py/gc: Implement GC running by allocation threshold.

Currently, MicroPython runs GC when it could not allocate a block of memory,
which happens when heap is exhausted. However, that policy can't work well
with "inifinity" heaps, e.g. backed by a virtual memory - there will be a
lot of swap thrashing long before VM will be exhausted. Instead, in such
cases "allocation threshold" policy is used: a GC is run after some number of
allocations have been made. Details vary, for example, number or total amount
of allocations can be used, threshold may be self-adjusting based on GC
outcome, etc.

This change implements a simple variant of such policy for MicroPython. Amount
of allocated memory so far is used for threshold, to make it useful to typical
finite-size, and small, heaps as used with MicroPython ports. And such GC policy
is indeed useful for such types of heaps too, as it allows to better control
fragmentation. For example, if a threshold is set to half size of heap, then
for an application which usually makes big number of small allocations, that
will (try to) keep half of heap memory in a nice defragmented state for an
occasional large allocation.

For an application which doesn't exhibit such behavior, there won't be any
visible effects, except for GC running more frequently, which however may
affect performance. To address this, the GC threshold is configurable, and
by default is off so far. It's configured with gc.threshold(amount_in_bytes)
call (can be queries without an argument).

4 files changed, 55 insertions, 0 deletions

diff --git a/py/gc.c b/py/gc.c
index 1c1865cdb4..97868c07f8 100644
--- a/py/gc.c
+++ b/py/gc.c
@@ -152,6 +152,12 @@ void gc_init(void *start, void *end) {
     // allow auto collection
     MP_STATE_MEM(gc_auto_collect_enabled) = 1;
 
+    #if MICROPY_GC_ALLOC_THRESHOLD
+    // by default, maxuint for gc threshold, effectively turning gc-by-threshold off
+    MP_STATE_MEM(gc_alloc_threshold) = (size_t)-1;
+    MP_STATE_MEM(gc_alloc_amount) = 0;
+    #endif
+
     #if MICROPY_PY_THREAD
     mp_thread_mutex_init(&MP_STATE_MEM(gc_mutex));
     #endif
@@ -294,6 +300,9 @@ STATIC void gc_sweep(void) {
 void gc_collect_start(void) {
     GC_ENTER();
     MP_STATE_MEM(gc_lock_depth)++;
+    #if MICROPY_GC_ALLOC_THRESHOLD
+    MP_STATE_MEM(gc_alloc_amount) = 0;
+    #endif
     MP_STATE_MEM(gc_stack_overflow) = 0;
     MP_STATE_MEM(gc_sp) = MP_STATE_MEM(gc_stack);
     // Trace root pointers.  This relies on the root pointers being organised
@@ -405,6 +414,15 @@ void *gc_alloc(size_t n_bytes, bool has_finaliser) {
     size_t start_block;
     size_t n_free = 0;
     int collected = !MP_STATE_MEM(gc_auto_collect_enabled);
+
+    #if MICROPY_GC_ALLOC_THRESHOLD
+    if (!collected && MP_STATE_MEM(gc_alloc_amount) >= MP_STATE_MEM(gc_alloc_threshold)) {
+        GC_EXIT();
+        gc_collect();
+        GC_ENTER();
+    }
+    #endif
+
     for (;;) {
 
         // look for a run of n_blocks available blocks
@@ -456,6 +474,10 @@ found:
     void *ret_ptr = (void*)(MP_STATE_MEM(gc_pool_start) + start_block * BYTES_PER_BLOCK);
     DEBUG_printf("gc_alloc(%p)\n", ret_ptr);
 
+    #if MICROPY_GC_ALLOC_THRESHOLD
+    MP_STATE_MEM(gc_alloc_amount) += n_blocks;
+    #endif
+
     GC_EXIT();
 
