From e64833f2273ac67becbca10d9f2f1598872dc99e Mon Sep 17 00:00:00 2001 From: Remy Horton Date: Wed, 18 Nov 2015 14:05:16 +0000 Subject: [PATCH] examples/l2fwd-keepalive: add sample application Modified version of l2fwd to demonstrate keep-alive functionality. Signed-off-by: Remy Horton Signed-off-by: Maryam Tahhan Signed-off-by: John J Browne --- MAINTAINERS | 2 + doc/guides/rel_notes/release_2_2.rst | 2 +- doc/guides/sample_app_ug/index.rst | 1 + doc/guides/sample_app_ug/keep_alive.rst | 191 ++++++ examples/Makefile | 1 + examples/l2fwd-keepalive/Makefile | 50 ++ examples/l2fwd-keepalive/main.c | 806 ++++++++++++++++++++++++ 7 files changed, 1052 insertions(+), 1 deletion(-) create mode 100644 doc/guides/sample_app_ug/keep_alive.rst create mode 100644 examples/l2fwd-keepalive/Makefile create mode 100644 examples/l2fwd-keepalive/main.c diff --git a/MAINTAINERS b/MAINTAINERS index 0bfb9417da..8ae688d35e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -112,6 +112,8 @@ Keep alive M: Remy Horton F: lib/librte_eal/common/include/rte_keepalive.h F: lib/librte_eal/common/rte_keepalive.c +F: examples/l2fwd-keepalive/ +F: doc/guides/sample_app_ug/keep_alive.rst Secondary process K: RTE_PROC_ diff --git a/doc/guides/rel_notes/release_2_2.rst b/doc/guides/rel_notes/release_2_2.rst index 56743ca7e8..2d91bdca7a 100644 --- a/doc/guides/rel_notes/release_2_2.rst +++ b/doc/guides/rel_notes/release_2_2.rst @@ -15,7 +15,7 @@ New Features New function rte_ring_free() allows the user to free a ring if it was created with rte_ring_create(). -* **Added keepalive support to EAL.** +* **Added keepalive support to EAL and example application.** * **Added ethdev API to support IEEE1588.** diff --git a/doc/guides/sample_app_ug/index.rst b/doc/guides/sample_app_ug/index.rst index 8ae86c0063..1f62ef52ad 100644 --- a/doc/guides/sample_app_ug/index.rst +++ b/doc/guides/sample_app_ug/index.rst @@ -49,6 +49,7 @@ Sample Applications User Guide ipv4_multicast ip_reassembly kernel_nic_interface + keep_alive l2_forward_job_stats l2_forward_real_virtual l3_forward diff --git a/doc/guides/sample_app_ug/keep_alive.rst b/doc/guides/sample_app_ug/keep_alive.rst new file mode 100644 index 0000000000..080811b6c1 --- /dev/null +++ b/doc/guides/sample_app_ug/keep_alive.rst @@ -0,0 +1,191 @@ + +.. BSD LICENSE + Copyright(c) 2015 Intel Corporation. All rights reserved. + All rights reserved. + + Redistribution and use in source and binary forms, with or without + modification, are permitted provided that the following conditions + are met: + + * Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in + the documentation and/or other materials provided with the + distribution. + * Neither the name of Intel Corporation nor the names of its + contributors may be used to endorse or promote products derived + from this software without specific prior written permission. + + THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +Keep Alive Sample Application +============================= + +The Keep Alive application is a simple example of a +heartbeat/watchdog for packet processing cores. It demonstrates how +to detect 'failed' DPDK cores and notify a fault management entity +of this failure. Its purpose is to ensure the failure of the core +does not result in a fault that is not detectable by a management +entity. + + +Overview +-------- + +The application demonstrates how to protect against 'silent outages' +on packet processing cores. A Keep Alive Monitor Agent Core (master) +monitors the state of packet processing cores (worker cores) by +dispatching