dpif-netdev: Make pmd-rxq-show time configurable.

pmd-rxq-show shows the Rx queue to pmd assignments as well as the
pmd usage of each Rx queue.

Up until now a tail length of 60 seconds pmd usage was shown
for each Rx queue, as this is the value used during rebalance
to avoid any spike effects.

When debugging or tuning, it is also convenient to display the
pmd usage of an Rx queue over a shorter time frame, so any changes
config or traffic that impact pmd usage can be evaluated more quickly.

A parameter is added that allows pmd-rxq-show stats pmd usage to
be shown for a shorter time frame. Values are rounded up to the
nearest 5 seconds as that is the measurement granularity and the value
used is displayed. e.g.

$ ovs-appctl dpif-netdev/pmd-rxq-show -secs 5
 Displaying last 5 seconds pmd usage %
 pmd thread numa_id 0 core_id 4:
   isolated : false
   port: dpdk0            queue-id:  0 (enabled)   pmd usage: 95 %
   overhead:  4 %

The default time frame has not changed and the maximum value
is limited to the maximum stored tail length (60 seconds).

Reviewed-by: David Marchand <david.marchand@redhat.com>
Signed-off-by: Kevin Traynor <ktraynor@redhat.com>
Signed-off-by: Ilya Maximets <i.maximets@ovn.org>

lib/dpif-netdev-private-thread.h

@@ -114,7 +114,7 @@ struct dp_netdev_pmd_thread {
     atomic_ullong intrvl_cycles;
 
     /* Write index for 'busy_cycles_intrvl'. */
-    unsigned int intrvl_idx;
+    atomic_count intrvl_idx;
     /* Busy cycles in last PMD_INTERVAL_MAX intervals. */
     atomic_ullong *busy_cycles_intrvl;
 

lib/dpif-netdev.c

@@ -160,11 +160,13 @@ static struct odp_support dp_netdev_support = {
 
 /* Time in microseconds of the interval in which rxq processing cycles used
  * in rxq to pmd assignments is measured and stored. */
-#define PMD_INTERVAL_LEN 10000000LL
+#define PMD_INTERVAL_LEN 5000000LL
+/* For converting PMD_INTERVAL_LEN to secs. */
+#define INTERVAL_USEC_TO_SEC 1000000LL
 
 /* Number of intervals for which cycles are stored
  * and used during rxq to pmd assignment. */
-#define PMD_INTERVAL_MAX 6
+#define PMD_INTERVAL_MAX 12
 
 /* Time in microseconds to try RCU quiescing. */
 #define PMD_RCU_QUIESCE_INTERVAL 10000LL
@@ -428,7 +430,7 @@ struct dp_netdev_rxq {
                                           pinned. OVS_CORE_UNSPEC if the
                                           queue doesn't need to be pinned to a
                                           particular core. */
-    unsigned intrvl_idx;               /* Write index for 'cycles_intrvl'. */
+    atomic_count intrvl_idx;           /* Write index for 'cycles_intrvl'. */
     struct dp_netdev_pmd_thread *pmd;  /* pmd thread that polls this queue. */
     bool is_vhost;                     /* Is rxq of a vhost port. */
 
@@ -615,6 +617,9 @@ dp_netdev_rxq_set_intrvl_cycles(struct dp_netdev_rxq *rx,
                            unsigned long long cycles);
 static uint64_t
 dp_netdev_rxq_get_intrvl_cycles(struct dp_netdev_rxq *rx, unsigned idx);
+static uint64_t
+get_interval_values(atomic_ullong *source, atomic_count *cur_idx,
+                    int num_to_read);
 static void
 dpif_netdev_xps_revalidate_pmd(const struct dp_netdev_pmd_thread *pmd,
                                bool purge);
@@ -869,7 +874,8 @@ sorted_poll_list(struct dp_netdev_pmd_thread *pmd, struct rxq_poll **list,
 }
 
