[PATCH v4] examples/l3fwd: dynamic NUMA-aware alloc lcore_conf

[Konstantin Ananyev]

> Currently lcore_conf is a global static array. When multiple
> ports/lcores are distributed across different NUMA nodes, datapath
> suffers from severe cross-NUMA memory access penalty.
>
> On Kunpeng platform, sizeof(struct lcore_conf) reaches 133760 bytes.
> Such a huge per-lcore structure significantly amplifies cross-NUMA
> overhead in multi-port multi-NUMA deployment scenarios.
>
> This commit refactors lcore_conf to pointer array and implements
> per-lcore NUMA-aware hugepage allocation, allocating each lcore's
> configuration on its local socket to eliminate remote memory access.
>
> Signed-off-by: Chengwen Feng <fengchengwen at huawei.com>
> ---
> v4: Use SOCKET_ID_AN instead of zero when NUMA is disabled
> v3: Fix Thomas' comment: support no-numa parameter
>      Deinit lcore_conf on exit
> v2: Fix AI review comment: add cleanup when init lcore-conf fail
>
> ---
>   examples/l3fwd/l3fwd.h     |  2 +-
>   examples/l3fwd/l3fwd_acl.c |  2 +-
>   examples/l3fwd/l3fwd_em.c  |  8 +++---
>   examples/l3fwd/l3fwd_fib.c |  6 ++--
>   examples/l3fwd/l3fwd_lpm.c |  8 +++---
>   examples/l3fwd/main.c      | 59 ++++++++++++++++++++++++++++++++------
>   6 files changed, 63 insertions(+), 22 deletions(-)
>
> diff --git a/examples/l3fwd/l3fwd.h b/examples/l3fwd/l3fwd.h
> index 349fc37c79..20c457ee7f 100644
> --- a/examples/l3fwd/l3fwd.h
> +++ b/examples/l3fwd/l3fwd.h
> @@ -104,7 +104,7 @@ extern uint32_t hash_entry_number;
>   
>   extern xmm_t val_eth[RTE_MAX_ETHPORTS];
>   
> -extern struct lcore_conf lcore_conf[RTE_MAX_LCORE];
> +extern struct lcore_conf *lcore_conf[RTE_MAX_LCORE];
>   
>   extern struct parm_cfg parm_config;
>   
> diff --git a/examples/l3fwd/l3fwd_acl.c b/examples/l3fwd/l3fwd_acl.c
> index 4ee3411d2a..0605f6feb9 100644
> --- a/examples/l3fwd/l3fwd_acl.c
> +++ b/examples/l3fwd/l3fwd_acl.c
> @@ -1090,7 +1090,7 @@ acl_main_loop(__rte_unused void *dummy)
>   
>   	prev_tsc = 0;
>   	lcore_id = rte_lcore_id();
> -	qconf = &lcore_conf[lcore_id];
> +	qconf = lcore_conf[lcore_id];
>   	socketid = rte_lcore_to_socket_id(lcore_id);
>   
>   	if (qconf->n_rx_queue == 0) {
> diff --git a/examples/l3fwd/l3fwd_em.c b/examples/l3fwd/l3fwd_em.c
> index d8748a0edd..9aa23759d3 100644
> --- a/examples/l3fwd/l3fwd_em.c
> +++ b/examples/l3fwd/l3fwd_em.c
> @@ -597,7 +597,7 @@ em_main_loop(__rte_unused void *dummy)
>   		US_PER_S * BURST_TX_DRAIN_US;
>   
>   	lcore_id = rte_lcore_id();
> -	qconf = &lcore_conf[lcore_id];
> +	qconf = lcore_conf[lcore_id];
>   
>   	const uint16_t n_rx_q = qconf->n_rx_queue;
>   	const uint16_t n_tx_p = qconf->n_tx_port;
> @@ -685,7 +685,7 @@ em_event_loop_single(struct l3fwd_event_resources *evt_rsrc,
>   		return;
>   
>   	lcore_id = rte_lcore_id();
> -	lconf = &lcore_conf[lcore_id];
> +	lconf = lcore_conf[lcore_id];
>   
>   	RTE_LOG(INFO, L3FWD, "entering %s on lcore %u\n", __func__, lcore_id);
>   	while (!force_quit) {
> @@ -747,7 +747,7 @@ em_event_loop_burst(struct l3fwd_event_resources *evt_rsrc,
>   
>   	lcore_id = rte_lcore_id();
>   
> -	lconf = &lcore_conf[lcore_id];
> +	lconf = lcore_conf[lcore_id];
>   
>   	RTE_LOG(INFO, L3FWD, "entering %s on lcore %u\n", __func__, lcore_id);
>   
> @@ -877,7 +877,7 @@ em_event_loop_vector(struct l3fwd_event_resources *evt_rsrc,
>   	if (dst_ports == NULL)
>   		return;
>   	lcore_id = rte_lcore_id();
> -	lconf = &lcore_conf[lcore_id];