pings at a regular time interval (default is 5ms) and +monitoring the state of the cores. Cores states are: Alive, MIA, Dead +or Buried. MIA indicates a missed ping, and Dead indicates two missed +pings within the specified time interval. When a core is Dead, a +callback function is invoked to restart the packet processing core; +A real life application might use this callback function to notify a +higher level fault management entity of the core failure in order to +take the appropriate corrective action. + +Note: Only the worker cores are monitored. A local (on the host) mechanism +or agent to supervise the Keep Alive Monitor Agent Core DPDK core is required +to detect its failure. + +Note: This application is based on the L2 forwarding application. As +such, the initialization and run-time paths are very similar to those +of the L2 forwarding application. + +Compiling the Application +------------------------- + +To compile the application: + +#. Go to the sample application directory: + + .. code-block:: console + + export RTE_SDK=/path/to/rte_sdk cd ${RTE_SDK}/examples/keep_alive + +#. Set the target (a default target is used if not specified). For example: + + .. code-block:: console + + export RTE_TARGET=x86_64-native-linuxapp-gcc + + See the *DPDK Getting Started Guide* for possible RTE_TARGET values. + +#. Build the application: + + .. code-block:: console + + make + +Running the Application +----------------------- + +The application has a number of command line options: + +.. code-block:: console + + ./build/l2fwd-keepalive [EAL options] \ + -- -p PORTMASK [-q NQ] [-K PERIOD] [-T PERIOD] + +where, + +* ``p PORTMASK``: A hexadecimal bitmask of the ports to configure + +* ``q NQ``: A number of queues (=ports) per lcore (default is 1) + +* ``K PERIOD``: Heartbeat check period in ms(5ms default; 86400 max) + +* ``T PERIOD``: statistics will be refreshed each PERIOD seconds (0 to + disable, 10 default, 86400 maximum). + +To run the application in linuxapp environment with 4 lcores, 16 ports +8 RX queues per lcore and a ping interval of 10ms, issue the command: + +.. code-block:: console + + ./build/l2fwd-keepalive -c f -n 4 -- -q 8 -p ffff -K 10 + +Refer to the *DPDK Getting Started Guide* for general information on +running applications and the Environment Abstraction Layer (EAL) +options. + + +Explanation +----------- + +The following sections provide some explanation of the The +Keep-Alive/'Liveliness' conceptual scheme. As mentioned in the +overview section, the initialization and run-time paths are very +similar to those of the L2 forwarding application (see Chapter 9 +"L2 Forwarding Sample Application (in Real and Virtualized +Environments)" for more information). + +The Keep-Alive/'Liveliness' conceptual scheme: + +* A Keep- Alive Agent Runs every N Milliseconds. + +* DPDK Cores respond to the keep-alive agent. + +* If keep-alive agent detects time-outs, it notifies the + fault management entity through a callback function. + +The following sections provide some explanation of the code aspects +that are specific to the Keep Alive sample application. + +The heartbeat functionality is initialized with a struct +rte_heartbeat and the callback function to invoke in the +case of a timeout. + +.. code-block:: c + + rte_global_keepalive_info = rte_keepalive_create(&dead_core, NULL); + if (rte_global_hbeat_info == NULL) + rte_exit(EXIT_FAILURE, "keepalive_create() failed"); + +The function that issues the pings hbeat_dispatch_pings() +is configured to run every check_period milliseconds. + +.. code-block:: c + + if (rte_timer_reset(&hb_timer, + (check_period * rte_get_timer_hz()) / 1000, + PERIODICAL, + rte_lcore_id(), + &hbeat_dispatch_pings, rte_global_keepalive_info + ) != 0 ) + rte_exit(EXIT_FAILURE, "Keepalive setup failure.