[PATCH v3] malloc: Reduce maximum arenas

[Wilco Dijkstra]

v3: Update tunables too 

The default maximum arenas is 8 times the number of cores in a 64-bit system.
Since modern CPUs have many cores and big servers have 256 cores, this results
in excessive number of arenas, which wastes memory.  Limit the number of arenas
to max (8, ncores) which is less extreme.  In the future the limit should be
lowered further for large systems.

Passes regress, OK for commit?

---

diff --git a/malloc/arena.c b/malloc/arena.c
index 023cb3ba067d0de097a687b73c81f5d860393413..1ed419a30569f59e169c5c3138e38a2bdb9e5de2 100644
--- a/malloc/arena.c
+++ b/malloc/arena.c
@@ -799,16 +799,11 @@ arena_get2 (size_t size, mstate avoid_arena)
         {
           if (mp_.arena_max != 0)
             narenas_limit = mp_.arena_max;
-          else if (narenas > mp_.arena_test)
+          else if (narenas >= mp_.arena_test)
             {
-              int n = __get_nprocs ();
-
-              if (n >= 1)
-                narenas_limit = NARENAS_FROM_NCORES (n);
-              else
-                /* We have no information about the system.  Assume two
-                   cores.  */
-                narenas_limit = NARENAS_FROM_NCORES (2);
+	      narenas_limit = __get_nprocs ();
+	      if (narenas_limit < mp_.arena_test)
+		narenas_limit = mp_.arena_test;
             }
         }
     repeat:;
diff --git a/malloc/malloc.c b/malloc/malloc.c
index 6ce76cb4df88930b2bd65e35e4f83bee0c635c27..f0e17443fb2d34a2e2dec75d99ba771b8d4e8397 100644
--- a/malloc/malloc.c
+++ b/malloc/malloc.c
@@ -1650,8 +1650,7 @@ static struct malloc_par mp_ =
   .n_mmaps_max = DEFAULT_MMAP_MAX,
   .mmap_threshold = DEFAULT_MMAP_THRESHOLD,
   .trim_threshold = DEFAULT_TRIM_THRESHOLD,
-#define NARENAS_FROM_NCORES(n) ((n) * (sizeof (long) == 4 ? 2 : 8))
-  .arena_test = NARENAS_FROM_NCORES (1),
+  .arena_test = 8,
   .thp_mode = thp_mode_not_supported
 #if USE_TCACHE
   ,
diff --git a/manual/memory.texi b/manual/memory.texi
index f8b6be6ee781cafda1774598585b50524d6cdca0..818d7837833b377f439409074f6563a20e4553f9 100644
--- a/manual/memory.texi
+++ b/manual/memory.texi
@@ -1378,8 +1378,7 @@ This parameter specifies the number of arenas that can be created before the
 test on the limit to the number of arenas is conducted. The value is ignored if
 @code{M_ARENA_MAX} is set.
 
-The default value of this parameter is 2 on 32-bit systems and 8 on 64-bit
-systems.
+The default value of this parameter is 8.
 
 This parameter can also be set for the process at startup by setting the
 environment variable @env{MALLOC_ARENA_TEST} to the desired value.
@@ -1389,10 +1388,9 @@ This parameter sets the number of arenas to use regardless of the number of
 cores in the system.
 
 The default value of this tunable is @code{0}, meaning that the limit on the
-number of arenas is determined by the number of CPU cores online. For 32-bit
-systems the limit is twice the number of cores online and on 64-bit systems, it
-is eight times the number of cores online.  Note that the default value is not
-derived from the default value of M_ARENA_TEST and is computed independently.
+number of arenas is determined by the number of CPU cores online. The limit is
+the number of cores online.  Note that the default value is not derived from
+the default value of M_ARENA_TEST and is computed independently.
 
 This parameter can also be set for the process at startup by setting the
 environment variable @env{MALLOC_ARENA_MAX} to the desired value.
diff --git a/manual/tunables.texi b/manual/tunables.texi
index 05f5e65a8901b67301a9d8b1da9369e2e5395e28..c245e31866965a8e090dde1f9f60fe76c0595271 100644
--- a/manual/tunables.texi
+++ b/manual/tunables.texi
@@ -221,9 +221,7 @@ This tunable sets the number of arenas to use in a process regardless of the
 number of cores in the system.
 
 The default value of this tunable is @code{0}, meaning that the limit on the
-number of arenas is determined by the number of CPU cores online.  For 32-bit
-systems the limit is twice the number of cores online and on 64-bit systems, it
-is 8 times the number of cores online.
+number of arenas is the number of CPU cores online.
 @end deftp
 
 @deftp Tunable glibc.malloc.tcache_max