> +	lconf = lcore_conf[lcore_id];
>   
>   	RTE_LOG(INFO, L3FWD, "entering %s on lcore %u\n", __func__, lcore_id);
>   
> diff --git a/examples/l3fwd/l3fwd_fib.c b/examples/l3fwd/l3fwd_fib.c
> index 4fc6bf90d5..32c8847130 100644
> --- a/examples/l3fwd/l3fwd_fib.c
> +++ b/examples/l3fwd/l3fwd_fib.c
> @@ -192,7 +192,7 @@ fib_main_loop(__rte_unused void *dummy)
>   			US_PER_S * BURST_TX_DRAIN_US;
>   
>   	lcore_id = rte_lcore_id();
> -	qconf = &lcore_conf[lcore_id];
> +	qconf = lcore_conf[lcore_id];
>   
>   	const uint16_t n_rx_q = qconf->n_rx_queue;
>   	const uint16_t n_tx_p = qconf->n_tx_port;
> @@ -282,7 +282,7 @@ fib_event_loop(struct l3fwd_event_resources *evt_rsrc,
>   
>   	lcore_id = rte_lcore_id();
>   
> -	lconf = &lcore_conf[lcore_id];
> +	lconf = lcore_conf[lcore_id];
>   
>   	RTE_LOG(INFO, L3FWD, "entering %s on lcore %u\n", __func__, lcore_id);
>   
> @@ -446,7 +446,7 @@ fib_process_event_vector(struct rte_event_vector *vec, uint8_t *type_arr,
>   	uint16_t nh;
>   	int i;
>   
> -	lconf = &lcore_conf[rte_lcore_id()];
> +	lconf = lcore_conf[rte_lcore_id()];
>   
>   	/* Reset counters. */
>   	ipv4_cnt = 0;
> diff --git a/examples/l3fwd/l3fwd_lpm.c b/examples/l3fwd/l3fwd_lpm.c
> index 2d2651e750..77701503f7 100644
> --- a/examples/l3fwd/l3fwd_lpm.c
> +++ b/examples/l3fwd/l3fwd_lpm.c
> @@ -154,7 +154,7 @@ lpm_main_loop(__rte_unused void *dummy)
>   		US_PER_S * BURST_TX_DRAIN_US;
>   
>   	lcore_id = rte_lcore_id();
> -	qconf = &lcore_conf[lcore_id];
> +	qconf = lcore_conf[lcore_id];
>   
>   	const uint16_t n_rx_q = qconf->n_rx_queue;
>   	const uint16_t n_tx_p = qconf->n_tx_port;
> @@ -270,7 +270,7 @@ lpm_event_loop_single(struct l3fwd_event_resources *evt_rsrc,
>   		return;
>   
>   	lcore_id = rte_lcore_id();
> -	lconf = &lcore_conf[lcore_id];
> +	lconf = lcore_conf[lcore_id];
>   
>   	RTE_LOG(INFO, L3FWD, "entering %s on lcore %u\n", __func__, lcore_id);
>   	while (!force_quit) {
> @@ -324,7 +324,7 @@ lpm_event_loop_burst(struct l3fwd_event_resources *evt_rsrc,
>   
>   	lcore_id = rte_lcore_id();
>   
> -	lconf = &lcore_conf[lcore_id];
> +	lconf = lcore_conf[lcore_id];
>   
>   	RTE_LOG(INFO, L3FWD, "entering %s on lcore %u\n", __func__, lcore_id);
>   
> @@ -468,7 +468,7 @@ lpm_event_loop_vector(struct l3fwd_event_resources *evt_rsrc,
>   		return;
>   
>   	lcore_id = rte_lcore_id();
> -	lconf = &lcore_conf[lcore_id];
> +	lconf = lcore_conf[lcore_id];
>   	dst_port_list =
>   		rte_zmalloc("", sizeof(uint16_t) * evt_rsrc->vector_size,
>   			    RTE_CACHE_LINE_SIZE);
> diff --git a/examples/l3fwd/main.c b/examples/l3fwd/main.c
> index 6866811526..626f187454 100644
> --- a/examples/l3fwd/main.c
> +++ b/examples/l3fwd/main.c
> @@ -95,7 +95,7 @@ uint32_t enabled_port_mask;
>   /* Used only in exact match mode. */
>   bool ipv6_enabled; /**< ipv6 is false by default. */
>   
> -struct lcore_conf lcore_conf[RTE_MAX_LCORE];
> +struct lcore_conf *lcore_conf[RTE_MAX_LCORE];
>   
>   struct parm_cfg parm_config;
>   
> @@ -367,17 +367,17 @@ init_lcore_rx_queues(void)
>   
>   	for (i = 0; i < nb_lcore_params; ++i) {
>   		lcore = lcore_params[i].lcore_id;
> -		nb_rx_queue = lcore_conf[lcore].n_rx_queue;
> +		nb_rx_queue = lcore_conf[lcore]->n_rx_queue;
>   		if (nb_rx_queue >= MAX_RX_QUEUE_PER_LCORE) {
>   			printf("error: too many queues (%u) for lcore: %u\n",
>   				(unsigned int)nb_rx_queue + 1, lcore);
>   			return -1;
>   		} else {
