On 09/12/2016 04:42 PM, Steve Wise wrote:
One concern I have is that cxgb4 CQs require contiguous memory, So a scheme
like CQ pooling might cause resource problems on large core systems.
Hello Steve,
Had you already noticed the following code in the first patch of this
series? I think this code guarantees that never more than
dev->num_comp_vectors CQs are allocated at once:
nr_cqs = min_t(int, dev->num_comp_vectors, num_possible_cpus())
Bart.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html