#include <getopt.h>
#include <stdbool.h>
#include <sys/time.h>
+#include <signal.h>
+#include <unistd.h>
#include <rte_malloc.h>
#include <rte_mempool.h>
#include <rte_flow.h>
#include "config.h"
+#include "flow_gen.h"
+
+#define MAX_ITERATIONS 100
+#define DEFAULT_RULES_COUNT 4000000
+#define DEFAULT_ITERATION 100000
+
+struct rte_flow *flow;
+static uint8_t flow_group;
+
+static uint64_t flow_items;
+static uint64_t flow_actions;
+static uint64_t flow_attrs;
+
+static volatile bool force_quit;
+static bool dump_iterations;
+static bool delete_flag;
+static bool dump_socket_mem_flag;
+static bool enable_fwd;
static struct rte_mempool *mbuf_mp;
static uint32_t nb_lcores;
+static uint32_t flows_count;
+static uint32_t iterations_number;
+static uint32_t hairpin_queues_num; /* total hairpin q number - default: 0 */
+static uint32_t nb_lcores;
+
+#define MAX_PKT_BURST 32
+#define LCORE_MODE_PKT 1
+#define LCORE_MODE_STATS 2
+#define MAX_STREAMS 64
+#define MAX_LCORES 64
+
+struct stream {
+ int tx_port;
+ int tx_queue;
+ int rx_port;
+ int rx_queue;
+};
+
+struct lcore_info {
+ int mode;
+ int streams_nb;
+ struct stream streams[MAX_STREAMS];
+ /* stats */
+ uint64_t tx_pkts;
+ uint64_t tx_drops;
+ uint64_t rx_pkts;
+ struct rte_mbuf *pkts[MAX_PKT_BURST];
+} __rte_cache_aligned;
+
+static struct lcore_info lcore_infos[MAX_LCORES];
static void
usage(char *progname)
{
printf("\nusage: %s\n", progname);
+ printf("\nControl configurations:\n");
+ printf(" --flows-count=N: to set the number of needed"
+ " flows to insert, default is 4,000,000\n");
+ printf(" --dump-iterations: To print rates for each"
+ " iteration\n");
+ printf(" --deletion-rate: Enable deletion rate"
+ " calculations\n");
+ printf(" --dump-socket-mem: To dump all socket memory\n");
+ printf(" --enable-fwd: To enable packets forwarding"
+ " after insertion\n");
+
+ printf("To set flow attributes:\n");
+ printf(" --ingress: set ingress attribute in flows\n");
+ printf(" --egress: set egress attribute in flows\n");
+ printf(" --transfer: set transfer attribute in flows\n");
+ printf(" --group=N: set group for all flows,"
+ " default is 0\n");
+
+ printf("To set flow items:\n");
+ printf(" --ether: add ether layer in flow items\n");
+ printf(" --vlan: add vlan layer in flow items\n");
+ printf(" --ipv4: add ipv4 layer in flow items\n");
+ printf(" --ipv6: add ipv6 layer in flow items\n");
+ printf(" --tcp: add tcp layer in flow items\n");
+ printf(" --udp: add udp layer in flow items\n");
+ printf(" --vxlan: add vxlan layer in flow items\n");
+ printf(" --vxlan-gpe: add vxlan-gpe layer in flow items\n");
+ printf(" --gre: add gre layer in flow items\n");
+ printf(" --geneve: add geneve layer in flow items\n");
+ printf(" --gtp: add gtp layer in flow items\n");
+ printf(" --meta: add meta layer in flow items\n");
+ printf(" --tag: add tag layer in flow items\n");
+
+ printf("To set flow actions:\n");
+ printf(" --port-id: add port-id action in flow actions\n");
+ printf(" --rss: add rss action in flow actions\n");
+ printf(" --queue: add queue action in flow actions\n");
+ printf(" --jump: add jump action in flow actions\n");
+ printf(" --mark: add mark action in flow actions\n");
+ printf(" --count: add count action in flow actions\n");
+ printf(" --set-meta: add set meta action in flow actions\n");
+ printf(" --set-tag: add set tag action in flow actions\n");
