The batch size in percpu_counter_add_batch should be very large in
heavy writing and rare reading case. Add the "_local" version, and
mostly it will do local adding, reduce the global updating and
mitigate lock contention in writing.
Signed-off-by: Jiebin Sun <jiebin.sun@xxxxxxxxx>
Reviewed-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Reported-by: kernel test robot <lkp@xxxxxxxxx>
---
include/linux/percpu_counter.h | 32 ++++++++++++++++++++++++++++++++
1 file changed, 32 insertions(+)
diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 01861eebed79..8ed5fba6d156 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -15,6 +15,9 @@
#include <linux/types.h>
#include <linux/gfp.h>
+/* percpu_counter batch for local add or sub */
+#define PERCPU_COUNTER_LOCAL_BATCH INT_MAX
+
#ifdef CONFIG_SMP
struct percpu_counter {
@@ -56,6 +59,22 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
percpu_counter_add_batch(fbc, amount, percpu_counter_batch);
}
+/*
+ * With percpu_counter_add_local() and percpu_counter_sub_local(), counts
+ * are accumulated in local per cpu counter and not in fbc->count until
+ * local count overflows PERCPU_COUNTER_LOCAL_BATCH. This makes counter
+ * write efficient.
+ * But percpu_counter_sum(), instead of percpu_counter_read(), needs to be
+ * used to add up the counts from each CPU to account for all the local
+ * counts. So percpu_counter_add_local() and percpu_counter_sub_local()
+ * should be used when a counter is updated frequently and read rarely.
+ */
+static inline void
+percpu_counter_add_local(struct percpu_counter *fbc, s64 amount)
+{
+ percpu_counter_add_batch(fbc, amount, PERCPU_COUNTER_LOCAL_BATCH);
+}
+
static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc)
{
s64 ret = __percpu_counter_sum(fbc);
@@ -138,6 +157,13 @@ percpu_counter_add(struct percpu_counter *fbc, s64 amount)
preempt_enable();
}
+/* non-SMP percpu_counter_add_local is the same with percpu_counter_add */
+static inline void
+percpu_counter_add_local(struct percpu_counter *fbc, s64 amount)
+{
+ percpu_counter_add(fbc, amount);
+}
+
static inline void
percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
{
@@ -193,4 +219,10 @@ static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount)
percpu_counter_add(fbc, -amount);
}
+static inline void
+percpu_counter_sub_local(struct percpu_counter *fbc, s64 amount)
+{
+ percpu_counter_add_local(fbc, -amount);
+}
+
#endif /* _LINUX_PERCPU_COUNTER_H */
--
2.31.1
