qemu/include/block/block_int.h

475 lines
18 KiB
C
Raw Normal View History

/*
* QEMU System Emulator block driver
*
* Copyright (c) 2003 Fabrice Bellard
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#ifndef BLOCK_INT_H
#define BLOCK_INT_H
#include "block/block.h"
#include "qemu/option.h"
#include "qemu/queue.h"
#include "block/coroutine.h"
#include "qemu/timer.h"
#include "qapi-types.h"
#include "qapi/qmp/qerror.h"
#include "monitor/monitor.h"
#include "qemu/hbitmap.h"
#include "block/snapshot.h"
#include "qemu/main-loop.h"
#include "qemu/throttle.h"
#define BLOCK_FLAG_ENCRYPT 1
#define BLOCK_FLAG_COMPAT6 4
#define BLOCK_FLAG_LAZY_REFCOUNTS 8
#define BLOCK_OPT_SIZE "size"
#define BLOCK_OPT_ENCRYPT "encryption"
#define BLOCK_OPT_COMPAT6 "compat6"
#define BLOCK_OPT_BACKING_FILE "backing_file"
#define BLOCK_OPT_BACKING_FMT "backing_fmt"
#define BLOCK_OPT_CLUSTER_SIZE "cluster_size"
#define BLOCK_OPT_TABLE_SIZE "table_size"
#define BLOCK_OPT_PREALLOC "preallocation"
#define BLOCK_OPT_SUBFMT "subformat"
#define BLOCK_OPT_COMPAT_LEVEL "compat"
#define BLOCK_OPT_LAZY_REFCOUNTS "lazy_refcounts"
#define BLOCK_OPT_ADAPTER_TYPE "adapter_type"
#define BLOCK_OPT_REDUNDANCY "redundancy"
typedef struct BdrvTrackedRequest {
BlockDriverState *bs;
int64_t sector_num;
int nb_sectors;
bool is_write;
QLIST_ENTRY(BdrvTrackedRequest) list;
Coroutine *co; /* owner, used for deadlock detection */
CoQueue wait_queue; /* coroutines blocked on this request */
} BdrvTrackedRequest;
struct BlockDriver {
const char *format_name;
int instance_size;
/* if not defined external snapshots are allowed
* future block filters will query their children to build the response
*/
ExtSnapshotPerm (*bdrv_check_ext_snapshot)(BlockDriverState *bs);
int (*bdrv_probe)(const uint8_t *buf, int buf_size, const char *filename);
int (*bdrv_probe_device)(const char *filename);
/* Any driver implementing this callback is expected to be able to handle
* NULL file names in its .bdrv_open() implementation */
void (*bdrv_parse_filename)(const char *filename, QDict *options, Error **errp);
/* Drivers not implementing bdrv_parse_filename nor bdrv_open should have
* this field set to true, except ones that are defined only by their
* child's bs.
* An example of the last type will be the quorum block driver.
*/
bool bdrv_needs_filename;
/* For handling image reopen for split or non-split files */
int (*bdrv_reopen_prepare)(BDRVReopenState *reopen_state,
BlockReopenQueue *queue, Error **errp);
void (*bdrv_reopen_commit)(BDRVReopenState *reopen_state);
void (*bdrv_reopen_abort)(BDRVReopenState *reopen_state);
int (*bdrv_open)(BlockDriverState *bs, QDict *options, int flags,
Error **errp);
int (*bdrv_file_open)(BlockDriverState *bs, QDict *options, int flags,
Error **errp);
int (*bdrv_read)(BlockDriverState *bs, int64_t sector_num,
uint8_t *buf, int nb_sectors);
int (*bdrv_write)(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors);
void (*bdrv_close)(BlockDriverState *bs);
void (*bdrv_rebind)(BlockDriverState *bs);
int (*bdrv_create)(const char *filename, QEMUOptionParameter *options,
Error **errp);
int (*bdrv_set_key)(BlockDriverState *bs, const char *key);
int (*bdrv_make_empty)(BlockDriverState *bs);
/* aio */
BlockDriverAIOCB *(*bdrv_aio_readv)(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque);
BlockDriverAIOCB *(*bdrv_aio_writev)(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque);
BlockDriverAIOCB *(*bdrv_aio_flush)(BlockDriverState *bs,
BlockDriverCompletionFunc *cb, void *opaque);
BlockDriverAIOCB *(*bdrv_aio_discard)(BlockDriverState *bs,
int64_t sector_num, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque);
int coroutine_fn (*bdrv_co_readv)(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
int coroutine_fn (*bdrv_co_writev)(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, QEMUIOVector *qiov);
/*
* Efficiently zero a region of the disk image. Typically an image format
* would use a compact metadata representation to implement this. This
* function pointer may be NULL and .bdrv_co_writev() will be called
* instead.
