Re: [dpdk-dev] [EXT] Re: [PATCH v4 1/8] eventdev: introduce event vector capability
From: Pavan Nikhilesh Bhagavatula <hidden>
Date: 2021-03-22 09:11:06
On 19/03/2021 20:57, pbhagavatula@marvell.com wrote:quoted
From: Pavan Nikhilesh <redacted> 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 eventdevice.quoted
Add a event vector mempool create handler to create mempoolsbased onquoted
the best mempool ops available on a given platform. Signed-off-by: Pavan Nikhilesh <redacted> --- doc/guides/prog_guide/eventdev.rst | 36 +++++++++- lib/librte_eventdev/rte_eventdev.h | 112++++++++++++++++++++++++++++-quoted
lib/librte_eventdev/version.map | 3 + 3 files changed, 148 insertions(+), 3 deletions(-)[SNIP]quoted
diff --git a/lib/librte_eventdev/rte_eventdev.hb/lib/librte_eventdev/rte_eventdev.hquoted
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,quoted
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 eventtype thequoted
+ * vector array can be an array of mbufs or pointers or opaqueu64quoted
+ * 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 ofEVENT_TYPE_VECTOR.quoted
+ * This simplifies the pipeline design as we can split processing theeventsquoted
+ * 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)quoted
+/**< 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 withmbuf */quoted
+ struct rte_event_vector *vec; + /**< Event vector pointer. */ }; };@@ -2023,6 +2061,78 @@ rte_event_dev_xstats_reset(uint8_tdev_id,quoted
*/ int rte_event_dev_selftest(uint8_t dev_id); +/** + * Get the memory required per event vector based on the number ofelements perquoted
+ * vector. + * This should be used to create the mempool that holds the eventvectors.quoted
+ * + * @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 beable to hold.quoted
+ * @param socket_id + * The socket identifier where the memory should be allocated. The + * value can be *SOCKET_ID_ANY* if there is no NUMA constraintfor thequoted
+ * reserved zone + * + * @return + * The pointer to the newly allocated mempool, on success. NULLon errorquoted
+ * with rte_errno set appropriately. Possible rte_errno valuesinclude:quoted
+ * - E_RTE_NO_CONFIG - function could not get pointer torte_config structurequoted
+ * - E_RTE_SECONDARY - function was called from a secondaryprocess instancequoted
+ * - EINVAL - cache size provided is too large, or priv_size is notaligned.quoted
+ * - ENOSPC - the maximum number of memzones has already beenallocatedquoted
+ * - EEXIST - a memzone with the same name already exists + * - ENOMEM - no appropriate memory area found in which tocreate memzonequoted
+ */ +__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.
Makes sense, I will move it to .c in the next version. Thanks, Pavan.
quoted
+{ + 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);quoted
+ rte_errno = -EINVAL; + return NULL; + } + + elt_sz = + sizeof(struct rte_event_vector) + (nb_elem *sizeof(uintptr_t));quoted
+ mp = rte_mempool_create_empty(name, n, elt_sz, cache_size,0, socket_id,quoted
+ 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);quoted
+ if (ret != 0) { + RTE_LOG(ERR, EVENTDEV, "error setting mempoolhandler\n");quoted
+ 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 } #endifdiff --git a/lib/librte_eventdev/version.mapb/lib/librte_eventdev/version.mapquoted
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 {