Skip to contentSkip to conversation

io_uring: retry in case of short read on block device

PATCH Applied Ming Lei 3 participants 4 messages Aug 21, 2021 – Aug 31, 2021

Subsystems (2)
lore
Share & tools
lore

Ming Lei

author
#0 lore raw

PATCH 1/1 io_uring: retry in case of short read on block device

In case of buffered reading from block device, when short read happens, we should retry to read more, otherwise the IO will be completed partially, for example, the following fio expects to read 2MB, but it can only read 1M or less bytes:

    fio --name=onessd --filename=/dev/nvme0n1 --filesize=2M \
	--rw=randread --bs=2M --direct=0 --overwrite=0 --numjobs=1 \
	--iodepth=1 --time_based=0 --runtime=2 --ioengine=io_uring \
	--registerfiles --fixedbufs --gtod_reduce=1 --group_reporting

Fix the issue by allowing short read retry for block device, which sets FMODE_BUF_RASYNC really.

Fixes 9a173346bd9e ("io_uring: fix short read retries for non-reg files")
Cc Pavel Begunkov <[email protected]>
---
 fs/io_uring.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)
fs/io_uring.c +7 -1
index bf548af0426c..bbcd1a9e75e5 100644
@@ -3268,6 +3268,12 @@ static inline int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter)
 		return -EINVAL;
 }
 
+static bool need_read_all(struct io_kiocb *req)
+{
+	return req->flags & REQ_F_ISREG ||
+		S_ISBLK(file_inode(req->file)->i_mode);
+}
+
 static int io_read(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
@@ -3322,7 +3328,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
 	} else if (ret == -EIOCBQUEUED) {
 		goto out_free;
 	} else if (ret <= 0 || ret == io_size || !force_nonblock ||
-		   (req->flags & REQ_F_NOWAIT) || !(req->flags & REQ_F_ISREG)) {
+		   (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) {
 		/* read all, failed, already did sync or don't want to retry */
 		goto done;
 	}
Signature · 1 line
2.31.1
author
#1 lore raw
Quoted 10 lines · Ming Lei

In case of buffered reading from block device, when short read happens, we should retry to read more, otherwise the IO will be completed partially, for example, the following fio expects to read 2MB, but it can only read 1M or less bytes:

    fio --name=onessd --filename=/dev/nvme0n1 --filesize=2M \
	--rw=randread --bs=2M --direct=0 --overwrite=0 --numjobs=1 \
	--iodepth=1 --time_based=0 --runtime=2 --ioengine=io_uring \
	--registerfiles --fixedbufs --gtod_reduce=1 --group_reporting
Quoted 6 lines

Fix the issue by allowing short read retry for block device, which sets FMODE_BUF_RASYNC really.

Fixes 9a173346bd9e ("io_uring: fix short read retries for non-reg files")
Cc Pavel Begunkov <[email protected]>

Hello Jens and Pavel,

Any comments on this fix?

Thanks,
Ming

Reviewed-by on v1 1/1
#2 lore raw
In reply to Ming Lei
Quoted 5 lines · Ming Lei

In case of buffered reading from block device, when short read happens, we should retry to read more, otherwise the IO will be completed partially, for example, the following fio expects to read 2MB, but it can only read 1M or less bytes:

Quoted 7 lines
    fio --name=onessd --filename=/dev/nvme0n1 --filesize=2M \
	--rw=randread --bs=2M --direct=0 --overwrite=0 --numjobs=1 \
	--iodepth=1 --time_based=0 --runtime=2 --ioengine=io_uring \
	--registerfiles --fixedbufs --gtod_reduce=1 --group_reporting

Fix the issue by allowing short read retry for block device, which sets FMODE_BUF_RASYNC really.

Should note that overhead on touching inode shouldn't be of concern at this point, so all looks good

Quoted 34 lines
Fixes 9a173346bd9e ("io_uring: fix short read retries for non-reg files")
Cc Pavel Begunkov <[email protected]>
---
 fs/io_uring.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)
fs/io_uring.c +7 -1
index bf548af0426c..bbcd1a9e75e5 100644
@@ -3268,6 +3268,12 @@ static inline int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter)
 		return -EINVAL;
 }
 
+static bool need_read_all(struct io_kiocb *req)
+{
+	return req->flags & REQ_F_ISREG ||
+		S_ISBLK(file_inode(req->file)->i_mode);
+}
+
 static int io_read(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
@@ -3322,7 +3328,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
 	} else if (ret == -EIOCBQUEUED) {
 		goto out_free;
 	} else if (ret <= 0 || ret == io_size || !force_nonblock ||
-		   (req->flags & REQ_F_NOWAIT) || !(req->flags & REQ_F_ISREG)) {
+		   (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) {
 		/* read all, failed, already did sync or don't want to retry */
 		goto done;
 	}
Signature · 1 line
Pavel Begunkov
maintainer Applied
#3 lore raw
In reply to Ming Lei
Quoted 5 lines · Ming Lei

In case of buffered reading from block device, when short read happens, we should retry to read more, otherwise the IO will be completed partially, for example, the following fio expects to read 2MB, but it can only read 1M or less bytes:

Quoted 7 lines
    fio --name=onessd --filename=/dev/nvme0n1 --filesize=2M \
	--rw=randread --bs=2M --direct=0 --overwrite=0 --numjobs=1 \
	--iodepth=1 --time_based=0 --runtime=2 --ioengine=io_uring \
	--registerfiles --fixedbufs --gtod_reduce=1 --group_reporting

Fix the issue by allowing short read retry for block device, which sets FMODE_BUF_RASYNC really.

Applied, thanks Ming.

Signature · 1 line
Jens Axboe