[ofa-general] Re: IPoIB path caching

[Or Gerlitz]

Michael S. Tsirkin wrote:
>> Quoting Or Gerlitz <ogerlitz at voltaire.com>:

>> 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.

>> 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?

What I have in mind is that IPoIB must not use cached IB path info.

If the IB stack has path caching which is in the default flow of 
requesting a path record, it should provide an API (eg flag to the 
function through which one does path query) to request a non cached path.

The design I was thinking to suggest for IPoIB is to almost always use 
this API since this policy makes the implementation consistent with the 
decisions made by the network stack neighbour cache

Or.