\n"); + +The rest of the initialization and run-time path follows +the same paths as the the L2 forwarding application. The only +addition to the main processing loop is the mark alive +functionality and the example random failures. + +.. code-block:: c + + rte_keepalive_mark_alive(&rte_global_hbeat_info); + cur_tsc = rte_rdtsc(); + + /* Die randomly within 7 secs for demo purposes.. */ + if (cur_tsc - tsc_initial > tsc_lifetime) + break; + +The rte_keepalive_mark_alive function simply sets the core state to alive. + +.. code-block:: c + + static inline void + rte_keepalive_mark_alive(struct rte_heartbeat *keepcfg) + { + keepcfg->state_flags[rte_lcore_id()] = 1; + } diff --git a/examples/Makefile b/examples/Makefile index 830e31a669..d4f19328be 100644 --- a/examples/Makefile +++ b/examples/Makefile @@ -53,6 +53,7 @@ DIRS-$(CONFIG_RTE_LIBRTE_KNI) += kni DIRS-y += l2fwd DIRS-$(CONFIG_RTE_LIBRTE_IVSHMEM) += l2fwd-ivshmem DIRS-$(CONFIG_RTE_LIBRTE_JOBSTATS) += l2fwd-jobstats +DIRS-y += l2fwd-keepalive DIRS-y += l3fwd DIRS-$(CONFIG_RTE_LIBRTE_ACL) += l3fwd-acl DIRS-$(CONFIG_RTE_LIBRTE_POWER) += l3fwd-power diff --git a/examples/l2fwd-keepalive/Makefile b/examples/l2fwd-keepalive/Makefile new file mode 100644 index 0000000000..568edcb432 --- /dev/null +++ b/examples/l2fwd-keepalive/Makefile @@ -0,0 +1,50 @@ +# BSD LICENSE +# +# Copyright(c) 2010-2014 Intel Corporation. All rights reserved. +# All rights reserved. +# +# Redistribution and use in source and binary forms, with or without +# modification, are permitted provided that the following conditions +# are met: +# +# * Redistributions of source code must retain the above copyright +# notice, this list of conditions and the following disclaimer. +# * Redistributions in binary form must reproduce the above copyright +# notice, this list of conditions and the following disclaimer in +# the documentation and/or other materials provided with the +# distribution. +# * Neither the name of Intel Corporation nor the names of its +# contributors may be used to endorse or promote products derived +# from this software without specific prior written permission. +# +# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +ifeq ($(RTE_SDK),) +$(error "Please define RTE_SDK environment variable") +endif + +# Default target, can be overridden by command line or environment +RTE_TARGET ?= x86_64-native-linuxapp-gcc + +include $(RTE_SDK)/mk/rte.vars.mk + +# binary name +APP = l2fwd-keepalive + +# all source are stored in SRCS-y +SRCS-y := main.c + +CFLAGS += -O3 +CFLAGS += $(WERROR_FLAGS) + +include $(RTE_SDK)/mk/rte.extapp.mk diff --git a/examples/l2fwd-keepalive/main.c b/examples/l2fwd-keepalive/main.c new file mode 100644 index 0000000000..8d7b09ee23 --- /dev/null +++ b/examples/l2fwd-keepalive/main.c @@ -0,0 +1,806 @@ +/*- + * BSD LICENSE + * + * Copyright(c) 2010-2015 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define RTE_LOGTYPE_L2FWD RTE_LOGTYPE_USER1 + +#define NB_MBUF 8192 + +#define MAX_PKT_BURST 32 +#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */ + +/* + * Configurable number of RX/TX ring descriptors + */ +#define RTE_TEST_RX_DESC_DEFAULT 128 +#define RTE_TEST_TX_DESC_DEFAULT 512 +static uint16_t nb_rxd = RTE_TEST_RX_DESC_DEFAULT; +static uint16_t nb_txd = RTE_TEST_TX_DESC_DEFAULT; + +/* ethernet addresses of ports */ +static struct