diff mbox series

[v7,11/11] zonefs: use REQ_OP_ZONE_APPEND for sync DIO

Message ID 20200417121536.5393-12-johannes.thumshirn@wdc.com (mailing list archive)
State Superseded
Headers show
Series Introduce Zone Append for writing to zoned block devices | expand

Commit Message

Johannes Thumshirn April 17, 2020, 12:15 p.m. UTC
Synchronous direct I/O to a sequential write only zone can be issued using
the new REQ_OP_ZONE_APPEND request operation. As dispatching multiple
BIOs can potentially result in reordering, we cannot support asynchronous
IO via this interface.

We also can only dispatch up to queue_max_zone_append_sectors() via the
new zone-append method and have to return a short write back to user-space
in case an IO larger than queue_max_zone_append_sectors() has been issued.

Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
---
 fs/zonefs/super.c | 80 ++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 72 insertions(+), 8 deletions(-)

Comments

Bart Van Assche April 18, 2020, 9:45 p.m. UTC | #1
On 4/17/20 5:15 AM, Johannes Thumshirn wrote:
> Synchronous direct I/O to a sequential write only zone can be issued using
> the new REQ_OP_ZONE_APPEND request operation. As dispatching multiple
> BIOs can potentially result in reordering, we cannot support asynchronous
> IO via this interface.
> 
> We also can only dispatch up to queue_max_zone_append_sectors() via the
> new zone-append method and have to return a short write back to user-space
> in case an IO larger than queue_max_zone_append_sectors() has been issued.

Is this patch the only patch that adds a user space interface through 
which REQ_OP_ZONE_APPEND operations can be submitted? Has it been 
considered to make it possible to submit REQ_OP_ZONE_APPEND operations 
through the asynchronous I/O mechanism?

Thanks,

Bart.
Damien Le Moal April 20, 2020, 12:36 a.m. UTC | #2
On 2020/04/19 6:45, Bart Van Assche wrote:
> On 4/17/20 5:15 AM, Johannes Thumshirn wrote:
>> Synchronous direct I/O to a sequential write only zone can be issued using
>> the new REQ_OP_ZONE_APPEND request operation. As dispatching multiple
>> BIOs can potentially result in reordering, we cannot support asynchronous
>> IO via this interface.
>>
>> We also can only dispatch up to queue_max_zone_append_sectors() via the
>> new zone-append method and have to return a short write back to user-space
>> in case an IO larger than queue_max_zone_append_sectors() has been issued.
> 
> Is this patch the only patch that adds a user space interface through 
> which REQ_OP_ZONE_APPEND operations can be submitted? Has it been 
> considered to make it possible to submit REQ_OP_ZONE_APPEND operations 
> through the asynchronous I/O mechanism?

Yes, we have looked into it. We do have some hack-ish code working for that. For
the initial feature post though, we didn't want to add that part to facilitate
reviews and also because we need more work to cleanly handle zone append in the
aio code (that code is written assuming that BIOs can always be split and so
never returns short writes).

> 
> Thanks,
> 
> Bart.
>
diff mbox series

Patch

diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 3ce9829a6936..0bf7009f50a2 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -20,6 +20,7 @@ 
 #include <linux/mman.h>
 #include <linux/sched/mm.h>
 #include <linux/crc32.h>
+#include <linux/task_io_accounting_ops.h>
 
 #include "zonefs.h"
 
@@ -596,6 +597,61 @@  static const struct iomap_dio_ops zonefs_write_dio_ops = {
 	.end_io			= zonefs_file_write_dio_end_io,
 };
 
+static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct zonefs_inode_info *zi = ZONEFS_I(inode);
+	struct block_device *bdev = inode->i_sb->s_bdev;
+	unsigned int max;
+	struct bio *bio;
+	ssize_t size;
+	int nr_pages;
+	ssize_t ret;
+
+	nr_pages = iov_iter_npages(from, BIO_MAX_PAGES);
+	if (!nr_pages)
+		return 0;
+
+	max = queue_max_zone_append_sectors(bdev_get_queue(bdev));
+	max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize);
+	iov_iter_truncate(from, max);
+
+	bio = bio_alloc_bioset(GFP_NOFS, nr_pages, &fs_bio_set);
+	if (!bio)
+		return -ENOMEM;
+
+	bio_set_dev(bio, bdev);
+	bio->bi_iter.bi_sector = zi->i_zsector;
+	bio->bi_write_hint = iocb->ki_hint;
+	bio->bi_ioprio = iocb->ki_ioprio;
+	bio->bi_opf = REQ_OP_ZONE_APPEND | REQ_SYNC | REQ_IDLE;
+	if (iocb->ki_flags & IOCB_DSYNC)
+		bio->bi_opf |= REQ_FUA;
+
+	ret = bio_iov_iter_get_pages(bio, from);
+	if (unlikely(ret)) {
+		bio_io_error(bio);
+		return ret;
+	}
+	size = bio->bi_iter.bi_size;
+	task_io_account_write(ret);
+
+	if (iocb->ki_flags & IOCB_HIPRI)
+		bio_set_polled(bio, iocb);
+
+	ret = submit_bio_wait(bio);
+
+	bio_put(bio);
+
+	zonefs_file_write_dio_end_io(iocb, size, ret, 0);
+	if (ret >= 0) {
+		iocb->ki_pos += size;
+		return size;
+	}
+
+	return ret;
+}
+
 /*
  * Handle direct writes. For sequential zone files, this is the only possible
  * write path. For these files, check that the user is issuing writes
@@ -611,6 +667,8 @@  static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	struct zonefs_inode_info *zi = ZONEFS_I(inode);
 	struct super_block *sb = inode->i_sb;
+	bool sync = is_sync_kiocb(iocb);
+	bool append = false;
 	size_t count;
 	ssize_t ret;
 
@@ -619,7 +677,7 @@  static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 	 * as this can cause write reordering (e.g. the first aio gets EAGAIN
 	 * on the inode lock but the second goes through but is now unaligned).
 	 */
-	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && !is_sync_kiocb(iocb) &&
+	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && !sync &&
 	    (iocb->ki_flags & IOCB_NOWAIT))
 		return -EOPNOTSUPP;
 
@@ -643,16 +701,22 @@  static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 	}
 
 	/* Enforce sequential writes (append only) in sequential zones */
-	mutex_lock(&zi->i_truncate_mutex);
-	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && iocb->ki_pos != zi->i_wpoffset) {
+	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ) {
+		mutex_lock(&zi->i_truncate_mutex);
+		if (iocb->ki_pos != zi->i_wpoffset) {
+			mutex_unlock(&zi->i_truncate_mutex);
+			ret = -EINVAL;
+			goto inode_unlock;
+		}
 		mutex_unlock(&zi->i_truncate_mutex);
-		ret = -EINVAL;
-		goto inode_unlock;
+		append = sync;
 	}
-	mutex_unlock(&zi->i_truncate_mutex);
 
-	ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops,
-			   &zonefs_write_dio_ops, is_sync_kiocb(iocb));
+	if (append)
+		ret = zonefs_file_dio_append(iocb, from);
+	else
+		ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops,
+				   &zonefs_write_dio_ops, sync);
 	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
 	    (ret > 0 || ret == -EIOCBQUEUED)) {
 		if (ret > 0)