From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id C542BA0519; Fri, 3 Jul 2020 17:18:46 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id A7BDB1DC51; Fri, 3 Jul 2020 17:18:46 +0200 (CEST) Received: from lizzard.sbs.de (lizzard.sbs.de [194.138.37.39]) by dpdk.org (Postfix) with ESMTP id 0F4C01DBED for ; Fri, 3 Jul 2020 17:18:45 +0200 (CEST) Received: from mail1.sbs.de (mail1.sbs.de [192.129.41.35]) by lizzard.sbs.de (8.15.2/8.15.2) with ESMTPS id 063FIiKn007201 (version=TLSv1.2 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Fri, 3 Jul 2020 17:18:44 +0200 Received: from MD1UYK9C-docker.ad001.siemens.net ([139.21.146.159]) by mail1.sbs.de (8.15.2/8.15.2) with ESMTP id 063FIVj8008929; Fri, 3 Jul 2020 17:18:44 +0200 From: Felix Moessbauer To: thomas@monjalon.net Cc: dev@dpdk.org, Felix Moessbauer , Henning Schild Date: Fri, 3 Jul 2020 17:18:11 +0200 Message-Id: <20200703151811.38372-2-felix.moessbauer@siemens.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20200703151811.38372-1-felix.moessbauer@siemens.com> References: <20200703151811.38372-1-felix.moessbauer@siemens.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Subject: [dpdk-dev] [RFC PATCH 1/1] Add l2reflect measurement application X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" The l2reflect application implements a ping-pong benchmark to measure the latency between two instances. For communication, we use raw ethernet and send one packet at a time. The timing data is collected locally and min/max/avg values are displayed in a TUI. Finally, a histogram of the latencies is printed which can be further processed with the jitterdebugger visualization scripts. To debug latency spikes, a max threshold can be defined. If it is hit, a trace point is created on both instances. Signed-off-by: Felix Moessbauer Signed-off-by: Henning Schild --- examples/l2reflect/Makefile | 31 ++ examples/l2reflect/l2reflect.h | 56 +++ examples/l2reflect/main.c | 833 +++++++++++++++++++++++++++++++++ examples/l2reflect/meson.build | 21 + examples/l2reflect/stats.c | 198 ++++++++ examples/l2reflect/stats.h | 67 +++ examples/meson.build | 1 + 7 files changed, 1207 insertions(+) create mode 100644 examples/l2reflect/Makefile create mode 100644 examples/l2reflect/l2reflect.h create mode 100644 examples/l2reflect/main.c create mode 100644 examples/l2reflect/meson.build create mode 100644 examples/l2reflect/stats.c create mode 100644 examples/l2reflect/stats.h diff --git a/examples/l2reflect/Makefile b/examples/l2reflect/Makefile new file mode 100644 index 000000000..4f3e74236 --- /dev/null +++ b/examples/l2reflect/Makefile @@ -0,0 +1,31 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2020 Siemens AG + +APP = l2reflect +SOURCES := main.c stats.c +OBJECTS = $(SOURCES:%.c=%.o) + +ifneq ($(RTE_SDK),) + RTE_TARGET ?= $(notdir $(abspath $(dir $(firstword $(wildcard $(RTE_SDK)/*/.config))))) + include $(RTE_SDK)/mk/rte.vars.mk + SRCS-y := $(SOURCES) + CFLAGS += -O3 -Wall -Wpedantic -Werror +else + CFLAGS += -O3 $(shell pkg-config --cflags libdpdk) + LDFLAGS += -Wl,-static $(shell pkg-config --static --libs libdpdk) +endif +CFLAGS += -DRTE_HAS_CJSON -Wstrict-prototypes -Wsign-compare -Wunused-parameter -Wunused-parameter +LDFLAGS += -lcjson + +ifeq ($(RTE_SDK),) +%.o: %.c Makefile + $(CC) -c -o $@ $< $(CFLAGS) + +$(APP): $(OBJECTS) Makefile + $(CC) -o $@ $(OBJECTS) $(LDFLAGS) + +clean: + rm -f $(APP) $(OBJECTS) +else + include $(RTE_SDK)/mk/rte.extapp.mk +endif diff --git a/examples/l2reflect/l2reflect.h b/examples/l2reflect/l2reflect.h new file mode 100644 index 000000000..04c49d641 --- /dev/null +++ b/examples/l2reflect/l2reflect.h @@ -0,0 +1,56 @@ +/* + * SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2020 Siemens AG + * + * authors: + * Felix Moessbauer + * Henning Schild + */ +#ifndef _L2REFLECT_H_ +#define _L2REFLECT_H_ +#define MAGIC_TRACE_PAYLOAD 0xd00faffeaffed00full +/* IEEE Std 802 - Local Experimental Ethertype */ +#define ETHER_TYPE_L2REFLECT 0x88B5 +/* Used to compare MAC addresses. */ +#define MAC_ADDR_CMP 0xFFFFFFFFFFFFull + +enum { TRACE_TYPE_DATA, + TRACE_TYPE_HELO, + TRACE_TYPE_EHLO, + TRACE_TYPE_RSET, + TRACE_TYPE_QUIT, +}; + +struct