Yes It will, and hence reduce the initial SA traffic generated on a big cluster...just imagin, the cluster is quite big and every node is trying to build its cache initially. It will create large burst of SA packets.
In general I agree with the notion of enhancing the cache to allow it to load locally from a file. But I'd really like to get a framework merged upstream first before trying to add in these sort of enhancements.
Initially loading of caches on a large fabric can be limited to a single GetTable PR query per node, and by enabling the caches across the fabric at different times, the single burst to the SA can be avoided.
Incomplete connectivity will be till first PR is requested for that destination, Because if its a cache miss, any how application is going to initiate a ib_sa_get_path_rec() and resolved PR will be added in cache for future reference.
ib_sa_get_path_rec() only returns a single path. If multiple paths exist, adding a single path to the cache may cause all applications to make use of that single path. Updating the cache on demand isn't as simple as it seems.
- Sean _______________________________________________ general mailing list [email protected] http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
