
discussion that is ongoing with the distros.

IMHO, this is how to get end-user orgs like RH, suse, LANL, etc to
particpate financially in the testing process.

>>>[JR] I'm asking you to not lose this train of thought. I think this could be really useful, w/o prejudging the outcome of the discussion. Plz continue

> Finally, I realized I failed to respond to a point you made earlier. It's kinda
> delicate, but important. The OFA is specifically not "chartered" to develop
> specs and the IBTA and others are. There are IP provisions that need to exist
> if this is part of our mission or not. I can give you boring details if you
> want to hear more.

Yes, as I said, I've argued this semantic point with Paul before ...

>>>[JR] yes, again, we've walked this thin line. We can certainly address this as part of our Bylaws review and that, of course, is the right way to address this issue. Please don't give up; this could be extremely important to us

Jim

I think this is something to fix in the new bylaws..

> The reason this is delicate is because the OFIWG has had to go right
> to the edge of what we can do, to use MAN pages to document expected
> API functionality. We have agreed this is short of a spec, but you
> get the point; it's a fine but important distinction.

.. because IP protections exist for a reason. Just because you call
the spec a MAN page, doesn't remove the need to be careful of IP
issues :)

Safeguarding against IP issues is an important role for an open source
foundation.
x

On Thu, Aug 31, 2017 at 7:13 PM, Jason Gunthorpe <jgunthorpe at obsidianresearch.com<mailto:jgunthorpe at obsidianresearch.com>> wrote:
I broke the thread and revised the subject so it is easier to
follow. Thanks for suggesting it Paul.

On Thu, Aug 31, 2017 at 05:28:04PM -0700, Jim Ryan wrote:
> Ok, I think I see your point. Your consciously blending membership dues with
> interop program participation to make a point. I don't want to argue that
> point, but I do want to be painfully clear about something. The approach we
> take is conscious and, for example, specifically contrary to, for example the

Yes, I at least, have always understood this is how IWG operates.

> IBTA. We view interop as a program of value to participants who make the biz
> decision to fund it.

> actual components are, AFAIK, left behind after testing. I have requested
> another call for donations but, for whatever reason, that hasn't happened.