+ printf(" --drop: add drop action in flow actions\n");
+ printf(" --hairpin-queue=N: add hairpin-queue action in flow actions\n");
+ printf(" --hairpin-rss=N: add hairping-rss action in flow actions\n");
}
static void
args_parse(int argc, char **argv)
{
char **argvopt;
- int opt;
+ int n, opt;
int opt_idx;
- static struct option lgopts[] = {
+ size_t i;
+
+ static const struct option_dict {
+ const char *str;
+ const uint64_t mask;
+ uint64_t *bitmap;
+ } flow_options[] = {
+ {
+ .str = "ether",
+ .mask = FLOW_ITEM_MASK(RTE_FLOW_ITEM_TYPE_ETH),
+ .bitmap = &flow_items
+ },
+ {
+ .str = "ipv4",
+ .mask = FLOW_ITEM_MASK(RTE_FLOW_ITEM_TYPE_IPV4),
+ .bitmap = &flow_items
+ },
+ {
+ .str = "ipv6",
+ .mask = FLOW_ITEM_MASK(RTE_FLOW_ITEM_TYPE_IPV6),
+ .bitmap = &flow_items
+ },
+ {
+ .str = "vlan",
+ .mask = FLOW_ITEM_MASK(RTE_FLOW_ITEM_TYPE_VLAN),
+ .bitmap = &flow_items
+ },
+ {
+ .str = "tcp",
+ .mask = FLOW_ITEM_MASK(RTE_FLOW_ITEM_TYPE_TCP),
+ .bitmap = &flow_items
+ },
+ {
+ .str = "udp",
+ .mask = FLOW_ITEM_MASK(RTE_FLOW_ITEM_TYPE_UDP),
+ .bitmap = &flow_items
+ },
+ {
+ .str = "vxlan",
+ .mask = FLOW_ITEM_MASK(RTE_FLOW_ITEM_TYPE_VXLAN),
+ .bitmap = &flow_items
+ },
+ {
+ .str = "vxlan-gpe",
+ .mask = FLOW_ITEM_MASK(RTE_FLOW_ITEM_TYPE_VXLAN_GPE),
+ .bitmap = &flow_items
+ },
+ {
+ .str = "gre",
+ .mask = FLOW_ITEM_MASK(RTE_FLOW_ITEM_TYPE_GRE),
+ .bitmap = &flow_items
+ },
+ {
+ .str = "geneve",
+ .mask = FLOW_ITEM_MASK(RTE_FLOW_ITEM_TYPE_GENEVE),
+ .bitmap = &flow_items
+ },
+ {
+ .str = "gtp",
+ .mask = FLOW_ITEM_MASK(RTE_FLOW_ITEM_TYPE_GTP),
+ .bitmap = &flow_items
+ },
+ {
+ .str = "meta",
+ .mask = FLOW_ITEM_MASK(RTE_FLOW_ITEM_TYPE_META),
+ .bitmap = &flow_items
+ },
+ {
+ .str = "tag",
+ .mask = FLOW_ITEM_MASK(RTE_FLOW_ITEM_TYPE_TAG),
+ .bitmap = &flow_items
+ },
+ {
+ .str = "ingress",
+ .mask = INGRESS,
+ .bitmap = &flow_attrs
+ },
+ {
+ .str = "egress",
+ .mask = EGRESS,
+ .bitmap = &flow_attrs
+ },
+ {
+ .str = "transfer",
+ .mask = TRANSFER,
+ .bitmap = &flow_attrs
+ },
+ {
+ .str = "port-id",
+ .mask = FLOW_ACTION_MASK(RTE_FLOW_ACTION_TYPE_PORT_ID),
+ .bitmap = &flow_actions
+ },
+ {
+ .str = "rss",
+ .mask = FLOW_ACTION_MASK(RTE_FLOW_ACTION_TYPE_RSS),
+ .bitmap = &flow_actions
+ },
+ {
+ .str = "queue",
+ .mask = FLOW_ACTION_MASK(RTE_FLOW_ACTION_TYPE_QUEUE),
+ .bitmap = &flow_actions
+ },
+ {
+ .str = "jump",
+ .mask = FLOW_ACTION_MASK(RTE_FLOW_ACTION_TYPE_JUMP),
+ .bitmap = &flow_actions
+ },
+ {
+ .str = "mark",
+ .mask = FLOW_ACTION_MASK(RTE_FLOW_ACTION_TYPE_MARK),
+ .bitmap = &flow_actions
+ },
+ {
+ .str = "count",
+ .mask = FLOW_ACTION_MASK(RTE_FLOW_ACTION_TYPE_COUNT),
+ .bitmap = &flow_actions
+ },
+ {
+ .str = "set-meta",
+ .mask = FLOW_ACTION_MASK(RTE_FLOW_ACTION_TYPE_SET_META),
+ .bitmap = &flow_actions
+ },
+ {
+ .str = "set-tag",
+ .mask = FLOW_ACTION_MASK(RTE_FLOW_ACTION_TYPE_SET_TAG),
+ .bitmap = &flow_actions
+ },
+ {
+ .str = "drop",
+ .mask = FLOW_ACTION_MASK(RTE_FLOW_ACTION_TYPE_DROP),
+ .bitmap = &flow_actions
+ }
+ };
+
+ static const struct option lgopts[] = {
/* Control */
{ "help", 0, 0, 0 },
+ { "flows-count", 1, 0, 0 },
+ { "dump-iterations", 0, 0, 0 },
+ { "deletion-rate", 0, 0, 0 },
+ { "dump-socket-mem", 0, 0, 0 },
+ { "enable-fwd", 0, 0, 0 },
+ /* Attributes */
+ { "ingress", 0, 0, 0 },
+ { "egress", 0, 0, 0 },
+ { "transfer", 0, 0, 0 },