*/
int coroutine_fn (*bdrv_co_write_zeroes)(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, BdrvRequestFlags flags);
int coroutine_fn (*bdrv_co_discard)(BlockDriverState *bs,
int64_t sector_num, int nb_sectors);
int64_t coroutine_fn (*bdrv_co_get_block_status)(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, int *pnum);
/*
* Invalidate any cached meta-data.
*/
void (*bdrv_invalidate_cache)(BlockDriverState *bs);
/*
* Flushes all data that was already written to the OS all the way down to
* the disk (for example raw-posix calls fsync()).
*/
int coroutine_fn (*bdrv_co_flush_to_disk)(BlockDriverState *bs);
/*
* Flushes all internal caches to the OS. The data may still sit in a
* writeback cache of the host OS, but it will survive a crash of the qemu
* process.
*/
int coroutine_fn (*bdrv_co_flush_to_os)(BlockDriverState *bs);
const char *protocol_name;
int (*bdrv_truncate)(BlockDriverState *bs, int64_t offset);
2013-10-29 15:18:58 +04:00
int64_t (*bdrv_getlength)(BlockDriverState *bs);
2013-10-29 15:18:58 +04:00
bool has_variable_length;
int64_t (*bdrv_get_allocated_file_size)(BlockDriverState *bs);
2013-10-29 15:18:58 +04:00
int (*bdrv_write_compressed)(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors);
int (*bdrv_snapshot_create)(BlockDriverState *bs,
QEMUSnapshotInfo *sn_info);
int (*bdrv_snapshot_goto)(BlockDriverState *bs,
const char *snapshot_id);
int (*bdrv_snapshot_delete)(BlockDriverState *bs,
const char *snapshot_id,
const char *name,
Error **errp);
int (*bdrv_snapshot_list)(BlockDriverState *bs,
QEMUSnapshotInfo **psn_info);
int (*bdrv_snapshot_load_tmp)(BlockDriverState *bs,
const char *snapshot_id,
const char *name,
Error **errp);
int (*bdrv_get_info)(BlockDriverState *bs, BlockDriverInfo *bdi);
ImageInfoSpecific *(*bdrv_get_specific_info)(BlockDriverState *bs);
int (*bdrv_save_vmstate)(BlockDriverState *bs, QEMUIOVector *qiov,
int64_t pos);
int (*bdrv_load_vmstate)(BlockDriverState *bs, uint8_t *buf,
int64_t pos, int size);
int (*bdrv_change_backing_file)(BlockDriverState *bs,
const char *backing_file, const char *backing_fmt);
/* removable device specific */
int (*bdrv_is_inserted)(BlockDriverState *bs);
int (*bdrv_media_changed)(BlockDriverState *bs);
void (*bdrv_eject)(BlockDriverState *bs, bool eject_flag);
void (*bdrv_lock_medium)(BlockDriverState *bs, bool locked);
/* to control generic scsi devices */
int (*bdrv_ioctl)(BlockDriverState *bs, unsigned long int req, void *buf);
BlockDriverAIOCB *(*bdrv_aio_ioctl)(BlockDriverState *bs,
unsigned long int req, void *buf,
BlockDriverCompletionFunc *cb, void *opaque);
/* List of options for creating images, terminated by name == NULL */
QEMUOptionParameter *create_options;
/*
* Returns 0 for completed check, -errno for internal errors.
* The check results are stored in result.
