mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-26 19:19:32 +03:00
a10e552b99
Adding O_DIRECT support to ZFS to bypass the ARC for writes/reads.
O_DIRECT support in ZFS will always ensure there is coherency between
buffered and O_DIRECT IO requests. This ensures that all IO requests,
whether buffered or direct, will see the same file contents at all
times. Just as in other FS's , O_DIRECT does not imply O_SYNC. While
data is written directly to VDEV disks, metadata will not be synced
until the associated TXG is synced.
For both O_DIRECT read and write request the offset and request sizes,
at a minimum, must be PAGE_SIZE aligned. In the event they are not,
then EINVAL is returned unless the direct property is set to always (see
below).
For O_DIRECT writes:
The request also must be block aligned (recordsize) or the write
request will take the normal (buffered) write path. In the event that
request is block aligned and a cached copy of the buffer in the ARC,
then it will be discarded from the ARC forcing all further reads to
retrieve the data from disk.
For O_DIRECT reads:
The only alignment restrictions are PAGE_SIZE alignment. In the event
that the requested data is in buffered (in the ARC) it will just be
copied from the ARC into the user buffer.
For both O_DIRECT writes and reads the O_DIRECT flag will be ignored in
the event that file contents are mmap'ed. In this case, all requests
that are at least PAGE_SIZE aligned will just fall back to the buffered
paths. If the request however is not PAGE_SIZE aligned, EINVAL will
be returned as always regardless if the file's contents are mmap'ed.
Since O_DIRECT writes go through the normal ZIO pipeline, the
following operations are supported just as with normal buffered writes:
Checksum
Compression
Encryption
Erasure Coding
There is one caveat for the data integrity of O_DIRECT writes that is
distinct for each of the OS's supported by ZFS.
FreeBSD - FreeBSD is able to place user pages under write protection so
any data in the user buffers and written directly down to the
VDEV disks is guaranteed to not change. There is no concern
with data integrity and O_DIRECT writes.
Linux - Linux is not able to place anonymous user pages under write
protection. Because of this, if the user decides to manipulate
the page contents while the write operation is occurring, data
integrity can not be guaranteed. However, there is a module
parameter `zfs_vdev_direct_write_verify` that controls the
if a O_DIRECT writes that can occur to a top-level VDEV before
a checksum verify is run before the contents of the I/O buffer
are committed to disk. In the event of a checksum verification
failure the write will return EIO. The number of O_DIRECT write
checksum verification errors can be observed by doing
`zpool status -d`, which will list all verification errors that
have occurred on a top-level VDEV. Along with `zpool status`, a
ZED event will be issues as `dio_verify` when a checksum
verification error occurs.
ZVOLs and dedup is not currently supported with Direct I/O.
A new dataset property `direct` has been added with the following 3
allowable values:
disabled - Accepts O_DIRECT flag, but silently ignores it and treats
the request as a buffered IO request.
standard - Follows the alignment restrictions outlined above for
write/read IO requests when the O_DIRECT flag is used.
always - Treats every write/read IO request as though it passed
O_DIRECT and will do O_DIRECT if the alignment restrictions
are met otherwise will redirect through the ARC. This
property will not allow a request to fail.
There is also a module parameter zfs_dio_enabled that can be used to
force all reads and writes through the ARC. By setting this module
parameter to 0, it mimics as if the direct dataset property is set to
disabled.
Reviewed-by: Brian Behlendorf <behlendorf@llnl.gov>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Brian Atkinson <batkinson@lanl.gov>
Co-authored-by: Mark Maybee <mark.maybee@delphix.com>
Co-authored-by: Matt Macy <mmacy@FreeBSD.org>
Co-authored-by: Brian Behlendorf <behlendorf@llnl.gov>
Closes #10018
128 lines
3.4 KiB
C
128 lines
3.4 KiB
C
/*
|
|
* CDDL HEADER START
|
|
*
|
|
* The contents of this file are subject to the terms of the
|
|
* Common Development and Distribution License (the "License").
|
|
* You may not use this file except in compliance with the License.
|
|
*
|
|
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
|
|
* or https://opensource.org/licenses/CDDL-1.0.
|
|
* See the License for the specific language governing permissions
|
|
* and limitations under the License.
|
|
*
|
|
* When distributing Covered Code, include this CDDL HEADER in each
|
|
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
|
|
* If applicable, add the following below this CDDL HEADER, with the
|
|
* fields enclosed by brackets "[]" replaced with your own identifying
|
|
* information: Portions Copyright [yyyy] [name of copyright owner]
|
|
*
|
|
* CDDL HEADER END
|
|
*/
|
|
/*
|
|
* Copyright (c) 2014 by Chunwei Chen. All rights reserved.