+ { "group", 1, 0, 0 },
+ /* Items */
+ { "ether", 0, 0, 0 },
+ { "vlan", 0, 0, 0 },
+ { "ipv4", 0, 0, 0 },
+ { "ipv6", 0, 0, 0 },
+ { "tcp", 0, 0, 0 },
+ { "udp", 0, 0, 0 },
+ { "vxlan", 0, 0, 0 },
+ { "vxlan-gpe", 0, 0, 0 },
+ { "gre", 0, 0, 0 },
+ { "geneve", 0, 0, 0 },
+ { "gtp", 0, 0, 0 },
+ { "meta", 0, 0, 0 },
+ { "tag", 0, 0, 0 },
+ /* Actions */
+ { "port-id", 0, 0, 0 },
+ { "rss", 0, 0, 0 },
+ { "queue", 0, 0, 0 },
+ { "jump", 0, 0, 0 },
+ { "mark", 0, 0, 0 },
+ { "count", 0, 0, 0 },
+ { "set-meta", 0, 0, 0 },
+ { "set-tag", 0, 0, 0 },
+ { "drop", 0, 0, 0 },
+ { "hairpin-queue", 1, 0, 0 },
+ { "hairpin-rss", 1, 0, 0 },
};
+ flow_items = 0;
+ flow_actions = 0;
+ flow_attrs = 0;
+ hairpin_queues_num = 0;
argvopt = argv;
+ printf(":: Flow -> ");
while ((opt = getopt_long(argc, argvopt, "",
lgopts, &opt_idx)) != EOF) {
switch (opt) {
usage(argv[0]);
rte_exit(EXIT_SUCCESS, "Displayed help\n");
}
+
+ if (strcmp(lgopts[opt_idx].name, "group") == 0) {
+ n = atoi(optarg);
+ if (n >= 0)
+ flow_group = n;
+ else
+ rte_exit(EXIT_SUCCESS,
+ "flow group should be >= 0\n");
+ printf("group %d ", flow_group);
+ }
+
+ for (i = 0; i < RTE_DIM(flow_options); i++)
+ if (strcmp(lgopts[opt_idx].name,
+ flow_options[i].str) == 0) {
+ *flow_options[i].bitmap |=
+ flow_options[i].mask;
+ printf("%s / ", flow_options[i].str);
+ }
+
+ if (strcmp(lgopts[opt_idx].name,
+ "hairpin-rss") == 0) {
+ n = atoi(optarg);
+ if (n > 0)
+ hairpin_queues_num = n;
+ else
+ rte_exit(EXIT_SUCCESS,
+ "Hairpin queues should be > 0\n");
+
+ flow_actions |= HAIRPIN_RSS_ACTION;
+ printf("hairpin-rss / ");
+ }
+ if (strcmp(lgopts[opt_idx].name,
+ "hairpin-queue") == 0) {
+ n = atoi(optarg);
+ if (n > 0)
+ hairpin_queues_num = n;
+ else
+ rte_exit(EXIT_SUCCESS,
+ "Hairpin queues should be > 0\n");
+
+ flow_actions |= HAIRPIN_QUEUE_ACTION;
+ printf("hairpin-queue / ");
+ }
+
+ /* Control */
+ if (strcmp(lgopts[opt_idx].name,
+ "flows-count") == 0) {
+ n = atoi(optarg);
+ if (n > (int) iterations_number)
+ flows_count = n;
+ else {
+ printf("\n\nflows_count should be > %d\n",
+ iterations_number);
+ rte_exit(EXIT_SUCCESS, " ");
+ }
+ }
+ if (strcmp(lgopts[opt_idx].name,
+ "dump-iterations") == 0)
+ dump_iterations = true;
+ if (strcmp(lgopts[opt_idx].name,
+ "deletion-rate") == 0)
+ delete_flag = true;
+ if (strcmp(lgopts[opt_idx].name,
+ "dump-socket-mem") == 0)
+ dump_socket_mem_flag = true;
+ if (strcmp(lgopts[opt_idx].name,
+ "enable-fwd") == 0)
+ enable_fwd = true;
break;
default:
fprintf(stderr, "Invalid option: %s\n", argv[optind]);
break;
}
}
+ printf("end_flow\n");
+}
+
+/* Dump the socket memory statistics on console */
+static size_t
+dump_socket_mem(FILE *f)
+{
+ struct rte_malloc_socket_stats socket_stats;
+ unsigned int i = 0;
+ size_t total = 0;
+ size_t alloc = 0;
+ size_t free = 0;
+ unsigned int n_alloc = 0;
+ unsigned int n_free = 0;
+ bool active_nodes = false;
+
+
+ for (i = 0; i < RTE_MAX_NUMA_NODES; i++) {
+ if (rte_malloc_get_socket_stats(i, &socket_stats) ||
+ !socket_stats.heap_totalsz_bytes)
+ continue;
+ active_nodes = true;
+ total += socket_stats.heap_totalsz_bytes;
+ alloc += socket_stats.heap_allocsz_bytes;
+ free += socket_stats.heap_freesz_bytes;
+ n_alloc += socket_stats.alloc_count;
+ n_free += socket_stats.free_count;
+ if (dump_socket_mem_flag) {
+ fprintf(f, "::::::::::::::::::::::::::::::::::::::::");
