app/flow-perf: configure rule batches

Currently, flow-perf measures the performance of
rule installation/deletion operations by breaking
down the entire number of operations into windows
of fixed size (i.e., 100000 operations per window).
Then, flow-perf measures the total time per window
and computes an average time across all windows.

This commit allows flow-perf users to configure
the number of rules per window instead of using
a fixed pre-compiled value. To do so, users must
pass --rules-batch=N, where N is the number of
rules per window (or batch).
For consistency reasons, flow_count variable is
now renamed to rules_count. This variable is the
total number of rules to be installed/deleted.

For example, if a user wants to measure how much
time it takes to install 1M rules in a certain NIC,
he/she can input:
--rules-count=1000000
This way flow-perf will break down 1M flow rules into
10 batches of 100k flow rules each (this is the default
batch size) and compute an average across the 10
measurements.
Now, if the user modifies the number of rules per
batch as follows:
--rules-count=1000000 --rules-batch=500000
then flow-perf will break down 1M flow rules into
2 batches of 500k flow rules each and compute the
average across the 2 measurements.

Finally, this commit also adds default variables
to the usage function instead of hardcoded values.

Signed-off-by: Georgios Katsikas <katsikas.gp@gmail.com>
Acked-by: Wisam Jaddo <wisamm@nvidia.com>

diff --git a/app/test-flow-perf/main.c b/app/test-flow-perf/main.c
index 03d01a8..e2fc5b7 100644 (file)
--- a/app/test-flow-perf/main.c
+++ b/app/test-flow-perf/main.c
@@ -40,7 +40,8 @@
 
 #define MAX_ITERATIONS             100
 #define DEFAULT_RULES_COUNT    4000000
-#define DEFAULT_ITERATION       100000
+#define DEFAULT_RULES_BATCH     100000
+#define DEFAULT_GROUP                0
 
 struct rte_flow *flow;
 static uint8_t flow_group;
@@ -62,8 +63,8 @@ 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 rules_count;
+static uint32_t rules_batch;
 static uint32_t hairpin_queues_num; /* total hairpin q number - default: 0 */
 static uint32_t nb_lcores;
 
@@ -98,8 +99,10 @@ 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("  --rules-count=N: to set the number of needed"
+               " rules to insert, default is %d\n", DEFAULT_RULES_COUNT);
+       printf("  --rules-batch=N: set number of batched rules,"
+               " default is %d\n", DEFAULT_RULES_BATCH);
        printf("  --dump-iterations: To print rates for each"
                " iteration\n");
        printf("  --deletion-rate: Enable deletion rate"
@@ -114,7 +117,7 @@ usage(char *progname)
        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");
+               " default is %d\n", DEFAULT_GROUP);
 
        printf("To set flow items:\n");
        printf("  --ether: add ether layer in flow items\n");
@@ -527,7 +530,8 @@ args_parse(int argc, char **argv)
        static const struct option lgopts[] = {
                /* Control */
                { "help",                       0, 0, 0 },
-               { "flows-count",                1, 0, 0 },
+               { "rules-count",                1, 0, 0 },
+               { "rules-batch",                1, 0, 0 },
                { "dump-iterations",            0, 0, 0 },
                { "deletion-rate",              0, 0, 0 },
                { "dump-socket-mem",            0, 0, 0 },
@@ -705,16 +709,26 @@ args_parse(int argc, char **argv)
                        }
                        /* Control */
                        if (strcmp(lgopts[opt_idx].name,
-                                       "flows-count") == 0) {
+                                       "rules-batch") == 0) {
                                n = atoi(optarg);
-                               if (n > (int) iterations_number)
-                                       flows_count = n;
+                               if (n >= DEFAULT_RULES_BATCH)
+                                       rules_batch = n;
                                else {
-                                       printf("\n\nflows_count should be > %d\n",
-                                               iterations_number);
+                                       printf("\n\nrules_batch should be >= %d\n",
+                                               DEFAULT_RULES_BATCH);
                                        rte_exit(EXIT_SUCCESS, " ");
                                }
                        }
+                       if (strcmp(lgopts[opt_idx].name,
+                                       "rules-count") == 0) {
+                               n = atoi(optarg);
+                               if (n >= (int) rules_batch)
+                                       rules_count = n;
+                               else {
+                                       printf("\n\nrules_count should be >= %d\n",
+                                               rules_batch);
+                               }
+                       }
                        if (strcmp(lgopts[opt_idx].name,
                                        "dump-iterations") == 0)
                                dump_iterations = true;
@@ -826,13 +840,13 @@ destroy_flows(int port_id, struct rte_flow **flow_list)
        for (i = 0; i < MAX_ITERATIONS; i++)
                cpu_time_per_iter[i] = -1;
 
