Re: [Qemu-devel] [PATCH v8 07/10] qmp: Add support of "dirty-bitmap" sync mode for drive-backup

[Fam Zheng]

On Wed, 11/26 12:41, John Snow wrote:
> From: Fam Zheng <address@hidden>
> 
> For "dirty-bitmap" sync mode, the block job will iterate through the
> given dirty bitmap to decide if a sector needs backup (backup all the
> dirty clusters and skip clean ones), just as allocation conditions of
> "top" sync mode.
> 
> There are two bitmap use modes for sync=dirty-bitmap:
> 
>  - reset: backup job makes a copy of bitmap and resets the original
>    one.
>  - consume: backup job makes the original anonymous (invisible to user)
>    and releases it after use.
> 
> Signed-off-by: Fam Zheng <address@hidden>
> Signed-off-by: John Snow <address@hidden>
> ---
>  block.c                   |   5 ++
>  block/backup.c            | 130 
> ++++++++++++++++++++++++++++++++++++++--------
>  block/mirror.c            |   4 ++
>  blockdev.c                |  18 ++++++-
>  hmp.c                     |   4 +-
>  include/block/block.h     |   1 +
>  include/block/block_int.h |   6 +++
>  qapi/block-core.json      |  30 +++++++++--
>  qmp-commands.hx           |   7 +--
>  9 files changed, 175 insertions(+), 30 deletions(-)
> 
> diff --git a/block.c b/block.c
> index 1aa723b..e341844 100644
> --- a/block.c
> +++ b/block.c
> @@ -5454,6 +5454,11 @@ void bdrv_dirty_iter_init(BlockDriverState *bs,
>      hbitmap_iter_init(hbi, bitmap->bitmap, 0);
>  }
>  
> +void bdrv_dirty_iter_set(HBitmapIter *hbi, int64_t offset)
> +{
> +    hbitmap_iter_init(hbi, hbi->hb, offset);
> +}
> +
>  void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector,
>                      int nr_sectors)
>  {
> diff --git a/block/backup.c b/block/backup.c
> index 792e655..2aab68f 100644
> --- a/block/backup.c
> +++ b/block/backup.c
> @@ -37,6 +37,10 @@ typedef struct CowRequest {
>  typedef struct BackupBlockJob {
>      BlockJob common;
>      BlockDriverState *target;
> +    /* bitmap for sync=dirty-bitmap */
> +    BdrvDirtyBitmap *sync_bitmap;
> +    /* dirty bitmap granularity */
> +    int64_t sync_bitmap_gran;
>      MirrorSyncMode sync_mode;
>      RateLimit limit;
>      BlockdevOnError on_source_error;
> @@ -242,6 +246,31 @@ static void backup_complete(BlockJob *job, void *opaque)
>      g_free(data);
>  }
>  
> +static bool yield_and_check(BackupBlockJob *job)
> +{
> +    if (block_job_is_cancelled(&job->common)) {
> +        return true;
> +    }
> +
> +    /* we need to yield so that qemu_aio_flush() returns.
> +     * (without, VM does not reboot)
> +     */
> +    if (job->common.speed) {
> +        uint64_t delay_ns = ratelimit_calculate_delay(&job->limit,
> +                                                      job->sectors_read);
> +        job->sectors_read = 0;
> +        block_job_sleep_ns(&job->common, QEMU_CLOCK_REALTIME, delay_ns);
> +    } else {
> +        block_job_sleep_ns(&job->common, QEMU_CLOCK_REALTIME, 0);
> +    }
> +
> +    if (block_job_is_cancelled(&job->common)) {
> +        return true;
> +    }
> +
> +    return false;
> +}
> +
>  static void coroutine_fn backup_run(void *opaque)
>  {
>      BackupBlockJob *job = opaque;
> @@ -254,13 +283,13 @@ static void coroutine_fn backup_run(void *opaque)
>      };
>      int64_t start, end;
>      int ret = 0;
> +    bool error_is_read;
>  
>      QLIST_INIT(&job->inflight_reqs);
>      qemu_co_rwlock_init(&job->flush_rwlock);
>  
>      start = 0;
> -    end = DIV_ROUND_UP(job->common.len / BDRV_SECTOR_SIZE,
> -                       BACKUP_SECTORS_PER_CLUSTER);
> +    end = DIV_ROUND_UP(job->common.len, BACKUP_CLUSTER_SIZE);
>  
>      job->bitmap = hbitmap_alloc(end, 0);
>  
> @@ -278,28 +307,44 @@ static void coroutine_fn backup_run(void *opaque)
>              qemu_coroutine_yield();
>              job->common.busy = true;
>          }
> +    } else if (job->sync_mode == MIRROR_SYNC_MODE_DIRTY_BITMAP) {
> +        /* Dirty Bitmap sync has a slightly different iteration method */
> +        HBitmapIter hbi;
> +        int64_t sector;
