dpif-netdev: Add percentage of pmd/core used by each rxq.

It is based on the length of history that is stored about an
rxq (currently 1 min).

$ ovs-appctl dpif-netdev/pmd-rxq-show
pmd thread numa_id 0 core_id 4:
        isolated : false
        port: dpdkphy1         queue-id:  0    pmd usage: 70 %
        port: dpdkvhost0       queue-id:  0    pmd usage:  0 %
pmd thread numa_id 0 core_id 6:
        isolated : false
        port: dpdkphy0         queue-id:  0    pmd usage: 64 %
        port: dpdkvhost1       queue-id:  0    pmd usage:  0 %

These values are what would be used as part of rxq to pmd
assignment due to a reconfiguration event e.g. adding pmds,
adding rxqs or with the command:

ovs-appctl dpif-netdev/pmd-rxq-rebalance

Signed-off-by: Jan Scheurich <jan.scheurich@ericsson.com>
Co-authored-by: Jan Scheurich <jan.scheurich@ericsson.com>
Signed-off-by: Kevin Traynor <ktraynor@redhat.com>
Signed-off-by: Ian Stokes <ian.stokes@intel.com>

diff --git a/Documentation/howto/dpdk.rst b/Documentation/howto/dpdk.rst
index 587aaed5b0af1a9b7921dd64ae73280e5313a373..40f9d96496dfb4265af8c8393d84094157af84de 100644 (file)
--- a/Documentation/howto/dpdk.rst
+++ b/Documentation/howto/dpdk.rst
@@ -139,6 +139,17 @@ Core 3: Q1 (80%) |
 Core 7: Q4 (70%) | Q5 (10%)
 core 8: Q3 (60%) | Q0 (30%)
 
+To see the current measured usage history of pmd core cycles for each rxq::
+
+    $ ovs-appctl dpif-netdev/pmd-rxq-show
+
+.. note::
+
+  A history of one minute is recorded and shown for each rxq to allow for
+  traffic pattern spikes. An rxq's pmd core cycles usage changes due to traffic
+  pattern or reconfig changes will take one minute before they are fully
+  reflected in the stats.
+
 Rxq to pmds assignment takes place whenever there are configuration changes
 or can be triggered by using::
 

diff --git a/NEWS b/NEWS
index 2c28456b536777a43ce1b43feec7addfa30585aa..96c7c8da4c7aa69a355778b12f7e44e77cbd970c 100644 (file)
--- a/NEWS
+++ b/NEWS
@@ -42,6 +42,7 @@ Post-v2.8.0
           "management" statistics.
         - ovs-ofctl dump-ports command now prints new of set custom statistics
           if available (for OpenFlow 1.4+).
+     * Add rxq utilization of pmd to appctl 'dpif-netdev/pmd-rxq-show'.
    - Userspace datapath:
      * Output packet batching support.
    - vswitchd:

diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.c
index 48a8ebb9082071a73ac089d33d749aa380fc61d4..f94b189e0403c6a2caa3fa356e8a1f57cd59acc7 100644 (file)
--- a/lib/dpif-netdev.c
+++ b/lib/dpif-netdev.c
@@ -567,6 +567,11 @@ struct dp_netdev_pmd_thread {
        are stored for each polled rxq. */
     long long int rxq_next_cycle_store;
 
+    /* Last interval timestamp. */
+    uint64_t intrvl_tsc_prev;
+    /* Last interval cycles. */
+    atomic_ullong intrvl_cycles;
+
     /* Current context of the PMD thread. */
     struct dp_netdev_pmd_thread_ctx ctx;
 
@@ -932,9 +937,9 @@ static void
 pmd_info_show_rxq(struct ds *reply, struct dp_netdev_pmd_thread *pmd)
 {
     if (pmd->core_id != NON_PMD_CORE_ID) {
-        const char *prev_name = NULL;
         struct rxq_poll *list;
-        size_t i, n;
+        size_t n_rxq;
+        uint64_t total_cycles = 0;
 
         ds_put_format(reply,
                       "pmd thread numa_id %d core_id %u:\n\tisolated : %s\n",
@@ -942,22 +947,34 @@ pmd_info_show_rxq(struct ds *reply, struct dp_netdev_pmd_thread *pmd)
                                                   ? "true" : "false");
 
         ovs_mutex_lock(&pmd->port_mutex);
-        sorted_poll_list(pmd, &list, &n);
-        for (i = 0; i < n; i++) {
-            const char *name = netdev_rxq_get_name(list[i].rxq->rx);
+        sorted_poll_list(pmd, &list, &n_rxq);
 
