[dpdk-dev] [PATCH v8] app/testpmd: support multi-process

["Min Hu (Connor)" <humin29@huawei.com>]

From: Lijun Ou <oulijun@huawei.com>

This patch adds multi-process support for testpmd.
The test cmd example as follows:
the primary cmd:
./dpdk-testpmd -a xxx --proc-type=auto -l 0-1 -- -i \
--rxq=4 --txq=4 --num-procs=2 --proc-id=0

the secondary cmd:
./dpdk-testpmd -a xxx --proc-type=auto -l 2-3 -- -i \
--rxq=4 --txq=4 --num-procs=2 --proc-id=1

Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
Signed-off-by: Lijun Ou <oulijun@huawei.com>
---
v8:
* Added warning info about queue numbers and process numbers.

v7:
* Fixed compiling error for unexpected unindent.

v6:
* Add rte flow description for multiple process.

v5:
* Fixed run_app.rst for multiple process description.
* Fix compiling error.

v4:
* Fixed minimum vlaue of Rxq or Txq in doc.

v3:
* Fixed compiling error using gcc10.0.

v2:
* Added document for this patch.
---
 app/test-pmd/cmdline.c                |  12 +++-
 app/test-pmd/config.c                 |  14 +++-
 app/test-pmd/parameters.c             |  11 +++
 app/test-pmd/testpmd.c                | 127 ++++++++++++++++++++++------------
 app/test-pmd/testpmd.h                |   7 ++
 doc/guides/testpmd_app_ug/run_app.rst | 101 +++++++++++++++++++++++++++
 6 files changed, 226 insertions(+), 46 deletions(-)

diff --git a/app/test-pmd/cmdline.c b/app/test-pmd/cmdline.c
index f44116b..38c97e3 100644
--- a/app/test-pmd/cmdline.c
+++ b/app/test-pmd/cmdline.c
@@ -71,8 +71,6 @@
 #include "cmdline_tm.h"
 #include "bpf_cmd.h"
 
-static struct cmdline *testpmd_cl;
-
 static void cmd_reconfig_device_queue(portid_t id, uint8_t dev, uint8_t queue);
 
 /* *** Help command with introduction. *** */
@@ -5351,6 +5349,12 @@ cmd_set_flush_rx_parsed(void *parsed_result,
 		__rte_unused void *data)
 {
 	struct cmd_set_flush_rx *res = parsed_result;
+
+	if (num_procs > 1 && (strcmp(res->mode, "on") == 0)) {
+		printf("multi-process doesn't support to flush rx queues.\n");
+		return;
+	}
+
 	no_flush_rx = (uint8_t)((strcmp(res->mode, "on") == 0) ? 0 : 1);
 }
 
@@ -17229,6 +17233,10 @@ prompt(void)
 		printf("Cannot set exit function for cmdline\n");
 
 	cmdline_interact(testpmd_cl);
+	if (unlikely(f_quit == 1)) {
+		dup2(testpmd_fd_copy, testpmd_cl->s_in);
+		close(testpmd_fd_copy);
+	}
 	if (ret != 0)
 		cmdline_stdin_exit(testpmd_cl);
 }
diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c
index ef0b978..ec7d030 100644
--- a/app/test-pmd/config.c
+++ b/app/test-pmd/config.c
@@ -2827,6 +2827,8 @@ rss_fwd_config_setup(void)
 	queueid_t  rxq;
 	queueid_t  nb_q;
 	streamid_t  sm_id;
+	int start;
+	int end;
 
 	nb_q = nb_rxq;
 	if (nb_q > nb_txq)
@@ -2844,7 +2846,15 @@ rss_fwd_config_setup(void)
 	init_fwd_streams();
 
 	setup_fwd_config_of_each_lcore(&cur_fwd_config);
-	rxp = 0; rxq = 0;
+
+	if (proc_id > 0 && nb_q % num_procs)
+		printf("Warning! queue numbers should be multiple of "
+			"processes, or packet loss will happen.\n");
+
+	start = proc_id * nb_q / num_procs;
+	end = start + nb_q / num_procs;
+	rxp = 0;
+	rxq = start;
 	for (sm_id = 0; sm_id < cur_fwd_config.nb_fwd_streams; sm_id++) {
 		struct fwd_stream *fs;
 