|
|
* Copyright (c) 2016, 2019 by Delphix. All rights reserved.
|
|
* Copyright (c) 2023, 2024, Klara Inc.
|
|
*/
|
|
|
|
#ifndef _ABD_IMPL_H
|
|
#define _ABD_IMPL_H
|
|
|
|
#include <sys/abd.h>
|
|
#include <sys/abd_impl_os.h>
|
|
#include <sys/wmsum.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
typedef enum abd_stats_op {
|
|
ABDSTAT_INCR, /* Increase abdstat values */
|
|
ABDSTAT_DECR /* Decrease abdstat values */
|
|
} abd_stats_op_t;
|
|
|
|
/* forward declarations */
|
|
struct scatterlist;
|
|
struct page;
|
|
#if defined(__FreeBSD__) && defined(_KERNEL)
|
|
struct sf_buf;
|
|
#endif
|
|
|
|
struct abd_iter {
|
|
/* public interface */
|
|
union {
|
|
/* for abd_iter_map()/abd_iter_unmap() */
|
|
struct {
|
|
/* addr corresponding to iter_pos */
|
|
void *iter_mapaddr;
|
|
/* length of data valid at mapaddr */
|
|
size_t iter_mapsize;
|
|
};
|
|
/* for abd_iter_page() */
|
|
struct {
|
|
/* current page */
|
|
struct page *iter_page;
|
|
/* offset of data in page */
|
|
size_t iter_page_doff;
|
|
/* size of data in page */
|
|
size_t iter_page_dsize;
|
|
};
|
|
};
|
|
|
|
/* private */
|
|
abd_t *iter_abd; /* ABD being iterated through */
|
|
size_t iter_pos;
|
|
size_t iter_offset; /* offset in current sg/abd_buf, */
|
|
/* abd_offset included */
|
|
#if defined(__FreeBSD__) && defined(_KERNEL)
|
|
struct sf_buf *sf; /* used to map in vm_page_t FreeBSD */
|
|
#else
|
|
struct scatterlist *iter_sg; /* current sg */
|
|
#endif
|
|
};
|
|
|
|
extern abd_t *abd_zero_scatter;
|
|
|
|
abd_t *abd_gang_get_offset(abd_t *, size_t *);
|
|
abd_t *abd_alloc_struct(size_t);
|
|
void abd_free_struct(abd_t *);
|
|
void abd_init_struct(abd_t *);
|
|
|
|
/*
|
|
* OS specific functions
|
|
*/
|
|
|
|
abd_t *abd_alloc_struct_impl(size_t);
|
|
abd_t *abd_get_offset_scatter(abd_t *, abd_t *, size_t, size_t);
|
|
void abd_free_struct_impl(abd_t *);
|
|
void abd_alloc_chunks(abd_t *, size_t);
|
|
void abd_free_chunks(abd_t *);
|
|
void abd_update_scatter_stats(abd_t *, abd_stats_op_t);
|
|
void abd_update_linear_stats(abd_t *, abd_stats_op_t);
|
|
void abd_verify_scatter(abd_t *);
|
|
void abd_free_linear_page(abd_t *);
|
|
/* OS specific abd_iter functions */
|
|
void abd_iter_init(struct abd_iter *, abd_t *);
|
|
boolean_t abd_iter_at_end(struct abd_iter *);
|
|
void abd_iter_advance(struct abd_iter *, size_t);
|
|
void abd_iter_map(struct abd_iter *);
|
|
void abd_iter_unmap(struct abd_iter *);
|
|
void abd_iter_page(struct abd_iter *);
|
|
|
|
/*
|
|
* Helper macros
|
|
*/
|
|
#define ABDSTAT_INCR(stat, val) \
|
|
wmsum_add(&abd_sums.stat, (val))
|
|
#define ABDSTAT_BUMP(stat) ABDSTAT_INCR(stat, 1)
|
|
#define ABDSTAT_BUMPDOWN(stat) ABDSTAT_INCR(stat, -1)
|
|
|
|
#define ABD_SCATTER(abd) ((abd)->abd_u.abd_scatter)
|
|
#define ABD_LINEAR_BUF(abd) ((abd)->abd_u.abd_linear.abd_buf)
|
|
#define ABD_GANG(abd) ((abd)->abd_u.abd_gang)
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _ABD_IMPL_H */
|