[dpdk-dev] [PATCH v4 1/8] eventdev: introduce event vector capability

[Kinsella, Ray]

On 19/03/2021 20:57, pbhagavatula at marvell.com wrote:
> From: Pavan Nikhilesh <pbhagavatula at marvell.com>
> 
> Introduce rte_event_vector datastructure which is capable of holding
> multiple uintptr_t of the same flow thereby allowing applications
> to vectorize their pipeline and reducing the complexity of pipelining
> the events across multiple stages.
> This approach also reduces the scheduling overhead on a event device.
> 
> Add a event vector mempool create handler to create mempools based on
> the best mempool ops available on a given platform.
> 
> Signed-off-by: Pavan Nikhilesh <pbhagavatula at marvell.com>
> ---
>  doc/guides/prog_guide/eventdev.rst |  36 +++++++++-
>  lib/librte_eventdev/rte_eventdev.h | 112 ++++++++++++++++++++++++++++-
>  lib/librte_eventdev/version.map    |   3 +
>  3 files changed, 148 insertions(+), 3 deletions(-)
> 

[SNIP]

>  
> diff --git a/lib/librte_eventdev/rte_eventdev.h b/lib/librte_eventdev/rte_eventdev.h
> index ce1fc2ce0..5586a3f15 100644
> --- a/lib/librte_eventdev/rte_eventdev.h
> +++ b/lib/librte_eventdev/rte_eventdev.h
> @@ -212,8 +212,10 @@ extern "C" {
>  
>  #include <rte_common.h>
>  #include <rte_config.h>
> -#include <rte_memory.h>
>  #include <rte_errno.h>
> +#include <rte_mbuf_pool_ops.h>
> +#include <rte_memory.h>
> +#include <rte_mempool.h>
>  
>  #include "rte_eventdev_trace_fp.h"
>  
> @@ -913,6 +915,25 @@ rte_event_dev_stop_flush_callback_register(uint8_t dev_id,
>  int
>  rte_event_dev_close(uint8_t dev_id);
>  
> +/**
> + * Event vector structure.
> + */
> +struct rte_event_vector {
> +	uint64_t nb_elem : 16;
> +	/**< Number of elements in this event vector. */
> +	uint64_t rsvd : 48;
> +	uint64_t impl_opaque;
> +	union {
> +		struct rte_mbuf *mbufs[0];
> +		void *ptrs[0];
> +		uint64_t *u64s[0];
> +	} __rte_aligned(16);
> +	/**< Start of the vector array union. Depending upon the event type the
> +	 * vector array can be an array of mbufs or pointers or opaque u64
> +	 * values.
> +	 */
> +};
> +
>  /* Scheduler type definitions */
>  #define RTE_SCHED_TYPE_ORDERED          0
>  /**< Ordered scheduling
> @@ -986,6 +1007,21 @@ rte_event_dev_close(uint8_t dev_id);
>   */
>  #define RTE_EVENT_TYPE_ETH_RX_ADAPTER   0x4
>  /**< The event generated from event eth Rx adapter */
> +#define RTE_EVENT_TYPE_VECTOR           0x8
> +/**< Indicates that event is a vector.
> + * All vector event types should be an logical OR of EVENT_TYPE_VECTOR.
> + * This simplifies the pipeline design as we can split processing the events
> + * between vector events and normal event across event types.
> + * Example:
> + *	if (ev.event_type & RTE_EVENT_TYPE_VECTOR) {
> + *		// Classify and handle vector event.
> + *	} else {
> + *		// Classify and handle event.
> + *	}
> + */
> +#define RTE_EVENT_TYPE_CPU_VECTOR (RTE_EVENT_TYPE_VECTOR | RTE_EVENT_TYPE_CPU)
> +/**< The event vector generated from cpu for pipelining. */
> +
>  #define RTE_EVENT_TYPE_MAX              0x10
>  /**< Maximum number of event types */
>  
> @@ -1108,6 +1144,8 @@ struct rte_event {
>  		/**< Opaque event pointer */
>  		struct rte_mbuf *mbuf;
>  		/**< mbuf pointer if dequeued event is associated with mbuf */
> +		struct rte_event_vector *vec;
> +		/**< Event vector pointer. */
>  	};
>  };
>  
> @@ -2023,6 +2061,78 @@ rte_event_dev_xstats_reset(uint8_t dev_id,
>   */
>  int rte_event_dev_selftest(uint8_t dev_id);
>  
> +/**
> + * Get the memory required per event vector based on the number of elements per
> + * vector.
> + * This should be used to create the mempool that holds the event vectors.
> + *
> + * @param name
> + *   The name of the vector pool.
> + * @param n
> + *   The number of elements in the mbuf pool.
> + * @param cache_size
> + *   Size of the per-core object cache. See rte_mempool_create() for
> + *   details.
> + * @param nb_elem
> + *   The number of elements then a single event vector should be able to hold.
> + * @param socket_id
> + *   The socket identifier where the memory should be allocated. The
> + *   value can be *SOCKET_ID_ANY* if there is no NUMA constraint for the
> + *   reserved zone
> + *
> + * @return
> + *   The pointer to the newly allocated mempool, on success. NULL on error
> + *   with rte_errno set appropriately. Possible rte_errno values include:
> + *    - E_RTE_NO_CONFIG - function could not get pointer to rte_config structure
> + *    - E_RTE_SECONDARY - function was called from a secondary process instance
> + *    - EINVAL - cache size provided is too large, or priv_size is not aligned.
> + *    - ENOSPC - the maximum number of memzones has already been allocated
> + *    - EEXIST - a memzone with the same name already exists
> + *    - ENOMEM - no appropriate memory area found in which to create memzone
> + */
> +__rte_experimental
> +static inline struct rte_mempool *
> +rte_event_vector_pool_create(const char *name, unsigned int n,
> +			     unsigned int cache_size, uint16_t nb_elem,
> +			     int socket_id)

