diff mbox

[dpdk-dev,RFC,v2] app/testpmd: add option ring-bind-lcpu to bind Q with CPU

Message ID 1499173284-8270-1-git-send-email-wei.guo.simon@gmail.com (mailing list archive)
State Superseded, archived
Delegated to: Thomas Monjalon
Headers show

Checks

Context Check Description
ci/checkpatch success coding style OK
ci/Intel-compilation success Compilation OK

Commit Message

wei.guo.simon@gmail.com July 4, 2017, 1:01 p.m. UTC
From: Simon Guo <wei.guo.simon@gmail.com>

Currently the rx/tx queue is allocated from the buffer pool on socket of:
- port's socket if --port-numa-config specified
- or ring-numa-config setting per port

All the above will "bind" queue to single socket per port configuration.
But it can actually archieve better performance if one port's queue can
be spread across multiple NUMA nodes, and the rx/tx queue is allocated
per lcpu socket.

With this patch, testpmd can utilize the PCI-e bus bandwidth on another
NUMA nodes.  with 64bytes package, When running in PowerPC with Mellanox
CX-4 card, single port(100G), with 8 cores, fw mode:
- Without this patch:  52.5Mpps throughput
- With this patch: 66Mpps throughput

Signed-off-by: Simon Guo <wei.guo.simon@gmail.com>
---
 app/test-pmd/parameters.c |  10 +++++
 app/test-pmd/testpmd.c    | 102 ++++++++++++++++++++++++++++++++--------------
 app/test-pmd/testpmd.h    |   1 +
 3 files changed, 82 insertions(+), 31 deletions(-)

Comments

Lu, Wenzhuo Jan. 5, 2018, 2:59 a.m. UTC | #1
Hi Simon,


> Currently the rx/tx queue is allocated from the buffer pool on socket of:
> - port's socket if --port-numa-config specified
> - or ring-numa-config setting per port
>
> All the above will "bind" queue to single socket per port configuration.
> But it can actually archieve better performance if one port's queue can
> be spread across multiple NUMA nodes, and the rx/tx queue is allocated
> per lcpu socket.
>
> With this patch, testpmd can utilize the PCI-e bus bandwidth on another
> NUMA nodes.  with 64bytes package, When running in PowerPC with Mellanox
> CX-4 card, single port(100G), with 8 cores, fw mode:
> - Without this patch:  52.5Mpps throughput
> - With this patch: 66Mpps throughput
>
> Signed-off-by: Simon Guo <wei.guo.simon@gmail.com>


> diff --git a/app/test-pmd/parameters.c b/app/test-pmd/parameters.c
> index fbe6284..d02059d 100644
> --- a/app/test-pmd/parameters.c
> +++ b/app/test-pmd/parameters.c
> @@ -130,6 +130,11 @@
>  	       "(flag: 1 for RX; 2 for TX; 3 for RX and TX).\n");
>  	printf("  --socket-num=N: set socket from which all memory is allocated "
>  	       "in NUMA mode.\n");
> +	printf("  --ring-bind-lcpu: "
> +		"specify TX/RX rings will be allocated on local socket of lcpu."
> +		"It will overrridden ring-numa-config or port-numa-config if success."
> +		"If local ring buffer is unavailable, it will use --ring-numa-config or port-numa-config instead."
> +		"It allows one port binds to multiple NUMA nodes.\n");
I think it's a good patch to give the APP an example about how to choose the appropriate core.
Just have some concern about the priority. Maybe ring-numa-config and port-numa-config should have higher priority.
Becuase if APP assigned the specific socket by some purpose, it's not good to overwrite it silently.

>  	printf("  --mbuf-size=N: set the data size of mbuf to N bytes.\n");
>  	printf("  --total-num-mbufs=N: set the number of mbufs to be allocated "
>  	       "in mbuf pools.\n");
diff mbox

Patch

diff --git a/app/test-pmd/parameters.c b/app/test-pmd/parameters.c
index fbe6284..d02059d 100644
--- a/app/test-pmd/parameters.c
+++ b/app/test-pmd/parameters.c
@@ -130,6 +130,11 @@ 
 	       "(flag: 1 for RX; 2 for TX; 3 for RX and TX).\n");
 	printf("  --socket-num=N: set socket from which all memory is allocated "
 	       "in NUMA mode.\n");
+	printf("  --ring-bind-lcpu: "
+		"specify TX/RX rings will be allocated on local socket of lcpu."
+		"It will overrridden ring-numa-config or port-numa-config if success."
+		"If local ring buffer is unavailable, it will use --ring-numa-config or port-numa-config instead."
+		"It allows one port binds to multiple NUMA nodes.\n");
 	printf("  --mbuf-size=N: set the data size of mbuf to N bytes.\n");
 	printf("  --total-num-mbufs=N: set the number of mbufs to be allocated "
 	       "in mbuf pools.\n");
@@ -563,6 +568,7 @@ 
 		{ "interactive",		0, 0, 0 },
 		{ "cmdline-file",		1, 0, 0 },
 		{ "auto-start",			0, 0, 0 },
+		{ "ring-bind-lcpu",		0, 0, 0 },
 		{ "eth-peers-configfile",	1, 0, 0 },
 		{ "eth-peer",			1, 0, 0 },
 #endif
@@ -674,6 +680,10 @@ 
 				printf("Auto-start selected\n");
 				auto_start = 1;
 			}
+			if (!strcmp(lgopts[opt_idx].name, "ring-bind-lcpu")) {
+				printf("RingBuffer bind with local CPU selected\n");
+				ring_bind_lcpu = 1;
+			}
 			if (!strcmp(lgopts[opt_idx].name,
 				    "eth-peers-configfile")) {
 				if (init_peer_eth_addrs(optarg) != 0)
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
index b29328a..e538ad0 100644
--- a/app/test-pmd/testpmd.c
+++ b/app/test-pmd/testpmd.c
@@ -98,6 +98,7 @@ 
 /* use master core for command line ? */
 uint8_t interactive = 0;
 uint8_t auto_start = 0;
+uint8_t ring_bind_lcpu;
 char cmdline_filename[PATH_MAX] = {0};
 
