[dpdk-dev] [PATCH v4 2/2] lib/mempool: distinguish debug counters from cache and pool

[Olivier Matz]

Hi Dharmik,

Few comments below.

On Thu, Apr 22, 2021 at 08:29:38PM -0500, Dharmik Thakkar wrote:
> From: Joyce Kong <joyce.kong at arm.com>
> 
> If cache is enabled, objects will be retrieved/put from/to cache,
> subsequently from/to the common pool. Now the debug stats calculate
> the objects retrieved/put from/to cache and pool together, it is
> better to distinguish them.
> 
> Signed-off-by: Joyce Kong <joyce.kong at arm.com>
> Signed-off-by: Dharmik Thakkar <dharmik.thakkar at arm.com>
> Reviewed-by: Ruifeng Wang <ruifeng.wang at arm.com>
> Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli at arm.com>
> ---
>  lib/mempool/rte_mempool.c | 16 +++++++++++++++
>  lib/mempool/rte_mempool.h | 43 ++++++++++++++++++++++++++-------------
>  2 files changed, 45 insertions(+), 14 deletions(-)
> 
> diff --git a/lib/mempool/rte_mempool.c b/lib/mempool/rte_mempool.c
> index afb1239c8d48..e9343c2a7f6b 100644
> --- a/lib/mempool/rte_mempool.c
> +++ b/lib/mempool/rte_mempool.c
> @@ -1244,6 +1244,14 @@ rte_mempool_dump(FILE *f, struct rte_mempool *mp)
>  	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; 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;
> +		sum.put_common_pool_objs +=
> +			mp->stats[lcore_id].put_common_pool_objs;
> +		sum.get_common_pool_bulk +=
> +			mp->stats[lcore_id].get_common_pool_bulk;
> +		sum.get_common_pool_objs +=
> +			mp->stats[lcore_id].get_common_pool_objs;
>  		sum.get_success_bulk += mp->stats[lcore_id].get_success_bulk;
>  		sum.get_success_objs += mp->stats[lcore_id].get_success_objs;
>  		sum.get_fail_bulk += mp->stats[lcore_id].get_fail_bulk;
> @@ -1254,6 +1262,14 @@ rte_mempool_dump(FILE *f, struct rte_mempool *mp)
>  	fprintf(f, "  stats:\n");
>  	fprintf(f, "    put_bulk=%"PRIu64"\n", sum.put_bulk);
>  	fprintf(f, "    put_objs=%"PRIu64"\n", sum.put_objs);
> +	fprintf(f, "    put_common_pool_bulk=%"PRIu64"\n",
> +						sum.put_common_pool_bulk);
> +	fprintf(f, "    put_common_pool_objs=%"PRIu64"\n",
> +						sum.put_common_pool_objs);
> +	fprintf(f, "    get_common_pool_bulk=%"PRIu64"\n",
> +						sum.get_common_pool_bulk);
> +	fprintf(f, "    get_common_pool_objs=%"PRIu64"\n",
> +						sum.get_common_pool_objs);
>  	fprintf(f, "    get_success_bulk=%"PRIu64"\n", sum.get_success_bulk);
>  	fprintf(f, "    get_success_objs=%"PRIu64"\n", sum.get_success_objs);
>  	fprintf(f, "    get_fail_bulk=%"PRIu64"\n", sum.get_fail_bulk);
> diff --git a/lib/mempool/rte_mempool.h b/lib/mempool/rte_mempool.h
> index 848a19226149..4343b287dc4e 100644
> --- a/lib/mempool/rte_mempool.h
> +++ b/lib/mempool/rte_mempool.h
> @@ -64,14 +64,21 @@ extern "C" {
>  #ifdef RTE_LIBRTE_MEMPOOL_DEBUG
>  /**
>   * A structure that stores the mempool statistics (per-lcore).
> + * Note: Cache stats (put_cache_bulk/objs, get_cache_bulk/objs) are not
> + * captured since they can be calculated from other stats.
> + * For example: put_cache_objs = put_objs - put_common_pool_objs.
>   */
>  struct rte_mempool_debug_stats {
> -	uint64_t put_bulk;         /**< Number of puts. */
> -	uint64_t put_objs;         /**< Number of objects successfully put. */
> -	uint64_t get_success_bulk; /**< Successful allocation number. */
> -	uint64_t get_success_objs; /**< Objects successfully allocated. */
> -	uint64_t get_fail_bulk;    /**< Failed allocation number. */
> -	uint64_t get_fail_objs;    /**< Objects that failed to be allocated. */
> +	uint64_t put_bulk;		  /**< Number of puts. */
> +	uint64_t put_objs;		  /**< Number of objects successfully put. */
> +	uint64_t put_common_pool_bulk;	  /**< Number of bulks enqueued in common pool. */
> +	uint64_t put_common_pool_objs;	  /**< Number of objects enqueued in common pool. */
> +	uint64_t get_common_pool_bulk;    /**< Number of bulks dequeued from common pool. */
> +	uint64_t get_common_pool_objs;	  /**< Number of objects dequeued from common pool. */
> +	uint64_t get_success_bulk;	  /**< Successful allocation number. */
> +	uint64_t get_success_objs;	  /**< Objects successfully allocated. */
> +	uint64_t get_fail_bulk;		  /**< Failed allocation number. */
> +	uint64_t get_fail_objs;		  /**< Objects that failed to be allocated. */
>  	/** Successful allocation number of contiguous blocks. */
>  	uint64_t get_success_blks;
>  	/** Failed allocation number of contiguous blocks. */
> @@ -699,10 +706,18 @@ rte_mempool_ops_dequeue_bulk(struct rte_mempool *mp,
>  		void **obj_table, unsigned n)
>  {
>  	struct rte_mempool_ops *ops;
> +	int ret;
>  
>  	rte_mempool_trace_ops_dequeue_bulk(mp, obj_table, n);
>  	ops = rte_mempool_get_ops(mp->ops_index);
> -	return ops->dequeue(mp, obj_table, n);
> +	ret = ops->dequeue(mp, obj_table, n);
> +	if (ret == 0) {
> +		__MEMPOOL_STAT_ADD(mp, get_common_pool_bulk, 1);
> +		__MEMPOOL_STAT_ADD(mp, get_common_pool_objs, n);
> +		__MEMPOOL_STAT_ADD(mp, get_success_bulk, 1);
> +		__MEMPOOL_STAT_ADD(mp, get_success_objs, n);
> +	}
> +	return ret;
>  }