> +        int64_t cluster;
> +        bool polyrhythmic;
> +
> +        bdrv_dirty_iter_init(bs, job->sync_bitmap, &hbi);
> +        /* Does the granularity happen to match our backup cluster size? */
> +        polyrhythmic = (job->sync_bitmap_gran != BACKUP_CLUSTER_SIZE);
> +
> +        /* Find the next dirty /sector/ and copy that /cluster/ */
> +        while ((sector = hbitmap_iter_next(&hbi)) != -1) {
> +            if (yield_and_check(job)) {
> +                goto leave;
> +            }
> +            cluster = sector / BACKUP_SECTORS_PER_CLUSTER;
> +
> +            do {
> +                ret = backup_do_cow(bs, cluster * BACKUP_SECTORS_PER_CLUSTER,
> +                                    BACKUP_SECTORS_PER_CLUSTER, 
> &error_is_read);
> +                if ((ret < 0) &&
> +                    backup_error_action(job, error_is_read, -ret) ==
> +                    BLOCK_ERROR_ACTION_REPORT) {
> +                    goto leave;
> +                }
> +            } while (ret < 0);
> +
> +            /* Advance (or rewind) our iterator if we need to. */
> +            if (polyrhythmic) {
> +                bdrv_dirty_iter_set(&hbi,
> +                                    (cluster + 1) * 
> BACKUP_SECTORS_PER_CLUSTER);
> +            }
> +        }
>      } else {
>          /* Both FULL and TOP SYNC_MODE's require copying.. */
>          for (; start < end; start++) {
> -            bool error_is_read;
> -
> -            if (block_job_is_cancelled(&job->common)) {
> -                break;
> -            }
> -
> -            /* we need to yield so that qemu_aio_flush() returns.
> -             * (without, VM does not reboot)
> -             */
> -            if (job->common.speed) {
> -                uint64_t delay_ns = ratelimit_calculate_delay(
> -                        &job->limit, job->sectors_read);
> -                job->sectors_read = 0;
> -                block_job_sleep_ns(&job->common, QEMU_CLOCK_REALTIME, 
> delay_ns);
> -            } else {
> -                block_job_sleep_ns(&job->common, QEMU_CLOCK_REALTIME, 0);
> -            }
> -
> -            if (block_job_is_cancelled(&job->common)) {
> +            if (yield_and_check(job)) {
>                  break;
>              }
>  
> @@ -351,12 +396,16 @@ static void coroutine_fn backup_run(void *opaque)
>          }
>      }
>  
> +leave:
>      notifier_with_return_remove(&before_write);
>  
>      /* wait until pending backup_do_cow() calls have completed */
>      qemu_co_rwlock_wrlock(&job->flush_rwlock);
>      qemu_co_rwlock_unlock(&job->flush_rwlock);
>  
> +    if (job->sync_bitmap) {
> +        bdrv_release_dirty_bitmap(bs, job->sync_bitmap);
> +    }
>      hbitmap_free(job->bitmap);
>  
>      bdrv_iostatus_disable(target);
> @@ -368,12 +417,15 @@ static void coroutine_fn backup_run(void *opaque)
>  
>  void backup_start(BlockDriverState *bs, BlockDriverState *target,
>                    int64_t speed, MirrorSyncMode sync_mode,
> +                  BdrvDirtyBitmap *sync_bitmap,
> +                  BitmapUseMode bitmap_mode,
>                    BlockdevOnError on_source_error,
>                    BlockdevOnError on_target_error,
>                    BlockCompletionFunc *cb, void *opaque,
>                    Error **errp)
>  {
>      int64_t len;
> +    BdrvDirtyBitmap *original;
>  
>      assert(bs);
>      assert(target);
> @@ -386,6 +438,36 @@ void backup_start(BlockDriverState *bs, BlockDriverState 
> *target,
>          return;
>      }
>  
> +    if (sync_mode == MIRROR_SYNC_MODE_DIRTY_BITMAP) {
> +        if (!sync_bitmap) {
> +            error_setg(errp, "must provide a valid bitmap name for "
> +                             "\"dirty-bitmap\" sync mode");
> +            return;
> +        }
> +
> +        switch (bitmap_mode) {
> +        case BITMAP_USE_MODE_RESET:
> +            original = sync_bitmap;
> +            sync_bitmap = bdrv_copy_dirty_bitmap(bs, sync_bitmap, NULL);
> +            bdrv_reset_dirty_bitmap(bs, original);
> +            break;
> +        case BITMAP_USE_MODE_CONSUME:
> +            bdrv_dirty_bitmap_make_anon(bs, sync_bitmap);
> +            break;
> +        default:
> +            error_setg(errp, "Invalid BitmapUseMode (%s) given to 
> backup_start",
> +                       BitmapUseMode_lookup[bitmap_mode]);
> +            return;
> +        }
> +        bdrv_disable_dirty_bitmap(sync_bitmap);
> +    } else if (sync_bitmap) {
> +        error_setg(errp,
> +                   "a sync_bitmap was provided to backup_run, "
> +                   "but received an incompatible sync_mode (%s)",
> +                   BitmapUseMode_lookup[sync_mode]);
> +        return;
> +    }
> +
>      len = bdrv_getlength(bs);
>      if (len < 0) {
>          error_setg_errno(errp, -len, "unable to get length for '%s'",
> @@ -403,6 +485,12 @@ void backup_start(BlockDriverState *bs, BlockDriverState 
> *target,
>      job->on_target_error = on_target_error;
>      job->target = target;
>      job->sync_mode = sync_mode;
> +    job->sync_bitmap = sync_mode == MIRROR_SYNC_MODE_DIRTY_BITMAP ?
> +                       sync_bitmap : NULL;
> +    if (sync_bitmap) {
> +        job->sync_bitmap_gran =
> +            bdrv_dirty_bitmap_granularity(bs, job->sync_bitmap);
> +    }
>      job->common.len = len;
>      job->common.co = qemu_coroutine_create(backup_run);
>      qemu_coroutine_enter(job->common.co, job);
> diff --git a/block/mirror.c b/block/mirror.c
> index 3633632..af91ae0 100644
> --- a/block/mirror.c
> +++ b/block/mirror.c
> @@ -714,6 +714,10 @@ void mirror_start(BlockDriverState *bs, BlockDriverState 
> *target,
>      bool is_none_mode;
>      BlockDriverState *base;
>  
> +    if (mode == MIRROR_SYNC_MODE_DIRTY_BITMAP) {
> +        error_setg(errp, "Sync mode 'dirty-bitmap' not supported");
> +        return;
> +    }
>      is_none_mode = mode == MIRROR_SYNC_MODE_NONE;
>      base = mode == MIRROR_SYNC_MODE_TOP ? bs->backing_hd : NULL;
>      mirror_start_job(bs, target, replaces,
> diff --git a/blockdev.c b/blockdev.c
> index 276a31b..1a56959 100644
> --- a/blockdev.c
> +++ b/blockdev.c
> @@ -1505,6 +1505,8 @@ static void drive_backup_prepare(BlkTransactionState 
> *common, Error **errp)
>                       backup->sync,
>                       backup->has_mode, backup->mode,
>                       backup->has_speed, backup->speed,
> +                     backup->has_bitmap, backup->bitmap,
> +                     backup->has_bitmap_use_mode, backup->bitmap_use_mode,
>                       backup->has_on_source_error, backup->on_source_error,
>                       backup->has_on_target_error, backup->on_target_error,
>                       &local_err);
> @@ -2235,6 +2237,8 @@ void qmp_drive_backup(const char *device, const char 
> *target,
>                        enum MirrorSyncMode sync,
>                        bool has_mode, enum NewImageMode mode,
>                        bool has_speed, int64_t speed,
> +                      bool has_bitmap, const char *bitmap,
> +                      bool has_bitmap_use_mode, enum BitmapUseMode 
> bitmap_mode,
>                        bool has_on_source_error, BlockdevOnError 
> on_source_error,
>                        bool has_on_target_error, BlockdevOnError 
> on_target_error,
>                        Error **errp)
> @@ -2242,6 +2246,7 @@ void qmp_drive_backup(const char *device, const char 
> *target,
>      BlockDriverState *bs;
>      BlockDriverState *target_bs;
>      BlockDriverState *source = NULL;
> +    BdrvDirtyBitmap *bmap = NULL;
>      AioContext *aio_context;
>      BlockDriver *drv = NULL;
>      Error *local_err = NULL;
> @@ -2337,7 +2342,18 @@ void qmp_drive_backup(const char *device, const char 
> *target,
>  
>      bdrv_set_aio_context(target_bs, aio_context);
>  
> -    backup_start(bs, target_bs, speed, sync, on_source_error, 
> on_target_error,
> +    if (has_bitmap) {
> +        bmap = bdrv_find_dirty_bitmap(bs, bitmap);
> +        if (!bmap) {
> +            error_setg(errp, "A bitmap name was given, but bitmap '%s' could 
> not be found",

This line is too long.