my_magic_packet { + struct rte_ether_hdr eth; + uint8_t type; + uint64_t magic; + uint64_t breakval; +}; + +enum STATE { + S_ELECT_LEADER = 1, // elect the initial sender + S_RESET_TRX = 2, // reset the counters + S_RUNNING = 4, // measurement S_RUNNING + S_LOCAL_TERM = 8, // terminated by local event + S_REMOTE_TERM = 16, // terminated by remote event +}; + +int l2reflect_hist; +atomic_int l2reflect_output_hist; +uint64_t l2reflect_sleep_msec; +uint16_t l2reflect_port_number; +atomic_int l2reflect_state; +struct rte_ether_addr l2reflect_port_eth_addr; +struct rte_ether_addr l2reflect_remote_eth_addr; + +/* + * Compares a packet destination MAC address to a device MAC address. + */ +static inline int __attribute__((always_inline)) +ether_addr_cmp(struct rte_ether_addr *ea, struct rte_ether_addr *eb) +{ + return ((*(uint64_t *)ea ^ *(uint64_t *)eb) & MAC_ADDR_CMP) == 0; +} + +#endif // _L2REFLECT_H_ diff --git a/examples/l2reflect/main.c b/examples/l2reflect/main.c new file mode 100644 index 000000000..8e02bd5fe --- /dev/null +++ b/examples/l2reflect/main.c @@ -0,0 +1,833 @@ +/* + * SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2020 Siemens AG + * + * authors: + * Felix Moessbauer + * Henning Schild + * + * launch (non-rt kernel): l2reflect --lcores 0@0,1@6 -n 1 + * launch (rt kernel): l2reflect --lcores 0@0,1@6 -n 1 -- -P 50 -r -l + * + * The l2reflect application implements a ping-pong benchmark to + * measure the latency between two instances. For communication, + * we use raw ethernet and send one packet at a time. The timing data + * is collected locally and min/max/avg values are displayed in a TUI. + * Finally, a histogram of the latencies is printed which can be + * further processed with the jitterdebugger visualization scripts. + * To debug latency spikes, a max threshold can be defined. + * If it is hit, a trace point is created on both instances. + */ + +#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 +#include +#include + +#include "l2reflect.h" +#include "stats.h" + +#define RTE_LOGTYPE_L2REFLECT RTE_LOGTYPE_USER1 + +#define NSEC_PER_SEC 1000000000 + +#define MBUF_SIZE (2048 + sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM) +#define NB_MBUF 2047 + +#define MAX_PKT_BURST 32 +/* warmup a few round befor starting the measurement */ +#define WARMUP_ROUNDS 42 + +#define MAX(x, y) (((x) > (y)) ? (x) : (y)) +#define MIN(x, y) (((x) < (y)) ? (x) : (y)) + +static struct timespec last_sent, last_recv; +static int quiet, disable_int, priority, policy, l2reflect_mlock, + l2reflect_interrupt, trace_fd; + +static atomic_int sleep_start = 0; + +static uint64_t rounds = 0; +static int quiet, disable_int, priority, policy, l2reflect_mlock, + l2reflect_interrupt, trace_fd; + +/* + * 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; + +static struct rte_eth_conf port_conf = { + .rxmode = { + .split_hdr_size = 0, + }, + .txmode = { + .mq_mode = ETH_MQ_TX_NONE, + }, +}; + +static uint32_t l2reflect_q = 0; +static uint64_t l2reflect_break_usec = UINT64_MAX; +static uint64_t l2reflect_break_usec; + +static struct rte_ether_addr ether_bcast_addr = { + .addr_bytes = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff } +}; + +struct rte_mempool *l2reflect_pktmbuf_pool = NULL; + +static void +l2reflect_usage(const char *prgname) +{ + printf("%s [EAL options] -- [-p PORT] -P [PRIO] [-b USEC] [-r] [-f] [-l]" + "[-s] [-q] [-d] [-S] [-i MSEC]\n" + " -p PORT: port to configure\n" + " -P PRIO: scheduling priority to use\n" + " -b USEC: break when latency > USEC\n" + " -r: scheduling policy SCHED_RR\n" + " -f: scheduling policy SCHED_FIFO\n" + " -l: lock memory (mlockall)\n" + " -s: send one packet on startup\n" + " -q: quiet, do not print stats\n" + " -d: die die die cli\n" + " -H USEC: create histogram of latencies with USEC time slices\n" + " -F FILE: write histogram to file\n" + " -S: start processing threads in sleep, wake with SIGUSR2\n" + " -i MSEC: use interrupts instead of polling (cont. on interrupt or after MSEC)\n", + prgname); +} + +/* Parse the argument given in the command line of the application */ +static int +l2reflect_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; + policy = SCHED_OTHER; + hist_filename = NULL; + l2reflect_output_hist = 0; + + while ((opt = getopt_long(argc, argvopt, "p:P:b:H:F:i:sqdrflS", lgopts, + &option_index)) != EOF) { + switch (opt) { + /* port */ + case 'p': + l2reflect_port_number = + (uint16_t)strtoul(optarg, NULL, 10); + break; + case 'P': + priority = strtoul(optarg, NULL, 10); + if (priority > 0) { + if (policy == SCHED_OTHER) + policy = SCHED_RR; + l2reflect_mlock = 1; + } + break; + case 'b': + l2reflect_break_usec = strtoul(optarg, NULL, 10); + break; + case 'S': + sleep_start = 1; + break; + case 'q': + quiet = 1; + break; + case 'd': + disable_int = 1; + break; + case 'r': + policy = SCHED_RR; + break; + case 'f': + policy = SCHED_FIFO; + break; + case 'l': + l2reflect_mlock = 1; + break; + case 'H': + l2reflect_hist = 1; + hist_bucket_usec = strtoul(optarg, NULL, 10); +#ifndef RTE_HAS_CJSON + printf("not compiled with cjson support\n"); + return -1; +#endif + break; + case 'F': + hist_filename = strndup(optarg, 128); + break; + case 'i': + l2reflect_interrupt = 1; + l2reflect_sleep_msec = strtoul(optarg, NULL, 10); + break; + default: + l2reflect_usage(prgname); + return -1; + } + } + + if (optind >= 0) + argv[optind - 1] = prgname; + + if (hist_filename && !l2reflect_hist) { + printf("-F switch requires -H switch as well\n"); + return -1; + } + + ret = optind - 1; + optind = 0; /* reset getopt lib */ + return ret; +} + +__attribute__((__format__ (__printf__, 1, 0))) +static void +trace_write(const char *fmt, ...) +{ + va_list ap; + char buf[256]; + int n, err; + + if (trace_fd == 0) + trace_fd = open("/sys/kernel/debug/tracing/trace_marker", + O_WRONLY); + if (trace_fd < 0) + return; + + va_start(ap, fmt); + n = vsnprintf(buf, 256, fmt, ap); + va_end(ap); + + err = write(trace_fd, buf, n); + assert(err >= 1); +} + +/* Send a burst of one packet */ +static int +l2reflect_send_packet(struct rte_mbuf **m, uint16_t port) +{ + unsigned ret; + struct rte_ether_hdr *eth; + struct my_magic_packet *pkt; + uint16_t type; + + eth = rte_pktmbuf_mtod(*m, struct rte_ether_hdr *); + pkt = (struct my_magic_packet *)eth; + type = pkt->type; + + ret = rte_eth_tx_burst(port, l2reflect_q, m, 1); + if (unlikely(ret < 1)) { + rte_pktmbuf_free(*m); + } else { + if (type == TRACE_TYPE_DATA) { + clock_gettime(CLOCK_MONOTONIC, &last_sent); + l2reflect_state = S_RUNNING; + } + } + return 0; +} + +static void +l2reflect_simple_forward(struct rte_mbuf *m) +{ + struct rte_ether_hdr *eth; + struct my_magic_packet *pkt; + + eth = rte_pktmbuf_mtod(m, struct rte_ether_hdr *); + pkt = (struct my_magic_packet *)eth; + + /* dst addr */ + rte_ether_addr_copy(ð->s_addr, ð->d_addr); + /* src addr */ + rte_ether_addr_copy(&l2reflect_port_eth_addr, ð->s_addr); + + if ((eth->ether_type == rte_cpu_to_be_16(ETHER_TYPE_L2REFLECT)) && + (pkt->magic == MAGIC_TRACE_PAYLOAD)) { + /* and the native one */ + trace_write("sending traced packet\n"); + } + + l2reflect_send_packet(&m, l2reflect_port_number); +} + +static struct rte_mbuf * +l2reflect_new_pkt(unsigned type) +{ + struct rte_mbuf *m; + struct rte_ether_hdr *eth; + struct my_magic_packet *pkt; + + m = rte_pktmbuf_alloc(l2reflect_pktmbuf_pool); + if (m == NULL) + rte_exit(EXIT_FAILURE, "rte_pktmbuf_alloc failed\n"); + + eth = rte_pktmbuf_mtod(m, struct rte_ether_hdr *); + + if (l2reflect_state != S_ELECT_LEADER) + rte_ether_addr_copy(&l2reflect_remote_eth_addr, ð->d_addr); + else + rte_ether_addr_copy(ðer_bcast_addr, ð->d_addr); + + /* src addr */ + rte_ether_addr_copy(&l2reflect_port_eth_addr, ð->s_addr); + eth->ether_type = rte_cpu_to_be_16(ETHER_TYPE_L2REFLECT); + + m->data_len = 64; + m->nb_segs = 1; + m->pkt_len = 64; + m->l2_len = sizeof(struct rte_ether_hdr); + + pkt = (struct my_magic_packet *)eth; + pkt->type = type; + pkt->breakval = l2reflect_break_usec; + + return m; +} + +static void +l2reflect_send_reset(void) +{ + struct rte_mbuf *m; + m = l2reflect_new_pkt(TRACE_TYPE_RSET); + l2reflect_send_packet(&m, l2reflect_port_number); +} + +static void +l2reflect_send_quit(void) +{ + struct rte_mbuf *m; + m = l2reflect_new_pkt(TRACE_TYPE_QUIT); + l2reflect_send_packet(&m, l2reflect_port_number); +} + +static void +l2reflect_new_ball(void) +{ + struct rte_mbuf *pnewball; + struct rte_ether_hdr *eth; + struct my_magic_packet *pkt; + + printf("Should create a packet to play with ...