[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <tip-97dd552eb23c83dbf626a6e84666c7e281375d47@git.kernel.org>
Date: Sat, 4 Feb 2017 08:23:07 -0800
From: tip-bot for Waiman Long <tipbot@...or.com>
To: linux-tip-commits@...r.kernel.org
Cc: hpa@...or.com, jstancek@...hat.com, tglx@...utronix.de,
changbin.du@...el.com, akpm@...ux-foundation.org,
longman@...hat.com, borntraeger@...ibm.com,
linux-kernel@...r.kernel.org, mingo@...nel.org
Subject: [tip:core/debugobjects] debugobjects: Scale thresholds with # of
CPUs
Commit-ID: 97dd552eb23c83dbf626a6e84666c7e281375d47
Gitweb: http://git.kernel.org/tip/97dd552eb23c83dbf626a6e84666c7e281375d47
Author: Waiman Long <longman@...hat.com>
AuthorDate: Thu, 5 Jan 2017 15:17:04 -0500
Committer: Thomas Gleixner <tglx@...utronix.de>
CommitDate: Sat, 4 Feb 2017 09:01:55 +0100
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@...hat.com>
Cc: Christian Borntraeger <borntraeger@...ibm.com>
Cc: "Du Changbin" <changbin.du@...el.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: Jan Stancek <jstancek@...hat.com>
Link: http://lkml.kernel.org/r/1483647425-4135-3-git-send-email-longman@redhat.com
Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
---
lib/debugobjects.c | 20 +++++++++++++++-----
1 file changed, 15 insertions(+), 5 deletions(-)
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index d78673e..dc78217 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;
}
Powered by blists - more mailing lists