mirrors/qemu
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
cd3a4cf631
qemu/block/raw-aio.h

61 lines
2.1 KiB
C
Raw Normal View History

raw-posix: refactor AIO support Currently the raw-posix.c code contains a lot of knowledge about the asynchronous I/O scheme that is mostly implemented in posix-aio-compat.c. All this code does not really belong here and is getting a bit in the way of implementing native AIO on Linux. So instead move all the guts of the AIO implementation into posix-aio-compat.c (which might need a better name, btw). There's now a very small interface between the AIO providers and raw-posix.c: - an init routine is called from raw_open_common to return an AIO context for this drive. An AIO implementation may either re-use one context for all drives, or use a different one for each as the Linux native AIO support will do. - an submit routine is called from the aio_reav/writev methods to submit an AIO request There are no indirect calls involved in this interface as we need to decide which one to call manually. We will only call the Linux AIO native init function if we were requested to by vl.c, and we will only call the native submit function if we are asked to and the request is properly aligned. That's also the reason why the alignment check actually does the inverse move and now goes into raw-posix.c. The old posix-aio-compat.h headers is removed now that most of it's content is private to posix-aio-compat.c, and instead we add a new block/raw-posix-aio.h headers is created containing only the tiny interface between raw-posix.c and the AIO implementation. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-08-20 18:58:19 +04:00
/*
raw-posix: rename raw-posix-aio.h, hide unavailable prototypes Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2012-06-09 12:57:37 +04:00
* Declarations for AIO in the raw protocol
raw-posix: refactor AIO support Currently the raw-posix.c code contains a lot of knowledge about the asynchronous I/O scheme that is mostly implemented in posix-aio-compat.c. All this code does not really belong here and is getting a bit in the way of implementing native AIO on Linux. So instead move all the guts of the AIO implementation into posix-aio-compat.c (which might need a better name, btw). There's now a very small interface between the AIO providers and raw-posix.c: - an init routine is called from raw_open_common to return an AIO context for this drive. An AIO implementation may either re-use one context for all drives, or use a different one for each as the Linux native AIO support will do. - an submit routine is called from the aio_reav/writev methods to submit an AIO request There are no indirect calls involved in this interface as we need to decide which one to call manually. We will only call the Linux AIO native init function if we were requested to by vl.c, and we will only call the native submit function if we are asked to and the request is properly aligned. That's also the reason why the alignment check actually does the inverse move and now goes into raw-posix.c. The old posix-aio-compat.h headers is removed now that most of it's content is private to posix-aio-compat.c, and instead we add a new block/raw-posix-aio.h headers is created containing only the tiny interface between raw-posix.c and the AIO implementation. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-08-20 18:58:19 +04:00
*
* 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.
*
prepare for future GPLv2+ relicensing All files under GPLv2 will get GPLv2+ changes starting tomorrow. event_notifier.c and exec-obsolete.h were only ever touched by Red Hat employees and can be relicensed now. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2012-01-13 20:44:23 +04:00
* Contributions after 2012-01-13 are licensed under the terms of the
* GNU GPL, version 2 or (at your option) any later version.