-            if (!prev_name || strcmp(name, prev_name)) {
-                if (prev_name) {
-                    ds_put_cstr(reply, "\n");
-                }
-                ds_put_format(reply, "\tport: %s\tqueue-id:", name);
+        /* Get the total pmd cycles for an interval. */
+        atomic_read_relaxed(&pmd->intrvl_cycles, &total_cycles);
+        /* Estimate the cycles to cover all intervals. */
+        total_cycles *= PMD_RXQ_INTERVAL_MAX;
+
+        for (int i = 0; i < n_rxq; i++) {
+            struct dp_netdev_rxq *rxq = list[i].rxq;
+            const char *name = netdev_rxq_get_name(rxq->rx);
+            uint64_t proc_cycles = 0;
+
+            for (int j = 0; j < PMD_RXQ_INTERVAL_MAX; j++) {
+                proc_cycles += dp_netdev_rxq_get_intrvl_cycles(rxq, j);
             }
-            ds_put_format(reply, " %d",
+            ds_put_format(reply, "\tport: %-16s\tqueue-id: %2d", name,
                           netdev_rxq_get_queue_id(list[i].rxq->rx));
-            prev_name = name;
+            ds_put_format(reply, "\tpmd usage: ");
+            if (total_cycles) {
+                ds_put_format(reply, "%2"PRIu64"",
+                              proc_cycles * 100 / total_cycles);
+                ds_put_cstr(reply, " %");
+            } else {
+                ds_put_format(reply, "%s", "NOT AVAIL");
+            }
+            ds_put_cstr(reply, "\n");
         }
         ovs_mutex_unlock(&pmd->port_mutex);
-        ds_put_cstr(reply, "\n");
         free(list);
     }
 }
@@ -4117,6 +4134,8 @@ reload:
         lc = UINT_MAX;
     }
 
+    pmd->intrvl_tsc_prev = 0;
+    atomic_store_relaxed(&pmd->intrvl_cycles, 0);
     cycles_counter_update(s);
     for (;;) {
         uint64_t iter_packets = 0;
@@ -6116,6 +6135,7 @@ dp_netdev_pmd_try_optimize(struct dp_netdev_pmd_thread *pmd,
     struct dpcls *cls;
 
     if (pmd->ctx.now > pmd->rxq_next_cycle_store) {
+        uint64_t curr_tsc;
         /* Get the cycles that were used to process each queue and store. */
         for (unsigned i = 0; i < poll_cnt; i++) {
             uint64_t rxq_cyc_curr = dp_netdev_rxq_get_cycles(poll_list[i].rxq,
@@ -6124,6 +6144,13 @@ dp_netdev_pmd_try_optimize(struct dp_netdev_pmd_thread *pmd,
             dp_netdev_rxq_set_cycles(poll_list[i].rxq, RXQ_CYCLES_PROC_CURR,
                                      0);
         }
+        curr_tsc = cycles_counter_update(&pmd->perf_stats);
+        if (pmd->intrvl_tsc_prev) {
+            /* There is a prev timestamp, store a new intrvl cycle count. */
+            atomic_store_relaxed(&pmd->intrvl_cycles,
+                                 curr_tsc - pmd->intrvl_tsc_prev);
+        }
+        pmd->intrvl_tsc_prev = curr_tsc;
         /* Start new measuring interval */
         pmd->rxq_next_cycle_store = pmd->ctx.now + PMD_RXQ_INTERVAL_LEN;
     }

diff --git a/tests/pmd.at b/tests/pmd.at
index 83d60f8d339d206654891a676e1cb534d40ffc94..5e9d01e8c79f12a31ecaf4d57e566952061eb7bc 100644 (file)
--- a/tests/pmd.at
+++ b/tests/pmd.at
@@ -6,7 +6,15 @@ m4_divert_push([PREPARE_TESTS])
 # of every rxq (one per line) in the form:
 # port_name rxq_id numa_id core_id
 parse_pmd_rxq_show () {
-    awk '/pmd/ {numa=$4; core=substr($6, 1, length($6) - 1)} /\t/{for (i=4; i<=NF; i++) print  $2, $i, numa, core}' | sort
+    awk '/pmd thread/ {numa=$4; core=substr($6, 1, length($6) - 1)} /\tport:/ {print  $2, $4, numa, core}' | sort
+}
+
+# Given the output of `ovs-appctl dpif-netdev/pmd-rxq-show`,
+# and with queues for each core on one line, prints the rxqs
+# of the core on one line
+# 'port:' port_name 'queue_id:' rxq_id rxq_id rxq_id rxq_id
+parse_pmd_rxq_show_group () {
+   awk '/port:/ {print  $1, $2, $3, $4, $12, $20, $28}'
 }
 
 # Given the output of `ovs-appctl dpctl/dump-flows`, prints a list of flows
@@ -53,7 +61,7 @@ m4_define([CHECK_PMD_THREADS_CREATED], [
 ])
 
 m4_define([SED_NUMA_CORE_PATTERN], ["s/\(numa_id \)[[0-9]]*\( core_id \)[[0-9]]*:/\1<cleared>\2<cleared>:/"])
-m4_define([SED_NUMA_CORE_QUEUE_PATTERN], ["s/\(numa_id \)[[0-9]]*\( core_id \)[[0-9]]*:/\1<cleared>\2<cleared>:/;s/\(queue-id: \)1 2 5 6/\1<cleared>/;s/\(queue-id: \)0 3 4 7/\1<cleared>/"])
+m4_define([SED_NUMA_CORE_QUEUE_PATTERN], ["s/1 2 5 6/<group>/;s/0 3 4 7/<group>/"])
 m4_define([DUMMY_NUMA], [--dummy-numa="0,0,0,0"])
 