+ fprintf(f,
+ "\nSocket %u:\nsize(M) total: %.6lf\nalloc:"
+ " %.6lf(%.3lf%%)\nfree: %.6lf"
+ "\nmax: %.6lf"
+ "\ncount alloc: %u\nfree: %u\n",
+ i,
+ socket_stats.heap_totalsz_bytes / 1.0e6,
+ socket_stats.heap_allocsz_bytes / 1.0e6,
+ (double)socket_stats.heap_allocsz_bytes * 100 /
+ (double)socket_stats.heap_totalsz_bytes,
+ socket_stats.heap_freesz_bytes / 1.0e6,
+ socket_stats.greatest_free_size / 1.0e6,
+ socket_stats.alloc_count,
+ socket_stats.free_count);
+ fprintf(f, "::::::::::::::::::::::::::::::::::::::::");
+ }
+ }
+ if (dump_socket_mem_flag && active_nodes) {
+ fprintf(f,
+ "\nTotal: size(M)\ntotal: %.6lf"
+ "\nalloc: %.6lf(%.3lf%%)\nfree: %.6lf"
+ "\ncount alloc: %u\nfree: %u\n",
+ total / 1.0e6, alloc / 1.0e6,
+ (double)alloc * 100 / (double)total, free / 1.0e6,
+ n_alloc, n_free);
+ fprintf(f, "::::::::::::::::::::::::::::::::::::::::\n");
+ }
+ return alloc;
+}
+
+static void
+print_flow_error(struct rte_flow_error error)
+{
+ printf("Flow can't be created %d message: %s\n",
+ error.type,
+ error.message ? error.message : "(no stated reason)");
+}
+
+static inline void
+destroy_flows(int port_id, struct rte_flow **flow_list)
+{
+ struct rte_flow_error error;
+ clock_t start_iter, end_iter;
+ double cpu_time_used = 0;
+ double flows_rate;
+ double cpu_time_per_iter[MAX_ITERATIONS];
+ double delta;
+ uint32_t i;
+ int iter_id;
+
+ for (i = 0; i < MAX_ITERATIONS; i++)
+ cpu_time_per_iter[i] = -1;
+
+ if (iterations_number > flows_count)
+ iterations_number = flows_count;
+
+ /* Deletion Rate */
+ printf("Flows Deletion on port = %d\n", port_id);
+ start_iter = clock();
+ for (i = 0; i < flows_count; i++) {
+ if (flow_list[i] == 0)
+ break;
+
+ memset(&error, 0x33, sizeof(error));
+ if (rte_flow_destroy(port_id, flow_list[i], &error)) {
+ print_flow_error(error);
+ rte_exit(EXIT_FAILURE, "Error in deleting flow");
+ }
+
+ if (i && !((i + 1) % iterations_number)) {
+ /* Save the deletion rate of each iter */
+ end_iter = clock();
+ delta = (double) (end_iter - start_iter);
+ iter_id = ((i + 1) / iterations_number) - 1;
+ cpu_time_per_iter[iter_id] =
+ delta / CLOCKS_PER_SEC;
+ cpu_time_used += cpu_time_per_iter[iter_id];
+ start_iter = clock();
+ }
+ }
+
+ /* Deletion rate per iteration */
+ if (dump_iterations)
+ for (i = 0; i < MAX_ITERATIONS; i++) {
+ if (cpu_time_per_iter[i] == -1)
+ continue;
+ delta = (double)(iterations_number /
+ cpu_time_per_iter[i]);
+ flows_rate = delta / 1000;
+ printf(":: Iteration #%d: %d flows "
+ "in %f sec[ Rate = %f K/Sec ]\n",
+ i, iterations_number,
+ cpu_time_per_iter[i], flows_rate);
+ }
+
+ /* Deletion rate for all flows */
+ flows_rate = ((double) (flows_count / cpu_time_used) / 1000);
+ printf("\n:: Total flow deletion rate -> %f K/Sec\n",
+ flows_rate);
+ printf(":: The time for deleting %d in flows %f seconds\n",
+ flows_count, cpu_time_used);
+}
+
+static inline void
+flows_handler(void)
+{
+ struct rte_flow **flow_list;
+ struct rte_flow_error error;
+ clock_t start_iter, end_iter;
+ double cpu_time_used;
+ double flows_rate;
+ double cpu_time_per_iter[MAX_ITERATIONS];
+ double delta;
+ uint16_t nr_ports;
+ uint32_t i;
+ int port_id;
+ int iter_id;
+ uint32_t flow_index;
+
+ nr_ports = rte_eth_dev_count_avail();
+
+ for (i = 0; i < MAX_ITERATIONS; i++)
+ cpu_time_per_iter[i] = -1;
+
+ if (iterations_number > flows_count)