raw-posix: refactor AIO support Currently the raw-posix.c code contains a lot of knowledge about the asynchronous I/O scheme that is mostly implemented in posix-aio-compat.c. All this code does not really belong here and is getting a bit in the way of implementing native AIO on Linux. So instead move all the guts of the AIO implementation into posix-aio-compat.c (which might need a better name, btw). There's now a very small interface between the AIO providers and raw-posix.c: - an init routine is called from raw_open_common to return an AIO context for this drive. An AIO implementation may either re-use one context for all drives, or use a different one for each as the Linux native AIO support will do. - an submit routine is called from the aio_reav/writev methods to submit an AIO request There are no indirect calls involved in this interface as we need to decide which one to call manually. We will only call the Linux AIO native init function if we were requested to by vl.c, and we will only call the native submit function if we are asked to and the request is properly aligned. That's also the reason why the alignment check actually does the inverse move and now goes into raw-posix.c. The old posix-aio-compat.h headers is removed now that most of it's content is private to posix-aio-compat.c, and instead we add a new block/raw-posix-aio.h headers is created containing only the tiny interface between raw-posix.c and the AIO implementation. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-08-20 18:58:19 +04:00
*/
raw-posix: rename raw-posix-aio.h, hide unavailable prototypes Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2012-06-09 12:57:37 +04:00
#ifndef QEMU_RAW_AIO_H
#define QEMU_RAW_AIO_H
raw-posix: refactor AIO support Currently the raw-posix.c code contains a lot of knowledge about the asynchronous I/O scheme that is mostly implemented in posix-aio-compat.c. All this code does not really belong here and is getting a bit in the way of implementing native AIO on Linux. So instead move all the guts of the AIO implementation into posix-aio-compat.c (which might need a better name, btw). There's now a very small interface between the AIO providers and raw-posix.c: - an init routine is called from raw_open_common to return an AIO context for this drive. An AIO implementation may either re-use one context for all drives, or use a different one for each as the Linux native AIO support will do. - an submit routine is called from the aio_reav/writev methods to submit an AIO request There are no indirect calls involved in this interface as we need to decide which one to call manually. We will only call the Linux AIO native init function if we were requested to by vl.c, and we will only call the native submit function if we are asked to and the request is properly aligned. That's also the reason why the alignment check actually does the inverse move and now goes into raw-posix.c. The old posix-aio-compat.h headers is removed now that most of it's content is private to posix-aio-compat.c, and instead we add a new block/raw-posix-aio.h headers is created containing only the tiny interface between raw-posix.c and the AIO implementation. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-08-20 18:58:19 +04:00
/* AIO request types */
#define QEMU_AIO_READ 0x0001
#define QEMU_AIO_WRITE 0x0002
#define QEMU_AIO_IOCTL 0x0004
block: add aio_flush operation Instead stalling the VCPU while serving a cache flush try to do it asynchronously. Use our good old helper thread pool to issue an asynchronous fdatasync for raw-posix. Note that while Linux AIO implements a fdatasync operation it is not useful for us because it isn't actually implement in asynchronous fashion. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-09-04 21:01:49 +04:00
#define QEMU_AIO_FLUSH 0x0008
block: make discard asynchronous This is easy with the thread pool, because we can use s->is_xfs and s->has_discard from the worker function. QEMU has a widespread assumption that each I/O operation writes less than 2^32 bytes. This patch doesn't fix it throughout of course, but it starts correcting struct RawPosixAIOData so that there is no regression with respect to the synchronous discard implementation. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-01-14 19:26:55 +04:00
#define QEMU_AIO_DISCARD 0x0010
raw-posix: add support for write_zeroes on XFS and block devices The code is similar to the implementation of discard and write_zeroes with UNMAP. However, failure must be propagated up to block.c. The stale page cache problem can be reproduced as follows: # modprobe scsi-debug lbpws=1 lbprz=1 # ./qemu-io /dev/sdXX qemu-io> write -P 0xcc 0 2M qemu-io> write -z 0 1M qemu-io> read -P 0x00 0 512 Pattern verification failed at offset 0, 512 bytes qemu-io> read -v 0 512 00000000: cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc ................ ... # ./qemu-io --cache=none /dev/sdXX qemu-io> write -P 0xcc 0 2M qemu-io> write -z 0 1M qemu-io> read -P 0x00 0 512 qemu-io> read -v 0 512 00000000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ ... And similarly with discard instead of "write -z". Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-11-22 16:39:57 +04:00
