block: Add flag for telling the IO schedulers NOT to anticipate more IO
By default, CFQ will anticipate more IO from a given io context if the
previously completed IO was sync. This used to be fine, since the only
sync IO was reads and O_DIRECT writes. But with more "normal" sync writes
being used now, we don't want to anticipate for those.
Add a bio/request flag that informs the IO scheduler that this is a sync
request that we should not idle for. Introduce WRITE_ODIRECT specifically
for O_DIRECT writes, and make sure that the other sync writes set this
flag.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 67dae3b..e036609 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -118,6 +118,7 @@
__REQ_COPY_USER, /* contains copies of user pages */
__REQ_INTEGRITY, /* integrity metadata has been remapped */
__REQ_UNPLUG, /* unplug queue on submission */
+ __REQ_NOIDLE, /* Don't anticipate more IO after this one */
__REQ_NR_BITS, /* stops here */
};
@@ -145,6 +146,7 @@
#define REQ_COPY_USER (1 << __REQ_COPY_USER)
#define REQ_INTEGRITY (1 << __REQ_INTEGRITY)
#define REQ_UNPLUG (1 << __REQ_UNPLUG)
+#define REQ_NOIDLE (1 << __REQ_NOIDLE)
#define BLK_MAX_CDB 16
@@ -633,6 +635,7 @@
}
#define rq_is_meta(rq) ((rq)->cmd_flags & REQ_RW_META)
+#define rq_noidle(rq) ((rq)->cmd_flags & REQ_NOIDLE)
static inline int blk_queue_full(struct request_queue *q, int sync)
{