ether_addr l2fwd_ports_eth_addr[RTE_MAX_ETHPORTS]; + +/* mask of enabled ports */ +static uint32_t l2fwd_enabled_port_mask; + +/* list of enabled ports */ +static uint32_t l2fwd_dst_ports[RTE_MAX_ETHPORTS]; + +static unsigned int l2fwd_rx_queue_per_lcore = 1; + +struct mbuf_table { + unsigned len; + struct rte_mbuf *m_table[MAX_PKT_BURST]; +}; + +#define MAX_RX_QUEUE_PER_LCORE 16 +#define MAX_TX_QUEUE_PER_PORT 16 +struct lcore_queue_conf { + unsigned n_rx_port; + unsigned rx_port_list[MAX_RX_QUEUE_PER_LCORE]; + struct mbuf_table tx_mbufs[RTE_MAX_ETHPORTS]; + +} __rte_cache_aligned; +struct lcore_queue_conf lcore_queue_conf[RTE_MAX_LCORE]; + +static const struct rte_eth_conf port_conf = { + .rxmode = { + .split_hdr_size = 0, + .header_split = 0, /**< Header Split disabled */ + .hw_ip_checksum = 0, /**< IP checksum offload disabled */ + .hw_vlan_filter = 0, /**< VLAN filtering disabled */ + .jumbo_frame = 0, /**< Jumbo Frame Support disabled */ + .hw_strip_crc = 0, /**< CRC stripped by hardware */ + }, + .txmode = { + .mq_mode = ETH_MQ_TX_NONE, + }, +}; + +struct rte_mempool *l2fwd_pktmbuf_pool = NULL; + +/* Per-port statistics struct */ +struct l2fwd_port_statistics { + uint64_t tx; + uint64_t rx; + uint64_t dropped; +} __rte_cache_aligned; +struct l2fwd_port_statistics port_statistics[RTE_MAX_ETHPORTS]; + +/* A tsc-based timer responsible for triggering statistics printout */ +#define TIMER_MILLISECOND 1 +#define MAX_TIMER_PERIOD 86400 /* 1 day max */ +static int64_t timer_period = 10 * TIMER_MILLISECOND * 1000; /* 10 seconds */ +static int64_t check_period = 5; /* default check cycle is 5ms */ + +/* Keepalive structure */ +struct rte_keepalive *rte_global_keepalive_info; + +/* Print out statistics on packets dropped */ +static void +print_stats(__attribute__((unused)) struct rte_timer *ptr_timer, + __attribute__((unused)) void *ptr_data) +{ + uint64_t total_packets_dropped, total_packets_tx, total_packets_rx; + unsigned portid; + + total_packets_dropped = 0; + total_packets_tx = 0; + total_packets_rx = 0; + + const char clr[] = { 27, '[', '2', 'J', '\0' }; + const char topLeft[] = { 27, '[', '1', ';', '1', 'H', '\0' }; + + /* Clear screen and move to top left */ + printf("%s%s", clr, topLeft); + + printf("\nPort statistics ===================================="); + + for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) { + /* skip disabled ports */ + if ((l2fwd_enabled_port_mask & (1 << portid)) == 0) + continue; + printf("\nStatistics for port %u ------------------------------" + "\nPackets sent: %24"PRIu64 + "\nPackets received: %20"PRIu64 + "\nPackets dropped: %21"PRIu64, + portid, + port_statistics[portid].tx, + port_statistics[portid].rx, + port_statistics[portid].dropped); + + total_packets_dropped += port_statistics[portid].dropped; + total_packets_tx += port_statistics[portid].tx; + total_packets_rx += port_statistics[portid].rx; + } + printf("\nAggregate statistics ===============================" + "\nTotal packets sent: %18"PRIu64 + "\nTotal packets received: %14"PRIu64 + "\nTotal packets dropped: %15"PRIu64, + total_packets_tx, + total_packets_rx, + total_packets_dropped); + printf("\n====================================================\n"); +} + +/* Send the burst of packets on an output interface */ +static int +l2fwd_send_burst(struct lcore_queue_conf *qconf, unsigned n, uint8_t port) +{ + struct rte_mbuf **m_table; + unsigned ret; + unsigned queueid = 0; + + m_table = (struct rte_mbuf **)qconf->tx_mbufs[port].m_table; + + ret = rte_eth_tx_burst(port, (uint16_t) queueid, m_table, (uint16_t) n); + port_statistics[port].tx += ret; + if (unlikely(ret < n)) { + port_statistics[port].dropped += (n - ret); + do { + rte_pktmbuf_free(m_table[ret]); + } while (++ret < n); + } + + return 0; +} + +/* Enqueue packets for TX and prepare them to be sent */ +static int +l2fwd_send_packet(struct rte_mbuf *m, uint8_t port) +{ + unsigned lcore_id, len; + struct lcore_queue_conf *qconf; + + lcore_id = rte_lcore_id(); + + qconf = &lcore_queue_conf[lcore_id]; + len = qconf->tx_mbufs[port].len; + qconf->tx_mbufs[port].m_table[len] = m; + len++; + + /* enough pkts to be sent */ + if (unlikely(len == MAX_PKT_BURST)) { + l2fwd_send_burst(qconf, MAX_PKT_BURST, port); + len = 0; + } + + qconf->tx_mbufs[port].len = len; + return 0; +} + +static void +l2fwd_simple_forward(struct rte_mbuf *m, unsigned portid) +{ + struct ether_hdr *eth; + void *tmp; + unsigned dst_port; + + dst_port = l2fwd_dst_ports[portid]; + eth = rte_pktmbuf_mtod(m, struct ether_hdr *); + + /* 02:00:00:00:00:xx */ + tmp = ð->d_addr.addr_bytes[0]; + *((uint64_t *)tmp) = 0x000000000002 + ((uint64_t)dst_port << 40); + + /* src addr */ + ether_addr_copy(&l2fwd_ports_eth_addr[dst_port], ð->s_addr); + + l2fwd_send_packet(m, (uint8_t) dst_port); +} + +/* main processing loop */ +static void +l2fwd_main_loop(void) +{ + struct rte_mbuf *pkts_burst[MAX_PKT_BURST]; + struct rte_mbuf *m; + unsigned lcore_id; + uint64_t prev_tsc, diff_tsc, cur_tsc; + unsigned i, j, portid, nb_rx; + struct lcore_queue_conf *qconf; + const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) + / US_PER_S * BURST_TX_DRAIN_US; + + prev_tsc = 0; + + lcore_id = rte_lcore_id(); + qconf = &lcore_queue_conf[lcore_id]; + + if (qconf->n_rx_port == 0) { + RTE_LOG(INFO, L2FWD, "lcore %u has nothing to do\n", lcore_id); + return; + } + + RTE_LOG(INFO, L2FWD, "entering main loop on lcore %u\n", lcore_id); + + for (i = 0; i < qconf->n_rx_port; i++) { + + portid = qconf->rx_port_list[i]; + RTE_LOG(INFO, L2FWD, " -- lcoreid=%u portid=%u\n", lcore_id, + portid); + } + + uint64_t tsc_initial = rte_rdtsc(); + uint64_t tsc_lifetime = (rand()&0x07) * rte_get_tsc_hz(); + + while (1) { + /* Keepalive heartbeat */ + rte_keepalive_mark_alive(rte_global_keepalive_info); + + cur_tsc = rte_rdtsc(); + + /* + * Die randomly within 7 secs for demo purposes if + * keepalive enabled + */ + if (check_period > 0 && cur_tsc - tsc_initial > tsc_lifetime) + break; + + /* + * TX burst queue drain + */ + diff_tsc = cur_tsc - prev_tsc; + if (unlikely(diff_tsc > drain_tsc)) { + + for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) { + if (qconf->tx_mbufs[portid].len == 0) + continue; + l2fwd_send_burst(&lcore_queue_conf[lcore_id], + qconf->tx_mbufs[portid].len, + (uint8_t) portid); + qconf->tx_mbufs[portid].len = 0; + } + + prev_tsc = cur_tsc; + } + + /* + * Read packet from RX queues + */ + for (i = 0; i < qconf->n_rx_port; i++) { + + portid = qconf->rx_port_list[i]; + nb_rx = rte_eth_rx_burst((uint8_t) portid, 0, + pkts_burst, MAX_PKT_BURST); + + port_statistics[portid].rx += nb_rx; + + for (j = 0; j < nb_rx; j++) { + m = pkts_burst[j]; + rte_prefetch0(rte_pktmbuf_mtod(m, void *)); + l2fwd_simple_forward(m, portid); + } + } + } +} + +static int +l2fwd_launch_one_lcore(__attribute__((unused)) void *dummy) +{ + l2fwd_main_loop(); + return 0; +} + +/* display usage */ +static void +l2fwd_usage(const char *prgname) +{ + printf("%s [EAL options] -- -p PORTMASK [-q NQ]\n" + " -p PORTMASK: hexadecimal bitmask of ports to configure\n" + " -q NQ: number of queue (=ports) per lcore (default is 1)\n" + " -K PERIOD: Keepalive