[EXT] [PATCH v5 11/15] graph: introduce graph walk by cross-core dispatch

[Pavan Nikhilesh Bhagavatula]

> This patch introduces the task scheduler mechanism to enable dispatching
> tasks to another worker cores. Currently, there is only a local work
> queue for one graph to walk. We introduce a scheduler worker queue in
> each worker core for dispatching tasks. It will perform the walk on
> scheduler work queue first, then handle the local work queue.
> 
> Signed-off-by: Haiyue Wang <haiyue.wang at intel.com>
> Signed-off-by: Cunming Liang <cunming.liang at intel.com>
> Signed-off-by: Zhirun Yan <zhirun.yan at intel.com>
> ---
>  lib/graph/rte_graph_model_dispatch.h | 42
> ++++++++++++++++++++++++++++
>  1 file changed, 42 insertions(+)
> 
> diff --git a/lib/graph/rte_graph_model_dispatch.h
> b/lib/graph/rte_graph_model_dispatch.h
> index 18fa7ce0ab..65b2cc6d87 100644
> --- a/lib/graph/rte_graph_model_dispatch.h
> +++ b/lib/graph/rte_graph_model_dispatch.h
> @@ -73,6 +73,48 @@ __rte_experimental
>  int rte_graph_model_dispatch_lcore_affinity_set(const char *name,
>  						unsigned int lcore_id);
> 
> +/**
> + * Perform graph walk on the circular buffer and invoke the process
> function
> + * of the nodes and collect the stats.
> + *
> + * @param graph
> + *   Graph pointer returned from rte_graph_lookup function.
> + *
> + * @see rte_graph_lookup()
> + */
> +__rte_experimental
> +static inline void
> +rte_graph_walk_mcore_dispatch(struct rte_graph *graph)
> +{
> +	const rte_graph_off_t *cir_start = graph->cir_start;
> +	const rte_node_t mask = graph->cir_mask;
> +	uint32_t head = graph->head;
> +	struct rte_node *node;

I think we should add a RTE_ASSERT here to make sure that the graph object is a cloned graph.

> +
> +	if (graph->wq != NULL)
> +		__rte_graph_sched_wq_process(graph);
> +
> +	while (likely(head != graph->tail)) {
> +		node = (struct rte_node *)RTE_PTR_ADD(graph,
> cir_start[(int32_t)head++]);
> +
> +		/* skip the src nodes which not bind with current worker */
> +		if ((int32_t)head < 0 && node->lcore_id != graph->lcore_id)
> +			continue;
> +
> +		/* Schedule the node until all task/objs are done */
> +		if (node->lcore_id != RTE_MAX_LCORE &&
> +		    graph->lcore_id != node->lcore_id && graph->rq != NULL
> &&
> +		    __rte_graph_sched_node_enqueue(node, graph->rq))
> +			continue;
> +
> +		__rte_node_process(graph, node);
> +
> +		head = likely((int32_t)head > 0) ? head & mask : head;
> +	}
> +
> +	graph->tail = 0;
> +}
> +
>  #ifdef __cplusplus
>  }
>  #endif
> --
> 2.37.2