*/
int (*bdrv_check)(BlockDriverState* bs, BdrvCheckResult *result,
BdrvCheckMode fix);
int (*bdrv_amend_options)(BlockDriverState *bs,
QEMUOptionParameter *options);
void (*bdrv_debug_event)(BlockDriverState *bs, BlkDebugEvent event);
/* TODO Better pass a option string/QDict/QemuOpts to add any rule? */
int (*bdrv_debug_breakpoint)(BlockDriverState *bs, const char *event,
const char *tag);
int (*bdrv_debug_remove_breakpoint)(BlockDriverState *bs,
const char *tag);
int (*bdrv_debug_resume)(BlockDriverState *bs, const char *tag);
bool (*bdrv_debug_is_suspended)(BlockDriverState *bs, const char *tag);
/*
* Returns 1 if newly created images are guaranteed to contain only
* zeros, 0 otherwise.
*/
int (*bdrv_has_zero_init)(BlockDriverState *bs);
QLIST_ENTRY(BlockDriver) list;
};
typedef struct BlockLimits {
/* maximum number of sectors that can be discarded at once */
int max_discard;
/* optimal alignment for discard requests in sectors */
int64_t discard_alignment;
/* maximum number of sectors that can zeroized at once */
int max_write_zeroes;
/* optimal alignment for write zeroes requests in sectors */
int64_t write_zeroes_alignment;
/* optimal transfer length in sectors */
int opt_transfer_length;
} BlockLimits;
/*
* Note: the function bdrv_append() copies and swaps contents of
* BlockDriverStates, so if you add new fields to this struct, please
* inspect bdrv_append() to determine if the new fields need to be
* copied as well.
*/
struct BlockDriverState {
int64_t total_sectors; /* if we are reading a disk image, give its
size in sectors */
int read_only; /* if true, the media is read only */
int open_flags; /* flags used to open the file, re-used for re-open */
int encrypted; /* if true, the media is encrypted */
int valid_key; /* if true, a valid encryption key has been set */
int sg; /* if true, the device is a /dev/sg* */
int copy_on_read; /* if true, copy read backing sectors into image
note this is a reference count */
BlockDriver *drv; /* NULL means no media */
void *opaque;
void *dev; /* attached device model, if any */
/* TODO change to DeviceState when all users are qdevified */
const BlockDevOps *dev_ops;
void *dev_opaque;
char filename[1024];
char backing_file[1024]; /* if non zero, the image is a diff of
this file image */
char backing_format[16]; /* if non-zero and backing_file exists */
int is_temporary;
BlockDriverState *backing_hd;
BlockDriverState *file;
NotifierList close_notifiers;
/* Callback before write request is processed */
NotifierWithReturnList before_write_notifiers;
/* number of in-flight copy-on-read requests */
unsigned int copy_on_read_in_flight;
/* I/O throttling */
ThrottleState throttle_state;
CoQueue throttled_reqs[2];
bool io_limits_enabled;
/* I/O stats (display with "info blockstats"). */
uint64_t nr_bytes[BDRV_MAX_IOTYPE];
uint64_t nr_ops[BDRV_MAX_IOTYPE];
uint64_t total_time_ns[BDRV_MAX_IOTYPE];
uint64_t wr_highest_sector;
/* I/O Limits */
BlockLimits bl;
/* Whether the disk can expand beyond total_sectors */
int growable;
/* Whether produces zeros when read beyond eof */
bool zero_beyond_eof;
/* the memory alignment required for the buffers handled by this driver */
int buffer_alignment;
/* do we need to tell the quest if we have a volatile write cache? */
int enable_write_cache;
/* NOTE: the following infos are only hints for real hardware
drivers. They are not used by the block driver */
BlockdevOnError on_read_error, on_write_error;
bool iostatus_enabled;
BlockDeviceIoStatus iostatus;
char device_name[32];
QLIST_HEAD(, BdrvDirtyBitmap) dirty_bitmaps;
int refcnt;
int in_use; /* users other than guest access, eg. block migration */
QTAILQ_ENTRY(BlockDriverState) list;
QLIST_HEAD(, BdrvTrackedRequest) tracked_requests;
/* long-running background operation */
BlockJob *job;
QDict *options;
};
int get_tmp_filename(char *filename, int size);
void bdrv_set_io_limits(BlockDriverState *bs,
ThrottleConfig *cfg);
/**
* bdrv_add_before_write_notifier:
*
* Register a callback that is invoked before write requests are processed but
* after any throttling or waiting for overlapping requests.
