[openib-general] [PATCH] RE: regression in ofed 1.2

[Michael S. Tsirkin]

> Quoting Sean Hefty <mshefty at ichips.intel.com>:
> Subject: Re: [openib-general] [PATCH] RE:  regression in ofed 1.2
> 
> > - Sean, please base your branches on specific -rc from linus
> >   (OFED 1.2 is now -rc7).
> 
> My branches should be in sync with rc6.

If you check, they are not. ofed 1 2 branch has an extra
commit on top of -rc6. But I figured it out already.

> so that they get completely rebuilt off of the latest kernel?

No need to do anything at this point.

> > - Now that we are entering feature freeze, we should not do full replaces anymore.
> >   So Sean, please post incremental patches, labeled ofed-1.2 clearly.
> 
> Additional patches will be posted to my ofed_1-2 branch, which you should be 
> able to pull.

First, please post patches on list as well.
We can then just take the patch from git or from mail and add it under fixes.

> Do you see a problem with this process?

Yes. I had to jump through some hoops to first get a patch I can put in OFED due
to the issue outlined above, and then get the diff I got to apply without
conflicts, since port randomization code conflicted with the QoS patches. All
solved now - just put your patch before QoS one - but these conflicts should be
be figured out by whoever submits patches.

> I don't understand why you would need to do a full replace.

We won't do a full replace, just add patches in fixes directory.

What I expect everyone to do however, to get patches put in OFED,
is to test that patches one posts work in OFED git tree, not just against
upstream based git trees.

This currently includes testing for build against older kernels on various
architectures (me and Vlad put a cross-build setup for this at staging,
it now has kernel.org kernels but we will be adding distro kernels)
and testing on at least one of the main supported enterprise distros (RHEL/SLES).

I simply can't take untested patches - I have nightly tests but no time to test
all ULPs before I apply.

-- 
MST