[PATCH v1 08/13] graph: introduce stream moving cross cores

[Jerin Jacob]

On Thu, Nov 17, 2022 at 10:40 AM Zhirun Yan <zhirun.yan at intel.com> wrote:
>
> This patch introduces key functions to allow a worker thread to
> enable enqueue and move streams of objects to the next nodes over
> different cores.
>
> 1. add graph_sched_wq_node to hold graph scheduling workqueue node
> stream
> 2. add workqueue help functions to create/destroy/enqueue/dequeue

Two things, make as two patches


> @@ -39,6 +46,15 @@ struct rte_graph {
>         uint32_t cir_mask;           /**< Circular buffer wrap around mask. */
>         rte_node_t nb_nodes;         /**< Number of nodes in the graph. */
>         rte_graph_off_t *cir_start;  /**< Pointer to circular buffer. */
> +       /* Graph schedule */
> +       struct rte_graph_rq_head *rq __rte_cache_aligned; /* The run-queue */
> +       struct rte_graph_rq_head rq_head; /* The head for run-queue list */
> +
> +       SLIST_ENTRY(rte_graph) rq_next;   /* The next for run-queue list */
> +       unsigned int lcore_id;  /**< The graph running Lcore. */
> +       struct rte_ring *wq;    /**< The work-queue for pending streams. */
> +       struct rte_mempool *mp; /**< The mempool for scheduling streams. */
> +       /* Graph schedule area */
>         rte_graph_off_t nodes_start; /**< Offset at which node memory starts. */
>         rte_graph_t id; /**< Graph identifier. */
>         int socket;     /**< Socket ID where memory is allocated. */
> @@ -63,6 +79,8 @@ struct rte_node {
>         char parent[RTE_NODE_NAMESIZE]; /**< Parent node name. */
>         char name[RTE_NODE_NAMESIZE];   /**< Name of the node. */
>
> +       /* Fast schedule area */
> +       unsigned int lcore_id __rte_cache_aligned;  /**< Node running Lcore. */

Do we need __rte_cache_aligned here? I am wondering can we add union
for different model specific area ONLY for fast path so that we can
save memory and fast path data will be more warm.

>         /* Fast path area  */
>  #define RTE_NODE_CTX_SZ 16
>         uint8_t ctx[RTE_NODE_CTX_SZ] __rte_cache_aligned; /**< Node Context. */
> --
> 2.25.1
>