Handling in-lined function is tricky at best from an ABI stability PoV. 

Since this function is used at initialization time and I would suggest since performance is not issue here.
There is no need for this function to be an inline. 

> +{
> +	const char *mp_ops_name;
> +	struct rte_mempool *mp;
> +	unsigned int elt_sz;
> +	int ret;
> +
> +	if (!nb_elem) {
> +		RTE_LOG(ERR, EVENTDEV,
> +			"Invalid number of elements=%d requested\n", nb_elem);
> +		rte_errno = -EINVAL;
> +		return NULL;
> +	}
> +
> +	elt_sz =
> +		sizeof(struct rte_event_vector) + (nb_elem * sizeof(uintptr_t));
> +	mp = rte_mempool_create_empty(name, n, elt_sz, cache_size, 0, socket_id,
> +				      0);
> +	if (mp == NULL)
> +		return NULL;
> +
> +	mp_ops_name = rte_mbuf_best_mempool_ops();
> +	ret = rte_mempool_set_ops_byname(mp, mp_ops_name, NULL);
> +	if (ret != 0) {
> +		RTE_LOG(ERR, EVENTDEV, "error setting mempool handler\n");
> +		goto err;
> +	}
> +
> +	ret = rte_mempool_populate_default(mp);
> +	if (ret < 0)
> +		goto err;
> +
> +	return mp;
> +err:
> +	rte_mempool_free(mp);
> +	rte_errno = -ret;
> +	return NULL;
> +}
> +
>  #ifdef __cplusplus
>  }
>  #endif
> diff --git a/lib/librte_eventdev/version.map b/lib/librte_eventdev/version.map
> index 3e5c09cfd..a070ef56e 100644
> --- a/lib/librte_eventdev/version.map
> +++ b/lib/librte_eventdev/version.map
> @@ -138,6 +138,9 @@ EXPERIMENTAL {
>  	__rte_eventdev_trace_port_setup;
>  	# added in 20.11
>  	rte_event_pmd_pci_probe_named;
> +
> +	#added in 21.05
> +	rte_event_vector_pool_create;
>  };
>  
>  INTERNAL {
>