check period (5 default; 86400 max)\n" + " -T PERIOD: statistics will be refreshed each PERIOD seconds (0 to disable, 10 default, 86400 maximum)\n", + prgname); +} + +static int +l2fwd_parse_portmask(const char *portmask) +{ + char *end = NULL; + unsigned long pm; + + /* parse hexadecimal string */ + pm = strtoul(portmask, &end, 16); + if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + + if (pm == 0) + return -1; + + return pm; +} + +static unsigned int +l2fwd_parse_nqueue(const char *q_arg) +{ + char *end = NULL; + unsigned long n; + + /* parse hexadecimal string */ + n = strtoul(q_arg, &end, 10); + if ((q_arg[0] == '\0') || (end == NULL) || (*end != '\0')) + return 0; + if (n == 0) + return 0; + if (n >= MAX_RX_QUEUE_PER_LCORE) + return 0; + + return n; +} + +static int +l2fwd_parse_timer_period(const char *q_arg) +{ + char *end = NULL; + int n; + + /* parse number string */ + n = strtol(q_arg, &end, 10); + if ((q_arg[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + if (n >= MAX_TIMER_PERIOD) + return -1; + + return n; +} + +static int +l2fwd_parse_check_period(const char *q_arg) +{ + char *end = NULL; + int n; + + /* parse number string */ + n = strtol(q_arg, &end, 10); + if ((q_arg[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + if (n >= MAX_TIMER_PERIOD) + return -1; + + return n; +} + +/* Parse the argument given in the command line of the application */ +static int +l2fwd_parse_args(int argc, char **argv) +{ + int opt, ret; + char **argvopt; + int option_index; + char *prgname = argv[0]; + static struct option lgopts[] = { + {NULL, 0, 0, 0} + }; + + argvopt = argv; + + while ((opt = getopt_long(argc, argvopt, "p:q:T:K:", + lgopts, &option_index)) != EOF) { + + switch (opt) { + /* portmask */ + case 'p': + l2fwd_enabled_port_mask = l2fwd_parse_portmask(optarg); + if (l2fwd_enabled_port_mask == 0) { + printf("invalid portmask\n"); + l2fwd_usage(prgname); + return -1; + } + break; + + /* nqueue */ + case 'q': + l2fwd_rx_queue_per_lcore = l2fwd_parse_nqueue(optarg); + if (l2fwd_rx_queue_per_lcore == 0) { + printf("invalid queue number\n"); + l2fwd_usage(prgname); + return -1; + } + break; + + /* timer period */ + case 'T': + timer_period = l2fwd_parse_timer_period(optarg) + * 1000 * TIMER_MILLISECOND; + if (timer_period < 0) { + printf("invalid timer period\n"); + l2fwd_usage(prgname); + return -1; + } + break; + + /* Check period */ + case 'K': + check_period = l2fwd_parse_check_period(optarg); + if (check_period < 0) { + printf("invalid check period\n"); + l2fwd_usage(prgname); + return -1; + } + break; + + /* long options */ + case 0: + l2fwd_usage(prgname); + return -1; + + default: + l2fwd_usage(prgname); + return -1; + } + } + + if (optind >= 0) + argv[optind-1] = prgname; + + ret = optind-1; + optind = 0; /* reset getopt lib */ + return ret; +} + +/* Check the link status of all ports in up to 9s, and print them finally */ +static void +check_all_ports_link_status(uint8_t port_num, uint32_t port_mask) +{ +#define CHECK_INTERVAL 100 /* 100ms */ +#define MAX_CHECK_TIME 90 /* 9s (90 * 100ms) in total */ + uint8_t portid, count, all_ports_up, print_flag = 0; + struct rte_eth_link link; + + printf("\nChecking link status"); + fflush(stdout); + for (count = 0; count <= MAX_CHECK_TIME; count++) { + all_ports_up = 1; + for (portid = 0; portid < port_num; portid++) { + if ((port_mask & (1 << portid)) == 0) + continue; + memset(&link, 0, sizeof(link)); + rte_eth_link_get_nowait(portid, &link); + /* print link status if flag set */ + if (print_flag == 1) { + if (link.link_status) + printf("Port %d Link Up - speed %u " + "Mbps - %s\n", (uint8_t)portid, + (unsigned)link.link_speed, + (link.link_duplex == ETH_LINK_FULL_DUPLEX) ? + ("full-duplex") : ("half-duplex\n")); + else + printf("Port %d Link Down\n", + (uint8_t)portid); + continue; + } + /* clear all_ports_up flag if any link down */ + if (link.link_status == 0) { + all_ports_up = 0; + break; + } + } + /* after finally printing all link status, get out */ + if (print_flag == 1) + break; + + if (all_ports_up == 0) { + printf("."); + fflush(stdout); + rte_delay_ms(CHECK_INTERVAL); + } + + /* set the print_flag if all ports up or timeout */ + if (all_ports_up == 1 || count == (MAX_CHECK_TIME - 1)) { + print_flag = 1; + printf("done\n"); + } + } +} + +static void +dead_core(__attribute__((unused)) void *ptr_data, const int id_core) +{ + printf("Dead core %i - restarting..\n", id_core); + if (rte_eal_get_lcore_state(id_core) == FINISHED) { + rte_eal_wait_lcore(id_core); + rte_eal_remote_launch(l2fwd_launch_one_lcore, NULL, id_core); + } else { + printf("..false positive!\n"); + } +} + +int +main(int argc, char **argv) +{ + struct lcore_queue_conf *qconf; + struct rte_eth_dev_info dev_info; + int ret; + uint8_t nb_ports; + uint8_t nb_ports_available; + uint8_t portid, last_port; + unsigned lcore_id, rx_lcore_id; + unsigned nb_ports_in_mask = 0; + + /* init EAL */ + ret = rte_eal_init(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid EAL arguments\n"); + argc -= ret; + argv += ret; + + l2fwd_enabled_port_mask = 0; + + /* parse application arguments (after the EAL ones) */ + ret = l2fwd_parse_args(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid L2FWD arguments\n"); + + /* create the mbuf pool */ + l2fwd_pktmbuf_pool = rte_pktmbuf_pool_create("mbuf_pool", NB_MBUF, 32, + 0, RTE_MBUF_DEFAULT_BUF_SIZE, rte_socket_id()); + if (l2fwd_pktmbuf_pool == NULL) + rte_exit(EXIT_FAILURE, "Cannot init mbuf pool\n"); + + nb_ports = rte_eth_dev_count(); + if (nb_ports == 0) + rte_exit(EXIT_FAILURE, "No Ethernet ports - bye\n"); + + if (nb_ports > RTE_MAX_ETHPORTS) + nb_ports = RTE_MAX_ETHPORTS; + + /* reset l2fwd_dst_ports */ + for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) + l2fwd_dst_ports[portid] = 0; + last_port = 0; + + /* + * Each logical core is assigned a dedicated TX queue on each port. + */ + for (portid = 0; portid < nb_ports; portid++) { + /* skip ports that are not enabled */ + if ((l2fwd_enabled_port_mask & (1 << portid)) == 0) + continue; + + if (nb_ports_in_mask % 2) { + l2fwd_dst_ports[portid] = last_port; + l2fwd_dst_ports[last_port] = portid; + } else + last_port = portid; + + nb_ports_in_mask++; + + rte_eth_dev_info_get(portid, &dev_info); + } + if (nb_ports_in_mask % 2) { + printf("Notice: odd number of ports in portmask.\n"); + l2fwd_dst_ports[last_port] = last_port; + } + + rx_lcore_id = 1; + qconf = NULL; + + /* Initialize the port/queue configuration of each logical core */ + for (portid = 0; portid < nb_ports; portid++) { + /* skip ports that are not enabled */ + if ((l2fwd_enabled_port_mask & (1 << portid)) == 0) + continue; + + /* get the lcore_id for this port */ + while (rte_lcore_is_enabled(rx_lcore_id) == 0 || + lcore_queue_conf[rx_lcore_id].n_rx_port == + l2fwd_rx_queue_per_lcore) { + rx_lcore_id++; + if (rx_lcore_id >= RTE_MAX_LCORE) + rte_exit(EXIT_FAILURE, "Not enough cores\n"); + } + + if (qconf != &lcore_queue_conf[rx_lcore_id]) + /* Assigned a new logical core in the loop above. */ + qconf = &lcore_queue_conf[rx_lcore_id]; + + qconf->rx_port_list[qconf->n_rx_port] = portid; + qconf->n_rx_port++; + printf("Lcore %u: RX port %u\n", + rx_lcore_id, (unsigned) portid); + } + + nb_ports_available = nb_ports; + + /* Initialise each port */ + for (portid = 0; portid < nb_ports; portid++) { + /* skip ports that are not enabled */ + if ((l2fwd_enabled_port_mask & (1 << portid)) == 0) { + printf("Skipping disabled port %u\n", + (unsigned) portid); + nb_ports_available--; + continue; + } + /* init port */ + printf("Initializing port %u... ", (unsigned) portid); + fflush(stdout); + ret = rte_eth_dev_configure(portid, 1, 1, &port_conf); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "Cannot configure device: err=%d, port=%u\n", + ret, (unsigned) portid); + + rte_eth_macaddr_get(portid, &l2fwd_ports_eth_addr[portid]); + + /* init one RX queue */ + fflush(stdout); + ret = rte_eth_rx_queue_setup(portid, 0, nb_rxd, + rte_eth_dev_socket_id(portid), + NULL, + l2fwd_pktmbuf_pool); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "rte_eth_rx_queue_setup:err=%d, port=%u\n", + ret, (unsigned) portid); + + /* init one TX queue on each port */ + fflush(stdout); + ret = rte_eth_tx_queue_setup(portid, 0, nb_txd, + rte_eth_dev_socket_id(portid), + NULL); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "rte_eth_tx_queue_setup:err=%d, port=%u\n", + ret, (unsigned) portid); + + /* Start device */ + ret = rte_eth_dev_start(portid); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "rte_eth_dev_start:err=%d, port=%u\n", + ret, (unsigned) portid); + + rte_eth_promiscuous_enable(portid); + + printf("Port %u, MAC address: " + "%02X:%02X:%02X:%02X:%02X:%02X\n\n", + (unsigned) portid, + l2fwd_ports_eth_addr[portid].addr_bytes[0], + l2fwd_ports_eth_addr[portid].addr_bytes[1], + l2fwd_ports_eth_addr[portid].addr_bytes[2], + l2fwd_ports_eth_addr[portid].addr_bytes[3], + l2fwd_ports_eth_addr[portid].addr_bytes[4], + l2fwd_ports_eth_addr[portid].addr_bytes[5]); + + /* initialize port stats */ + memset(&port_statistics, 0, sizeof(port_statistics)); + } + + if (!nb_ports_available) { + rte_exit(EXIT_FAILURE, + "All available ports are disabled. Please set portmask.\n"); + } + + check_all_ports_link_status(nb_ports, l2fwd_enabled_port_mask); + + struct rte_timer hb_timer, stats_timer; + + rte_timer_subsystem_init(); + rte_timer_init(&stats_timer); + + if (check_period > 0) { + rte_global_keepalive_info = + rte_keepalive_create(&dead_core, NULL); + if (rte_global_keepalive_info == NULL) + rte_exit(EXIT_FAILURE, "init_keep_alive() failed"); + rte_timer_init(&hb_timer); + if (rte_timer_reset(&hb_timer, + (check_period * rte_get_timer_hz()) / 1000, + PERIODICAL, + rte_lcore_id(), + (void(*)(struct rte_timer*, void*)) + &rte_keepalive_dispatch_pings, + rte_global_keepalive_info + ) != 0 ) + rte_exit(EXIT_FAILURE, "Keepalive setup failure.\n"); + } + if (timer_period > 0) { + if (rte_timer_reset(&stats_timer, + (timer_period * rte_get_timer_hz()) / 1000, + PERIODICAL, + rte_lcore_id(), + &print_stats, NULL + ) != 0 ) + rte_exit(EXIT_FAILURE, "Stats setup failure.\n"); + } + /* launch per-lcore init on every slave lcore */ + RTE_LCORE_FOREACH_SLAVE(lcore_id) { + struct lcore_queue_conf *qconf = &lcore_queue_conf[lcore_id]; + + if (qconf->n_rx_port == 0) + RTE_LOG(INFO, L2FWD, + "lcore %u has nothing to do\n", + lcore_id + ); + else { + rte_eal_remote_launch( + l2fwd_launch_one_lcore, + NULL, + lcore_id + ); + rte_keepalive_register_core(rte_global_keepalive_info, + lcore_id); + } + } + for (;;) { + rte_timer_manage(); + rte_delay_ms(5); + } + + RTE_LCORE_FOREACH_SLAVE(lcore_id) { + if (rte_eal_wait_lcore(lcore_id) < 0) + return -1; + } + + return 0; +}