mm: tune vm_committed_as percpu_counter batching size

Currently the per cpu counter's batch size for memory accounting is
configured as twice the number of cpus in the system.  However, for
system with very large memory, it is more appropriate to make it
proportional to the memory size per cpu in the system.

For example, for a x86_64 system with 64 cpus and 128 GB of memory, the
batch size is only 2*64 pages (0.5 MB).  So any memory accounting
changes of more than 0.5MB will overflow the per cpu counter into the
global counter.  Instead, for the new scheme, the batch size is
configured to be 0.4% of the memory/cpu = 8MB (128 GB/64 /256), which is
more inline with the memory size.

I've done a repeated brk test of 800KB (from will-it-scale test suite)
with 80 concurrent processes on a 4 socket Westmere machine with a total
of 40 cores.  Without the patch, about 80% of cpu is spent on spin-lock
contention within the vm_committed_as counter.  With the patch, there's
a 73x speedup on the benchmark and the lock contention drops off almost
entirely.

[[email protected]: fix section mismatch]
Signed-off-by: Tim Chen <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Eric Dumazet <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Wu Fengguang <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/mman.h

@@ -11,11 +11,17 @@ extern int sysctl_overcommit_memory;
 extern int sysctl_overcommit_ratio;
 extern struct percpu_counter vm_committed_as;
 
+#ifdef CONFIG_SMP
+extern s32 vm_committed_as_batch;
+#else
+#define vm_committed_as_batch 0
+#endif
+
 unsigned long vm_memory_committed(void);
 
 static inline void vm_acct_memory(long pages)
 {
-	percpu_counter_add(&vm_committed_as, pages);
+	__percpu_counter_add(&vm_committed_as, pages, vm_committed_as_batch);
 }
 
 static inline void vm_unacct_memory(long pages)

mm/mm_init.c

@@ -9,6 +9,8 @@
 #include <linux/init.h>
 #include <linux/kobject.h>
 #include <linux/export.h>
+#include <linux/memory.h>
+#include <linux/notifier.h>
 #include "internal.h"
 
 #ifdef CONFIG_DEBUG_MEMORY_INIT
@@ -147,6 +149,51 @@ early_param("mminit_loglevel", set_mminit_loglevel);
 struct kobject *mm_kobj;
 EXPORT_SYMBOL_GPL(mm_kobj);
 
+#ifdef CONFIG_SMP
+s32 vm_committed_as_batch = 32;
+
+static void __meminit mm_compute_batch(void)
+{
+	u64 memsized_batch;
+	s32 nr = num_present_cpus();
+	s32 batch = max_t(s32, nr*2, 32);
+
+	/* batch size set to 0.4% of (total memory/#cpus), or max int32 */
+	memsized_batch = min_t(u64, (totalram_pages/nr)/256, 0x7fffffff);
+
+	vm_committed_as_batch = max_t(s32, memsized_batch, batch);
+}
+
+static int __meminit mm_compute_batch_notifier(struct notifier_block *self,
+					unsigned long action, void *arg)
+{
+	switch (action) {
+	case MEM_ONLINE:
+	case MEM_OFFLINE:
+		mm_compute_batch();
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block compute_batch_nb __meminitdata = {
+	.notifier_call = mm_compute_batch_notifier,
+	.priority = IPC_CALLBACK_PRI, /* use lowest priority */
+};
+
+static int __init mm_compute_batch_init(void)
+{
+	mm_compute_batch();
+	register_hotmemory_notifier(&compute_batch_nb);
+
+	return 0;
+}
+
+__initcall(mm_compute_batch_init);
+
+#endif
+
 static int __init mm_sysfs_init(void)
 {
 	mm_kobj = kobject_create_and_add("mm", kernel_kobj);