malloc: Trim unused arenas on thread exit

[Florian Weimer <fweimer at redhat dot com>]

I tried the attached patch to trim unused arenas on thread exit.  The 
trimming actually happens (the heap consolidation is visible in the 
malloc_info output from tst-malloc_info), but the arena heaps aren't 
deallocated.

I think trimming unused arenas as much as possible is a good heuristics 
to minimize RSS, so getting this to work might be worthwhile.

Thanks,
Florian

diff --git a/malloc/arena.c b/malloc/arena.c
index 85b985e193..758226c222 100644
--- a/malloc/arena.c
+++ b/malloc/arena.c
@@ -953,12 +953,22 @@ arena_thread_freeres (void)
       /* If this was the last attached thread for this arena, put the
 	 arena on the free list.  */
       assert (a->attached_threads > 0);
-      if (--a->attached_threads == 0)
+      bool arena_is_unused = --a->attached_threads == 0;
+      if (arena_is_unused)
 	{
 	  a->next_free = free_list;
 	  free_list = a;
 	}
       __libc_lock_unlock (free_list_lock);
+
+      /* If there are no more users, compact the arena as much as
+	 possible.  */
+      if (arena_is_unused)
+	{
+	  __libc_lock_lock (a->mutex);
+	  mtrim (a, 0);
+	  __libc_lock_unlock (a->mutex);
+	}
     }
 }
 text_set_element (__libc_thread_subfreeres, arena_thread_freeres);
diff --git a/malloc/malloc.c b/malloc/malloc.c
index 1f003d2ef0..a0b11784d2 100644
--- a/malloc/malloc.c
+++ b/malloc/malloc.c
@@ -1831,7 +1831,7 @@ malloc_init_state (mstate av)
 static void *sysmalloc (INTERNAL_SIZE_T, mstate);
 static int      systrim (size_t, mstate);
 static void     malloc_consolidate (mstate);
-
+static int mtrim (mstate av, size_t pad);
 
 /* -------------- Early definitions for debugging hooks ---------------- */