+ iterations_number = flows_count;
+
+ printf(":: Flows Count per port: %d\n", flows_count);
+
+ flow_list = rte_zmalloc("flow_list",
+ (sizeof(struct rte_flow *) * flows_count) + 1, 0);
+ if (flow_list == NULL)
+ rte_exit(EXIT_FAILURE, "No Memory available!");
+
+ for (port_id = 0; port_id < nr_ports; port_id++) {
+ cpu_time_used = 0;
+ flow_index = 0;
+ if (flow_group > 0) {
+ /*
+ * Create global rule to jump into flow_group,
+ * this way the app will avoid the default rules.
+ *
+ * Global rule:
+ * group 0 eth / end actions jump group <flow_group>
+ *
+ */
+ flow = generate_flow(port_id, 0, flow_attrs,
+ FLOW_ITEM_MASK(RTE_FLOW_ITEM_TYPE_ETH),
+ FLOW_ITEM_MASK(RTE_FLOW_ACTION_TYPE_JUMP),
+ flow_group, 0, 0, &error);
+
+ if (flow == NULL) {
+ print_flow_error(error);
+ rte_exit(EXIT_FAILURE, "error in creating flow");
+ }
+ flow_list[flow_index++] = flow;
+ }
+
+ /* Insertion Rate */
+ printf("Flows insertion on port = %d\n", port_id);
+ start_iter = clock();
+ for (i = 0; i < flows_count; i++) {
+ flow = generate_flow(port_id, flow_group,
+ flow_attrs, flow_items, flow_actions,
+ JUMP_ACTION_TABLE, i,
+ hairpin_queues_num, &error);
+
+ if (force_quit)
+ i = flows_count;
+
+ if (!flow) {
+ print_flow_error(error);
+ rte_exit(EXIT_FAILURE, "error in creating flow");
+ }
+
+ flow_list[flow_index++] = flow;
+
+ if (i && !((i + 1) % iterations_number)) {
+ /* Save the insertion rate of each iter */
+ end_iter = clock();
+ delta = (double) (end_iter - start_iter);
+ iter_id = ((i + 1) / iterations_number) - 1;
+ cpu_time_per_iter[iter_id] =
+ delta / CLOCKS_PER_SEC;
+ cpu_time_used += cpu_time_per_iter[iter_id];
+ start_iter = clock();
+ }
+ }
+
+ /* Iteration rate per iteration */
+ if (dump_iterations)
+ for (i = 0; i < MAX_ITERATIONS; i++) {
+ if (cpu_time_per_iter[i] == -1)
+ continue;
+ delta = (double)(iterations_number /
+ cpu_time_per_iter[i]);
+ flows_rate = delta / 1000;
+ printf(":: Iteration #%d: %d flows "
+ "in %f sec[ Rate = %f K/Sec ]\n",
+ i, iterations_number,
+ cpu_time_per_iter[i], flows_rate);
+ }
+
+ /* Insertion rate for all flows */
+ flows_rate = ((double) (flows_count / cpu_time_used) / 1000);
+ printf("\n:: Total flow insertion rate -> %f K/Sec\n",
+ flows_rate);
+ printf(":: The time for creating %d in flows %f seconds\n",
+ flows_count, cpu_time_used);
+
+ if (delete_flag)
+ destroy_flows(port_id, flow_list);
+ }
+}
+
+static void
+signal_handler(int signum)
+{
+ if (signum == SIGINT || signum == SIGTERM) {
+ printf("\n\nSignal %d received, preparing to exit...\n",
+ signum);
+ printf("Error: Stats are wrong due to sudden signal!\n\n");
+ force_quit = true;
+ }
+}
+
+static inline uint16_t
+do_rx(struct lcore_info *li, uint16_t rx_port, uint16_t rx_queue)
+{
+ uint16_t cnt = 0;
+ cnt = rte_eth_rx_burst(rx_port, rx_queue, li->pkts, MAX_PKT_BURST);
+ li->rx_pkts += cnt;
+ return cnt;
+}
+
+static inline void
+do_tx(struct lcore_info *li, uint16_t cnt, uint16_t tx_port,
+ uint16_t tx_queue)
+{
+ uint16_t nr_tx = 0;
+ uint16_t i;
+
+ nr_tx = rte_eth_tx_burst(tx_port, tx_queue, li->pkts, cnt);
+ li->tx_pkts += nr_tx;
+ li->tx_drops += cnt - nr_tx;
+
+ for (i = nr_tx; i < cnt; i++)
+ rte_pktmbuf_free(li->pkts[i]);
+}
+
+/*
+ * Method to convert numbers into pretty numbers that easy
+ * to read. The design here is to add comma after each three
+ * digits and set all of this inside buffer.