 static void
-pmd_info_show_rxq(struct ds *reply, struct dp_netdev_pmd_thread *pmd)
+pmd_info_show_rxq(struct ds *reply, struct dp_netdev_pmd_thread *pmd,
+                  int secs)
 {
     if (pmd->core_id != NON_PMD_CORE_ID) {
         struct rxq_poll *list;
@@ -877,6 +883,7 @@ pmd_info_show_rxq(struct ds *reply, struct dp_netdev_pmd_thread *pmd)
         uint64_t total_cycles = 0;
         uint64_t busy_cycles = 0;
         uint64_t total_rxq_proc_cycles = 0;
+        unsigned int intervals;
 
         ds_put_format(reply,
                       "pmd thread numa_id %d core_id %u:\n  isolated : %s\n",
@@ -888,15 +895,14 @@ pmd_info_show_rxq(struct ds *reply, struct dp_netdev_pmd_thread *pmd)
 
         /* Get the total pmd cycles for an interval. */
         atomic_read_relaxed(&pmd->intrvl_cycles, &total_cycles);
+        /* Calculate how many intervals are to be used. */
+        intervals = DIV_ROUND_UP(secs,
+                                 PMD_INTERVAL_LEN / INTERVAL_USEC_TO_SEC);
         /* Estimate the cycles to cover all intervals. */
-        total_cycles *= PMD_INTERVAL_MAX;
+        total_cycles *= intervals;
-
+        busy_cycles = get_interval_values(pmd->busy_cycles_intrvl,
-        for (int j = 0; j < PMD_INTERVAL_MAX; j++) {
+                                          &pmd->intrvl_idx,
-            uint64_t cycles;
+                                          intervals);
-
-            atomic_read_relaxed(&pmd->busy_cycles_intrvl[j], &cycles);
-            busy_cycles += cycles;
-        }
         if (busy_cycles > total_cycles) {
             busy_cycles = total_cycles;
         }
@@ -906,9 +912,9 @@ pmd_info_show_rxq(struct ds *reply, struct dp_netdev_pmd_thread *pmd)
             const char *name = netdev_rxq_get_name(rxq->rx);
             uint64_t rxq_proc_cycles = 0;
 
-            for (int j = 0; j < PMD_INTERVAL_MAX; j++) {
+            rxq_proc_cycles = get_interval_values(rxq->cycles_intrvl,
-                rxq_proc_cycles += dp_netdev_rxq_get_intrvl_cycles(rxq, j);
+                                                  &rxq->intrvl_idx,
-            }
+                                                  intervals);
             total_rxq_proc_cycles += rxq_proc_cycles;
             ds_put_format(reply, "  port: %-16s  queue-id: %2d", name,
                           netdev_rxq_get_queue_id(list[i].rxq->rx));
@@ -1422,6 +1428,10 @@ dpif_netdev_pmd_info(struct unixctl_conn *conn, int argc, const char *argv[],
     unsigned int core_id;
     bool filter_on_pmd = false;
     size_t n;
+    unsigned int secs = 0;
+    unsigned long long max_secs = (PMD_INTERVAL_LEN * PMD_INTERVAL_MAX)
+                                      / INTERVAL_USEC_TO_SEC;
+    bool first_show_rxq = true;
 
     ovs_mutex_lock(&dp_netdev_mutex);
 