-       if (iterations_number > flows_count)
-               iterations_number = flows_count;
+       if (rules_batch > rules_count)
+               rules_batch = rules_count;
 
        /* Deletion Rate */
        printf("Flows Deletion on port = %d\n", port_id);
        start_iter = clock();
-       for (i = 0; i < flows_count; i++) {
+       for (i = 0; i < rules_count; i++) {
                if (flow_list[i] == 0)
                        break;
 
@@ -842,11 +856,11 @@ destroy_flows(int port_id, struct rte_flow **flow_list)
                        rte_exit(EXIT_FAILURE, "Error in deleting flow");
                }
 
-               if (i && !((i + 1) % iterations_number)) {
+               if (i && !((i + 1) % rules_batch)) {
                        /* Save the deletion rate of each iter */
                        end_iter = clock();
                        delta = (double) (end_iter - start_iter);
-                       iter_id = ((i + 1) / iterations_number) - 1;
+                       iter_id = ((i + 1) / rules_batch) - 1;
                        cpu_time_per_iter[iter_id] =
                                delta / CLOCKS_PER_SEC;
                        cpu_time_used += cpu_time_per_iter[iter_id];
@@ -859,21 +873,21 @@ destroy_flows(int port_id, struct rte_flow **flow_list)
                for (i = 0; i < MAX_ITERATIONS; i++) {
                        if (cpu_time_per_iter[i] == -1)
                                continue;
-                       delta = (double)(iterations_number /
+                       delta = (double)(rules_batch /
                                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,
+                               i, rules_batch,
                                cpu_time_per_iter[i], flows_rate);
                }
 
        /* Deletion rate for all flows */
-       flows_rate = ((double) (flows_count / cpu_time_used) / 1000);
+       flows_rate = ((double) (rules_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);
+               rules_count, cpu_time_used);
 }
 
 static inline void
@@ -902,13 +916,13 @@ flows_handler(void)
        for (i = 0; i < MAX_ITERATIONS; i++)
                cpu_time_per_iter[i] = -1;
 
-       if (iterations_number > flows_count)
-               iterations_number = flows_count;
+       if (rules_batch > rules_count)
+               rules_batch = rules_count;
 
-       printf(":: Flows Count per port: %d\n", flows_count);
+       printf(":: Flows Count per port: %d\n", rules_count);
 
        flow_list = rte_zmalloc("flow_list",
-               (sizeof(struct rte_flow *) * flows_count) + 1, 0);
+               (sizeof(struct rte_flow *) * rules_count) + 1, 0);
        if (flow_list == NULL)
                rte_exit(EXIT_FAILURE, "No Memory available!");
 
@@ -941,7 +955,7 @@ flows_handler(void)
                /* Insertion Rate */
                printf("Flows insertion on port = %d\n", port_id);
                start_iter = clock();
-               for (i = 0; i < flows_count; i++) {
+               for (i = 0; i < rules_count; i++) {
                        flow = generate_flow(port_id, flow_group,
                                flow_attrs, flow_items, flow_actions,
                                JUMP_ACTION_TABLE, i,
@@ -950,7 +964,7 @@ flows_handler(void)
                                &error);
 
                        if (force_quit)
-                               i = flows_count;
+                               i = rules_count;
 
                        if (!flow) {
                                print_flow_error(error);
@@ -959,11 +973,11 @@ flows_handler(void)
 
                        flow_list[flow_index++] = flow;
 
-                       if (i && !((i + 1) % iterations_number)) {
+                       if (i && !((i + 1) % rules_batch)) {
                                /* Save the insertion rate of each iter */
                                end_iter = clock();
                                delta = (double) (end_iter - start_iter);
-                               iter_id = ((i + 1) / iterations_number) - 1;
+                               iter_id = ((i + 1) / rules_batch) - 1;
                                cpu_time_per_iter[iter_id] =
                                        delta / CLOCKS_PER_SEC;
                                cpu_time_used += cpu_time_per_iter[iter_id];
@@ -976,21 +990,21 @@ flows_handler(void)
                        for (i = 0; i < MAX_ITERATIONS; i++) {
                                if (cpu_time_per_iter[i] == -1)
                                        continue;
-                               delta = (double)(iterations_number /
+                               delta = (double)(rules_batch /
                                        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,
+                                       i, rules_batch,
                                        cpu_time_per_iter[i], flows_rate);
                        }
 