*/
void bdrv_add_before_write_notifier(BlockDriverState *bs,
NotifierWithReturn *notifier);
/**
* bdrv_get_aio_context:
*
* Returns: the currently bound #AioContext
*/
AioContext *bdrv_get_aio_context(BlockDriverState *bs);
#ifdef _WIN32
int is_windows_drive(const char *filename);
#endif
void bdrv_emit_qmp_error_event(const BlockDriverState *bdrv,
enum MonitorEvent ev,
BlockErrorAction action, bool is_read);
/**
* stream_start:
* @bs: Block device to operate on.
* @base: Block device that will become the new base, or %NULL to
* flatten the whole backing file chain onto @bs.
* @base_id: The file name that will be written to @bs as the new
* backing file if the job completes. Ignored if @base is %NULL.
* @speed: The maximum speed, in bytes per second, or 0 for unlimited.
* @on_error: The action to take upon error.
* @cb: Completion function for the job.
* @opaque: Opaque pointer value passed to @cb.
* @errp: Error object.
*
* Start a streaming operation on @bs. Clusters that are unallocated
* in @bs, but allocated in any image between @base and @bs (both
* exclusive) will be written to @bs. At the end of a successful
* streaming job, the backing file of @bs will be changed to
* @base_id in the written image and to @base in the live BlockDriverState.
*/
void stream_start(BlockDriverState *bs, BlockDriverState *base,
const char *base_id, int64_t speed, BlockdevOnError on_error,
BlockDriverCompletionFunc *cb,
void *opaque, Error **errp);
/**
* commit_start:
* @bs: Active block device.
* @top: Top block device to be committed.
* @base: Block device that will be written into, and become the new top.
* @speed: The maximum speed, in bytes per second, or 0 for unlimited.
* @on_error: The action to take upon error.
* @cb: Completion function for the job.
* @opaque: Opaque pointer value passed to @cb.
* @errp: Error object.
*
*/
void commit_start(BlockDriverState *bs, BlockDriverState *base,
BlockDriverState *top, int64_t speed,
BlockdevOnError on_error, BlockDriverCompletionFunc *cb,
void *opaque, Error **errp);
/**
* commit_active_start:
* @bs: Active block device to be committed.
* @base: Block device that will be written into, and become the new top.
* @speed: The maximum speed, in bytes per second, or 0 for unlimited.
* @on_error: The action to take upon error.
* @cb: Completion function for the job.
* @opaque: Opaque pointer value passed to @cb.
* @errp: Error object.
*
*/
void commit_active_start(BlockDriverState *bs, BlockDriverState *base,
int64_t speed,
BlockdevOnError on_error,
BlockDriverCompletionFunc *cb,
void *opaque, Error **errp);
mirror: introduce mirror job This patch adds the implementation of a new job that mirrors a disk to a new image while letting the guest continue using the old image. The target is treated as a "black box" and data is copied from the source to the target in the background. This can be used for several purposes, including storage migration, continuous replication, and observation of the guest I/O in an external program. It is also a first step in replacing the inefficient block migration code that is part of QEMU. The job is possibly never-ending, but it is logically structured into two phases: 1) copy all data as fast as possible until the target first gets in sync with the source; 2) keep target in sync and ensure that reopening to the target gets a correct (full) copy of the source data. The second phase is indicated by the progress in "info block-jobs" reporting the current offset to be equal to the length of the file. When the job is cancelled in the second phase, QEMU will run the job until the source is clean and quiescent, then it will report successful completion of the job. In other words, the BLOCK_JOB_CANCELLED event means that the target may _not_ be consistent with a past state of the source; the BLOCK_JOB_COMPLETED event means that the target is consistent with a past state of the source. (Note that it could already happen that management lost the race against QEMU and got a completion event instead of cancellation). It is not yet possible to complete the job and switch over to the target disk. The next patches will fix this and add many refinements to the basic idea introduced here. These include improved error management, some tunable knobs and performance optimizations. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-10-18 18:49:23 +04:00
/*
* mirror_start:
* @bs: Block device to operate on.
* @target: Block device to write to.
* @speed: The maximum speed, in bytes per second, or 0 for unlimited.
* @granularity: The chosen granularity for the dirty bitmap.
