Re: [PATCH v3] iomap: set REQ_NOWAIT according to IOCB_NOWAIT in Direct IO

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 




On 11/23/20 4:45 PM, Hao Xu wrote:
Currently, IOCB_NOWAIT is ignored in Direct IO, REQ_NOWAIT is only set
when IOCB_HIPRI is set. But REQ_NOWAIT should be set as well when
IOCB_NOWAIT is set.

Suggested-by: Jeffle Xu <jefflexu@xxxxxxxxxxxxxxxxx>
Signed-off-by: Konstantin Khlebnikov <khlebnikov@xxxxxxxxxxxxxx>
Signed-off-by: Hao Xu <haoxu@xxxxxxxxxxxxxxxxx>
---

Hi all,
I tested fio io_uring direct read for a file on ext4 filesystem on a
nvme ssd. I found that IOCB_NOWAIT is ignored in iomap layer, which
means REQ_NOWAIT is not set in bio->bi_opf. This makes nowait IO a
normal IO. Since I'm new to iomap and block layer, I sincerely ask
yours opinions in case I misunderstand the code which is very likely
to happen.:)

I found that Konstantin found this issue before in May
2020 (https://www.spinics.net/lists/linux-block/msg53275.html), here add
his signature, add Jeffle's as well since he gave me some help.

v1->v2:
* add same logic in __blkdev_direct_IO_simple()
v2->v3:
* add same logic in do_blockdev_direct_IO()

  fs/block_dev.c       | 7 +++++++
  fs/direct-io.c       | 6 ++++--
  fs/iomap/direct-io.c | 3 +++
  3 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9e84b1928b94..f3e9e13a9a9f 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -263,6 +263,10 @@ static void blkdev_bio_end_io_simple(struct bio *bio)
  		bio.bi_opf = dio_bio_write_op(iocb);
  		task_io_account_write(ret);
  	}
+
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		bio.bi_opf |= REQ_NOWAIT;
+
  	if (iocb->ki_flags & IOCB_HIPRI)
  		bio_set_polled(&bio, iocb);
@@ -424,6 +428,9 @@ static void blkdev_bio_end_io(struct bio *bio)
  		if (!nr_pages) {
  			bool polled = false;
+ if (iocb->ki_flags & IOCB_NOWAIT)
+				bio->bi_opf |= REQ_NOWAIT;
+

This should be moved outside the "if (!nr_pages) {}" clause. One direct IO can be split

into several bios, among which only the last split bio will get into this conditional clause.


Thanks,

Jeffle


  			if (iocb->ki_flags & IOCB_HIPRI) {
  				bio_set_polled(bio, iocb);
  				polled = true;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index d53fa92a1ab6..b221ed351c1c 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1206,11 +1206,13 @@ static inline int drop_refcount(struct dio *dio)
  	if (iov_iter_rw(iter) == WRITE) {
  		dio->op = REQ_OP_WRITE;
  		dio->op_flags = REQ_SYNC | REQ_IDLE;
-		if (iocb->ki_flags & IOCB_NOWAIT)
-			dio->op_flags |= REQ_NOWAIT;
  	} else {
  		dio->op = REQ_OP_READ;
  	}
+
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		dio->op_flags |= REQ_NOWAIT;
+
  	if (iocb->ki_flags & IOCB_HIPRI)
  		dio->op_flags |= REQ_HIPRI;
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 933f234d5bec..2e897688ed6d 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -64,6 +64,9 @@ static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
  {
  	atomic_inc(&dio->ref);
+ if (dio->iocb->ki_flags & IOCB_NOWAIT)
+		bio->bi_opf |= REQ_NOWAIT;
+
  	if (dio->iocb->ki_flags & IOCB_HIPRI)
  		bio_set_polled(bio, dio->iocb);

--
Thanks,
Jeffle




[Index of Archives]     [Linux Ext4 Filesystem]     [Union Filesystem]     [Filesystem Testing]     [Ceph Users]     [Ecryptfs]     [AutoFS]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux Cachefs]     [Reiser Filesystem]     [Linux RAID]     [Samba]     [Device Mapper]     [CEPH Development]

  Powered by Linux