                /* Insertion rate for all flows */
-               flows_rate = ((double) (flows_count / cpu_time_used) / 1000);
+               flows_rate = ((double) (rules_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);
+                                               rules_count, cpu_time_used);
 
                if (delete_flag)
                        destroy_flows(port_id, flow_list);
@@ -1415,11 +1429,11 @@ main(int argc, char **argv)
 
        force_quit = false;
        dump_iterations = false;
-       flows_count = DEFAULT_RULES_COUNT;
-       iterations_number = DEFAULT_ITERATION;
+       rules_count = DEFAULT_RULES_COUNT;
+       rules_batch = DEFAULT_RULES_BATCH;
        delete_flag = false;
        dump_socket_mem_flag = false;
-       flow_group = 0;
+       flow_group = DEFAULT_GROUP;
 
        signal(SIGINT, signal_handler);
        signal(SIGTERM, signal_handler);

diff --git a/doc/guides/tools/flow-perf.rst b/doc/guides/tools/flow-perf.rst
index 7e5dc0c..018358a 100644 (file)
--- a/doc/guides/tools/flow-perf.rst
+++ b/doc/guides/tools/flow-perf.rst
@@ -5,19 +5,25 @@ Flow Performance Tool
 =====================
 
 Application for rte_flow performance testing.
-The application provide the ability to test insertion rate of specific
-rte_flow rule, by stressing it to the NIC, and calculate the insertion
-rate.
+The application provides the ability to test insertion rate of specific
+rte_flow rule, by stressing it to the NIC, and calculates the insertion
+and deletion rates.
 
-The application offers some options in the command line, to configure
-which rule to apply.
+The application allows to configure which rule to apply through several
+options of the command line.
 
 After that the application will start producing rules with same pattern
 but increasing the outer IP source address by 1 each time, thus it will
 give different flow each time, and all other items will have open masks.
 
-The application also provide the ability to measure rte flow deletion rate,
-in addition to memory consumption before and after the flows creation.
+To assess the rule insertion rate, the flow performance tool breaks
+down the entire number of flow rule operations into windows of fixed size
+(defaults to 100000 flow rule operations per window, but can be configured).
+Then, the flow performance tool measures the total time per window and
+computes an average time across all windows.
+
+The application also provides the ability to measure rte flow deletion rate,
+in addition to memory consumption before and after the flow rules' creation.
 
 The app supports single and multi core performance measurements.
 
@@ -59,21 +65,31 @@ with a ``--`` separator:
 
 .. code-block:: console
 
-       sudo ./dpdk-test-flow_perf -n 4 -w 08:00.0 -- --ingress --ether --ipv4 --queue --flows-count=1000000
+       sudo ./dpdk-test-flow_perf -n 4 -w 08:00.0 -- --ingress --ether --ipv4 --queue --rules-count=1000000
 
 The command line options are:
 
 *      ``--help``
        Display a help message and quit.
 
-*      ``--flows-count=N``
-       Set the number of needed flows to insert,
-       where 1 <= N <= "number of flows".
+*      ``--rules-count=N``
+       Set the total number of flow rules to insert,
+       where 1 <= N <= "number of flow rules".
        The default value is 4,000,000.
 
+*      ``--rules-batch=N``
+       Set the number of flow rules to insert per iteration window,
+       where 1 <= N <= "number of flow rules per iteration window".
+       The default value is 100,000 flow rules per iteration window.
+       For a total of --rules-count=1000000 flow rules to be inserted
+       and an iteration window size of --rules-batch=100000 flow rules,
+       the application will measure the insertion rate 10 times
+       (i.e., once every 100000 flow rules) and then report an average
+       insertion rate across the 10 measurements.
+
 *      ``--dump-iterations``
-       Print rates for each iteration of flows.
-       Default iteration is 1,00,000.
+       Print rates for each iteration window.
+       Default iteration window equals to the rules-batch size (i.e., 100,000).
 
 *      ``--deletion-rate``
        Enable deletion rate calculations.