\n"); + pnewball = l2reflect_new_pkt(TRACE_TYPE_DATA); + + eth = rte_pktmbuf_mtod(pnewball, struct rte_ether_hdr *); + + printf("from MAC address: %02X:%02X:%02X:%02X:%02X:%02X to" + " %02X:%02X:%02X:%02X:%02X:%02X \n\n", + eth->s_addr.addr_bytes[0], eth->s_addr.addr_bytes[1], + eth->s_addr.addr_bytes[2], eth->s_addr.addr_bytes[3], + eth->s_addr.addr_bytes[4], eth->s_addr.addr_bytes[5], + eth->d_addr.addr_bytes[0], eth->d_addr.addr_bytes[1], + eth->d_addr.addr_bytes[2], eth->d_addr.addr_bytes[3], + eth->d_addr.addr_bytes[4], eth->d_addr.addr_bytes[5]); + + pkt = (struct my_magic_packet *)eth; + + /* we are tracing lets tell the others */ + if (l2reflect_break_usec) + pkt->magic = MAGIC_TRACE_PAYLOAD; + + l2reflect_send_packet(&pnewball, l2reflect_port_number); +} + +static inline int64_t +calcdiff_ns(struct timespec t1, struct timespec t2) +{ + int64_t diff; + diff = NSEC_PER_SEC * (int64_t)((int)t1.tv_sec - (int)t2.tv_sec); + diff += ((int)t1.tv_nsec - (int)t2.tv_nsec); + return diff; +} + +static inline unsigned +l2reflect_rx_filter(struct rte_mbuf **bufs, unsigned nb_rx, unsigned data_only) +{ + struct rte_ether_hdr *eth; + struct my_magic_packet *pkt; + unsigned i, ret; + + ret = 0; + for (i = 0; i < nb_rx; i++) { + eth = rte_pktmbuf_mtod(bufs[i], struct rte_ether_hdr *); + if (l2reflect_state != S_ELECT_LEADER && + !ether_addr_cmp(ð->s_addr, &l2reflect_remote_eth_addr)) + goto drop; + + if (eth->ether_type != rte_cpu_to_be_16(ETHER_TYPE_L2REFLECT)) + goto drop; + + pkt = (struct my_magic_packet *)eth; + if (data_only && (pkt->type != TRACE_TYPE_DATA && + pkt->type != TRACE_TYPE_RSET && + pkt->type != TRACE_TYPE_QUIT)) + goto drop; + + bufs[ret++] = bufs[i]; + continue; + drop: + rte_pktmbuf_free(bufs[i]); + } + + return ret; +} + +static int +elect_leader(uint16_t portid) +{ + struct rte_mbuf *pkts_burst[MAX_PKT_BURST]; + struct rte_mbuf *m; + struct rte_ether_hdr *eth; + struct my_magic_packet *pkt; + uint64_t my_mac, other_mac, breakval; + unsigned i, nb_rx; + int i_win; + int searching = 1; + + other_mac = 0ULL; + my_mac = 0ULL; + breakval = 0; + + while (l2reflect_state == S_ELECT_LEADER) { + nb_rx = rte_eth_rx_burst(portid, l2reflect_q, pkts_burst, + MAX_PKT_BURST); + nb_rx = l2reflect_rx_filter(pkts_burst, nb_rx, 0); + for (i = 0; i < nb_rx && searching; i++) { + eth = rte_pktmbuf_mtod(pkts_burst[i], + struct rte_ether_hdr *); + pkt = (struct my_magic_packet *)eth; + if (pkt->type == TRACE_TYPE_HELO || + pkt->type == TRACE_TYPE_EHLO) { + l2reflect_state = S_RUNNING; + rte_ether_addr_copy(ð->s_addr, + &l2reflect_remote_eth_addr); + rte_ether_addr_copy( + ð->s_addr, + (struct rte_ether_addr *)&other_mac); + rte_ether_addr_copy( + &l2reflect_port_eth_addr, + (struct rte_ether_addr *)&my_mac); + breakval = pkt->breakval; + /* break, but cleanup */ + searching = 0; + } + if (pkt->type == TRACE_TYPE_HELO) { + m = l2reflect_new_pkt(TRACE_TYPE_EHLO); + RTE_LOG(INFO, L2REFLECT, "found one EHLO\n"); + l2reflect_send_packet(&m, + l2reflect_port_number); + } + rte_pktmbuf_free(pkts_burst[i]); + } + m = l2reflect_new_pkt(TRACE_TYPE_HELO); + RTE_LOG(INFO, L2REFLECT, "looking for player HELO\n"); + l2reflect_send_packet(&m, l2reflect_port_number); + usleep(500000); + } + /* leave election logic */ + if (l2reflect_state != S_RUNNING) + return 0; + + if (my_mac == other_mac) + rte_exit(EXIT_FAILURE, "talking to myself ... confused\n"); + + /* the one with the bigger MAC is the leader */ + i_win = (my_mac > other_mac); + + RTE_LOG(INFO, L2REFLECT, "i am the \"%s\"\n", i_win ? "rick" : "morty"); + + /* looser takes tracing break value from winner */ + if (!i_win) + l2reflect_break_usec = breakval; + + return i_win; +} + +/* main processing loop */ +static void +l2reflect_main_loop(void) +{ + struct rte_mbuf *pkts_burst[MAX_PKT_BURST]; + struct rte_mbuf *m; + unsigned lcore_id; + unsigned j, nb_rx, nb_evt; + uint16_t portid; + uint64_t diff = 0; + int sender; + struct my_magic_packet *pkt; + struct rte_ether_hdr *eth; + struct