[PATCH] percpu_counters: approximate but scalable counters

Several places in ext2 and ext3 are using filesystem-wide counters which use
global locking.  Mainly for the orlov allocator's heuristics.

To solve the contention which this causes we can trade off accuracy against
speed.

This patch introduces a "percpu_counter" library type in which the counts are
per-cpu and are periodically spilled into a global counter.  Readers only
read the global counter.

These objects are *large*.  On a 32 CPU P4, they are 4 kbytes.  On a 4 way
p3, 128 bytes.

2 files changed, 19 insertions, 0 deletions

diff --git a/lib/Makefile b/lib/Makefile
index 24e6b3adc098..6ab94d3cb906 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -14,6 +14,7 @@ obj-y := errno.o ctype.o string.o vsprintf.o brlock.o cmdline.o \
 
 obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
+obj-$(CONFIG_SMP) += percpu_counter.o
 
 ifneq ($(CONFIG_HAVE_DEC_LOCK),y) 
   obj-y += dec_and_lock.o
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
new file mode 100644
index 000000000000..73f99d99f9ac
--- /dev/null
+++ b/lib/percpu_counter.c
@@ -0,0 +1,18 @@
+
+#include <linux/percpu_counter.h>
+
+void percpu_counter_mod(struct percpu_counter *fbc, long amount)
+{
+	int cpu = get_cpu();
+	long count = fbc->counters[cpu].count;
+
+	count += amount;
+	if (count >= FBC_BATCH || count <= -FBC_BATCH) {
+		spin_lock(&fbc->lock);
+		fbc->count += count;
+		spin_unlock(&fbc->lock);
+		count = 0;
+	}
+	fbc->counters[cpu].count = count;
+	put_cpu();
+}