[ofa-general] Re: IPoIB path caching

[Michael S. Tsirkin]

> Quoting Or Gerlitz <ogerlitz at voltaire.com>:
> Subject: Re: [ofa-general] Re: IPoIB path caching
> 
> Roland Dreier wrote:
> >
> > > Do you agree that using cached IB L2 info where the net stack wants to
> > > renew its IPoIB L2 (which is IB L3 && L4) info is a bug?
> >
> >Yes, looks that way.
> >
> >Also your point that there's no reason for IPoIB to keep the path info
> >once it has created the AH makes sense to me.  I haven't had a chance
> >to look at the code but it seems we could kill off a lot of stuff by
> >just creating AHs immediately and then dumping the path record.
> 
> Indeed.
> 
> It does make sense to keep the path info for admin / debugging purposes, 
> eg printing them through debugfs etc, but no more.
> 
> In the context of the local sa, this seems to be another requirement 
> namely: provide the consumer with an API to specify if it is willing to 
> get from the ib_sa module a cached IB L2 info (path) or not.
> 
> As I said above, if the network stack decides to renew its IPoIB L2 
> info, the IB stack must provide it with non-cached IB L2 info

If what you have in mind is keeping local sa cache in sync
with IPoIB cache, wouldn't it be better to have an API to
invalidate a cache entry?

-- 
MST