@@ -1432,6 +1442,14 @@ dpif_netdev_pmd_info(struct unixctl_conn *conn, int argc, const char *argv[],
             }
             argc -= 2;
             argv += 2;
+        } else if (type == PMD_INFO_SHOW_RXQ &&
+                       !strcmp(argv[1], "-secs") &&
+                       argc > 2) {
+            if (!str_to_uint(argv[2], 10, &secs)) {
+                secs = max_secs;
+            }
+            argc -= 2;
+            argv += 2;
         } else {
             dp = shash_find_data(&dp_netdevs, argv[1]);
             argc -= 1;
@@ -1461,7 +1479,18 @@ dpif_netdev_pmd_info(struct unixctl_conn *conn, int argc, const char *argv[],
             continue;
         }
         if (type == PMD_INFO_SHOW_RXQ) {
-            pmd_info_show_rxq(&reply, pmd);
+            if (first_show_rxq) {
+                if (!secs || secs > max_secs) {
+                    secs = max_secs;
+                } else {
+                    secs = ROUND_UP(secs,
+                                    PMD_INTERVAL_LEN / INTERVAL_USEC_TO_SEC);
+                }
+                ds_put_format(&reply, "Displaying last %u seconds "
+                              "pmd usage %%\n", secs);
+                first_show_rxq = false;
+            }
+            pmd_info_show_rxq(&reply, pmd, secs);
         } else if (type == PMD_INFO_CLEAR_STATS) {
             pmd_perf_stats_clear(&pmd->perf_stats);
         } else if (type == PMD_INFO_SHOW_STATS) {
@@ -1576,8 +1605,9 @@ dpif_netdev_init(void)
     unixctl_command_register("dpif-netdev/pmd-stats-clear", "[-pmd core] [dp]",
                              0, 3, dpif_netdev_pmd_info,
                              (void *)&clear_aux);
-    unixctl_command_register("dpif-netdev/pmd-rxq-show", "[-pmd core] [dp]",
+    unixctl_command_register("dpif-netdev/pmd-rxq-show", "[-pmd core] "
-                             0, 3, dpif_netdev_pmd_info,
+                             "[-secs secs] [dp]",
+                             0, 5, dpif_netdev_pmd_info,
                              (void *)&poll_aux);
     unixctl_command_register("dpif-netdev/pmd-perf-show",
                              "[-nh] [-it iter-history-len]"
@@ -5174,7 +5204,7 @@ static void
 dp_netdev_rxq_set_intrvl_cycles(struct dp_netdev_rxq *rx,
                                 unsigned long long cycles)
 {
-    unsigned int idx = rx->intrvl_idx++ % PMD_INTERVAL_MAX;
+    unsigned int idx = atomic_count_inc(&rx->intrvl_idx) % PMD_INTERVAL_MAX;
     atomic_store_relaxed(&rx->cycles_intrvl[idx], cycles);
 }
 
@@ -6914,6 +6944,9 @@ pmd_thread_main(void *f_)
 reload:
     atomic_count_init(&pmd->pmd_overloaded, 0);
 
+    pmd->intrvl_tsc_prev = 0;
+    atomic_store_relaxed(&pmd->intrvl_cycles, 0);
+
     if (!dpdk_attached) {
         dpdk_attached = dpdk_attach_thread(pmd->core_id);
     }
@@ -6945,12 +6978,10 @@ reload:
         }
     }
 
-    pmd->intrvl_tsc_prev = 0;
-    atomic_store_relaxed(&pmd->intrvl_cycles, 0);
     for (i = 0; i < PMD_INTERVAL_MAX; i++) {
         atomic_store_relaxed(&pmd->busy_cycles_intrvl[i], 0);
     }
-    pmd->intrvl_idx = 0;
+    atomic_count_set(&pmd->intrvl_idx, 0);
     cycles_counter_update(s);
 
     pmd->next_rcu_quiesce = pmd->ctx.now + PMD_RCU_QUIESCE_INTERVAL;
@@ -9931,7 +9962,7 @@ dp_netdev_pmd_try_optimize(struct dp_netdev_pmd_thread *pmd,
             atomic_store_relaxed(&pmd->intrvl_cycles,
                                  curr_tsc - pmd->intrvl_tsc_prev);
         }
-        idx = pmd->intrvl_idx++ % PMD_INTERVAL_MAX;
+        idx = atomic_count_inc(&pmd->intrvl_idx) % PMD_INTERVAL_MAX;
         atomic_store_relaxed(&pmd->busy_cycles_intrvl[idx], tot_proc);
         pmd->intrvl_tsc_prev = curr_tsc;
         /* Start new measuring interval */
@@ -9954,6 +9985,27 @@ dp_netdev_pmd_try_optimize(struct dp_netdev_pmd_thread *pmd,
     }
 }
 