@@ -2861,6 +2871,8 @@ rss_fwd_config_setup(void)
 			continue;
 		rxp = 0;
 		rxq++;
+		if (rxq >= end)
+			rxq = start;
 	}
 }
 
diff --git a/app/test-pmd/parameters.c b/app/test-pmd/parameters.c
index a326c8c..ec3bc62 100644
--- a/app/test-pmd/parameters.c
+++ b/app/test-pmd/parameters.c
@@ -45,6 +45,8 @@
 #include <rte_flow.h>
 
 #include "testpmd.h"
+#define PARAM_PROC_ID "proc-id"
+#define PARAM_NUM_PROCS "num-procs"
 
 static void
 usage(char* progname)
@@ -644,6 +646,8 @@ launch_args_parse(int argc, char** argv)
 		{ "rx-mq-mode",                 1, 0, 0 },
 		{ "record-core-cycles",         0, 0, 0 },
 		{ "record-burst-stats",         0, 0, 0 },
+		{ PARAM_NUM_PROCS,              1, 0, 0 },
+		{ PARAM_PROC_ID,                1, 0, 0 },
 		{ 0, 0, 0, 0 },
 	};
 
@@ -1410,6 +1414,13 @@ launch_args_parse(int argc, char** argv)
 				record_core_cycles = 1;
 			if (!strcmp(lgopts[opt_idx].name, "record-burst-stats"))
 				record_burst_stats = 1;
+
+			if (strncmp(lgopts[opt_idx].name,
+				    PARAM_NUM_PROCS, 8) == 0)
+				num_procs = atoi(optarg);
+			if (strncmp(lgopts[opt_idx].name,
+				    PARAM_PROC_ID, 7) == 0)
+				proc_id = atoi(optarg);
 			break;
 		case 'h':
 			usage(argv[0]);
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
index 96d2e0f..c31234e 100644
--- a/app/test-pmd/testpmd.c
+++ b/app/test-pmd/testpmd.c
@@ -63,6 +63,9 @@
 
 #include "testpmd.h"
 
+int testpmd_fd_copy; /* the copy of STDIN_FILENO */
+struct cmdline *testpmd_cl;
+
 #ifndef MAP_HUGETLB
 /* FreeBSD may not have MAP_HUGETLB (in fact, it probably doesn't) */
 #define HUGE_FLAG (0x40000)
@@ -125,6 +128,9 @@ uint8_t port_numa[RTE_MAX_ETHPORTS];
  */
 uint8_t rxring_numa[RTE_MAX_ETHPORTS];
 
+int proc_id;
+unsigned int num_procs = 1;
+
 /*
  * Store specified sockets on which TX ring to be used by ports
  * is allocated.
@@ -977,6 +983,11 @@ mbuf_pool_create(uint16_t mbuf_seg_size, unsigned nb_mbuf,
 	mb_size = sizeof(struct rte_mbuf) + mbuf_seg_size;
 	mbuf_poolname_build(socket_id, pool_name, sizeof(pool_name), size_idx);
 
+	if (rte_eal_process_type() != RTE_PROC_PRIMARY) {
+		rte_mp = rte_mempool_lookup(pool_name);
+		goto err;
+	}
+
 	TESTPMD_LOG(INFO,
 		"create a new mbuf pool <%s>: n=%u, size=%u, socket=%u\n",
 		pool_name, nb_mbuf, mbuf_seg_size, socket_id);
@@ -1059,9 +1070,14 @@ mbuf_pool_create(uint16_t mbuf_seg_size, unsigned nb_mbuf,
 
 err:
 	if (rte_mp == NULL) {
-		rte_exit(EXIT_FAILURE,
-			"Creation of mbuf pool for socket %u failed: %s\n",
-			socket_id, rte_strerror(rte_errno));
+		if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+			rte_exit(EXIT_FAILURE,
+				"Creation of mbuf pool for socket %u failed: %s\n",
+				socket_id, rte_strerror(rte_errno));
+		else
+			rte_exit(EXIT_FAILURE,
+				"Get mbuf pool for socket %u failed: %s\n",
+				socket_id, rte_strerror(rte_errno));
 	} else if (verbose_level > 0) {
 		rte_mempool_dump(stdout, rte_mp);
 	}
@@ -2002,6 +2018,12 @@ flush_fwd_rx_queues(void)
 	uint64_t prev_tsc = 0, diff_tsc, cur_tsc, timer_tsc = 0;
 	uint64_t timer_period;
 
