Re: [Qemu-block] [Qemu-devel] [PATCH v2 10/11] blockjob: refactor backup_start as backup_job_create

[John Snow]

On 09/30/2016 06:00 PM, John Snow wrote:
> Refactor backup_start as backup_job_create, which only creates the job,
> but does not automatically start it. The old interface, 'backup_start',
> is not kept in favor of limiting the number of nearly-identical iterfaces
> that would have to be edited to keep up with QAPI changes in the future.
>
> Callers that wish to synchronously start the backup_block_job can
> instead just call block_job_start immediately after calling
> backup_job_create.
>
> Transactions are updated to use the new interface, calling block_job_start
> only during the .commit phase, which helps prevent race conditions where
> jobs may finish before we even finish building the transaction. This may
> happen, for instance, during empty block backup jobs.

Sadly for me, I realized this patch has a potential problem. When we 
were adding the bitmap operations, it became clear that the atomicity 
point was during .prepare, not .commit.

e.g. the bitmap is cleared or created during prepare, and backup_run 
installs its Write Notifier at that point in time, too.

By changing BlockJobs to only run on commit, we've severed the atomicity 
point such that some actions will take effect during prepare, and others 
at commit.

I still think it's the correct thing to do to delay the BlockJobs until 
the commit phase, so I will start auditing the code to see how hard it 
is to shift the atomicity point to commit instead. If it's possible to 
do that, I think from the POV of the managing application, having the 
atomicity point be

Feel free to chime in with suggestions and counterpoints until then.

