On Tue, Feb 21, 2017 at 03:17:40AM +0000, David Hunt wrote:
> Signed-off-by: David Hunt <david.h...@intel.com>
> ---
> lib/librte_distributor/rte_distributor_private.h | 61
> ++++++++++++++++++++++++
> 1 file changed, 61 insertions(+)
>
> diff --git a/lib/librte_distributor/rte_distributor_private.h
> b/lib/librte_distributor/rte_distributor_private.h
> index 2d85b9b..c8e0f98 100644
> --- a/lib/librte_distributor/rte_distributor_private.h
> +++ b/lib/librte_distributor/rte_distributor_private.h
> @@ -129,6 +129,67 @@ struct rte_distributor_v20 {
> struct rte_distributor_returned_pkts returns;
> };
>
> +/* All different signature compare functions */
> +enum rte_distributor_match_function {
> + RTE_DIST_MATCH_SCALAR = 0,
> + RTE_DIST_MATCH_VECTOR,
> + RTE_DIST_NUM_MATCH_FNS
> +};
> +
> +/**
> + * Buffer structure used to pass the pointer data between cores. This is
> cache
> + * line aligned, but to improve performance and prevent adjacent cache-line
> + * prefetches of buffers for other workers, e.g. when worker 1's buffer is on
> + * the next cache line to worker 0, we pad this out to two cache lines.
> + * We can pass up to 8 mbufs at a time in one cacheline.
> + * There is a separate cacheline for returns in the burst API.
> + */
> +struct rte_distributor_buffer {
> + volatile int64_t bufptr64[RTE_DIST_BURST_SIZE]
> + __rte_cache_aligned; /* <= outgoing to worker */
> +
> + int64_t pad1 __rte_cache_aligned; /* <= one cache line */
> +
> + volatile int64_t retptr64[RTE_DIST_BURST_SIZE]
> + __rte_cache_aligned; /* <= incoming from worker */
> +
> + int64_t pad2 __rte_cache_aligned; /* <= one cache line */
> +
> + int count __rte_cache_aligned; /* <= number of current mbufs */
> +};
Rather than adding padding elements here, would it be better and clearer
just to align the values to 128B (or more strictly CACHE_LINE_SZ * 2)?
/Bruce