* @buf_size: The amount of data that can be in flight at one time.
mirror: introduce mirror job This patch adds the implementation of a new job that mirrors a disk to a new image while letting the guest continue using the old image. The target is treated as a "black box" and data is copied from the source to the target in the background. This can be used for several purposes, including storage migration, continuous replication, and observation of the guest I/O in an external program. It is also a first step in replacing the inefficient block migration code that is part of QEMU. The job is possibly never-ending, but it is logically structured into two phases: 1) copy all data as fast as possible until the target first gets in sync with the source; 2) keep target in sync and ensure that reopening to the target gets a correct (full) copy of the source data. The second phase is indicated by the progress in "info block-jobs" reporting the current offset to be equal to the length of the file. When the job is cancelled in the second phase, QEMU will run the job until the source is clean and quiescent, then it will report successful completion of the job. In other words, the BLOCK_JOB_CANCELLED event means that the target may _not_ be consistent with a past state of the source; the BLOCK_JOB_COMPLETED event means that the target is consistent with a past state of the source. (Note that it could already happen that management lost the race against QEMU and got a completion event instead of cancellation). It is not yet possible to complete the job and switch over to the target disk. The next patches will fix this and add many refinements to the basic idea introduced here. These include improved error management, some tunable knobs and performance optimizations. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-10-18 18:49:23 +04:00
* @mode: Whether to collapse all images in the chain to the target.
* @on_source_error: The action to take upon error reading from the source.
* @on_target_error: The action to take upon error writing to the target.
mirror: introduce mirror job This patch adds the implementation of a new job that mirrors a disk to a new image while letting the guest continue using the old image. The target is treated as a "black box" and data is copied from the source to the target in the background. This can be used for several purposes, including storage migration, continuous replication, and observation of the guest I/O in an external program. It is also a first step in replacing the inefficient block migration code that is part of QEMU. The job is possibly never-ending, but it is logically structured into two phases: 1) copy all data as fast as possible until the target first gets in sync with the source; 2) keep target in sync and ensure that reopening to the target gets a correct (full) copy of the source data. The second phase is indicated by the progress in "info block-jobs" reporting the current offset to be equal to the length of the file. When the job is cancelled in the second phase, QEMU will run the job until the source is clean and quiescent, then it will report successful completion of the job. In other words, the BLOCK_JOB_CANCELLED event means that the target may _not_ be consistent with a past state of the source; the BLOCK_JOB_COMPLETED event means that the target is consistent with a past state of the source. (Note that it could already happen that management lost the race against QEMU and got a completion event instead of cancellation). It is not yet possible to complete the job and switch over to the target disk. The next patches will fix this and add many refinements to the basic idea introduced here. These include improved error management, some tunable knobs and performance optimizations. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-10-18 18:49:23 +04:00
* @cb: Completion function for the job.
* @opaque: Opaque pointer value passed to @cb.
* @errp: Error object.
*
* Start a mirroring operation on @bs. Clusters that are allocated
* in @bs will be written to @bs until the job is cancelled or
* manually completed. At the end of a successful mirroring job,
* @bs will be switched to read from @target.