#define QEMU_AIO_WRITE_ZEROES 0x0020
raw-posix: refactor AIO support Currently the raw-posix.c code contains a lot of knowledge about the asynchronous I/O scheme that is mostly implemented in posix-aio-compat.c. All this code does not really belong here and is getting a bit in the way of implementing native AIO on Linux. So instead move all the guts of the AIO implementation into posix-aio-compat.c (which might need a better name, btw). There's now a very small interface between the AIO providers and raw-posix.c: - an init routine is called from raw_open_common to return an AIO context for this drive. An AIO implementation may either re-use one context for all drives, or use a different one for each as the Linux native AIO support will do. - an submit routine is called from the aio_reav/writev methods to submit an AIO request There are no indirect calls involved in this interface as we need to decide which one to call manually. We will only call the Linux AIO native init function if we were requested to by vl.c, and we will only call the native submit function if we are asked to and the request is properly aligned. That's also the reason why the alignment check actually does the inverse move and now goes into raw-posix.c. The old posix-aio-compat.h headers is removed now that most of it's content is private to posix-aio-compat.c, and instead we add a new block/raw-posix-aio.h headers is created containing only the tiny interface between raw-posix.c and the AIO implementation. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-08-20 18:58:19 +04:00
#define QEMU_AIO_TYPE_MASK \
block: make discard asynchronous This is easy with the thread pool, because we can use s->is_xfs and s->has_discard from the worker function. QEMU has a widespread assumption that each I/O operation writes less than 2^32 bytes. This patch doesn't fix it throughout of course, but it starts correcting struct RawPosixAIOData so that there is no regression with respect to the synchronous discard implementation. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-01-14 19:26:55 +04:00
(QEMU_AIO_READ|QEMU_AIO_WRITE|QEMU_AIO_IOCTL|QEMU_AIO_FLUSH| \
raw-posix: add support for write_zeroes on XFS and block devices The code is similar to the implementation of discard and write_zeroes with UNMAP. However, failure must be propagated up to block.c. The stale page cache problem can be reproduced as follows: # modprobe scsi-debug lbpws=1 lbprz=1 # ./qemu-io /dev/sdXX qemu-io> write -P 0xcc 0 2M qemu-io> write -z 0 1M qemu-io> read -P 0x00 0 512 Pattern verification failed at offset 0, 512 bytes qemu-io> read -v 0 512 00000000: cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc ................ ... # ./qemu-io --cache=none /dev/sdXX qemu-io> write -P 0xcc 0 2M qemu-io> write -z 0 1M qemu-io> read -P 0x00 0 512 qemu-io> read -v 0 512 00000000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ ... And similarly with discard instead of "write -z". Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-11-22 16:39:57 +04:00
QEMU_AIO_DISCARD|QEMU_AIO_WRITE_ZEROES)
raw-posix: refactor AIO support Currently the raw-posix.c code contains a lot of knowledge about the asynchronous I/O scheme that is mostly implemented in posix-aio-compat.c. All this code does not really belong here and is getting a bit in the way of implementing native AIO on Linux. So instead move all the guts of the AIO implementation into posix-aio-compat.c (which might need a better name, btw). There's now a very small interface between the AIO providers and raw-posix.c: - an init routine is called from raw_open_common to return an AIO context for this drive. An AIO implementation may either re-use one context for all drives, or use a different one for each as the Linux native AIO support will do. - an submit routine is called from the aio_reav/writev methods to submit an AIO request There are no indirect calls involved in this interface as we need to decide which one to call manually. We will only call the Linux AIO native init function if we were requested to by vl.c, and we will only call the native submit function if we are asked to and the request is properly aligned. That's also the reason why the alignment check actually does the inverse move and now goes into raw-posix.c. The old posix-aio-compat.h headers is removed now that most of it's content is private to posix-aio-compat.c, and instead we add a new block/raw-posix-aio.h headers is created containing only the tiny interface between raw-posix.c and the AIO implementation. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-08-20 18:58:19 +04:00