--js

> Reported-by: Vladimir Sementsov-Ogievskiy <address@hidden>
> Signed-off-by: John Snow <address@hidden>
> ---
>  block/backup.c            | 26 ++++++++-------
>  block/replication.c       | 11 ++++---
>  blockdev.c                | 81 +++++++++++++++++++++++++++++++----------------
>  include/block/block_int.h | 21 ++++++------
>  4 files changed, 86 insertions(+), 53 deletions(-)
>
> diff --git a/block/backup.c b/block/backup.c
> index 7294169..aad69eb 100644
> --- a/block/backup.c
> +++ b/block/backup.c
> @@ -527,7 +527,7 @@ static const BlockJobDriver backup_job_driver = {
>      .attached_aio_context   = backup_attached_aio_context,
>  };
>
> -void backup_start(const char *job_id, BlockDriverState *bs,
> +BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
>                    BlockDriverState *target, int64_t speed,
>                    MirrorSyncMode sync_mode, BdrvDirtyBitmap *sync_bitmap,
>                    bool compress,
> @@ -546,52 +546,52 @@ void backup_start(const char *job_id, BlockDriverState 
> *bs,
>
>      if (bs == target) {
>          error_setg(errp, "Source and target cannot be the same");
> -        return;
> +        return NULL;
>      }
>
>      if (!bdrv_is_inserted(bs)) {
>          error_setg(errp, "Device is not inserted: %s",
>                     bdrv_get_device_name(bs));
> -        return;
> +        return NULL;
>      }
>
>      if (!bdrv_is_inserted(target)) {
>          error_setg(errp, "Device is not inserted: %s",
>                     bdrv_get_device_name(target));
> -        return;
> +        return NULL;
>      }
>
>      if (compress && target->drv->bdrv_co_pwritev_compressed == NULL) {
>          error_setg(errp, "Compression is not supported for this drive %s",
>                     bdrv_get_device_name(target));
> -        return;
> +        return NULL;
>      }
>
>      if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_BACKUP_SOURCE, errp)) {
> -        return;
> +        return NULL;
>      }
>
>      if (bdrv_op_is_blocked(target, BLOCK_OP_TYPE_BACKUP_TARGET, errp)) {
> -        return;
> +        return NULL;
>      }
>
>      if (sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) {
>          if (!sync_bitmap) {
>              error_setg(errp, "must provide a valid bitmap name for "
>                               "\"incremental\" sync mode");
> -            return;
> +            return NULL;
>          }
>
>          /* Create a new bitmap, and freeze/disable this one. */
>          if (bdrv_dirty_bitmap_create_successor(bs, sync_bitmap, errp) < 0) {
> -            return;
> +            return NULL;
>          }
>      } else if (sync_bitmap) {
>          error_setg(errp,
>                     "a sync_bitmap was provided to backup_run, "
>                     "but received an incompatible sync_mode (%s)",
>                     MirrorSyncMode_lookup[sync_mode]);
> -        return;
> +        return NULL;
>      }
>
>      len = bdrv_getlength(bs);
> @@ -638,8 +638,8 @@ void backup_start(const char *job_id, BlockDriverState *bs,
>      bdrv_op_block_all(target, job->common.blocker);
>      job->common.len = len;
>      block_job_txn_add_job(txn, &job->common);
> -    block_job_start(&job->common);
> -    return;
> +
> +    return &job->common;
>
>   error:
>      if (sync_bitmap) {
> @@ -649,4 +649,6 @@ void backup_start(const char *job_id, BlockDriverState *bs,
>          blk_unref(job->target);
>          block_job_unref(&job->common);
>      }
> +
> +    return NULL;
>  }
> diff --git a/block/replication.c b/block/replication.c
> index b604b93..d9cdc36 100644
> --- a/block/replication.c
> +++ b/block/replication.c
> @@ -409,6 +409,7 @@ static void replication_start(ReplicationState *rs, 
> ReplicationMode mode,
>      int64_t active_length, hidden_length, disk_length;
>      AioContext *aio_context;
>      Error *local_err = NULL;
> +    BlockJob *job;
>
>      aio_context = bdrv_get_aio_context(bs);
>      aio_context_acquire(aio_context);
> @@ -496,16 +497,18 @@ static void replication_start(ReplicationState *rs, 
> ReplicationMode mode,
>          bdrv_op_block_all(top_bs, s->blocker);
>          bdrv_op_unblock(top_bs, BLOCK_OP_TYPE_DATAPLANE, s->blocker);
>
> -        backup_start("replication-backup", s->secondary_disk->bs,
