984a32f17e
Until now, FUA was always emulated with a separate flush after the write
for file-posix. The overhead of processing a second request can reduce
performance significantly for a guest disk that has disabled the write
cache, especially if the host disk is already write through, too, and
the flush isn't actually doing anything.
Advertise support for REQ_FUA in write requests and implement it for
Linux AIO and io_uring using the RWF_DSYNC flag for write requests. The
thread pool still performs a separate fdatasync() call. This can be
improved later by using the pwritev2() syscall if available.
As an example, this is how fio numbers can be improved in some scenarios
with this patch (all using virtio-blk with cache=directsync on an nvme
block device for the VM, fio with ioengine=libaio,direct=1,sync=1):
| old | with FUA support
------------------------------+---------------+-------------------
bs=4k, iodepth=1, numjobs=1 | 45.6k iops | 56.1k iops
bs=4k, iodepth=1, numjobs=16 | 183.3k iops | 236.0k iops
bs=4k, iodepth=16, numjobs=1 | 258.4k iops | 311.1k iops
However, not all scenarios are clear wins. On another slower disk I saw
little to no improvment. In fact, in two corner case scenarios, I even
observed a regression, which I however consider acceptable:
1. On slow host disks in a write through cache mode, when the guest is
using virtio-blk in a separate iothread so that polling can be
enabled, and each completion is quickly followed up with a new
request (so that polling gets it), it can happen that enabling FUA
makes things slower - the additional very fast no-op flush we used to
have gave the adaptive polling algorithm a success so that it kept
polling. Without it, we only have the slow write request, which
disables polling. This is a problem in the polling algorithm that
will be fixed later in this series.
2. With a high queue depth, it can be beneficial to have flush requests
for another reason: The optimisation in bdrv_co_flush() that flushes
only once per write generation acts as a synchronisation mechanism
that lets all requests complete at the same time. This can result in
better batching and if the disk is very fast (I only saw this with a
null_blk backend), this can make up for the overhead of the flush and
improve throughput. In theory, we could optionally introduce a
similar artificial latency in the normal completion path to achieve
the same kind of completion batching. This is not implemented in this
series.
Compatibility is not a concern for the kernel side of io_uring, it has
supported RWF_DSYNC from the start. However, io_uring_prep_writev2() is
not available before liburing 2.2.
Linux AIO started supporting it in Linux 4.13 and libaio 0.3.111. The
kernel is not a problem for any supported build platform, so it's not
necessary to add runtime checks. However, openSUSE is still stuck with
an older libaio version that would break the build.
We must detect the presence of the writev2 functions in the user space
libraries at build time to avoid build failures.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-ID: <20250307221634.71951-2-kwolf@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
110 lines
3.5 KiB
C
110 lines
3.5 KiB
C
/*
|
|
* Declarations for AIO in the raw protocol
|
|
*
|
|
* Copyright IBM, Corp. 2008
|
|
*
|
|
* Authors:
|
|
* Anthony Liguori <aliguori@us.ibm.com>
|
|
*
|
|
* This work is licensed under the terms of the GNU GPL, version 2. See
|
|
* the COPYING file in the top-level directory.
|
|
*
|
|
* Contributions after 2012-01-13 are licensed under the terms of the
|
|
* GNU GPL, version 2 or (at your option) any later version.
