From 568636d562b4c64d0095ff2ac921b79eb69e520d Mon Sep 17 00:00:00 2001
From: Jeff Epler <jepler@gmail.com>
Date: Mon, 18 Nov 2019 09:53:12 -0600
Subject: [PATCH] run_background_tasks: Do nothing unless there has been a tick

This improves performance of running python code by 34%, based
on the "pystone" benchmark on metro m4 express at 5000 passes
(1127.65 -> 1521.6 passes/second).

In addition, by instrumenting the tick function and monitoring on an
oscilloscope, the time actually spent in run_background_tasks() on
the metro m4 decreases from average 43% to 0.5%. (however, there's
some additional overhead that is moved around and not accounted for
in that "0.5%" figure, each time supervisor_run_background_tasks_if_tick
is called but no tick has occurred)

On the CPB, it increases pystone from 633 to 769, a smaller percentage
increase of 21%.  I did not measure the time actually spent in
run_background_tasks() on CPB.

Testing performed: on metro m4 and cpb, run pystone adapted from python3.4
(change time.time to time.monotonic for sub-second resolution)

Besides running a 5000 pass test, I also ran a 50-pass test while
scoping how long an output pin was set.  Average: 34.59ms or 1445/s on m4,
67.61ms or 739/s on cbp, both matching the other pystone result reasonably
well.

import pystone
import board
import digitalio
import time

d = digitalio.DigitalInOut(board.D13)
d.direction = digitalio.Direction.OUTPUT

while True:
    d.value = 0
    time.sleep(.01)
    d.value = 1
    pystone.main(50)
---
 py/circuitpy_mpconfig.h  |  4 ++--
 supervisor/shared/tick.c | 12 ++++++++++++
 supervisor/shared/tick.h |  1 +
 3 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/py/circuitpy_mpconfig.h b/py/circuitpy_mpconfig.h
index 7853e4de95..3e83d0c510 100644
--- a/py/circuitpy_mpconfig.h
+++ b/py/circuitpy_mpconfig.h
@@ -653,8 +653,8 @@ extern const struct _mp_obj_module_t ustack_module;
     FLASH_ROOT_POINTERS \
     NETWORK_ROOT_POINTERS \
 
-void run_background_tasks(void);
-#define RUN_BACKGROUND_TASKS (run_background_tasks())
+void supervisor_run_background_tasks_if_tick(void);
+#define RUN_BACKGROUND_TASKS (supervisor_run_background_tasks_if_tick())
 
 // TODO: Used in wiznet5k driver, but may not be needed in the long run.
 #define MICROPY_THREAD_YIELD()
diff --git a/supervisor/shared/tick.c b/supervisor/shared/tick.c
index d4a6ac5d75..7dc5a52d32 100644
--- a/supervisor/shared/tick.c
+++ b/supervisor/shared/tick.c
@@ -24,10 +24,13 @@
  * THE SOFTWARE.
  */
 
+#include <stdatomic.h>
+
 #include "supervisor/shared/tick.h"
 #include "supervisor/filesystem.h"
 #include "supervisor/shared/autoreload.h"
 
+static atomic_bool tick_up;
 static volatile uint64_t ticks_ms;
 
 #if CIRCUITPY_GAMEPAD
@@ -44,6 +47,7 @@ void supervisor_tick(void) {
 
     ticks_ms ++;
 
+    atomic_store(&tick_up, true);
 
 #if CIRCUITPY_FILESYSTEM_FLUSH_INTERVAL_MS > 0
     filesystem_tick();
@@ -74,3 +78,11 @@ uint64_t supervisor_ticks_ms64() {
 uint32_t supervisor_ticks_ms32() {
     return ticks_ms;
 }
+
+extern void run_background_tasks(void);
+
+void supervisor_run_background_tasks_if_tick() {
+    if (atomic_exchange(&tick_up, false)) {
+        run_background_tasks();
+    }
+}
diff --git a/supervisor/shared/tick.h b/supervisor/shared/tick.h
index 3defeb1081..b662734492 100644
--- a/supervisor/shared/tick.h
+++ b/supervisor/shared/tick.h
@@ -33,5 +33,6 @@
 extern void supervisor_tick(void);
 extern uint32_t supervisor_ticks_ms32(void);
 extern uint64_t supervisor_ticks_ms64(void);
+extern void supervisor_run_background_if_tick(void);
 
 #endif