On 5/5/2016 10:28 PM, Stephen Hemminger wrote:
> Overall, this is ok, but why can't it be the default?
Backward compatibility would probably be the main reason, to have the
least impact when recompiling.
> Lots of little things should be cleaned up
I've submitted a v2, and addressed all your
This is a mempool handler that is useful for pipelining apps, where
the mempool cache doesn't really work - example, where we have one
core doing rx (and alloc), and another core doing Tx (and return). In
such a case, the mempool ring simply cycles through all the mbufs,
resulting in a LLC miss on
Overall, this is ok, but why can't it be the default?
Lots of little things should be cleaned up
> +struct rte_mempool_common_stack
> +{
> + /* Spinlock to protect access */
> + rte_spinlock_t sl;
> +
> + uint32_t size;
> + uint32_t len;
> + void *objs[];
> +
> +#ifdef
3 matches
Mail list logo