+	if (num_procs > 1) {
+		printf("multi-process not support for flushing fwd rx "
+		       "queues, skip the below lines and return.\n");
+		return;
+	}
+
 	/* convert to number of cycles */
 	timer_period = rte_get_timer_hz(); /* 1 second timeout */
 
@@ -2511,21 +2533,28 @@ start_port(portid_t pid)
 				return -1;
 			}
 			/* configure port */
-			diag = rte_eth_dev_configure(pi, nb_rxq + nb_hairpinq,
+			if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+				diag = rte_eth_dev_configure(pi,
+						     nb_rxq + nb_hairpinq,
 						     nb_txq + nb_hairpinq,
 						     &(port->dev_conf));
-			if (diag != 0) {
-				if (rte_atomic16_cmpset(&(port->port_status),
-				RTE_PORT_HANDLING, RTE_PORT_STOPPED) == 0)
-					printf("Port %d can not be set back "
-							"to stopped\n", pi);
-				printf("Fail to configure port %d\n", pi);
-				/* try to reconfigure port next time */
-				port->need_reconfig = 1;
-				return -1;
+				if (diag != 0) {
+					if (rte_atomic16_cmpset(
+							&(port->port_status),
+							RTE_PORT_HANDLING,
+							RTE_PORT_STOPPED) == 0)
+						printf("Port %d can not be set "
+						       "back to stopped\n", pi);
+					printf("Fail to configure port %d\n",
+						pi);
+					/* try to reconfigure port next time */
+					port->need_reconfig = 1;
+					return -1;
+				}
 			}
 		}
-		if (port->need_reconfig_queues > 0) {
+		if (port->need_reconfig_queues > 0 &&
+		    rte_eal_process_type() == RTE_PROC_PRIMARY) {
 			port->need_reconfig_queues = 0;
 			/* setup tx queues */
 			for (qi = 0; qi < nb_txq; qi++) {
@@ -2626,17 +2655,20 @@ start_port(portid_t pid)
 		cnt_pi++;
 
 		/* start port */
-		diag = rte_eth_dev_start(pi);
-		if (diag < 0) {
-			printf("Fail to start port %d: %s\n", pi,
-			       rte_strerror(-diag));
+		if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+			diag = rte_eth_dev_start(pi);
+			if (diag < 0) {
+				printf("Fail to start port %d: %s\n", pi,
+				       rte_strerror(-diag));
 
-			/* Fail to setup rx queue, return */
-			if (rte_atomic16_cmpset(&(port->port_status),
+				/* Fail to setup rx queue, return */
+				if (rte_atomic16_cmpset(&(port->port_status),
 				RTE_PORT_HANDLING, RTE_PORT_STOPPED) == 0)
-				printf("Port %d can not be set back to "
-							"stopped\n", pi);
-			continue;
+					printf("Port %d can not be set back to "
+								"stopped\n",
+						pi);
+				continue;
+			}
 		}
 
 		if (rte_atomic16_cmpset(&(port->port_status),
@@ -2765,7 +2797,8 @@ stop_port(portid_t pid)
 		if (port->flow_list)
 			port_flow_flush(pi);
 
-		if (rte_eth_dev_stop(pi) != 0)
+		if (rte_eal_process_type() == RTE_PROC_PRIMARY &&
+		    rte_eth_dev_stop(pi) != 0)
 			RTE_LOG(ERR, EAL, "rte_eth_dev_stop failed for port %u\n",
 				pi);
 
@@ -2834,8 +2867,10 @@ close_port(portid_t pid)
 			continue;
 		}
 
-		port_flow_flush(pi);
-		rte_eth_dev_close(pi);
+		if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+			port_flow_flush(pi);
+		if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+			rte_eth_dev_close(pi);
 	}
 
 	remove_invalid_ports();
@@ -3099,7 +3134,7 @@ pmd_test_exit(void)
 		}
 	}
 	for (i = 0 ; i < RTE_DIM(mempools) ; i++) {
-		if (mempools[i])
+		if (rte_eal_process_type() == RTE_PROC_PRIMARY && mempools[i])
 			rte_mempool_free(mempools[i]);
 	}
 