+/* Returns the sum of a specified number of newest to
+ * oldest interval values. 'cur_idx' is where the next
+ * write will be and wrap around needs to be handled.
+ */
+static uint64_t
+get_interval_values(atomic_ullong *source, atomic_count *cur_idx,
+                    int num_to_read) {
+    unsigned int i;
+    uint64_t total = 0;
+
+    i = atomic_count_get(cur_idx) % PMD_INTERVAL_MAX;
+    for (int read = 0; read < num_to_read; read++) {
+        uint64_t interval_value;
+
+        i = i ? i - 1 : PMD_INTERVAL_MAX - 1;
+        atomic_read_relaxed(&source[i], &interval_value);
+        total += interval_value;
+    }
+    return total;
+}
+
 /* Insert 'rule' into 'cls'. */
 static void
 dpcls_insert(struct dpcls *cls, struct dpcls_rule *rule,

tests/pmd.at

@@ -70,6 +70,7 @@ CHECK_CPU_DISCOVERED()
 CHECK_PMD_THREADS_CREATED()
 
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | sed SED_NUMA_CORE_PATTERN], [0], [dnl
+Displaying last 60 seconds pmd usage %
 pmd thread numa_id <cleared> core_id <cleared>:
   isolated : false
   port: p0                queue-id:  0 (enabled)   pmd usage: NOT AVAIL
@@ -102,6 +103,7 @@ dummy@ovs-dummy: hit:0 missed:0
 ])
 
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | sed SED_NUMA_CORE_PATTERN], [0], [dnl
+Displaying last 60 seconds pmd usage %
 pmd thread numa_id <cleared> core_id <cleared>:
   isolated : false
   port: p0                queue-id:  0 (enabled)   pmd usage: NOT AVAIL
@@ -134,6 +136,7 @@ dummy@ovs-dummy: hit:0 missed:0
 ])
 
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | sed SED_NUMA_CORE_PATTERN], [0], [dnl
+Displaying last 60 seconds pmd usage %
 pmd thread numa_id <cleared> core_id <cleared>:
   isolated : false
   port: p0                queue-id:  0 (enabled)   pmd usage: NOT AVAIL
@@ -183,6 +186,7 @@ AT_CHECK([ovs-vsctl set Open_vSwitch . other_config:pmd-cpu-mask=0x1])
 CHECK_PMD_THREADS_CREATED([1], [], [+$TMP])
 
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | sed SED_NUMA_CORE_PATTERN], [0], [dnl
+Displaying last 60 seconds pmd usage %
 pmd thread numa_id <cleared> core_id <cleared>:
   isolated : false
   port: p0                queue-id:  0 (enabled)   pmd usage: NOT AVAIL
@@ -215,6 +219,7 @@ dummy@ovs-dummy: hit:0 missed:0
 ])
 
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | sed SED_NUMA_CORE_PATTERN], [0], [dnl
+Displaying last 60 seconds pmd usage %
 pmd thread numa_id <cleared> core_id <cleared>:
   isolated : false
   port: p0                queue-id:  0 (enabled)   pmd usage: NOT AVAIL
@@ -280,6 +285,7 @@ CHECK_PMD_THREADS_CREATED([1], [1], [+$TMP])
 OVS_WAIT_UNTIL([tail -n +$TMP ovs-vswitchd.log | grep "Performing pmd to rx queue assignment using group algorithm"])
 