+ *
+ * For example if n = 1799321, the output will be
+ * 1,799,321 after this method which is easier to read.
+ */
+static char *
+pretty_number(uint64_t n, char *buf)
+{
+ char p[6][4];
+ int i = 0;
+ int off = 0;
+
+ while (n > 1000) {
+ sprintf(p[i], "%03d", (int)(n % 1000));
+ n /= 1000;
+ i += 1;
+ }
+
+ sprintf(p[i++], "%d", (int)n);
+
+ while (i--)
+ off += sprintf(buf + off, "%s,", p[i]);
+ buf[strlen(buf) - 1] = '\0';
+
+ return buf;
+}
+
+static void
+packet_per_second_stats(void)
+{
+ struct lcore_info *old;
+ struct lcore_info *li, *oli;
+ int nr_lines = 0;
+ int i;
+
+ old = rte_zmalloc("old",
+ sizeof(struct lcore_info) * MAX_LCORES, 0);
+ if (old == NULL)
+ rte_exit(EXIT_FAILURE, "No Memory available!");
+
+ memcpy(old, lcore_infos,
+ sizeof(struct lcore_info) * MAX_LCORES);
+
+ while (!force_quit) {
+ uint64_t total_tx_pkts = 0;
+ uint64_t total_rx_pkts = 0;
+ uint64_t total_tx_drops = 0;
+ uint64_t tx_delta, rx_delta, drops_delta;
+ char buf[3][32];
+ int nr_valid_core = 0;
+
+ sleep(1);
+
+ if (nr_lines) {
+ char go_up_nr_lines[16];
+
+ sprintf(go_up_nr_lines, "%c[%dA\r", 27, nr_lines);
+ printf("%s\r", go_up_nr_lines);
+ }
+
+ printf("\n%6s %16s %16s %16s\n", "core", "tx", "tx drops", "rx");
+ printf("%6s %16s %16s %16s\n", "------", "----------------",
+ "----------------", "----------------");
+ nr_lines = 3;
+ for (i = 0; i < MAX_LCORES; i++) {
+ li = &lcore_infos[i];
+ oli = &old[i];
+ if (li->mode != LCORE_MODE_PKT)
+ continue;
+
+ tx_delta = li->tx_pkts - oli->tx_pkts;
+ rx_delta = li->rx_pkts - oli->rx_pkts;
+ drops_delta = li->tx_drops - oli->tx_drops;
+ printf("%6d %16s %16s %16s\n", i,
+ pretty_number(tx_delta, buf[0]),
+ pretty_number(drops_delta, buf[1]),
+ pretty_number(rx_delta, buf[2]));
+
+ total_tx_pkts += tx_delta;
+ total_rx_pkts += rx_delta;
+ total_tx_drops += drops_delta;
+
+ nr_valid_core++;
+ nr_lines += 1;
+ }
+
+ if (nr_valid_core > 1) {
+ printf("%6s %16s %16s %16s\n", "total",
+ pretty_number(total_tx_pkts, buf[0]),
+ pretty_number(total_tx_drops, buf[1]),
+ pretty_number(total_rx_pkts, buf[2]));
+ nr_lines += 1;
+ }
+
+ memcpy(old, lcore_infos,
+ sizeof(struct lcore_info) * MAX_LCORES);
+ }
+}
+
+static int
+start_forwarding(void *data __rte_unused)
+{
+ int lcore = rte_lcore_id();
+ int stream_id;
+ uint16_t cnt;
+ struct lcore_info *li = &lcore_infos[lcore];
+
+ if (!li->mode)
+ return 0;
+