@@ -3621,6 +3656,10 @@ init_port_dcb_config(portid_t pid,
 	int retval;
 	uint16_t i;
 
+	if (num_procs > 1) {
+		printf("The multi-process feature doesn't support dcb.\n");
+		return -ENOTSUP;
+	}
 	rte_port = &ports[pid];
 
 	memset(&port_conf, 0, sizeof(struct rte_eth_conf));
@@ -3719,13 +3758,6 @@ init_port(void)
 }
 
 static void
-force_quit(void)
-{
-	pmd_test_exit();
-	prompt_exit();
-}
-
-static void
 print_stats(void)
 {
 	uint8_t i;
@@ -3756,12 +3788,16 @@ signal_handler(int signum)
 		if (latencystats_enabled != 0)
 			rte_latencystats_uninit();
 #endif
-		force_quit();
 		/* Set flag to indicate the force termination. */
 		f_quit = 1;
-		/* exit with the expected status */
-		signal(signum, SIG_DFL);
-		kill(getpid(), signum);
+		if (interactive == 1) {
+			dup2(testpmd_cl->s_in, testpmd_fd_copy);
+			close(testpmd_cl->s_in);
+		} else {
+			dup2(0, testpmd_fd_copy);
+			close(0);
+		}
+
 	}
 }
 
@@ -3786,10 +3822,6 @@ main(int argc, char** argv)
 		rte_exit(EXIT_FAILURE, "Cannot init EAL: %s\n",
 			 rte_strerror(rte_errno));
 
-	if (rte_eal_process_type() == RTE_PROC_SECONDARY)
-		rte_exit(EXIT_FAILURE,
-			 "Secondary process type not supported.\n");
-
 	ret = register_eth_event_callback();
 	if (ret != 0)
 		rte_exit(EXIT_FAILURE, "Cannot register for ethdev events");
@@ -3885,8 +3917,10 @@ main(int argc, char** argv)
 		}
 	}
 
-	if (!no_device_start && start_port(RTE_PORT_ALL) != 0)
+	if (!no_device_start && start_port(RTE_PORT_ALL) != 0) {
+		pmd_test_exit();
 		rte_exit(EXIT_FAILURE, "Start ports failed\n");
+	}
 
 	/* set all ports to promiscuous mode by default */
 	RTE_ETH_FOREACH_DEV(port_id) {
@@ -3932,6 +3966,8 @@ main(int argc, char** argv)
 		}
 		prompt();
 		pmd_test_exit();
+		if (unlikely(f_quit == 1))
+			prompt_exit();
 	} else
 #endif
 	{
@@ -3967,6 +4003,11 @@ main(int argc, char** argv)
 		printf("Press enter to exit\n");
 		rc = read(0, &c, 1);
 		pmd_test_exit();
+		if (unlikely(f_quit == 1)) {
+			dup2(testpmd_fd_copy, 0);
+			close(testpmd_fd_copy);
+			prompt_exit();
+		}
 		if (rc < 0)
 			return 1;
 	}
diff --git a/app/test-pmd/testpmd.h b/app/test-pmd/testpmd.h
index a87ccb0..640a377 100644
--- a/app/test-pmd/testpmd.h
+++ b/app/test-pmd/testpmd.h
@@ -13,6 +13,7 @@
 #include <rte_gso.h>
 #include <cmdline.h>
 #include <sys/queue.h>
+#include  "cmdline.h"
 
 #define RTE_PORT_ALL            (~(portid_t)0x0)
 
@@ -24,6 +25,10 @@
 #define RTE_PORT_CLOSED         (uint16_t)2
 #define RTE_PORT_HANDLING       (uint16_t)3
 
