debugobjects: Scale thresholds with # of CPUs

On a large SMP systems with hundreds of CPUs, the current thresholds
for allocating and freeing debug objects (256 and 1024 respectively)
may not work well. This can cause a lot of needless calls to
kmem_aloc() and kmem_free() on those systems.

To alleviate this thrashing problem, the object freeing threshold
is now increased to "1024 + # of CPUs * 32". Whereas the object
allocation threshold is increased to "256 + # of CPUs * 4". That
should make the debug objects subsystem scale better with the number
of CPUs available in the system.

Signed-off-by: Waiman Long <longman@redhat.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: "Du Changbin" <changbin.du@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jan Stancek <jstancek@redhat.com>
Link: http://lkml.kernel.org/r/1483647425-4135-3-git-send-email-longman@redhat.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

1 files changed, 15 insertions, 5 deletions

diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index d78673e7dc56..dc78217b2199 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -52,7 +52,10 @@ static int			debug_objects_fixups __read_mostly;
 static int                      debug_objects_warnings __read_mostly;
 static int                      debug_objects_enabled __read_mostly
                                 = CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT;
-
+static int                      debug_objects_pool_size __read_mostly
+                                = ODEBUG_POOL_SIZE;
+static int                      debug_objects_pool_min_level __read_mostly
+                                = ODEBUG_POOL_MIN_LEVEL;
 static struct debug_obj_descr   *descr_test  __read_mostly;
 
 /*
@@ -94,13 +97,13 @@ static void fill_pool(void)
         struct debug_obj *new;
         unsigned long flags;
 
-        if (likely(obj_pool_free >= ODEBUG_POOL_MIN_LEVEL))
+        if (likely(obj_pool_free >= debug_objects_pool_min_level))
                 return;
 
         if (unlikely(!obj_cache))
                 return;
 
-        while (obj_pool_free < ODEBUG_POOL_MIN_LEVEL) {
+        while (obj_pool_free < debug_objects_pool_min_level) {
 
                 new = kmem_cache_zalloc(obj_cache, gfp);
                 if (!new)
@@ -176,7 +179,7 @@ static void free_obj_work(struct work_struct *work)
         unsigned long flags;
 
         raw_spin_lock_irqsave(&pool_lock, flags);
-        while (obj_pool_free > ODEBUG_POOL_SIZE) {
+        while (obj_pool_free > debug_objects_pool_size) {
                 obj = hlist_entry(obj_pool.first, typeof(*obj), node);
                 hlist_del(&obj->node);
                 obj_pool_free--;
@@ -206,7 +209,7 @@ static void free_object(struct debug_obj *obj)
          * schedule work when the pool is filled and the cache is
          * initialized:
          */
-        if (obj_pool_free > ODEBUG_POOL_SIZE && obj_cache)
+        if (obj_pool_free > debug_objects_pool_size && obj_cache)
                 sched = 1;
         hlist_add_head(&obj->node, &obj_pool);
         obj_pool_free++;
@@ -1126,4 +1129,11 @@ void __init debug_objects_mem_init(void)
                 pr_warn("out of memory.\n");
         } else
                 debug_objects_selftest();
+
+        /*
+         * Increase the thresholds for allocating and freeing objects
+         * according to the number of possible CPUs available in the system.
+         */
+        debug_objects_pool_size += num_possible_cpus() * 32;
+        debug_objects_pool_min_level += num_possible_cpus() * 4;
 }