+ if (li->mode == LCORE_MODE_STATS) {
+ printf(":: started stats on lcore %u\n", lcore);
+ packet_per_second_stats();
+ return 0;
+ }
+
+ while (!force_quit)
+ for (stream_id = 0; stream_id < MAX_STREAMS; stream_id++) {
+ if (li->streams[stream_id].rx_port == -1)
+ continue;
+
+ cnt = do_rx(li,
+ li->streams[stream_id].rx_port,
+ li->streams[stream_id].rx_queue);
+ if (cnt)
+ do_tx(li, cnt,
+ li->streams[stream_id].tx_port,
+ li->streams[stream_id].tx_queue);
+ }
+ return 0;
+}
+
+static void
+init_lcore_info(void)
+{
+ int i, j;
+ unsigned int lcore;
+ uint16_t nr_port;
+ uint16_t queue;
+ int port;
+ int stream_id = 0;
+ int streams_per_core;
+ int unassigned_streams;
+ int nb_fwd_streams;
+ nr_port = rte_eth_dev_count_avail();
+
+ /* First logical core is reserved for stats printing */
+ lcore = rte_get_next_lcore(-1, 0, 0);
+ lcore_infos[lcore].mode = LCORE_MODE_STATS;
+
+ /*
+ * Initialize all cores
+ * All cores at first must have -1 value in all streams
+ * This means that this stream is not used, or not set
+ * yet.
+ */
+ for (i = 0; i < MAX_LCORES; i++)
+ for (j = 0; j < MAX_STREAMS; j++) {
+ lcore_infos[i].streams[j].tx_port = -1;
+ lcore_infos[i].streams[j].rx_port = -1;
+ lcore_infos[i].streams[j].tx_queue = -1;
+ lcore_infos[i].streams[j].rx_queue = -1;
+ lcore_infos[i].streams_nb = 0;
+ }
+
+ /*
+ * Calculate the total streams count.
+ * Also distribute those streams count between the available
+ * logical cores except first core, since it's reserved for
+ * stats prints.
+ */
+ nb_fwd_streams = nr_port * RXQ_NUM;
+ if ((int)(nb_lcores - 1) >= nb_fwd_streams)
+ for (i = 0; i < (int)(nb_lcores - 1); i++) {
+ lcore = rte_get_next_lcore(lcore, 0, 0);
+ lcore_infos[lcore].streams_nb = 1;
+ }
+ else {
+ streams_per_core = nb_fwd_streams / (nb_lcores - 1);
+ unassigned_streams = nb_fwd_streams % (nb_lcores - 1);
+ for (i = 0; i < (int)(nb_lcores - 1); i++) {
+ lcore = rte_get_next_lcore(lcore, 0, 0);
+ lcore_infos[lcore].streams_nb = streams_per_core;
+ if (unassigned_streams) {
+ lcore_infos[lcore].streams_nb++;
+ unassigned_streams--;
+ }
+ }
+ }
+
+ /*
+ * Set the streams for the cores according to each logical
+ * core stream count.
+ * The streams is built on the design of what received should
+ * forward as well, this means that if you received packets on
+ * port 0 queue 0 then the same queue should forward the
+ * packets, using the same logical core.