> -                     s->hidden_disk->bs, 0, MIRROR_SYNC_MODE_NONE, NULL, false,
> -                     BLOCKDEV_ON_ERROR_REPORT, BLOCKDEV_ON_ERROR_REPORT,
> -                     backup_job_completed, s, NULL, &local_err);
> +        job = backup_job_create("replication-backup", s->secondary_disk->bs,
> +                                s->hidden_disk->bs, 0, MIRROR_SYNC_MODE_NONE,
> +                                NULL, false, BLOCKDEV_ON_ERROR_REPORT,
> +                                BLOCKDEV_ON_ERROR_REPORT, backup_job_completed,
> +                                s, NULL, &local_err);
>          if (local_err) {
>              error_propagate(errp, local_err);
>              backup_job_cleanup(s);
>              aio_context_release(aio_context);
>              return;
>          }
> +        block_job_start(job);
>          break;
>      default:
>          aio_context_release(aio_context);
> diff --git a/blockdev.c b/blockdev.c
> index 0ac507f..37d78d3 100644
> --- a/blockdev.c
> +++ b/blockdev.c
> @@ -1866,7 +1866,7 @@ typedef struct DriveBackupState {
>      BlockJob *job;
>  } DriveBackupState;
>
> -static void do_drive_backup(DriveBackup *backup, BlockJobTxn *txn,
> +static BlockJob *do_drive_backup(DriveBackup *backup, BlockJobTxn *txn,
>                              Error **errp);
>
>  static void drive_backup_prepare(BlkActionState *common, Error **errp)
> @@ -1890,23 +1890,27 @@ static void drive_backup_prepare(BlkActionState 
> *common, Error **errp)
>      bdrv_drained_begin(bs);
>      state->bs = bs;
>
> -    do_drive_backup(backup, common->block_job_txn, &local_err);
> +    state->job = do_drive_backup(backup, common->block_job_txn, &local_err);
>      if (local_err) {
>          error_propagate(errp, local_err);
>          return;
>      }
> +}
>
> -    state->job = state->bs->job;
> +static void drive_backup_commit(BlkActionState *common)
> +{
> +    DriveBackupState *state = DO_UPCAST(DriveBackupState, common, common);
> +    if (state->job) {
> +        block_job_start(state->job);
> +    }
>  }
>
>  static void drive_backup_abort(BlkActionState *common)
>  {
>      DriveBackupState *state = DO_UPCAST(DriveBackupState, common, common);
> -    BlockDriverState *bs = state->bs;
>
> -    /* Only cancel if it's the job we started */
> -    if (bs && bs->job && bs->job == state->job) {
> -        block_job_cancel_sync(bs->job);
> +    if (state->job) {
> +        block_job_cancel_sync(state->job);
>      }
>  }
>
> @@ -1927,8 +1931,8 @@ typedef struct BlockdevBackupState {
>      AioContext *aio_context;
>  } BlockdevBackupState;
>
> -static void do_blockdev_backup(BlockdevBackup *backup, BlockJobTxn *txn,
> -                               Error **errp);
> +static BlockJob *do_blockdev_backup(BlockdevBackup *backup, BlockJobTxn *txn,
> +                                    Error **errp);
>
>  static void blockdev_backup_prepare(BlkActionState *common, Error **errp)
>  {
> @@ -1961,23 +1965,27 @@ static void blockdev_backup_prepare(BlkActionState 
> *common, Error **errp)
>      state->bs = bs;
>      bdrv_drained_begin(state->bs);
>
> -    do_blockdev_backup(backup, common->block_job_txn, &local_err);
> +    state->job = do_blockdev_backup(backup, common->block_job_txn, &local_err);
>      if (local_err) {
>          error_propagate(errp, local_err);
>          return;
>      }
> +}
>
> -    state->job = state->bs->job;
> +static void blockdev_backup_commit(BlkActionState *common)
> +{
> +    BlockdevBackupState *state = DO_UPCAST(BlockdevBackupState, common, 
> common);
> +    if (state->job) {
> +        block_job_start(state->job);
> +    }
>  }
>
>  static void blockdev_backup_abort(BlkActionState *common)
>  {
>      BlockdevBackupState *state = DO_UPCAST(BlockdevBackupState, common, 
> common);
> -    BlockDriverState *bs = state->bs;
>
> -    /* Only cancel if it's the job we started */
> -    if (bs && bs->job && bs->job == state->job) {
> -        block_job_cancel_sync(bs->job);
> +    if (state->job) {
> +        block_job_cancel_sync(state->job);
>      }
>  }
>
> @@ -2127,12 +2135,14 @@ static const BlkActionOps actions[] = {
>      [TRANSACTION_ACTION_KIND_DRIVE_BACKUP] = {
>          .instance_size = sizeof(DriveBackupState),