> -			lcore_conf[lcore].rx_queue_list[nb_rx_queue].port_id =
> +			lcore_conf[lcore]->rx_queue_list[nb_rx_queue].port_id =
>   				lcore_params[i].port_id;
> -			lcore_conf[lcore].rx_queue_list[nb_rx_queue].queue_id =
> +			lcore_conf[lcore]->rx_queue_list[nb_rx_queue].queue_id =
>   				lcore_params[i].queue_id;
> -			lcore_conf[lcore].n_rx_queue++;
> +			lcore_conf[lcore]->n_rx_queue++;
>   		}
>   	}
>   	return 0;
> @@ -1117,6 +1117,41 @@ print_ethaddr(const char *name, const struct rte_ether_addr *eth_addr)
>   	printf("%s%s", name, buf);
>   }
>   
> +static void
> +deinit_lcore_conf(void)
> +{
> +	unsigned int lcore_id;
> +
> +	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
> +		if (lcore_conf[lcore_id] != NULL) {
> +			rte_free(lcore_conf[lcore_id]);
> +			lcore_conf[lcore_id] = NULL;
> +		}
> +	}
> +}
> +
> +static int
> +init_lcore_conf(void)
> +{
> +	unsigned int lcore_id;
> +	int socketid;
> +
> +	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
> +		if (rte_lcore_is_enabled(lcore_id) == 0)
> +			continue;
> +
> +		socketid = numa_on ? (int)rte_lcore_to_socket_id(lcore_id) : SOCKET_ID_ANY;
> +		lcore_conf[lcore_id] = rte_zmalloc_socket(NULL, sizeof(struct lcore_conf),
> +							  RTE_CACHE_LINE_SIZE, socketid);
> +		if (lcore_conf[lcore_id] == NULL) {
> +			deinit_lcore_conf();
> +			return -ENOMEM;
> +		}
> +	}
> +
> +	return 0;
> +}
> +
>   int
>   init_mem(uint16_t portid, unsigned int nb_mbuf)
>   {
> @@ -1188,7 +1223,7 @@ init_mem(uint16_t portid, unsigned int nb_mbuf)
>   		}
>   #endif
>   
> -		qconf = &lcore_conf[lcore_id];
> +		qconf = lcore_conf[lcore_id];
>   		qconf->ipv4_lookup_struct =
>   			l3fwd_lkp.get_ipv4_lookup_struct(socketid);
>   		qconf->ipv6_lookup_struct =
> @@ -1489,7 +1524,7 @@ l3fwd_poll_resource_setup(void)
>   					"rte_eth_tx_queue_setup: err=%d, "
>   					"port=%d\n", ret, portid);
>   
> -			qconf = &lcore_conf[lcore_id];
> +			qconf = lcore_conf[lcore_id];
>   			qconf->tx_queue_id[portid] = queueid;
>   			queueid++;
>   
> @@ -1502,7 +1537,7 @@ l3fwd_poll_resource_setup(void)
>   	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
>   		if (rte_lcore_is_enabled(lcore_id) == 0)
>   			continue;
> -		qconf = &lcore_conf[lcore_id];
> +		qconf = lcore_conf[lcore_id];
>   		printf("\nInitializing rx queues on lcore %u ... ", lcore_id );
>   		fflush(stdout);
>   		/* init RX queues */
> @@ -1683,6 +1718,10 @@ main(int argc, char **argv)
>   	if (ret < 0)
>   		rte_exit(EXIT_FAILURE, "Invalid L3FWD parameters\n");
>   
> +	ret = init_lcore_conf();
> +	if (ret)
> +		rte_exit(EXIT_FAILURE, "Init lcore conf failed!\n");
> +
>   	RTE_LOG(INFO, L3FWD, "Using Rx burst %u Tx burst %u\n", rx_burst_size, tx_burst_size);
>   
>   	/* Setup function pointers for lookup method. */
> @@ -1746,7 +1785,7 @@ main(int argc, char **argv)
>   	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
>   		if (rte_lcore_is_enabled(lcore_id) == 0)
>   			continue;
> -		qconf = &lcore_conf[lcore_id];
> +		qconf = lcore_conf[lcore_id];
>   		for (queue = 0; queue < qconf->n_rx_queue; ++queue) {
>   			portid = qconf->rx_queue_list[queue].port_id;
>   			queueid = qconf->rx_queue_list[queue].queue_id;
> @@ -1810,6 +1849,8 @@ main(int argc, char **argv)
>   	/* clean up config file routes */
>   	l3fwd_lkp.free_routes();
>   
> +	deinit_lcore_conf();
> +
>   	/* clean up the EAL */
>   	rte_eal_cleanup();
>   

Acked-by: Konstantin Ananyev <konstantin.v.ananyev at yandex.ru>