perfmon plugin: 2-way parallel stat collection

As a FUD reduction measure, this patch implements 2-way parallel
counter collection. Synthetic stat component counter pairs run at the
same time. Running two counters (of any kind) at the same time
naturally reduces the aggregate time required by an approximate
factor-of-2, depending on whether an even or odd number of stats have
been requested.

I don't completely buy the argument that computing synthetic stats
such as instructions-per-clock will be inaccurate if component counter
values are collected sequentially. Given uniform traffic pattern, it
must make no difference.

As the collection interval increases, the difference between serial
and parallel component counter collection will approach zero, see also
the Central Limit theorem.

Change-Id: I36ebdcf125e8882cca8a1929ec58f17fba1ad8f1
Signed-off-by: Dave Barach <dave@barachs.net>

1 files changed, 4 insertions, 2 deletions

diff --git a/src/vlib/node.h b/src/vlib/node.h
index f41eb60aa2c..8bb89f44bc7 100644
--- a/src/vlib/node.h
+++ b/src/vlib/node.h
@@ -258,7 +258,8 @@ typedef struct
   u64 calls, vectors, clocks, suspends;
   u64 max_clock;
   u64 max_clock_n;
-  u64 perf_counter_ticks;
+  u64 perf_counter0_ticks;
+  u64 perf_counter1_ticks;
   u64 perf_counter_vectors;
 } vlib_node_stats_t;
 
@@ -507,7 +508,8 @@ typedef struct vlib_node_runtime_t
   u32 vectors_since_last_overflow;	/**< Number of vector elements
 					  processed by this node. */
 
-  u32 perf_counter_ticks_since_last_overflow; /**< Perf counter ticks */
+  u32 perf_counter0_ticks_since_last_overflow; /**< Perf counter 0 ticks */
+  u32 perf_counter1_ticks_since_last_overflow; /**< Perf counter 1 ticks */
   u32 perf_counter_vectors_since_last_overflow;	/**< Perf counter vectors */
 
   u32 next_frame_index;			/**< Start of next frames for this