 /*
@@ -1395,6 +1396,46 @@  static void eth_event_callback(uint8_t port_id,
 	return 1;
 }
 
+static int find_local_socket(queueid_t qi, int is_rxq)
+{
+	/*
+	 * try to find the local mp with following logic:
+	 * 1) Find the correct stream for the queue;
+	 * 2) Find the correct lcore for the stream;
+	 * 3) Find the correct socket for the lcore;
+	 * 4) Find the correct mp for the scoket;
+	 *
+	 * If failed, failover to the old implementation.
+	 */
+	int i, j, socket = NUMA_NO_CONFIG;
+
+	/* find the stream based on queue no*/
+	for (i = 0; i < nb_fwd_streams; i++) {
+		if (is_rxq) {
+			if (fwd_streams[i]->rx_queue == qi)
+				break;
+		} else {
+			if (fwd_streams[i]->tx_queue == qi)
+				break;
+		}
+	}
+	if (i == nb_fwd_streams)
+		return NUMA_NO_CONFIG;
+
+	/* find the lcore based on stream idx */
+	for (j = 0; j < nb_lcores; j++) {
+		if (fwd_lcores[j]->stream_idx == i)
+			break;
+	}
+	if (j == nb_lcores)
+		return NUMA_NO_CONFIG;
+
+	/* find the scoket for the lcore */
+	socket = rte_lcore_to_socket_id(fwd_lcores_cpuids[j]);
+
+	return socket;
+}
+
 int
 start_port(portid_t pid)
 {
@@ -1445,14 +1486,19 @@  static void eth_event_callback(uint8_t port_id,
 			port->need_reconfig_queues = 0;
 			/* setup tx queues */
 			for (qi = 0; qi < nb_txq; qi++) {
+				int socket = port->socket_id;
 				if ((numa_support) &&
 					(txring_numa[pi] != NUMA_NO_CONFIG))
-					diag = rte_eth_tx_queue_setup(pi, qi,
-						nb_txd,txring_numa[pi],
-						&(port->tx_conf));
-				else
-					diag = rte_eth_tx_queue_setup(pi, qi,
-						nb_txd,port->socket_id,
+					socket = txring_numa[pi];
+
+				if (ring_bind_lcpu) {
+					int ret = find_local_socket(qi, 0);
+					if (ret != NUMA_NO_CONFIG)
+						socket = ret;
+				}
+
+				diag = rte_eth_tx_queue_setup(pi, qi,
+						nb_txd, socket,
 						&(port->tx_conf));
 
 				if (diag == 0)
@@ -1471,35 +1517,29 @@  static void eth_event_callback(uint8_t port_id,
 			}
 			/* setup rx queues */
 			for (qi = 0; qi < nb_rxq; qi++) {
+				int socket = port->socket_id;
 				if ((numa_support) &&
-					(rxring_numa[pi] != NUMA_NO_CONFIG)) {
-					struct rte_mempool * mp =
-						mbuf_pool_find(rxring_numa[pi]);
-					if (mp == NULL) {
-						printf("Failed to setup RX queue:"
-							"No mempool allocation"
-							" on the socket %d\n",
-							rxring_numa[pi]);
-						return -1;
-					}
-
-					diag = rte_eth_rx_queue_setup(pi, qi,
-					     nb_rxd,rxring_numa[pi],
-					     &(port->rx_conf),mp);
-				} else {
-					struct rte_mempool *mp =
-						mbuf_pool_find(port->socket_id);
-					if (mp == NULL) {
-						printf("Failed to setup RX queue:"
+					(rxring_numa[pi] != NUMA_NO_CONFIG))
+					socket = rxring_numa[pi];
+
+				if (ring_bind_lcpu) {
+					int ret = find_local_socket(qi, 1);
+					if (ret != NUMA_NO_CONFIG)
+						socket = ret;
+				}
+
+				struct rte_mempool *mp =
+					mbuf_pool_find(socket);
+				if (mp == NULL) {
+					printf("Failed to setup RX queue:"
 							"No mempool allocation"
 							" on the socket %d\n",
-							port->socket_id);
-						return -1;
-					}
-					diag = rte_eth_rx_queue_setup(pi, qi,
-					     nb_rxd,port->socket_id,
-					     &(port->rx_conf), mp);
+							socket);
+					return -1;
 				}
+				diag = rte_eth_rx_queue_setup(pi, qi,
+						nb_rxd, socket,
+						&(port->rx_conf), mp);
 				if (diag == 0)
 					continue;
 
diff --git a/app/test-pmd/testpmd.h b/app/test-pmd/testpmd.h
index 364502d..c45b2b8 100644
--- a/app/test-pmd/testpmd.h
+++ b/app/test-pmd/testpmd.h
@@ -299,6 +299,7 @@  struct queue_stats_mappings {
 extern uint16_t verbose_level; /**< Drives messages being displayed, if any. */
 extern uint8_t  interactive;
 extern uint8_t  auto_start;
+extern uint8_t  ring_bind_lcpu;
 extern char cmdline_filename[PATH_MAX]; /**< offline commands file */
 extern uint8_t  numa_support; /**< set by "--numa" parameter */
 extern uint16_t port_topology; /**< set by "--port-topology" parameter */