 AT_SETUP([PMD - creating a thread/add-port])
@@ -65,7 +73,7 @@ CHECK_PMD_THREADS_CREATED()
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | sed SED_NUMA_CORE_PATTERN], [0], [dnl
 pmd thread numa_id <cleared> core_id <cleared>:
        isolated : false
-       port: p0        queue-id: 0
+       port: p0                queue-id:  0    pmd usage: NOT AVAIL
 ])
 
 AT_CHECK([ovs-appctl dpif/show | sed 's/\(tx_queues=\)[[0-9]]*/\1<cleared>/g'], [0], [dnl
@@ -96,7 +104,14 @@ dummy@ovs-dummy: hit:0 missed:0
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | sed SED_NUMA_CORE_PATTERN], [0], [dnl
 pmd thread numa_id <cleared> core_id <cleared>:
        isolated : false
-       port: p0        queue-id: 0 1 2 3 4 5 6 7
+       port: p0                queue-id:  0    pmd usage: NOT AVAIL
+       port: p0                queue-id:  1    pmd usage: NOT AVAIL
+       port: p0                queue-id:  2    pmd usage: NOT AVAIL
+       port: p0                queue-id:  3    pmd usage: NOT AVAIL
+       port: p0                queue-id:  4    pmd usage: NOT AVAIL
+       port: p0                queue-id:  5    pmd usage: NOT AVAIL
+       port: p0                queue-id:  6    pmd usage: NOT AVAIL
+       port: p0                queue-id:  7    pmd usage: NOT AVAIL
 ])
 
 OVS_VSWITCHD_STOP
@@ -120,20 +135,23 @@ dummy@ovs-dummy: hit:0 missed:0
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | sed SED_NUMA_CORE_PATTERN], [0], [dnl
 pmd thread numa_id <cleared> core_id <cleared>:
        isolated : false
-       port: p0        queue-id: 0 1 2 3 4 5 6 7
+       port: p0                queue-id:  0    pmd usage: NOT AVAIL
+       port: p0                queue-id:  1    pmd usage: NOT AVAIL
+       port: p0                queue-id:  2    pmd usage: NOT AVAIL
+       port: p0                queue-id:  3    pmd usage: NOT AVAIL
+       port: p0                queue-id:  4    pmd usage: NOT AVAIL
+       port: p0                queue-id:  5    pmd usage: NOT AVAIL
+       port: p0                queue-id:  6    pmd usage: NOT AVAIL
+       port: p0                queue-id:  7    pmd usage: NOT AVAIL
 ])
 
 TMP=$(cat ovs-vswitchd.log | wc -l | tr -d [[:blank:]])
 AT_CHECK([ovs-vsctl set Open_vSwitch . other_config:pmd-cpu-mask=0x3])
 CHECK_PMD_THREADS_CREATED([2], [], [+$TMP])
 
-AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | sed SED_NUMA_CORE_QUEUE_PATTERN], [0], [dnl
-pmd thread numa_id <cleared> core_id <cleared>:
-       isolated : false
-       port: p0        queue-id: <cleared>
-pmd thread numa_id <cleared> core_id <cleared>:
-       isolated : false
-       port: p0        queue-id: <cleared>
+AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | sed ':a;/AVAIL$/{N;s/\n//;ba}' | parse_pmd_rxq_show_group | sed SED_NUMA_CORE_QUEUE_PATTERN], [0], [dnl
+port: p0 queue-id: <group>
+port: p0 queue-id: <group>
 ])
 
 TMP=$(cat ovs-vswitchd.log | wc -l | tr -d [[:blank:]])
@@ -143,7 +161,14 @@ CHECK_PMD_THREADS_CREATED([1], [], [+$TMP])
 AT_CHECK([ovs-appctl dpif-netdev/pmd-rxq-show | sed SED_NUMA_CORE_PATTERN], [0], [dnl
 pmd thread numa_id <cleared> core_id <cleared>:
        isolated : false
-       port: p0        queue-id: 0 1 2 3 4 5 6 7
+       port: p0                queue-id:  0    pmd usage: NOT AVAIL
+       port: p0                queue-id:  1    pmd usage: NOT AVAIL
+       port: p0                queue-id:  2    pmd usage: NOT AVAIL
+       port: p0                queue-id:  3    pmd usage: NOT AVAIL
+       port: p0                queue-id:  4    pmd usage: NOT AVAIL
+       port: p0                queue-id:  5    pmd usage: NOT AVAIL
+       port: p0                queue-id:  6    pmd usage: NOT AVAIL
+       port: p0                queue-id:  7    pmd usage: NOT AVAIL
 ])
 
 OVS_VSWITCHD_STOP