*/
void mirror_start(BlockDriverState *bs, BlockDriverState *target,
int64_t speed, int64_t granularity, int64_t buf_size,
MirrorSyncMode mode, BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
mirror: introduce mirror job This patch adds the implementation of a new job that mirrors a disk to a new image while letting the guest continue using the old image. The target is treated as a "black box" and data is copied from the source to the target in the background. This can be used for several purposes, including storage migration, continuous replication, and observation of the guest I/O in an external program. It is also a first step in replacing the inefficient block migration code that is part of QEMU. The job is possibly never-ending, but it is logically structured into two phases: 1) copy all data as fast as possible until the target first gets in sync with the source; 2) keep target in sync and ensure that reopening to the target gets a correct (full) copy of the source data. The second phase is indicated by the progress in "info block-jobs" reporting the current offset to be equal to the length of the file. When the job is cancelled in the second phase, QEMU will run the job until the source is clean and quiescent, then it will report successful completion of the job. In other words, the BLOCK_JOB_CANCELLED event means that the target may _not_ be consistent with a past state of the source; the BLOCK_JOB_COMPLETED event means that the target is consistent with a past state of the source. (Note that it could already happen that management lost the race against QEMU and got a completion event instead of cancellation). It is not yet possible to complete the job and switch over to the target disk. The next patches will fix this and add many refinements to the basic idea introduced here. These include improved error management, some tunable knobs and performance optimizations. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-10-18 18:49:23 +04:00
BlockDriverCompletionFunc *cb,
void *opaque, Error **errp);
block: add basic backup support to block driver backup_start() creates a block job that copies a point-in-time snapshot of a block device to a target block device. We call backup_do_cow() for each write during backup. That function reads the original data from the block device before it gets overwritten. The data is then written to the target device. Currently backup cluster size is hardcoded to 65536 bytes. [I made a number of changes to Dietmar's original patch and folded them in to make code review easy. Here is the full list: * Drop BackupDumpFunc interface in favor of a target block device * Detect zero clusters with buffer_is_zero() and use bdrv_co_write_zeroes() * Use 0 delay instead of 1us, like other block jobs * Unify creation/start functions into backup_start() * Simplify cleanup, free bitmap in backup_run() instead of cb * function * Use HBitmap to avoid duplicating bitmap code * Use bdrv_getlength() instead of accessing ->total_sectors * directly * Delete the backup.h header file, it is no longer necessary * Move ./backup.c to block/backup.c * Remove #ifdefed out code * Coding style and whitespace cleanups * Use bdrv_add_before_write_notifier() instead of blockjob-specific hooks * Keep our own in-flight CowRequest list instead of using block.c tracked requests. This means a little code duplication but is much simpler than trying to share the tracked requests list and use the backup block size. * Add on_source_error and on_target_error error handling. * Use trace events instead of DPRINTF() -- stefanha] Signed-off-by: Dietmar Maurer <dietmar@proxmox.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-06-24 19:13:11 +04:00
/*
* backup_start:
* @bs: Block device to operate on.
* @target: Block device to write to.
* @speed: The maximum speed, in bytes per second, or 0 for unlimited.
Implement sync modes for drive-backup. This patch adds sync-modes to the drive-backup interface and implements the FULL, NONE and TOP modes of synchronization. FULL performs as before copying the entire contents of the drive while preserving the point-in-time using CoW. NONE only copies new writes to the target drive. TOP copies changes to the topmost drive image and preserves the point-in-time using CoW. For sync mode TOP are creating a new target image using the same backing file as the original disk image. Then any new data that has been laid on top of it since creation is copied in the main backup_run() loop. There is an extra check in the 'TOP' case so that we don't bother to copy all the data of the backing file as it already exists in the target. This is where the bdrv_co_is_allocated() is used to determine if the data exists in the topmost layer or below. Also any new data being written is intercepted via the write_notifier hook which ends up calling backup_do_cow() to copy old data out before it gets overwritten. For mode 'NONE' we create the new target image and only copy in the original data from the disk image starting from the time the call was made. This preserves the point in time data by only copying the parts that are *going to change* to the target image. This way we can reconstruct the final image by checking to see if the given block exists in the new target image first, and if it does not, you can get it from the original image. This is basically an optimization allowing you to do point-in-time snapshots with low overhead vs the 'FULL' version. Since there is no old data to copy out the loop in backup_run() for the NONE case just calls qemu_coroutine_yield() which only wakes up after an event (usually cancel in this case). The rest is handled by the before_write notifier which again calls backup_do_cow() to write out the old data so it can be preserved. Signed-off-by: Ian Main <imain@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-07-26 22:39:04 +04:00
* @sync_mode: What parts of the disk image should be copied to the destination.
block: add basic backup support to block driver backup_start() creates a block job that copies a point-in-time snapshot of a block device to a target block device. We call backup_do_cow() for each write during backup. That function reads the original data from the block device before it gets overwritten. The data is then written to the target device. Currently backup cluster size is hardcoded to 65536 bytes. [I made a number of changes to Dietmar's original patch and folded them in to make code review easy. Here is the full list: * Drop BackupDumpFunc interface in favor of a target block device * Detect zero clusters with buffer_is_zero() and use bdrv_co_write_zeroes() * Use 0 delay instead of 1us, like other block jobs * Unify creation/start functions into backup_start() * Simplify cleanup, free bitmap in backup_run() instead of cb * function * Use HBitmap to avoid duplicating bitmap code * Use bdrv_getlength() instead of accessing ->total_sectors * directly * Delete the backup.h header file, it is no longer necessary * Move ./backup.c to block/backup.c * Remove #ifdefed out code * Coding style and whitespace cleanups * Use bdrv_add_before_write_notifier() instead of blockjob-specific hooks * Keep our own in-flight CowRequest list instead of using block.c tracked requests. This means a little code duplication but is much simpler than trying to share the tracked requests list and use the backup block size. * Add on_source_error and on_target_error error handling. * Use trace events instead of DPRINTF() -- stefanha] Signed-off-by: Dietmar Maurer <dietmar@proxmox.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-06-24 19:13:11 +04:00
* @on_source_error: The action to take upon error reading from the source.