Fam

> +                       bitmap);
> +            goto out;
> +        }
> +    }
> +
> +    backup_start(bs, target_bs, speed, sync, bmap,
> +                 has_bitmap_use_mode ? bitmap_mode : BITMAP_USE_MODE_RESET,
> +                 on_source_error, on_target_error,
>                   block_job_cb, bs, &local_err);
>      if (local_err != NULL) {
>          bdrv_unref(target_bs);
> diff --git a/hmp.c b/hmp.c
> index 63d7686..bc5a2d2 100644
> --- a/hmp.c
> +++ b/hmp.c
> @@ -966,7 +966,9 @@ void hmp_drive_backup(Monitor *mon, const QDict *qdict)
>  
>      qmp_drive_backup(device, filename, !!format, format,
>                       full ? MIRROR_SYNC_MODE_FULL : MIRROR_SYNC_MODE_TOP,
> -                     true, mode, false, 0, false, 0, false, 0, &err);
> +                     true, mode, false, 0, false, NULL,
> +                     false, 0,
> +                     false, 0, false, 0, &err);
>      hmp_handle_error(mon, &err);
>  }
>  
> diff --git a/include/block/block.h b/include/block/block.h
> index 14a0632..cbbb778 100644
> --- a/include/block/block.h
> +++ b/include/block/block.h
> @@ -451,6 +451,7 @@ void bdrv_set_dirty(BlockDriverState *bs, int64_t 
> cur_sector, int nr_sectors);
>  void bdrv_reset_dirty(BlockDriverState *bs, int64_t cur_sector, int 
> nr_sectors);
>  void bdrv_dirty_iter_init(BlockDriverState *bs,
>                            BdrvDirtyBitmap *bitmap, struct HBitmapIter *hbi);
> +void bdrv_dirty_iter_set(struct HBitmapIter *hbi, int64_t offset);
>  int64_t bdrv_get_dirty_count(BlockDriverState *bs, BdrvDirtyBitmap *bitmap);
>  
>  void bdrv_enable_copy_on_read(BlockDriverState *bs);
> diff --git a/include/block/block_int.h b/include/block/block_int.h
> index a1c17b9..215a27d 100644
> --- a/include/block/block_int.h
> +++ b/include/block/block_int.h
> @@ -571,6 +571,10 @@ void mirror_start(BlockDriverState *bs, BlockDriverState 
> *target,
>   * @target: Block device to write to.
>   * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
>   * @sync_mode: What parts of the disk image should be copied to the 
> destination.
> + * @sync_bitmap: The dirty bitmap if sync_mode is 
> MIRROR_SYNC_MODE_DIRTY_BITMAP.
> + * @bitmap_mode: BITMAP_USE_MODE_{CONSUME, RESET}
> + *               Reset: Make a copy and reset the original bitmap.
> + *               Consume: Anonymize the bitmap and free it after completion.
>   * @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.