/* AIO flags */
#define QEMU_AIO_MISALIGNED 0x1000
block: make discard asynchronous This is easy with the thread pool, because we can use s->is_xfs and s->has_discard from the worker function. QEMU has a widespread assumption that each I/O operation writes less than 2^32 bytes. This patch doesn't fix it throughout of course, but it starts correcting struct RawPosixAIOData so that there is no regression with respect to the synchronous discard implementation. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-01-14 19:26:55 +04:00
#define QEMU_AIO_BLKDEV 0x2000
raw-posix: refactor AIO support Currently the raw-posix.c code contains a lot of knowledge about the asynchronous I/O scheme that is mostly implemented in posix-aio-compat.c. All this code does not really belong here and is getting a bit in the way of implementing native AIO on Linux. So instead move all the guts of the AIO implementation into posix-aio-compat.c (which might need a better name, btw). There's now a very small interface between the AIO providers and raw-posix.c: - an init routine is called from raw_open_common to return an AIO context for this drive. An AIO implementation may either re-use one context for all drives, or use a different one for each as the Linux native AIO support will do. - an submit routine is called from the aio_reav/writev methods to submit an AIO request There are no indirect calls involved in this interface as we need to decide which one to call manually. We will only call the Linux AIO native init function if we were requested to by vl.c, and we will only call the native submit function if we are asked to and the request is properly aligned. That's also the reason why the alignment check actually does the inverse move and now goes into raw-posix.c. The old posix-aio-compat.h headers is removed now that most of it's content is private to posix-aio-compat.c, and instead we add a new block/raw-posix-aio.h headers is created containing only the tiny interface between raw-posix.c and the AIO implementation. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-08-20 18:58:19 +04:00
raw-posix: add Linux native AIO support Now that do have a nicer interface to work against we can add Linux native AIO support. It's an extremly thing layer just setting up an iocb for the io_submit system call in the submission path, and registering an eventfd with the qemu poll handler to do complete the iocbs directly from there. This started out based on Anthony's earlier AIO patch, but after estimated 42,000 rewrites and just as many build system changes there's not much left of it. To enable native kernel aio use the aio=native sub-command on the drive command line. I have also added an option to qemu-io to test the aio support without needing a guest. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-08-20 18:58:35 +04:00
/* linux-aio.c - Linux native implementation */
raw-posix: rename raw-posix-aio.h, hide unavailable prototypes Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2012-06-09 12:57:37 +04:00
#ifdef CONFIG_LINUX_AIO
raw-posix: add Linux native AIO support Now that do have a nicer interface to work against we can add Linux native AIO support. It's an extremly thing layer just setting up an iocb for the io_submit system call in the submission path, and registering an eventfd with the qemu poll handler to do complete the iocbs directly from there. This started out based on Anthony's earlier AIO patch, but after estimated 42,000 rewrites and just as many build system changes there's not much left of it. To enable native kernel aio use the aio=native sub-command on the drive command line. I have also added an option to qemu-io to test the aio support without needing a guest. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-08-20 18:58:35 +04:00
void *laio_init(void);
block/linux-aio: fix memory and fd leak Hot unplugging -drive aio=native,file=test.img,format=raw images leaves the Linux AIO event notifier and struct qemu_laio_state allocated. Luckily nothing will use the event notifier after the BlockDriverState has been closed so the handler function is never called. It's still worth fixing this resource leak. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-05-08 18:34:48 +04:00
void laio_cleanup(void *s);
raw-posix: add Linux native AIO support Now that do have a nicer interface to work against we can add Linux native AIO support. It's an extremly thing layer just setting up an iocb for the io_submit system call in the submission path, and registering an eventfd with the qemu poll handler to do complete the iocbs directly from there. This started out based on Anthony's earlier AIO patch, but after estimated 42,000 rewrites and just as many build system changes there's not much left of it. To enable native kernel aio use the aio=native sub-command on the drive command line. I have also added an option to qemu-io to test the aio support without needing a guest. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-08-20 18:58:35 +04:00
BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque, int type);
block/raw-posix: implement .bdrv_detach/attach_aio_context() Drop the assumption that we're using the main AioContext for Linux AIO. Convert the Linux AIO event notifier to use aio_set_event_notifier(). The .bdrv_detach/attach_aio_context() interfaces also need to be implemented to move the event notifier handler from the old to the new AioContext. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-05-08 18:34:47 +04:00
void laio_detach_aio_context(void *s, AioContext *old_context);
void laio_attach_aio_context(void *s, AioContext *new_context);
raw-posix: rename raw-posix-aio.h, hide unavailable prototypes Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2012-06-09 12:57:37 +04:00
#endif
raw-posix: add Linux native AIO support Now that do have a nicer interface to work against we can add Linux native AIO support. It's an extremly thing layer just setting up an iocb for the io_submit system call in the submission path, and registering an eventfd with the qemu poll handler to do complete the iocbs directly from there. This started out based on Anthony's earlier AIO patch, but after estimated 42,000 rewrites and just as many build system changes there's not much left of it. To enable native kernel aio use the aio=native sub-command on the drive command line. I have also added an option to qemu-io to test the aio support without needing a guest. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2009-08-20 18:58:35 +04:00
raw-win32: implement native asynchronous I/O With the new support for EventNotifiers in the AIO event loop, we can hook a completion port to every opened file and use asynchronous I/O on them. Wine's support is extremely inefficient, also because it really does the I/O synchronously on regular files. (!) But it works, and it is good to keep the Win32 and POSIX ports as similar as possible. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2012-10-26 13:43:58 +04:00
#ifdef _WIN32
typedef struct QEMUWin32AIOState QEMUWin32AIOState;
QEMUWin32AIOState *win32_aio_init(void);
block/raw-win32: create one QEMUWin32AIOState per BDRVRawState Each QEMUWin32AIOState event notifier is associated with an AioContext. Since BlockDriverState instances can use different AioContexts we cannot continue to use a global QEMUWin32AIOState. Let each BDRVRawState have its own QEMUWin32AIOState and free it when BDRVRawState is closed. Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-05-08 18:34:49 +04:00
void win32_aio_cleanup(QEMUWin32AIOState *aio);
raw-win32: implement native asynchronous I/O With the new support for EventNotifiers in the AIO event loop, we can hook a completion port to every opened file and use asynchronous I/O on them. Wine's support is extremely inefficient, also because it really does the I/O synchronously on regular files. (!) But it works, and it is good to keep the Win32 and POSIX ports as similar as possible. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2012-10-26 13:43:58 +04:00
int win32_aio_attach(QEMUWin32AIOState *aio, HANDLE hfile);
BlockDriverAIOCB *win32_aio_submit(BlockDriverState *bs,
QEMUWin32AIOState *aio, HANDLE hfile,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque, int type);
block/raw-win32: implement .bdrv_detach/attach_aio_context() Drop the assumption that we're using the main AioContext for raw-win32. Convert the aio-win32 code to support detach/attach and replace qemu_aio_wait() with aio_poll(). The .bdrv_detach/attach_aio_context() interfaces move the aio-win32 event notifier from the old to the new AioContext. Cc: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-05-08 18:34:50 +04:00
void win32_aio_detach_aio_context(QEMUWin32AIOState *aio,
AioContext *old_context);
void win32_aio_attach_aio_context(QEMUWin32AIOState *aio,
AioContext *new_context);
raw-win32: implement native asynchronous I/O With the new support for EventNotifiers in the AIO event loop, we can hook a completion port to every opened file and use asynchronous I/O on them. Wine's support is extremely inefficient, also because it really does the I/O synchronously on regular files. (!) But it works, and it is good to keep the Win32 and POSIX ports as similar as possible. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2012-10-26 13:43:58 +04:00
#endif
raw-posix: rename raw-posix-aio.h, hide unavailable prototypes Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2012-06-09 12:57:37 +04:00
#endif /* QEMU_RAW_AIO_H */
Reference in New Issue Copy Permalink