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show], [0], [dnl
+Displaying last 60 seconds pmd usage %
 pmd thread numa_id 1 core_id 1:
   isolated : false
   port: p0                queue-id:  0 (enabled)   pmd usage: NOT AVAIL
@@ -302,6 +308,7 @@ AT_CHECK([ovs-vsctl set Open_vSwitch . other_config:pmd-rxq-assign=roundrobin])
 OVS_WAIT_UNTIL([tail -n +$TMP ovs-vswitchd.log | grep "Performing pmd to rx queue assignment using roundrobin algorithm"])
 
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show], [0], [dnl
+Displaying last 60 seconds pmd usage %
 pmd thread numa_id 1 core_id 1:
   isolated : false
   port: p0                queue-id:  0 (enabled)   pmd usage: NOT AVAIL
@@ -322,6 +329,7 @@ AT_CHECK([ovs-vsctl set Open_vSwitch . other_config:pmd-rxq-assign=cycles])
 OVS_WAIT_UNTIL([tail -n +$TMP ovs-vswitchd.log | grep "Performing pmd to rx queue assignment using cycles algorithm"])
 
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show], [0], [dnl
+Displaying last 60 seconds pmd usage %
 pmd thread numa_id 1 core_id 1:
   isolated : false
   port: p0                queue-id:  0 (enabled)   pmd usage: NOT AVAIL
@@ -343,6 +351,7 @@ AT_CHECK([ovs-vsctl set Open_vSwitch . other_config:pmd-cpu-mask=0x1])
 CHECK_PMD_THREADS_CREATED([1], [1], [+$TMP])
 
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show], [0], [dnl
+Displaying last 60 seconds pmd usage %
 pmd thread numa_id 1 core_id 0:
   isolated : false
   port: p0                queue-id:  0 (enabled)   pmd usage: NOT AVAIL
@@ -471,6 +480,59 @@ pmd thread numa_id <cleared> core_id <cleared>:
 OVS_VSWITCHD_STOP
 AT_CLEANUP
 
+AT_SETUP([PMD - pmd-rxq-show pmd usage time])
+OVS_VSWITCHD_START([add-port br0 p0 -- set Interface p0 type=dummy-pmd], [], [], [DUMMY_NUMA])
+
+#CHECK_CPU_DISCOVERED()
+#CHECK_PMD_THREADS_CREATED()
+
+AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | grep Displaying], [0], [dnl
+Displaying last 60 seconds pmd usage %
+])
+
+AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show -secs -1 | grep Displaying], [0], [dnl
+Displaying last 60 seconds pmd usage %
+])
+
+AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show -secs 0 | grep Displaying], [0], [dnl
+Displaying last 60 seconds pmd usage %
+])
+
+AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show -secs 1 | grep Displaying], [0], [dnl
+Displaying last 5 seconds pmd usage %
+])
+
+AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show -secs 5 | grep Displaying], [0], [dnl
+Displaying last 5 seconds pmd usage %
+])
+
+AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show -secs 6 | grep Displaying], [0], [dnl
+Displaying last 10 seconds pmd usage %
+])
+
+AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show -secs 51 | grep Displaying], [0], [dnl
+Displaying last 55 seconds pmd usage %
+])
+
+AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show -secs 55 | grep Displaying], [0], [dnl
+Displaying last 55 seconds pmd usage %
+])
+
+AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show -secs 56 | grep Displaying], [0], [dnl
+Displaying last 60 seconds pmd usage %
+])
+
+AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show -secs 60 | grep Displaying], [0], [dnl
+Displaying last 60 seconds pmd usage %
+])
+
+AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show -secs 61 | grep Displaying], [0], [dnl
+Displaying last 60 seconds pmd usage %
+])
+
+OVS_VSWITCHD_STOP
+AT_CLEANUP
+
 dnl Reconfigure the number of rx queues of a port, make sure that all the
 dnl queues are polled by the datapath and try to send a couple of packets.
 AT_SETUP([PMD - reconfigure n_rxq])