enhance NUMA affinity heuristic

When a DPDK application is started on only one numa node, memory is
allocated for only one socket. When interrupt threads use memory,
memory may not be found on the socket where the interrupt thread
is currently located, and memory has to be reallocated on the hugepage,
this operation will lead to performance degradation.

Fixes: 705356f ("eal: simplify control thread creation")
Fixes: 770d41b ("malloc: fix allocation with unknown socket ID")
Cc: stable@dpdk.org

Signed-off-by: Kaisen You <kaisenx.you@intel.com>
Signed-off-by: 0-day Robot <robot@bytheb.org>

lib/eal/common/eal_common_thread.c

@@ -252,6 +252,12 @@ static int ctrl_thread_init(void *arg)
 	struct rte_thread_ctrl_params *params = arg;
 
 	__rte_thread_init(rte_lcore_id(), cpuset);
+	/* set the value of the per-core variable _socket_id to SOCKET_ID_ANY.
+	 * Satisfy the judgment condition when threads find memory.
+	 * If SOCKET_ID_ANY is not specified, the thread may go to a node with
+	 * unallocated memory in a subsequent memory search.
+	 */
+	RTE_PER_LCORE(_socket_id) = SOCKET_ID_ANY;
 	params->ret = rte_thread_set_affinity_by_id(rte_thread_self(), cpuset);
 	if (params->ret != 0) {
 		__atomic_store_n(&params->ctrl_thread_status,

lib/eal/common/malloc_heap.c

@@ -716,6 +716,15 @@ malloc_get_numa_socket(void)
 		if (conf->socket_mem[socket_id] != 0)
 			return socket_id;
 	}
+	/* Trying to allocate memory on the main lcore numa node.
+	 * especially when the DPDK application is started only on one numa node.
+	 */
+	socket_id = rte_lcore_to_socket_id(rte_get_main_lcore());
+	/* When the socket_id obtained in the main lcore numa is SOCKET_ID_ANY,
+	 * The probability of finding memory on rte_socket_id_by_idx(0) is higher.
+	 */
+	if (socket_id != (unsigned int)SOCKET_ID_ANY)
+		return socket_id;
 
 	return rte_socket_id_by_idx(0);
 }