|
|
*/
|
|
|
|
#ifndef QEMU_RAW_AIO_H
|
|
#define QEMU_RAW_AIO_H
|
|
|
|
#include "block/aio.h"
|
|
#include "block/block-common.h"
|
|
#include "qemu/iov.h"
|
|
|
|
/* AIO request types */
|
|
#define QEMU_AIO_READ 0x0001
|
|
#define QEMU_AIO_WRITE 0x0002
|
|
#define QEMU_AIO_IOCTL 0x0004
|
|
#define QEMU_AIO_FLUSH 0x0008
|
|
#define QEMU_AIO_DISCARD 0x0010
|
|
#define QEMU_AIO_WRITE_ZEROES 0x0020
|
|
#define QEMU_AIO_COPY_RANGE 0x0040
|
|
#define QEMU_AIO_TRUNCATE 0x0080
|
|
#define QEMU_AIO_ZONE_REPORT 0x0100
|
|
#define QEMU_AIO_ZONE_MGMT 0x0200
|
|
#define QEMU_AIO_ZONE_APPEND 0x0400
|
|
#define QEMU_AIO_TYPE_MASK \
|
|
(QEMU_AIO_READ | \
|
|
QEMU_AIO_WRITE | \
|
|
QEMU_AIO_IOCTL | \
|
|
QEMU_AIO_FLUSH | \
|
|
QEMU_AIO_DISCARD | \
|
|
QEMU_AIO_WRITE_ZEROES | \
|
|
QEMU_AIO_COPY_RANGE | \
|
|
QEMU_AIO_TRUNCATE | \
|
|
QEMU_AIO_ZONE_REPORT | \
|
|
QEMU_AIO_ZONE_MGMT | \
|
|
QEMU_AIO_ZONE_APPEND)
|
|
|
|
/* AIO flags */
|
|
#define QEMU_AIO_MISALIGNED 0x1000
|
|
#define QEMU_AIO_BLKDEV 0x2000
|
|
#define QEMU_AIO_NO_FALLBACK 0x4000
|
|
|
|
|
|
/* linux-aio.c - Linux native implementation */
|
|
#ifdef CONFIG_LINUX_AIO
|
|
typedef struct LinuxAioState LinuxAioState;
|
|
LinuxAioState *laio_init(Error **errp);
|
|
void laio_cleanup(LinuxAioState *s);
|
|
|
|
/* laio_co_submit: submit I/O requests in the thread's current AioContext. */
|
|
int coroutine_fn laio_co_submit(int fd, uint64_t offset, QEMUIOVector *qiov,
|
|
int type, BdrvRequestFlags flags,
|
|
uint64_t dev_max_batch);
|
|
|
|
bool laio_has_fdsync(int);
|
|
bool laio_has_fua(void);
|
|
void laio_detach_aio_context(LinuxAioState *s, AioContext *old_context);
|
|
void laio_attach_aio_context(LinuxAioState *s, AioContext *new_context);
|
|
#else
|
|
static inline bool laio_has_fua(void)
|
|
{
|
|
return false;
|
|
}
|
|
#endif
|
|
/* io_uring.c - Linux io_uring implementation */
|
|
#ifdef CONFIG_LINUX_IO_URING
|
|
LuringState *luring_init(Error **errp);
|
|
void luring_cleanup(LuringState *s);
|
|
|
|
/* luring_co_submit: submit I/O requests in the thread's current AioContext. */
|
|
int coroutine_fn luring_co_submit(BlockDriverState *bs, int fd, uint64_t offset,
|
|
QEMUIOVector *qiov, int type,
|
|
BdrvRequestFlags flags);
|
|
void luring_detach_aio_context(LuringState *s, AioContext *old_context);
|
|
void luring_attach_aio_context(LuringState *s, AioContext *new_context);
|
|
bool luring_has_fua(void);
|
|
#else
|
|
static inline bool luring_has_fua(void)
|
|
{
|
|
return false;
|
|
}
|
|
#endif
|
|
|
|
#ifdef _WIN32
|
|
typedef struct QEMUWin32AIOState QEMUWin32AIOState;
|
|
QEMUWin32AIOState *win32_aio_init(void);
|
|
void win32_aio_cleanup(QEMUWin32AIOState *aio);
|
|
int win32_aio_attach(QEMUWin32AIOState *aio, HANDLE hfile);
|
|
BlockAIOCB *win32_aio_submit(BlockDriverState *bs,
|
|
QEMUWin32AIOState *aio, HANDLE hfile,
|
|
uint64_t offset, uint64_t bytes, QEMUIOVector *qiov,
|
|
BlockCompletionFunc *cb, void *opaque, int type);
|
|
void win32_aio_detach_aio_context(QEMUWin32AIOState *aio,
|
|
AioContext *old_context);
|
|
void win32_aio_attach_aio_context(QEMUWin32AIOState *aio,
|
|
AioContext *new_context);
|
|
#endif
|
|
|
|
#endif /* QEMU_RAW_AIO_H */
|