Re: [PATCH] Configure GMP to use GC allocation functions, remove bignum finalizers

[Andy Wingo]

On Tue 29 Nov 2011 00:10, address@hidden (Ludovic Courtès) writes:

> Andy Wingo <address@hidden> skribis:
>
>> On Sun 27 Nov 2011 22:25, address@hidden (Ludovic Courtès) writes:
>>
>>> The problem is that this measurement doesn’t allow us to differentiate
>>> between a growing heap with objects that may be freed as a result of
>>> running the GC, and a growing heap just because the application needs
>>> more malloc’d objects.
>>
>> This is true, but typically the heap stabilizes at some point.
>
> Ooh, re-reading your previous message, I now see what you mean, and it
> makes sense to me.

WDYT?

>From 5dc96678aba01297a127aa6f3781ecedec3b24f1 Mon Sep 17 00:00:00 2001
From: Andy Wingo <address@hidden>
Date: Tue, 29 Nov 2011 00:48:56 +0100
Subject: [PATCH] increase garbage collection rate if the process is growing

* configure.ac: Check for GC_get_free_space_divisor.
* libguile/gc.c (GC_get_free_space_divisor): Define an implementation,
  if needed.
  (accumulate_gc_timer): Fix indentation.
  (get_image_size): New terrible hack.  Needs implementations on other
  platforms.
  (adjust_gc_frequency): Attempt to adjust the GC frequency based on
  process image growth.  Needs more comments.
  (scm_init_gc): Add the adjust_gc_frequency to the after_gc_c_hook.
---
 configure.ac  |    2 +-
 libguile/gc.c |  108 +++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 107 insertions(+), 3 deletions(-)

diff --git a/configure.ac b/configure.ac
index 3a56cda..d63dd63 100644
--- a/configure.ac
+++ b/configure.ac
@@ -1259,7 +1259,7 @@ save_LIBS="$LIBS"
 LIBS="$BDW_GC_LIBS $LIBS"
 CFLAGS="$BDW_GC_CFLAGS $CFLAGS"
 
-AC_CHECK_FUNCS([GC_do_blocking GC_call_with_gc_active GC_pthread_exit 
GC_pthread_cancel GC_allow_register_threads GC_pthread_sigmask 
GC_set_start_callback GC_get_heap_usage_safe])
+AC_CHECK_FUNCS([GC_do_blocking GC_call_with_gc_active GC_pthread_exit 
GC_pthread_cancel GC_allow_register_threads GC_pthread_sigmask 
GC_set_start_callback GC_get_heap_usage_safe GC_get_free_space_divisor])
 
 # Though the `GC_do_blocking ()' symbol is present in GC 7.1, it is not
 # declared, and has a different type (returning void instead of
diff --git a/libguile/gc.c b/libguile/gc.c
index 4895b7d..281efde 100644
--- a/libguile/gc.c
+++ b/libguile/gc.c
@@ -27,6 +27,7 @@
 #include <stdio.h>
 #include <errno.h>
 #include <string.h>
+#include <math.h>
 
 #ifdef __ia64__
 #include <ucontext.h>
@@ -194,6 +195,8 @@ SCM_DEFINE (scm_set_debug_cell_accesses_x, 
"set-debug-cell-accesses!", 1, 0, 0,
 
 
 
+/* Compatibility.  */
+
 #ifndef HAVE_GC_GET_HEAP_USAGE_SAFE
 static void
 GC_get_heap_usage_safe (GC_word *pheap_size, GC_word *pfree_bytes,
@@ -208,6 +211,14 @@ GC_get_heap_usage_safe (GC_word *pheap_size, GC_word 
*pfree_bytes,
 }
 #endif
 
+#ifndef HAVE_GC_GET_FREE_SPACE_DIVISOR
+static GC_word
+GC_get_free_space_divisor (void)
+{
+  return GC_free_space_divisor;
+}
+#endif
+
 
 /* Hooks.  */
 scm_t_c_hook scm_before_gc_c_hook;
@@ -230,6 +241,9 @@ unsigned long scm_gc_ports_collected = 0;
 static long gc_time_taken = 0;
 static long gc_start_time = 0;
 
+static unsigned long free_space_divisor;
+static unsigned long minimum_free_space_divisor;
+static double target_free_space_divisor;
 
 static unsigned long protected_obj_count = 0;
 