     // zero out the additional bytes of the newly allocated blocks
diff --git a/py/modgc.c b/py/modgc.c
index d68ff7e6c0..976fb89980 100644
--- a/py/modgc.c
+++ b/py/modgc.c
@@ -83,6 +83,25 @@ STATIC mp_obj_t gc_mem_alloc(void) {
 }
 MP_DEFINE_CONST_FUN_OBJ_0(gc_mem_alloc_obj, gc_mem_alloc);
 
+#if MICROPY_GC_ALLOC_THRESHOLD
+STATIC mp_obj_t gc_threshold(size_t n_args, const mp_obj_t *args) {
+    if (n_args == 0) {
+        if (MP_STATE_MEM(gc_alloc_threshold) == (size_t)-1) {
+            return MP_OBJ_NEW_SMALL_INT(-1);
+        }
+        return mp_obj_new_int(MP_STATE_MEM(gc_alloc_threshold) * MICROPY_BYTES_PER_GC_BLOCK);
+    }
+    mp_int_t val = mp_obj_get_int(args[0]);
+    if (val < 0) {
+        MP_STATE_MEM(gc_alloc_threshold) = (size_t)-1;
+    } else {
+        MP_STATE_MEM(gc_alloc_threshold) = val / MICROPY_BYTES_PER_GC_BLOCK;
+    }
+    return mp_const_none;
+}
+MP_DEFINE_CONST_FUN_OBJ_VAR_BETWEEN(gc_threshold_obj, 0, 1, gc_threshold);
+#endif
+
 STATIC const mp_rom_map_elem_t mp_module_gc_globals_table[] = {
     { MP_ROM_QSTR(MP_QSTR___name__), MP_ROM_QSTR(MP_QSTR_gc) },
     { MP_ROM_QSTR(MP_QSTR_collect), MP_ROM_PTR(&gc_collect_obj) },
@@ -91,6 +110,9 @@ STATIC const mp_rom_map_elem_t mp_module_gc_globals_table[] = {
     { MP_ROM_QSTR(MP_QSTR_isenabled), MP_ROM_PTR(&gc_isenabled_obj) },
     { MP_ROM_QSTR(MP_QSTR_mem_free), MP_ROM_PTR(&gc_mem_free_obj) },
     { MP_ROM_QSTR(MP_QSTR_mem_alloc), MP_ROM_PTR(&gc_mem_alloc_obj) },
+    #if MICROPY_GC_ALLOC_THRESHOLD
+    { MP_ROM_QSTR(MP_QSTR_threshold), MP_ROM_PTR(&gc_threshold_obj) },
+    #endif
 };
 
 STATIC MP_DEFINE_CONST_DICT(mp_module_gc_globals, mp_module_gc_globals_table);
diff --git a/py/mpconfig.h b/py/mpconfig.h
index aec5d40826..19e290c37e 100644
--- a/py/mpconfig.h
+++ b/py/mpconfig.h
@@ -107,6 +107,12 @@
 #define MICROPY_ALLOC_GC_STACK_SIZE (64)
 #endif
 
+// Support automatic GC when reaching allocation threshold,
+// configurable by gc.threshold().
+#ifndef MICROPY_GC_ALLOC_THRESHOLD
+#define MICROPY_GC_ALLOC_THRESHOLD (1)
+#endif
+
 // Number of bytes to allocate initially when creating new chunks to store
 // interned string data.  Smaller numbers lead to more chunks being needed
 // and more wastage at the end of the chunk.  Larger numbers lead to wasted
diff --git a/py/mpstate.h b/py/mpstate.h
index 281795773f..439ed66066 100644
--- a/py/mpstate.h
+++ b/py/mpstate.h
@@ -76,6 +76,11 @@ typedef struct _mp_state_mem_t {
     // you can still allocate/free memory and also explicitly call gc_collect.
     uint16_t gc_auto_collect_enabled;
 
+    #if MICROPY_GC_ALLOC_THRESHOLD
+    size_t gc_alloc_amount;
+    size_t gc_alloc_threshold;
+    #endif
+
     size_t gc_last_free_atb_index;
 
     #if MICROPY_PY_GC_COLLECT_RETVAL