rte_epoll_event event; + + lcore_id = rte_lcore_id(); + + RTE_LOG(INFO, L2REFLECT, "entering main loop on lcore %u\n", lcore_id); + + portid = l2reflect_port_number; + RTE_LOG(INFO, L2REFLECT, " -- lcoreid=%u portid=%u\n", lcore_id, + portid); + +restart: + init_record(); + l2reflect_state = S_ELECT_LEADER; + sender = elect_leader(portid); + + /* we are the sender so we bring one ball into the game */ + if (sender) + l2reflect_new_ball(); + + while (l2reflect_state == S_RUNNING) { + if (l2reflect_interrupt) { + rte_eth_dev_rx_intr_enable(portid, l2reflect_q); + /* wait for interrupt or timeout */ + nb_evt = rte_epoll_wait(RTE_EPOLL_PER_THREAD, &event, 1, + l2reflect_sleep_msec); + rte_eth_dev_rx_intr_disable(portid, l2reflect_q); + if (nb_evt == 0 && rounds > WARMUP_ROUNDS) + ++record.timeouts; + } + + nb_rx = rte_eth_rx_burst(portid, l2reflect_q, pkts_burst, + MAX_PKT_BURST); + + /* TODO use drivers/hw to filter mac */ + nb_rx = l2reflect_rx_filter(pkts_burst, nb_rx, 1); + + /* remote is telling us to reset or stop */ + if (nb_rx) { + eth = rte_pktmbuf_mtod(pkts_burst[0], + struct rte_ether_hdr *); + pkt = (struct my_magic_packet *)eth; + if (eth->ether_type == + rte_cpu_to_be_16(ETHER_TYPE_L2REFLECT)) { + if (pkt->type == TRACE_TYPE_RSET) { + rte_pktmbuf_free(pkts_burst[0]); + goto restart; + } + if (pkt->type == TRACE_TYPE_QUIT) { + l2reflect_state = S_REMOTE_TERM; + break; + } + } + } + + if (l2reflect_state == S_RUNNING && nb_rx) { + eth = rte_pktmbuf_mtod(pkts_burst[0], + struct rte_ether_hdr *); + pkt = (struct my_magic_packet *)eth; + if (eth->ether_type == + rte_cpu_to_be_16(ETHER_TYPE_L2REFLECT)) { + if (pkt->type == TRACE_TYPE_DATA) { + clock_gettime(CLOCK_MONOTONIC, + &last_recv); + diff = calcdiff_ns(last_recv, + last_sent); + record.rounds++; + /* do not count the first rounds, diff would be too high */ + if (record.rounds > WARMUP_ROUNDS) { + if (l2reflect_hist) + record.hist[MIN( + diff / (hist_bucket_usec * + 1000), + HIST_CAP_BUCKET)]++; + + record.avg_round += + (double)diff; + if (diff < record.min_round) + record.min_round = diff; + if (diff > record.max_round) { + record.max_round = diff; + if (l2reflect_break_usec && + (record.max_round > + l2reflect_break_usec * + 1000)) + break; + } + } + } + if (pkt->magic == MAGIC_TRACE_PAYLOAD) { + /* and the native one */ + trace_write("received traced packet\n"); + } + } + } + for (j = 0; j < nb_rx; j++) { + m = pkts_burst[j]; + rte_prefetch0(rte_pktmbuf_mtod(m, void *)); + l2reflect_simple_forward(m); + } + } + const int state_cpy = l2reflect_state; + switch (state_cpy) { + case S_RESET_TRX: + l2reflect_send_reset(); + l2reflect_state = S_ELECT_LEADER; + case S_ELECT_LEADER: + goto restart; + } + + if (state_cpy == S_LOCAL_TERM) { + l2reflect_send_quit(); + if (record.max_round > l2reflect_break_usec) { + printf("hit latency threshold (%" PRIu64 + ".%03u > %" PRIu64 ")\n", + diff / 1000, (unsigned int)(diff % 1000), + l2reflect_break_usec); + } + } else if (state_cpy == S_REMOTE_TERM) { + printf("received message that remote hit threshold (or is cancelled)\n"); + } +} + +static int +l2reflect_launch_one_lcore(__attribute__((unused)) void *dummy) +{ + struct sched_param param; + int err; + + if (sleep_start) { + printf("Sleeping and waiting for SIGCONT\n"); + while (sleep_start) { + usleep(10000); + } + printf("Got SIGCONT, continuing"); + } + if (l2reflect_mlock) { + err = mlockall(MCL_CURRENT | MCL_FUTURE); + if (err) + rte_exit(EXIT_FAILURE, "mlockall failed: %s\n", + strerror(errno)); + } + if (priority > 0 || policy != SCHED_OTHER) { + memset(¶m, 0, sizeof(param)); + param.sched_priority = priority; + err = sched_setscheduler(0, policy, ¶m); + if (err) + rte_exit(EXIT_FAILURE, + "sched_setscheduler failed: %s\n", + strerror(errno)); + } + if (l2reflect_interrupt) { + err = rte_eth_dev_rx_intr_ctl_q(l2reflect_port_number, + l2reflect_q, + RTE_EPOLL_PER_THREAD, + RTE_INTR_EVENT_ADD, NULL); + if (err) + rte_exit(EXIT_FAILURE, + "could not register I/O interrupt\n"); + } + l2reflect_main_loop(); + return 0; +} + +static void +sig_handler(int signum) +{ + switch (signum) { + case SIGUSR1: + if (l2reflect_state == S_RUNNING) + l2reflect_state = S_RESET_TRX; + break; + case SIGUSR2: + l2reflect_output_hist = 1; + break; + case SIGCONT: + sleep_start = 0; + break; + case SIGHUP: + /* FALLTHROUGH */ + case SIGINT: + l2reflect_state = S_LOCAL_TERM; + break; + } +} + +int +main(int argc, char **argv) +{ + struct rte_eth_dev_info dev_info; + int ret; + uint32_t i; + uint16_t nb_ports; + unsigned lcore_id; + struct sigaction action; + bzero(&action, sizeof(action)); + char mempool_name[128]; + + action.sa_handler = sig_handler; + if (sigaction(SIGHUP, &action, NULL) < 0 || + sigaction(SIGUSR1, &action, NULL) < 0 || + sigaction(SIGUSR2, &action, NULL) < 0 || + sigaction(SIGCONT, &action, NULL) < 0 || + sigaction(SIGINT, &action, NULL) < 0) { + rte_exit(EXIT_FAILURE, "Could not register signal handler\n"); + } + + lcore_id = rte_lcore_id(); + /* init EAL */ + ret = rte_eal_init(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid EAL arguments\n"); + argc -= ret; + argv += ret; + + /* parse application arguments (after the EAL ones) */ + ret = l2reflect_parse_args(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid L2REFLECT arguments\n"); + + snprintf(mempool_name, sizeof(mempool_name), "mbuf_pool_%d", getpid()); + printf("About to create mempool \"%s\"\n", mempool_name); + /* create the mbuf pool */ + l2reflect_pktmbuf_pool = + rte_mempool_create(mempool_name, NB_MBUF, MBUF_SIZE, MAX_PKT_BURST, + sizeof(struct rte_pktmbuf_pool_private), + rte_pktmbuf_pool_init, NULL, + rte_pktmbuf_init, NULL, rte_socket_id(), 0); + + if (l2reflect_pktmbuf_pool == NULL) + rte_exit(EXIT_FAILURE, + "Cannot init/find mbuf pool name %s\nError: %d %s\n", + mempool_name, rte_errno, rte_strerror(rte_errno)); + + nb_ports = rte_eth_dev_count_avail(); + if (nb_ports == 0) + rte_exit(EXIT_FAILURE, "No Ethernet ports - bye\n"); + if (l2reflect_port_number + 1 > nb_ports) + rte_exit(EXIT_FAILURE, "Chosen port %d does not exist - bye\n", + l2reflect_port_number); + printf("We have %d ports and will use port %d\n", nb_ports, + l2reflect_port_number); + + rte_eth_dev_info_get(l2reflect_port_number, &dev_info); + printf("Initializing port %u... ", l2reflect_port_number); + fflush(stdout); + + if (l2reflect_interrupt) + port_conf.intr_conf.rxq = 1; + ret = rte_eth_dev_configure(l2reflect_port_number, 1, 1, &port_conf); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "Cannot configure device: err=%s, port=%u\n", + strerror(-ret), l2reflect_port_number); + + rte_eth_macaddr_get(l2reflect_port_number, &l2reflect_port_eth_addr); + + /* init RX queues */ + fflush(stdout); + for (i = 0; i <= l2reflect_q; i++) { + ret = rte_eth_rx_queue_setup( + l2reflect_port_number, i, nb_rxd, + rte_eth_dev_socket_id(l2reflect_port_number), NULL, + l2reflect_pktmbuf_pool); + if (ret < 0) + rte_exit( + EXIT_FAILURE, + "rte_eth_rx_queue_setup:err=%s, port=%u q=%u\n", + strerror(-ret), l2reflect_port_number, i); + } + + /* init one TX queue on each port */ + fflush(stdout); + ret = rte_eth_tx_queue_setup( + l2reflect_port_number, 0, nb_txd, + rte_eth_dev_socket_id(l2reflect_port_number), NULL); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "rte_eth_tx_queue_setup:err=%s, port=%u\n", + strerror(-ret), (unsigned)l2reflect_port_number); + + /* Start device */ + ret = rte_eth_dev_start(l2reflect_port_number); + if (ret < 0) + rte_exit(EXIT_FAILURE, "rte_eth_dev_start:err=%s, port=%u\n", + strerror(-ret), (unsigned)l2reflect_port_number); + + rte_eth_promiscuous_enable(l2reflect_port_number); + + printf("Port %u, MAC address: %02X:%02X:%02X:%02X:%02X:%02X\n\n", + (unsigned)l2reflect_port_number, + l2reflect_port_eth_addr.addr_bytes[0], + l2reflect_port_eth_addr.addr_bytes[1], + l2reflect_port_eth_addr.addr_bytes[2], + l2reflect_port_eth_addr.addr_bytes[3], + l2reflect_port_eth_addr.addr_bytes[4], + l2reflect_port_eth_addr.addr_bytes[5]); + + /* + * in quiet mode the master executes the main packet loop + * otherwise the one slave does it and the master prints stats + */ + if (quiet) { + assert(rte_lcore_count() == 1); + if (disable_int) { + iopl(3); + asm("cli"); + } + l2reflect_launch_one_lcore(NULL); + } else { + assert(rte_lcore_count() == 2); + /* the slave reflects the packets */ + RTE_LCORE_FOREACH_SLAVE(lcore_id) + { + rte_eal_remote_launch(l2reflect_launch_one_lcore, NULL, + lcore_id); + } + + /* the master prints the stats */ + init_record(); + l2reflect_stats_loop(); + rte_eal_mp_wait_lcore(); + } + rte_eal_cleanup(); + + if (l2reflect_hist) { + output_histogram_snapshot(); + } + cleanup_record(); + + if (trace_fd) + close(trace_fd); + + return 0; +} diff --git a/examples/l2reflect/meson.build b/examples/l2reflect/meson.build new file mode 100644 index 000000000..503ed2831 --- /dev/null +++ b/examples/l2reflect/meson.build @@ -0,0 +1,21 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2020 Siemens AG + +# meson file, for building this example as part of a main DPDK build. + +cjson = dependency('libcjson', required: false) + +if not cjson.found() + cc = meson.get_compiler('c') + cjson = cc.find_library('cjson', required: false) +endif + +if not is_linux + build = false +endif + +sources = files('main.c', 'stats.c') +if cjson.found() + ext_deps += cjson + cflags += '-DRTE_HAS_CJSON' +endif diff --git a/examples/l2reflect/stats.c b/examples/l2reflect/stats.c new file mode 100644 index 000000000..e4e973354 --- /dev/null +++ b/examples/l2reflect/stats.c @@ -0,0 +1,198 @@ +/* + * SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2020 Siemens AG + * + * authors: + * Felix Moessbauer + * Henning Schild + */ +#include +#include +#include +#include +#ifdef RTE_HAS_CJSON +#include +#endif +#include "stats.h" + +#define ANSI_BOLD_RED "\x1b[01;31m" +#define ANSI_BOLD_GREEN "\x1b[01;32m" +#define ANSI_BOLD_YELLOW "\x1b[01;33m" +#define ANSI_BOLD_BLUE "\x1b[01;34m" +#define ANSI_BOLD_MAGENTA "\x1b[01;35m" +#define ANSI_BOLD_CYAN "\x1b[01;36m" +#define ANSI_RESET "\x1b[0m" + +void +init_record(void) +{ + record.max_round = 0; + record.min_round = MIN_INITIAL; + record.rounds = 0; + record.timeouts = 0; + record.avg_round = 0; + if (l2reflect_hist) { + if (!record.hist_size) { + record.hist = + calloc(HIST_NUM_BUCKETS, sizeof(uint64_t)); + record.hist_size = HIST_NUM_BUCKETS; + } else { + memset(record.hist, 0, + record.hist_size * sizeof(uint64_t)); + } + } +} + +void +cleanup_record(void) +{ + if (l2reflect_hist) { + free(record.hist); + record.hist = NULL; + record.hist_size = 0; + } +} + +void +output_histogram_snapshot(void) +{ + char *json = serialize_histogram(&record); + FILE *fd = stdout; + if (hist_filename) + fd = fopen(hist_filename, "w"); + fputs(json, fd); + fputs("\n", fd); + free(json); + if (hist_filename) + fclose(fd); +} + +void +print_stats(void) +{ + const char clr[] = { 27, '[', '2', 'J', '\0' }; + const char topLeft[] = { 27, '[', '1', ';', '1', 'H', '\0' }; + const uint64_t bytes_in_gib = 0x40000000; + struct rte_eth_stats stats; + + rte_eth_stats_get(l2reflect_port_number, &stats); + + /* Clear screen and move to top left */ + printf("%s%s", clr, topLeft); + + printf(ANSI_BOLD_GREEN "Networking Roundtrip Test\n" ANSI_RESET); + printf(ANSI_BOLD_MAGENTA + "\nPort statistics ====================================" ANSI_RESET); + + printf("\nMe: %02X:%02X:%02X:%02X:%02X:%02X <--> " + "Remote: %02X:%02X:%02X:%02X:%02X:%02X", + l2reflect_port_eth_addr.addr_bytes[0], + l2reflect_port_eth_addr.addr_bytes[1], + l2reflect_port_eth_addr.addr_bytes[2], + l2reflect_port_eth_addr.addr_bytes[3], + l2reflect_port_eth_addr.addr_bytes[4], + l2reflect_port_eth_addr.addr_bytes[5], + l2reflect_remote_eth_addr.addr_bytes[0], + l2reflect_remote_eth_addr.addr_bytes[1], + l2reflect_remote_eth_addr.addr_bytes[2], + l2reflect_remote_eth_addr.addr_bytes[3], + l2reflect_remote_eth_addr.addr_bytes[4], + l2reflect_remote_eth_addr.addr_bytes[5]); + printf("\nStatistics for port %d PID %d on lcore %d ---------" + "\nPackets tx: %22" PRIu64 "\nPackets rx: %22" PRIu64 + "\nBytes tx: %24" PRIu64 " (%8.2f GiB)" + "\nBytes rx: %24" PRIu64 " (%8.2f GiB)" + "\nErrors tx: %23" PRIu64 "\nErrors rx: %23" PRIu64 + "\nTimeouts rx: %21" PRIu64 " (>%9" PRIu64 "ms)", + l2reflect_port_number, getpid(), rte_lcore_id(), stats.opackets, + stats.ipackets, stats.obytes, + (double)stats.obytes / bytes_in_gib, stats.ibytes, + (double)stats.ibytes / bytes_in_gib, stats.oerrors, + stats.ierrors, record.timeouts, l2reflect_sleep_msec); + printf(ANSI_BOLD_MAGENTA + "\nPort timing statistics =============================" ANSI_RESET); + if (l2reflect_state == S_ELECT_LEADER || + record.min_round == MIN_INITIAL) { + printf("\n\nBenchmark not started yet...