I think we should only have the common_pool stats here, for 2 reasons:

- more consistent with put()
- in case we are called by __mempool_generic_get() for a "backfill"
  operation, the number of successes will not be incremented by the
  correct value (the "req" variable is != n)

>  
>  /**
> @@ -749,6 +764,8 @@ rte_mempool_ops_enqueue_bulk(struct rte_mempool *mp, void * const *obj_table,
>  {
>  	struct rte_mempool_ops *ops;
>  
> +	__MEMPOOL_STAT_ADD(mp, put_common_pool_bulk, 1);
> +	__MEMPOOL_STAT_ADD(mp, put_common_pool_objs, n);
>  	rte_mempool_trace_ops_enqueue_bulk(mp, obj_table, n);
>  	ops = rte_mempool_get_ops(mp->ops_index);
>  	return ops->enqueue(mp, obj_table, n);
> @@ -1297,9 +1314,10 @@ __mempool_generic_put(struct rte_mempool *mp, void * const *obj_table,
>  
>  	/* Add elements back into the cache */
>  	rte_memcpy(&cache_objs[0], obj_table, sizeof(void *) * n);
> -
>  	cache->len += n;
>  
> +	__MEMPOOL_STAT_ADD(mp, put_cache_bulk, 1);
> +

This one was forgotten, there is a compilation error:

In file included from ../lib/mempool/rte_mempool_ops_default.c:7:
../lib/mempool/rte_mempool.h: In function ‘__mempool_generic_put’:
../lib/mempool/rte_mempool.h:1319:25: error: ‘struct rte_mempool_debug_stats’ has no member named ‘put_cache_bulk’; did you mean ‘put_bulk’?
  __MEMPOOL_STAT_ADD(mp, put_cache_bulk, 1);
                         ^~~~~~~~~~~~~~
../lib/mempool/rte_mempool.h:283:26: note: in definition of macro ‘__MEMPOOL_STAT_ADD’
    mp->stats[__lcore_id].name += n; \
                          ^~~~



>  	if (cache->len >= cache->flushthresh) {
>  		rte_mempool_ops_enqueue_bulk(mp, &cache->objs[cache->size],
>  				cache->len - cache->size);
> @@ -1430,6 +1448,9 @@ __mempool_generic_get(struct rte_mempool *mp, void **obj_table,
>  		}
>  
>  		cache->len += req;
> +	} else {
> +		__MEMPOOL_STAT_ADD(mp, get_success_bulk, 1);
> +		__MEMPOOL_STAT_ADD(mp, get_success_objs, n);
>  	}
>  
>  	/* Now fill in the response ... */
> @@ -1438,9 +1459,6 @@ __mempool_generic_get(struct rte_mempool *mp, void **obj_table,
>  
>  	cache->len -= n;
>  
> -	__MEMPOOL_STAT_ADD(mp, get_success_bulk, 1);
> -	__MEMPOOL_STAT_ADD(mp, get_success_objs, n);
> -
>  	return 0;
>  
>  ring_dequeue:
> @@ -1451,9 +1469,6 @@ __mempool_generic_get(struct rte_mempool *mp, void **obj_table,
>  	if (ret < 0) {
>  		__MEMPOOL_STAT_ADD(mp, get_fail_bulk, 1);
>  		__MEMPOOL_STAT_ADD(mp, get_fail_objs, n);
> -	} else {
> -		__MEMPOOL_STAT_ADD(mp, get_success_bulk, 1);
> -		__MEMPOOL_STAT_ADD(mp, get_success_objs, n);
>  	}
>  
>  	return ret;
> -- 
> 2.17.1
>