[ofa-general] Re: IPoIB path caching

[Or Gerlitz]

Jason Gunthorpe wrote:
> On Sun, Jul 29, 2007 at 11:32:27AM +0300, Or Gerlitz wrote:
>> Jason Gunthorpe wrote:

>>> The existing trap monitoring in Sean's module covers about 90% of the
>>> cases in IB when you need to invalidate a PR, the last 10% will need
>>> something new :(

>> Let it be. Do you think the last 10% should not prevent the local sa 
>> merge to the upstream code?

> Only that the design philosophy should accommodate an eventual solution
> to this remaining problem. Mainly, as I've said, I'd like to see more
> stuff in userspace and a simple well defined kernel component.

> What about you? Your arguments about linking arp lifetime to PR cache
> lifetime are trying to address this very same 10%.

Indeed. The argument I was trying to make is that arp cache invalidation 
  requires IPoIB PR cache invalidation, this handles 100% of the cases, 
including the 10% not covered by doing cache invalidation based only on 
  IB events such as port up / sm lid change / sm reregister / etc

So far, my approach has not accepted as is by Sean and you (Roland, 
Michael - would be nice to get your say here), I have to see what other 
design is possible here.

Or.