\n"); + } else { + printf("\n" ANSI_BOLD_RED "Max" ANSI_RESET + " roundtrip: %19" PRIu64 " us", + record.max_round / 1000); + printf("\n" ANSI_BOLD_YELLOW "Avg" ANSI_RESET + " roundtrip: %19" PRIu64 " us", + record.rounds ? (uint64_t)(record.avg_round / + record.rounds / 1000) : + 0); + printf("\n" ANSI_BOLD_GREEN "Min" ANSI_RESET + " roundtrip: %19" PRIu64 " us", + record.min_round / 1000); + } + printf(ANSI_BOLD_MAGENTA + "\n====================================================" ANSI_RESET + "\n"); +} + +void +l2reflect_stats_loop(void) +{ + while (!(l2reflect_state & (S_LOCAL_TERM | S_REMOTE_TERM))) { + print_stats(); + if (l2reflect_hist && l2reflect_output_hist) { + output_histogram_snapshot(); + l2reflect_output_hist = 0; + } + sleep(1); + } +} + +char * +serialize_histogram(__attribute__((unused)) const struct stats *record) +{ +#ifndef RTE_HAS_CJSON + return strdup("to print histogram, build with cjson support"); +#else + char *str = NULL; + char key[8]; + unsigned i; + cJSON *hist0, *cpu0, *all_cpus, *output; + + output = cJSON_CreateObject(); + // version: 1 + cJSON_AddItemToObject(output, "version", cJSON_CreateNumber(1)); + + // cpu 0 histogram + hist0 = cJSON_CreateObject(); + for (i = 0; i < record->hist_size; ++i) { + // only write positive numbers to meed jitterplot expectations + if (record->hist[i] != 0) { + snprintf(key, 8, "%u", i * hist_bucket_usec); + cJSON_AddNumberToObject(hist0, key, record->hist[i]); + } + } + + // cpu 0 stats + cpu0 = cJSON_CreateObject(); + cJSON_AddItemToObject(cpu0, "histogram", hist0); + cJSON_AddItemToObject(cpu0, "count", + cJSON_CreateNumber(record->rounds)); + cJSON_AddItemToObject(cpu0, "min", + cJSON_CreateNumber(record->min_round)); + cJSON_AddItemToObject(cpu0, "max", + cJSON_CreateNumber(record->max_round)); + cJSON_AddItemToObject(cpu0, "avg", + cJSON_CreateNumber((record->avg_round / + record->rounds / 1000))); + + // combine objects + all_cpus = cJSON_CreateObject(); + cJSON_AddItemToObject(all_cpus, "0", cpu0); + cJSON_AddItemToObject(output, "cpu", all_cpus); + + str = cJSON_Print(output); + + // cleanup + cJSON_Delete(output); + + return str; +#endif +} diff --git a/examples/l2reflect/stats.h b/examples/l2reflect/stats.h new file mode 100644 index 000000000..ed6c9b693 --- /dev/null +++ b/examples/l2reflect/stats.h @@ -0,0 +1,67 @@ +/* + * SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2020 Siemens AG + * + * authors: + * Felix Moessbauer + * Henning Schild + */ +#ifndef _STATS_H_ +#define _STATS_H_ +#include +#include +#include + +#include + +#include "l2reflect.h" + +#define MIN_INITIAL ULONG_MAX +#define HIST_NUM_BUCKETS 128 +#define HIST_CAP_BUCKET (HIST_NUM_BUCKETS - 1) + +/* size of each histogram bucket in usec */ +unsigned hist_bucket_usec; + +/* runtime statistics */ +struct stats { + uint64_t max_round; + uint64_t min_round; + uint64_t rounds; + uint64_t timeouts; + double avg_round; + unsigned hist_size; + // each slot is 10us + uint64_t *hist; +}; + +struct stats record; +char *hist_filename; + +void +init_record(void); +void +cleanup_record(void); + +void +l2reflect_stats_loop(void); + +/* + * Write the histogram to file / stdio without any locking. + * When called during the measurement, values are approximations + * (racy reads). + */ +void +output_histogram_snapshot(void); + +/* Print out statistics on packets dropped */ +void +print_stats(void); + +/* + * get a JSON representation of the record + */ +char * +serialize_histogram(const struct stats *record); + +#endif // _STATS_H_ diff --git a/examples/meson.build b/examples/meson.build index 120eebf71..d9e476fd3 100644 --- a/examples/meson.build +++ b/examples/meson.build @@ -25,6 +25,7 @@ all_examples = [ 'l2fwd', 'l2fwd-cat', 'l2fwd-event', 'l2fwd-crypto', 'l2fwd-jobstats', 'l2fwd-keepalive', 'l3fwd', + 'l2reflect', 'l3fwd-acl', 'l3fwd-power', 'l3fwd-graph', 'link_status_interrupt', 'multi_process/client_server_mp/mp_client', -- 2.20.1