[openib-general] [PATCH 0/4] SA path record caching

[Sean Hefty]

Or Gerlitz wrote:
> Why not having a failed lookup as the --only-- trigger to update the 
> cache? so the cache contains only paths that were demanded by some 
> consumer. What is implementation you were considering, is it an SA 
> replica having all those paths whose sgid is the local node gid?

I view MPI as one of the primary reasons for having a cache.  The cache is 
updated using an SA GET_TABLE request, which is more efficient than sending 
separate SA GET requests for each path record.  Waiting for a failed lookup to 
create the initial cache would delay the startup time for apps wanting 
all-to-all connection establishment.  In this case, we also get the side effect 
that the SA receives GET_TABLE requests from every node at roughly the same time.

Your assumption is correct.  The implementation will contain copies of all path 
records whose SGID is a local node GID.  (Currently it contains only a single 
path record per SGID/DGID, but that will be expanded.)

- Sean