+ */
+ lcore = rte_get_next_lcore(-1, 0, 0);
+ for (port = 0; port < nr_port; port++) {
+ /* Create FWD stream */
+ for (queue = 0; queue < RXQ_NUM; queue++) {
+ if (!lcore_infos[lcore].streams_nb ||
+ !(stream_id % lcore_infos[lcore].streams_nb)) {
+ lcore = rte_get_next_lcore(lcore, 0, 0);
+ lcore_infos[lcore].mode = LCORE_MODE_PKT;
+ stream_id = 0;
+ }
+ lcore_infos[lcore].streams[stream_id].rx_queue = queue;
+ lcore_infos[lcore].streams[stream_id].tx_queue = queue;
+ lcore_infos[lcore].streams[stream_id].rx_port = port;
+ lcore_infos[lcore].streams[stream_id].tx_port = port;
+ stream_id++;
+ }
+ }
+
+ /* Print all streams */
+ printf(":: Stream -> core id[N]: (rx_port, rx_queue)->(tx_port, tx_queue)\n");
+ for (i = 0; i < MAX_LCORES; i++)
+ for (j = 0; j < MAX_STREAMS; j++) {
+ /* No streams for this core */
+ if (lcore_infos[i].streams[j].tx_port == -1)
+ break;
+ printf("Stream -> core id[%d]: (%d,%d)->(%d,%d)\n",
+ i,
+ lcore_infos[i].streams[j].rx_port,
+ lcore_infos[i].streams[j].rx_queue,
+ lcore_infos[i].streams[j].tx_port,
+ lcore_infos[i].streams[j].tx_queue);
+ }
}
static void
{
int ret;
uint16_t std_queue;
+ uint16_t hairpin_queue;
uint16_t port_id;
uint16_t nr_ports;
+ uint16_t nr_queues;
+ struct rte_eth_hairpin_conf hairpin_conf = {
+ .peer_count = 1,
+ };
struct rte_eth_conf port_conf = {
.rx_adv_conf = {
.rss_conf.rss_hf =
struct rte_eth_rxconf rxq_conf;
struct rte_eth_dev_info dev_info;
+ nr_queues = RXQ_NUM;
+ if (hairpin_queues_num != 0)
+ nr_queues = RXQ_NUM + hairpin_queues_num;
+
nr_ports = rte_eth_dev_count_avail();
if (nr_ports == 0)
rte_exit(EXIT_FAILURE, "Error: no port detected\n");
printf(":: initializing port: %d\n", port_id);
- ret = rte_eth_dev_configure(port_id, RXQ_NUM,
- TXQ_NUM, &port_conf);
+ ret = rte_eth_dev_configure(port_id, nr_queues,
+ nr_queues, &port_conf);
if (ret < 0)
rte_exit(EXIT_FAILURE,
":: cannot configure device: err=%d, port=%u\n",
":: promiscuous mode enable failed: err=%s, port=%u\n",
rte_strerror(-ret), port_id);
+ if (hairpin_queues_num != 0) {
+ /*
+ * Configure peer which represents hairpin Tx.
+ * Hairpin queue numbers start after standard queues
+ * (RXQ_NUM and TXQ_NUM).
+ */
+ for (hairpin_queue = RXQ_NUM, std_queue = 0;
+ hairpin_queue < nr_queues;
+ hairpin_queue++, std_queue++) {
+ hairpin_conf.peers[0].port = port_id;
+ hairpin_conf.peers[0].queue =
+ std_queue + TXQ_NUM;
+ ret = rte_eth_rx_hairpin_queue_setup(
+ port_id, hairpin_queue,
+ NR_RXD, &hairpin_conf);
+ if (ret != 0)
+ rte_exit(EXIT_FAILURE,
+ ":: Hairpin rx queue setup failed: err=%d, port=%u\n",
+ ret, port_id);
+ }
+
+ for (hairpin_queue = TXQ_NUM, std_queue = 0;
+ hairpin_queue < nr_queues;
+ hairpin_queue++, std_queue++) {
+ hairpin_conf.peers[0].port = port_id;
+ hairpin_conf.peers[0].queue =
+ std_queue + RXQ_NUM;
+ ret = rte_eth_tx_hairpin_queue_setup(
+ port_id, hairpin_queue,
+ NR_TXD, &hairpin_conf);
+ if (ret != 0)
+ rte_exit(EXIT_FAILURE,
+ ":: Hairpin tx queue setup failed: err=%d, port=%u\n",
+ ret, port_id);
+ }
+ }
+
ret = rte_eth_dev_start(port_id);
if (ret < 0)
rte_exit(EXIT_FAILURE,
int ret;
uint16_t port;
struct rte_flow_error error;
+ int64_t alloc, last_alloc;
ret = rte_eal_init(argc, argv);
if (ret < 0)
rte_exit(EXIT_FAILURE, "EAL init failed\n");
+ force_quit = false;
+ dump_iterations = false;
+ flows_count = DEFAULT_RULES_COUNT;
+ iterations_number = DEFAULT_ITERATION;
+ delete_flag = false;
+ dump_socket_mem_flag = false;
+ flow_group = 0;
+
+ signal(SIGINT, signal_handler);
+ signal(SIGTERM, signal_handler);
+
argc -= ret;
argv += ret;
if (argc > 1)
if (nb_lcores <= 1)
rte_exit(EXIT_FAILURE, "This app needs at least two cores\n");
+ last_alloc = (int64_t)dump_socket_mem(stdout);
+ flows_handler();
+ alloc = (int64_t)dump_socket_mem(stdout);
+
+ if (last_alloc)
+ fprintf(stdout, ":: Memory allocation change(M): %.6lf\n",
+ (alloc - last_alloc) / 1.0e6);
+
+ if (enable_fwd) {
+ init_lcore_info();
+ rte_eal_mp_remote_launch(start_forwarding, NULL, CALL_MASTER);
+ }
+
RTE_ETH_FOREACH_DEV(port) {
rte_flow_flush(port, &error);
rte_eth_dev_stop(port);