* @on_target_error: The action to take upon error writing to the target.
* @cb: Completion function for the job.
* @opaque: Opaque pointer value passed to @cb.
*
* Start a backup operation on @bs. Clusters in @bs are written to @target
* until the job is cancelled or manually completed.
*/
void backup_start(BlockDriverState *bs, BlockDriverState *target,
Implement sync modes for drive-backup. This patch adds sync-modes to the drive-backup interface and implements the FULL, NONE and TOP modes of synchronization. FULL performs as before copying the entire contents of the drive while preserving the point-in-time using CoW. NONE only copies new writes to the target drive. TOP copies changes to the topmost drive image and preserves the point-in-time using CoW. For sync mode TOP are creating a new target image using the same backing file as the original disk image. Then any new data that has been laid on top of it since creation is copied in the main backup_run() loop. There is an extra check in the 'TOP' case so that we don't bother to copy all the data of the backing file as it already exists in the target. This is where the bdrv_co_is_allocated() is used to determine if the data exists in the topmost layer or below. Also any new data being written is intercepted via the write_notifier hook which ends up calling backup_do_cow() to copy old data out before it gets overwritten. For mode 'NONE' we create the new target image and only copy in the original data from the disk image starting from the time the call was made. This preserves the point in time data by only copying the parts that are *going to change* to the target image. This way we can reconstruct the final image by checking to see if the given block exists in the new target image first, and if it does not, you can get it from the original image. This is basically an optimization allowing you to do point-in-time snapshots with low overhead vs the 'FULL' version. Since there is no old data to copy out the loop in backup_run() for the NONE case just calls qemu_coroutine_yield() which only wakes up after an event (usually cancel in this case). The rest is handled by the before_write notifier which again calls backup_do_cow() to write out the old data so it can be preserved. Signed-off-by: Ian Main <imain@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-07-26 22:39:04 +04:00
int64_t speed, MirrorSyncMode sync_mode,
BlockdevOnError on_source_error,
block: add basic backup support to block driver backup_start() creates a block job that copies a point-in-time snapshot of a block device to a target block device. We call backup_do_cow() for each write during backup. That function reads the original data from the block device before it gets overwritten. The data is then written to the target device. Currently backup cluster size is hardcoded to 65536 bytes. [I made a number of changes to Dietmar's original patch and folded them in to make code review easy. Here is the full list: * Drop BackupDumpFunc interface in favor of a target block device * Detect zero clusters with buffer_is_zero() and use bdrv_co_write_zeroes() * Use 0 delay instead of 1us, like other block jobs * Unify creation/start functions into backup_start() * Simplify cleanup, free bitmap in backup_run() instead of cb * function * Use HBitmap to avoid duplicating bitmap code * Use bdrv_getlength() instead of accessing ->total_sectors * directly * Delete the backup.h header file, it is no longer necessary * Move ./backup.c to block/backup.c * Remove #ifdefed out code * Coding style and whitespace cleanups * Use bdrv_add_before_write_notifier() instead of blockjob-specific hooks * Keep our own in-flight CowRequest list instead of using block.c tracked requests. This means a little code duplication but is much simpler than trying to share the tracked requests list and use the backup block size. * Add on_source_error and on_target_error error handling. * Use trace events instead of DPRINTF() -- stefanha] Signed-off-by: Dietmar Maurer <dietmar@proxmox.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-06-24 19:13:11 +04:00
BlockdevOnError on_target_error,
BlockDriverCompletionFunc *cb, void *opaque,
Error **errp);
#endif /* BLOCK_INT_H */