> @@ -581,6 +585,8 @@ void mirror_start(BlockDriverState *bs, BlockDriverState 
> *target,
>   */
>  void backup_start(BlockDriverState *bs, BlockDriverState *target,
>                    int64_t speed, MirrorSyncMode sync_mode,
> +                  BdrvDirtyBitmap *sync_bitmap,
> +                  BitmapUseMode bitmap_mode,
>                    BlockdevOnError on_source_error,
>                    BlockdevOnError on_target_error,
>                    BlockCompletionFunc *cb, void *opaque,
> diff --git a/qapi/block-core.json b/qapi/block-core.json
> index d77f19d..3ca9566 100644
> --- a/qapi/block-core.json
> +++ b/qapi/block-core.json
> @@ -470,7 +470,7 @@
>  # Since: 1.3
>  ##
>  { 'enum': 'MirrorSyncMode',
> -  'data': ['top', 'full', 'none'] }
> +  'data': ['top', 'full', 'none', 'dirty-bitmap'] }
>  
>  ##
>  # @BlockJobType:
> @@ -633,6 +633,21 @@
>              '*format': 'str', '*mode': 'NewImageMode' } }
>  
>  ##
> +# @BitmapUseMode
> +#
> +# An enumeration that tells QEMU what operation to take when using a bitmap
> +# in drive backup sync mode dirty-bitmap.
> +#
> +# @consume: QEMU should just consume the bitmap and release it after using
> +#
> +# @reset: QEMU should reset the dirty bitmap
> +#
> +# Since: 2.3
> +##
> +{ 'enum': 'BitmapUseMode',
> +'data': [ 'consume', 'reset' ] }
> +
> +##
>  # @DriveBackup
>  #
>  # @device: the name of the device which should be copied.
> @@ -645,14 +660,20 @@
>  #          probe if @mode is 'existing', else the format of the source
>  #
>  # @sync: what parts of the disk image should be copied to the destination
> -#        (all the disk, only the sectors allocated in the topmost image, or
> -#        only new I/O).
> +#        (all the disk, only the sectors allocated in the topmost image, 
> from a
> +#        dirty bitmap, or only new I/O).
>  #
>  # @mode: #optional whether and how QEMU should create a new image, default is
>  #        'absolute-paths'.
>  #
>  # @speed: #optional the maximum speed, in bytes per second
>  #
> +# @bitmap: #optional the name of dirty bitmap if sync is "dirty-bitmap"
> +#          (Since 2.3)
> +#
> +# @bitmap-use-mode: #optional which operation to take when consuming @bitmap,
> +#                   default is reset. (Since 2.3)
> +#
>  # @on-source-error: #optional the action to take on an error on the source,
>  #                   default 'report'.  'stop' and 'enospc' can only be used
>  #                   if the block device supports io-status (see BlockInfo).
> @@ -670,7 +691,8 @@
>  { 'type': 'DriveBackup',
>    'data': { 'device': 'str', 'target': 'str', '*format': 'str',
>              'sync': 'MirrorSyncMode', '*mode': 'NewImageMode',
> -            '*speed': 'int',
> +            '*speed': 'int', '*bitmap': 'str',
> +            '*bitmap-use-mode': 'BitmapUseMode',
>              '*on-source-error': 'BlockdevOnError',
>              '*on-target-error': 'BlockdevOnError' } }
>  
> diff --git a/qmp-commands.hx b/qmp-commands.hx
> index cc31e22..fb3545f 100644
> --- a/qmp-commands.hx
> +++ b/qmp-commands.hx
> @@ -1048,7 +1048,7 @@ EQMP
>      {
>          .name       = "drive-backup",
>          .args_type  = "sync:s,device:B,target:s,speed:i?,mode:s?,format:s?,"
> -                      "on-source-error:s?,on-target-error:s?",
> +                      "bitmap:s?,on-source-error:s?,on-target-error:s?",
>          .mhandler.cmd_new = qmp_marshal_input_drive_backup,
>      },
>  
> @@ -1075,8 +1075,9 @@ Arguments:
>              (json-string, optional)
>  - "sync": what parts of the disk image should be copied to the destination;
>    possibilities include "full" for all the disk, "top" for only the sectors
> -  allocated in the topmost image, or "none" to only replicate new I/O
> -  (MirrorSyncMode).
> +  allocated in the topmost image, "dirty-bitmap" for only the dirty sectors 
> in
> +  the bitmap, or "none" to only replicate new I/O (MirrorSyncMode).
> +- "bitmap": dirty bitmap name for sync==dirty-bitmap
>  - "mode": whether and how QEMU should create a new image
>            (NewImageMode, optional, default 'absolute-paths')
>  - "speed": the maximum speed, in bytes per second (json-int, optional)
> -- 
> 1.9.3
>