blk-mq: prefetch request in blk_mq_tag_to_rq()

When drivers or the core calls this function, they usually
dereference the request shortly there after. Prefetch the first
cache line.

Profiling IO workloads shows that this is the most common cache
miss on the block side of things.

Signed-off-by: Jens Axboe <axboe@fb.com>

diff --git a/block/blk-mq.c b/block/blk-mq.c
index b68fdcbe58f6fe95e418710cbb92853e8708042d..eea0d230faa1231f047b5194e52f2aa866062a66 100644 (file)
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -22,6 +22,7 @@
 #include <linux/sched/sysctl.h>
 #include <linux/delay.h>
 #include <linux/crash_dump.h>
+#include <linux/prefetch.h>
 
 #include <trace/events/block.h>
 
@@ -588,8 +589,10 @@ EXPORT_SYMBOL(blk_mq_abort_requeue_list);
 
 struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
 {
-       if (tag < tags->nr_tags)
+       if (tag < tags->nr_tags) {
+               prefetch(tags->rqs[tag]);
                return tags->rqs[tag];
+       }
 
        return NULL;
 }