+extern uint8_t f_quit;
+extern int testpmd_fd_copy;
+extern struct cmdline *testpmd_cl;
+
 /*
  * It is used to allocate the memory for hash key.
  * The hash key size is NIC dependent.
@@ -423,6 +428,8 @@ extern uint64_t noisy_lkup_mem_sz;
 extern uint64_t noisy_lkup_num_writes;
 extern uint64_t noisy_lkup_num_reads;
 extern uint64_t noisy_lkup_num_reads_writes;
+extern int proc_id;
+extern unsigned int num_procs;
 
 extern uint8_t dcb_config;
 extern uint8_t dcb_test;
diff --git a/doc/guides/testpmd_app_ug/run_app.rst b/doc/guides/testpmd_app_ug/run_app.rst
index ec1dc7d..7e60e80 100644
--- a/doc/guides/testpmd_app_ug/run_app.rst
+++ b/doc/guides/testpmd_app_ug/run_app.rst
@@ -551,3 +551,104 @@ The command line options are:
     bit 1 - two hairpin ports paired
     bit 0 - two hairpin ports loop
     The default value is 0. Hairpin will use single port mode and implicit Tx flow mode.
+
+
+Testpmd Support Multi Process Command-line Options
+--------------------------------------------------
+
+The following are the command-line options for the testpmd applications(support
+multi process).They must be separated from the EAL options, shown in the previous
+section, with a ``--`` separator:
+
+.. code-block:: console
+
+	primary process:
+	sudo ./dpdk-testpmd -a xxx --proc-type=auto -l 0-1 -- -i --rxq=4 --txq=4 \
+        --num-procs=2 --proc-id=0
+
+	secondary process:
+	sudo ./dpdk-testpmd -a xxx --proc-type=auto -l 2-3 -- -i --rxq=4 --txq=4 \
+        --num-procs=2 --proc-id=1
+
+The command line options are:
+
+*   ``-a, --allow``
+
+    Add a device to the allow list. ``xxx`` means device used which should be the
+    same in primary process and secondary process.
+
+*   ``--proc-type``
+
+    Specify a given process instance as the primary or secondary DPDK instance.
+    ``auto`` set here is OK.
+
+*   ``-l CORELIST``
+
+    List of cores to run on. the corelist should be different in primary process and
+    secondary process.
+
+*   ``--rxq=N``
+
+    Set the number of Rx queues per port to N. N is the sum of queues used by primary
+    and secondary process. Primary process and secondary process should have separate
+    queues, and each should occupy at least one queue. Where N should be the multiple
+    of number of processes.
+
+*   ``--txq=N``
+
+    Set the number of Tx queues per port to N. N is the sum of queues used by primary
+    and secondary process. Primary process and secondary process should have separate
+    queues, and each should occupy at least one queue. Where N should be the multiple
+    of number of processes.
+
+*   ``--num-procs=N``
+
+    The number of processes which will be used.
+
+*   ``--proc-id=id``
+
+    The id of the current process (id < num-procs). id should be different in primary
+    process and secondary process.
+
+Calculation rule for queue:
+All queues are allocated to different processes based on proc_num and proc_id.
+Calculation rule for the Testpmd to allocate queues to each process:
+start(queue start id) = proc_id * nb_q / num_procs；
+end(queue end id) = start + nb_q / num_procs；
+
+For example, if supports 4 txq and rxq
+the 0~1 for primary process
+the 2~3 for secondary process
+
+The number of rings should be a multiple of the number of processes. If not,
+redundant queues will exist after queues are allocated to processes. After RSS is
+enabled, packet loss occurs when traffic is sent to all processes at the same time.
+Some traffic enters redundant queues and cannot be forwarded.
+
+Most dev ops is supported in primary and secondary process. While secondary process
+is not permitted to allocate or release shared memory, so some ops are not supported
+as follows:
+``dev_configure``
+``dev_start``
+``dev_stop``
+``rx_queue_setup``
+``tx_queue_setup``
+``rx_queue_release``
+``tx_queue_release``
+
+So, any command from testpmd which calls those APIs will not be supported in secondary
+process, like:
+``port config all rxq|txq|rxd|txd <value>``
+``port config <port_id> rx_offload xxx on/off ``
+``port config <port_id> tx_offload xxx on/off``
+etc.
+
+RTE_FLOW supported, it applies only on its own process on SW side, but all on HW size.
+stats supported, stats will not change when one quit and start, As they share the same
+buffer to store the stats. Flow rules are maintained in process level: primary and secondary
+has its own flow list(but one flow list in HW). The two can see all the queues, so setting
+the flow rules for the other is OK. Of course, io(receive or transmit packets) in the queue
+from others is not permitted.
+
+RSS supported, Primary process and secondary process has separate queues to use, RSS
+will work in their own queues whether primary and secondary process.
-- 
2.7.4