@@ -598,7 +612,10 @@ void
 scm_storage_prehistory ()
 {
   GC_all_interior_pointers = 0;
-  GC_set_free_space_divisor (scm_getenv_int ("GC_FREE_SPACE_DIVISOR", 3));
+  free_space_divisor = scm_getenv_int ("GC_FREE_SPACE_DIVISOR", 3);
+  minimum_free_space_divisor = free_space_divisor;
+  target_free_space_divisor = free_space_divisor;
+  GC_set_free_space_divisor (free_space_divisor);
 
   GC_INIT ();
 
@@ -742,7 +759,8 @@ accumulate_gc_timer (void * hook_data SCM_UNUSED,
                 void *data SCM_UNUSED)
 {
   if (gc_start_time)
-    { long now = scm_c_get_internal_run_time ();
+    {
+      long now = scm_c_get_internal_run_time ();
       gc_time_taken += now - gc_start_time;
       gc_start_time = 0;
     }
@@ -750,6 +768,91 @@ accumulate_gc_timer (void * hook_data SCM_UNUSED,
   return NULL;
 }
 
+static size_t
+get_image_size (void)
+{
+  unsigned long size, resident, share;
+  size_t ret;
+
+  FILE *fp = fopen ("/proc/self/statm", "r");
+
+  if (fp && fscanf (fp, "%lu %lu %lu", &size, &resident, &share) == 3)
+    ret = resident * 4096;
+
+  if (fp)
+    fclose (fp);
+
+  return ret;
+}
+
+static void *
+adjust_gc_frequency (void * hook_data SCM_UNUSED,
+                     void *fn_data SCM_UNUSED,
+                     void *data SCM_UNUSED)
+{
+  static size_t prev_image_size = 0;
+  static size_t prev_bytes_alloced = 0;
+  size_t image_size;
+  size_t bytes_alloced;
+  
+  image_size = get_image_size ();
+  bytes_alloced = GC_get_total_bytes ();
+
+#define HEURISTICS_DEBUG 0
+
+#if HEURISTICS_DEBUG
+  fprintf (stderr, "prev image / alloced: %lu / %lu\n", prev_image_size, 
prev_bytes_alloced);
+  fprintf (stderr, "     image / alloced: %lu / %lu\n", image_size, 
bytes_alloced);
+  fprintf (stderr, "divisor %lu / %f\n", free_space_divisor, 
target_free_space_divisor);
+#endif
+
+  if (prev_image_size && bytes_alloced != prev_bytes_alloced)
+    {
+      double growth_rate, new_target_free_space_divisor;
+      double damping_factor = 0.5;
+      double hysteresis = 0.1;
+
+      growth_rate = ((double) image_size - prev_image_size)
+        / ((double)bytes_alloced - prev_bytes_alloced);
+      
+#if HEURISTICS_DEBUG
+      fprintf (stderr, "growth rate %f\n", growth_rate);
+#endif
+
+      new_target_free_space_divisor = minimum_free_space_divisor;
+
+      if (growth_rate > 0)
+        new_target_free_space_divisor *= 1.0 + growth_rate;
+
+#if HEURISTICS_DEBUG
+      fprintf (stderr, "new divisor %f\n", new_target_free_space_divisor);
+#endif
+
+      target_free_space_divisor =
+        (damping_factor * target_free_space_divisor
+         + (1.0 - damping_factor) * new_target_free_space_divisor);
+
+#if HEURISTICS_DEBUG
+      fprintf (stderr, "new target divisor %f\n", target_free_space_divisor);
+#endif
+
+      if (free_space_divisor + 0.5 + hysteresis < target_free_space_divisor
+          || free_space_divisor - 0.5 - hysteresis > target_free_space_divisor)
+        {
+          free_space_divisor = lround (target_free_space_divisor);
+#if HEURISTICS_DEBUG
+          fprintf (stderr, "new divisor %lu\n", free_space_divisor);
+#endif
+          GC_set_free_space_divisor (free_space_divisor);
+        }
+    }
+
+  prev_image_size = image_size;
+  prev_bytes_alloced = bytes_alloced;
+
+  return NULL;
+}
+
 
 
 
@@ -847,6 +950,7 @@ scm_init_gc ()
   scm_c_hook_add (&scm_before_gc_c_hook, queue_after_gc_hook, NULL, 0);
   scm_c_hook_add (&scm_before_gc_c_hook, start_gc_timer, NULL, 0);
   scm_c_hook_add (&scm_after_gc_c_hook, accumulate_gc_timer, NULL, 0);
+  scm_c_hook_add (&scm_after_gc_c_hook, adjust_gc_frequency, NULL, 0);
 
 #ifdef HAVE_GC_SET_START_CALLBACK
   GC_set_start_callback (run_before_gc_c_hook);
-- 
1.7.7.3

-- 
http://wingolog.org/