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/fs/direct-io.c b/fs/direct-io.c
index b6d4390..da258e7 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1126,7 +1126,7 @@
int acquire_i_mutex = 0;
if (rw & WRITE)
- rw = WRITE_SYNC;
+ rw = WRITE_ODIRECT;
if (bdev)
bdev_blkbits = blksize_bits(bdev_hardsect_size(bdev));