@@ -170,7 +170,8 @@ pmd_perf_format_overall_stats(struct ds *str, struct pmd_perf_stats *s,
double duration)
{
uint64_t stats[PMD_N_STATS];
- double us_per_cycle = 1000000.0 / get_tsc_hz();
+ uint64_t tsc_hz = get_tsc_hz();
+ double us_per_cycle = 1000000.0 / tsc_hz;
if (duration == 0) {
return;
@@ -191,25 +192,25 @@ pmd_perf_format_overall_stats(struct ds *str, struct pmd_perf_stats *s,
uint64_t busy_iter = tot_iter >= idle_iter ? tot_iter - idle_iter : 0;
ds_put_format(str,
- " Cycles: %12"PRIu64" (%.2f GHz)\n"
- " Iterations: %12"PRIu64" (%.2f us/it)\n"
- " - idle: %12"PRIu64" (%4.1f %% cycles)\n"
- " - busy: %12"PRIu64" (%4.1f %% cycles)\n",
- tot_cycles, (tot_cycles / duration) / 1E9,
+ " Iterations: %12"PRIu64" (%.2f us/it)\n"
+ " - Used TSC cycles: %12"PRIu64" (%5.1f %% of total cycles)\n"
+ " - idle iterations: %12"PRIu64" (%5.1f %% of used cycles)\n"
+ " - busy iterations: %12"PRIu64" (%5.1f %% of used cycles)\n",
tot_iter, tot_cycles * us_per_cycle / tot_iter,
+ tot_cycles, 100.0 * (tot_cycles / duration) / tsc_hz,
idle_iter,
100.0 * stats[PMD_CYCLES_ITER_IDLE] / tot_cycles,
busy_iter,
100.0 * stats[PMD_CYCLES_ITER_BUSY] / tot_cycles);
if (rx_packets > 0) {
ds_put_format(str,
- " Rx packets: %12"PRIu64" (%.0f Kpps, %.0f cycles/pkt)\n"
- " Datapath passes: %12"PRIu64" (%.2f passes/pkt)\n"
- " - EMC hits: %12"PRIu64" (%4.1f %%)\n"
- " - Megaflow hits: %12"PRIu64" (%4.1f %%, %.2f subtbl lookups/"
- "hit)\n"
- " - Upcalls: %12"PRIu64" (%4.1f %%, %.1f us/upcall)\n"
- " - Lost upcalls: %12"PRIu64" (%4.1f %%)\n",
+ " Rx packets: %12"PRIu64" (%.0f Kpps, %.0f cycles/pkt)\n"
+ " Datapath passes: %12"PRIu64" (%.2f passes/pkt)\n"
+ " - EMC hits: %12"PRIu64" (%5.1f %%)\n"
+ " - Megaflow hits: %12"PRIu64" (%5.1f %%, %.2f "
+ "subtbl lookups/hit)\n"
+ " - Upcalls: %12"PRIu64" (%5.1f %%, %.1f us/upcall)\n"
+ " - Lost upcalls: %12"PRIu64" (%5.1f %%)\n",
rx_packets, (rx_packets / duration) / 1000,
1.0 * stats[PMD_CYCLES_ITER_BUSY] / rx_packets,
passes, rx_packets ? 1.0 * passes / rx_packets : 0,
@@ -225,17 +226,16 @@ pmd_perf_format_overall_stats(struct ds *str, struct pmd_perf_stats *s,
stats[PMD_STAT_LOST],
100.0 * stats[PMD_STAT_LOST] / passes);
} else {
- ds_put_format(str, " Rx packets: %12d\n", 0);
+ ds_put_format(str, " Rx packets: %12d\n", 0);
}
if (tx_packets > 0) {
ds_put_format(str,
- " Tx packets: %12"PRIu64" (%.0f Kpps)\n"
- " Tx batches: %12"PRIu64" (%.2f pkts/batch)"
- "\n",
+ " Tx packets: %12"PRIu64" (%.0f Kpps)\n"
+ " Tx batches: %12"PRIu64" (%.2f pkts/batch)\n",
tx_packets, (tx_packets / duration) / 1000,
tx_batches, 1.0 * tx_packets / tx_batches);
} else {
- ds_put_format(str, " Tx packets: %12d\n\n", 0);
+ ds_put_format(str, " Tx packets: %12d\n\n", 0);
}
}
@@ -123,23 +123,25 @@ Display the last ms_len millisecond stats
The output always contains the following global PMD statistics:
.RS
.IP
-Time: 15:24:55.270 .br
+.EX
+Time: 15:24:55.270
Measurement duration: 1.008 s
pmd thread numa_id 0 core_id 1:
- Cycles: 2419034712 (2.40 GHz)
- Iterations: 572817 (1.76 us/it)
- - idle: 486808 (15.9 % cycles)
- - busy: 86009 (84.1 % cycles)
- Rx packets: 2399607 (2381 Kpps, 848 cycles/pkt)
- Datapath passes: 3599415 (1.50 passes/pkt)
- - EMC hits: 336472 ( 9.3 %)
- - Megaflow hits: 3262943 (90.7 %, 1.00 subtbl lookups/hit)
- - Upcalls: 0 ( 0.0 %, 0.0 us/upcall)
- - Lost upcalls: 0 ( 0.0 %)
- Tx packets: 2399607 (2381 Kpps)
- Tx batches: 171400 (14.00 pkts/batch)
+ Iterations: 572817 (1.76 us/it)
+ - Used TSC cycles: 2419034712 ( 99.9 % of total cycles)
+ - idle iterations: 486808 ( 15.9 % of used cycles)
+ - busy iterations: 86009 ( 84.1 % of used cycles)
+ Rx packets: 2399607 (2381 Kpps, 848 cycles/pkt)
+ Datapath passes: 3599415 (1.50 passes/pkt)
+ - EMC hits: 336472 ( 9.3 %)
+ - Megaflow hits: 3262943 ( 90.7 %, 1.00 subtbl lookups/hit)
+ - Upcalls: 0 ( 0.0 %, 0.0 us/upcall)
+ - Lost upcalls: 0 ( 0.0 %)
+ Tx packets: 2399607 (2381 Kpps)
+ Tx batches: 171400 (14.00 pkts/batch)
+.EE
.RE
.IP
Here "Rx packets" actually reflects the number of packets forwarded by the
@@ -255,6 +255,7 @@ vswitchd/ovs-vswitchd.8: \
lib/dpif-netdev-unixctl.man \
lib/memory-unixctl.man \
lib/netdev-dpdk-unixctl.man \
+ lib/ovs.tmac \
lib/service.man \
lib/ssl-bootstrap.man \
lib/ssl-peer-ca-cert.man \
@@ -273,6 +274,7 @@ lib/dpctl.man:
lib/dpif-netdev-unixctl.man:
lib/memory-unixctl.man:
lib/netdev-dpdk-unixctl.man:
+lib/ovs.tmac:
lib/service.man:
lib/ssl-bootstrap.man:
lib/ssl-peer-ca-cert.man:
@@ -1,9 +1,5 @@
.\" -*- nroff -*-
-.de IQ
-. br
-. ns
-. IP "\\$1"
-..
+.so lib/ovs.tmac
.TH ovs\-vswitchd 8 "@VERSION@" "Open vSwitch" "Open vSwitch Manual"
.\" This program's name:
.ds PN ovs\-vswitchd
'dpif-netdev/pmd-perf-show' command prints the frequency number calculated from the total number of cycles spent for iterations for the measured period. This number could be confusing, because users may think that it should be equal to CPU frequency, especially on non-x86 systems where TSC frequency likely does not match with CPU one. Moreover, counted TSC cycles could differ from the HW TSC cycles in case of a large number of PMD reloads, because cycles spent outside of the main polling loop are not taken into account anywhere. In this case the frequency will not match even TSC frequency. Let's clarify the meaning in order to avoid this misunderstanding. 'Cycles' replaced with 'Used TSC cycles', which describes how many TSC cycles consumed by the main polling loop. % of the total TSC cycles now printed instead of GHz frequency, because GHz is unclear for understanding, especially without knowing the exact TSC frequency. Signed-off-by: Ilya Maximets <i.maximets@samsung.com> --- Version 2: * Fixed OSX manpage build failure due to missing of .EX and .EE. lib/dpif-netdev-perf.c | 36 ++++++++++++++++++------------------ lib/dpif-netdev-unixctl.man | 28 +++++++++++++++------------- manpages.mk | 2 ++ vswitchd/ovs-vswitchd.8.in | 6 +----- 4 files changed, 36 insertions(+), 36 deletions(-)