[PATCH v2 2/3] mempool: include non-DPDK threads in statistics

[Mattias Rönnblom]

On 2022-10-31 12:26, Morten Brørup wrote:
> Offset the stats array index by one, and count non-DPDK threads at index
> zero.
> 
> This patch provides two benefits:
> * Non-DPDK threads are also included in the statistics.
> * A conditional in the fast path is removed. Static branch prediction was
>    correct, so the performance improvement is negligible.
> 
> v2:
> * New. No v1 of this patch in the series.
> 
> Suggested-by: Stephen Hemminger <stephen at networkplumber.org>
> Signed-off-by: Morten Brørup <mb at smartsharesystems.com>
> ---
>   lib/mempool/rte_mempool.c |  2 +-
>   lib/mempool/rte_mempool.h | 12 ++++++------
>   2 files changed, 7 insertions(+), 7 deletions(-)
> 
> diff --git a/lib/mempool/rte_mempool.c b/lib/mempool/rte_mempool.c
> index 62d1ce764e..e6208125e0 100644
> --- a/lib/mempool/rte_mempool.c
> +++ b/lib/mempool/rte_mempool.c
> @@ -1272,7 +1272,7 @@ rte_mempool_dump(FILE *f, struct rte_mempool *mp)
>   #ifdef RTE_LIBRTE_MEMPOOL_STATS
>   	rte_mempool_ops_get_info(mp, &info);
>   	memset(&sum, 0, sizeof(sum));
> -	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
> +	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE + 1; lcore_id++) {
>   		sum.put_bulk += mp->stats[lcore_id].put_bulk;
>   		sum.put_objs += mp->stats[lcore_id].put_objs;
>   		sum.put_common_pool_bulk += mp->stats[lcore_id].put_common_pool_bulk;
> diff --git a/lib/mempool/rte_mempool.h b/lib/mempool/rte_mempool.h
> index 9c4bf5549f..16e7e62e3c 100644
> --- a/lib/mempool/rte_mempool.h
> +++ b/lib/mempool/rte_mempool.h
> @@ -238,8 +238,11 @@ struct rte_mempool {
>   	struct rte_mempool_memhdr_list mem_list; /**< List of memory chunks */
>   
>   #ifdef RTE_LIBRTE_MEMPOOL_STATS
> -	/** Per-lcore statistics. */
> -	struct rte_mempool_debug_stats stats[RTE_MAX_LCORE];
> +	/** Per-lcore statistics.
> +	 *
> +	 * Offset by one, to include non-DPDK threads.
> +	 */
> +	struct rte_mempool_debug_stats stats[RTE_MAX_LCORE + 1];
>   #endif
>   }  __rte_cache_aligned;
>   
> @@ -304,10 +307,7 @@ struct rte_mempool {
>    */
>   #ifdef RTE_LIBRTE_MEMPOOL_STATS
>   #define RTE_MEMPOOL_STAT_ADD(mp, name, n) do {                  \
> -		unsigned __lcore_id = rte_lcore_id();           \
> -		if (__lcore_id < RTE_MAX_LCORE) {               \
> -			mp->stats[__lcore_id].name += n;        \
> -		}                                               \
> +		(mp)->stats[rte_lcore_id() + 1].name += n;      \

This relies on LCORE_ID_ANY being UINT32_MAX, and a wrap to 0, for an 
unregistered non-EAL thread? Might be worth a comment, or better a 
rewrite with an explicit LCORE_ID_ANY comparison.

You anyways need a conditional. An atomic add must be used in the 
unregistered EAL thread case.

>   	} while (0)
>   #else
>   #define RTE_MEMPOOL_STAT_ADD(mp, name, n) do {} while (0)