percpu_ida: make percpu_ida percpu size/batch configurable

Make percpu_ida percpu size/batch configurable. The block-mq-tag will
use it.

After block-mq uses percpu_ida to manage tags, performance is improved.
My test is done in a 2 sockets machine, 12 process cross the 2 sockets.
So if there is lock contention or ipi, should be stressed heavily.
Testing is done for null-blk.

hw_queue_depth	nopatch iops	patch iops
64		~800k/s		~1470k/s
2048		~4470k/s	~4340k/s

Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 17 insertions, 1 deletions

diff --git a/include/linux/percpu_ida.h b/include/linux/percpu_ida.h
index 0b23edbee309..56c14033e7e7 100644
--- a/include/linux/percpu_ida.h
+++ b/include/linux/percpu_ida.h
@@ -16,6 +16,8 @@ struct percpu_ida {
 	 * percpu_ida_init()
 	 */
 	unsigned			nr_tags;
+	unsigned			percpu_max_size;
+	unsigned			percpu_batch_size;
 
 	struct percpu_ida_cpu __percpu	*tag_cpu;
 
@@ -51,10 +53,24 @@ struct percpu_ida {
 	} ____cacheline_aligned_in_smp;
 };
 
+/*
+ * Number of tags we move between the percpu freelist and the global freelist at
+ * a time
+ */
+#define IDA_DEFAULT_PCPU_BATCH_MOVE	32U
+/* Max size of percpu freelist, */
+#define IDA_DEFAULT_PCPU_SIZE	((IDA_DEFAULT_PCPU_BATCH_MOVE * 3) / 2)
+
 int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp);
 void percpu_ida_free(struct percpu_ida *pool, unsigned tag);
 
 void percpu_ida_destroy(struct percpu_ida *pool);
-int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags);
+int __percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags,
+	unsigned long max_size, unsigned long batch_size);
+static inline int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags)
+{
+	return __percpu_ida_init(pool, nr_tags, IDA_DEFAULT_PCPU_SIZE,
+		IDA_DEFAULT_PCPU_BATCH_MOVE);
+}
 
 #endif /* __PERCPU_IDA_H__ */