>          .prepare = drive_backup_prepare,
> +        .commit = drive_backup_commit,
>          .abort = drive_backup_abort,
>          .clean = drive_backup_clean,
>      },
>      [TRANSACTION_ACTION_KIND_BLOCKDEV_BACKUP] = {
>          .instance_size = sizeof(BlockdevBackupState),
>          .prepare = blockdev_backup_prepare,
> +        .commit = blockdev_backup_commit,
>          .abort = blockdev_backup_abort,
>          .clean = blockdev_backup_clean,
>      },
> @@ -3126,11 +3136,13 @@ out:
>      aio_context_release(aio_context);
>  }
>
> -static void do_drive_backup(DriveBackup *backup, BlockJobTxn *txn, Error 
> **errp)
> +static BlockJob *do_drive_backup(DriveBackup *backup, BlockJobTxn *txn,
> +                                 Error **errp)
>  {
>      BlockDriverState *bs;
>      BlockDriverState *target_bs;
>      BlockDriverState *source = NULL;
> +    BlockJob *job = NULL;
>      BdrvDirtyBitmap *bmap = NULL;
>      AioContext *aio_context;
>      QDict *options = NULL;
> @@ -3159,7 +3171,7 @@ static void do_drive_backup(DriveBackup *backup, 
> BlockJobTxn *txn, Error **errp)
>
>      bs = qmp_get_root_bs(backup->device, errp);
>      if (!bs) {
> -        return;
> +        return NULL;
>      }
>
>      aio_context = bdrv_get_aio_context(bs);
> @@ -3233,9 +3245,10 @@ static void do_drive_backup(DriveBackup *backup, 
> BlockJobTxn *txn, Error **errp)
>          }
>      }
>
> -    backup_start(backup->job_id, bs, target_bs, backup->speed, backup->sync,
> -                 bmap, backup->compress, backup->on_source_error,
> -                 backup->on_target_error, NULL, bs, txn, &local_err);
> +    job = backup_job_create(backup->job_id, bs, target_bs, backup->speed,
> +                            backup->sync, bmap, backup->compress,
> +                            backup->on_source_error, backup->on_target_error,
> +                            NULL, bs, txn, &local_err);
>      bdrv_unref(target_bs);
>      if (local_err != NULL) {
>          error_propagate(errp, local_err);
> @@ -3244,11 +3257,17 @@ static void do_drive_backup(DriveBackup *backup, 
> BlockJobTxn *txn, Error **errp)
>
>  out:
>      aio_context_release(aio_context);
> +    return job;
>  }
>
>  void qmp_drive_backup(DriveBackup *arg, Error **errp)
>  {
> -    return do_drive_backup(arg, NULL, errp);
> +
> +    BlockJob *job;
> +    job = do_drive_backup(arg, NULL, errp);
> +    if (job) {
> +        block_job_start(job);
> +    }
>  }
>
>  BlockDeviceInfoList *qmp_query_named_block_nodes(Error **errp)
> @@ -3256,12 +3275,14 @@ BlockDeviceInfoList *qmp_query_named_block_nodes(Error 
> **errp)
>      return bdrv_named_nodes_list(errp);
>  }
>
> -void do_blockdev_backup(BlockdevBackup *backup, BlockJobTxn *txn, Error **errp)
> +BlockJob *do_blockdev_backup(BlockdevBackup *backup, BlockJobTxn *txn,
> +                             Error **errp)
>  {
>      BlockDriverState *bs;
>      BlockDriverState *target_bs;
>      Error *local_err = NULL;
>      AioContext *aio_context;
> +    BlockJob *job = NULL;
>
>      if (!backup->has_speed) {
>          backup->speed = 0;
> @@ -3281,7 +3302,7 @@ void do_blockdev_backup(BlockdevBackup *backup, 
> BlockJobTxn *txn, Error **errp)
>
>      bs = qmp_get_root_bs(backup->device, errp);
>      if (!bs) {
> -        return;
> +        return NULL;
>      }
>
>      aio_context = bdrv_get_aio_context(bs);
> @@ -3303,19 +3324,25 @@ void do_blockdev_backup(BlockdevBackup *backup, 
> BlockJobTxn *txn, Error **errp)
>              goto out;
>          }
>      }
> -    backup_start(backup->job_id, bs, target_bs, backup->speed, backup->sync,
> -                 NULL, backup->compress, backup->on_source_error,
> -                 backup->on_target_error, NULL, bs, txn, &local_err);
> +    job = backup_job_create(backup->job_id, bs, target_bs, backup->speed,
> +                            backup->sync, NULL, backup->compress,
> +                            backup->on_source_error, backup->on_target_error,
> +                            NULL, bs, txn, &local_err);
>      if (local_err != NULL) {
>          error_propagate(errp, local_err);
>      }
>  out:
>      aio_context_release(aio_context);
> +    return job;
>  }
>
>  void qmp_blockdev_backup(BlockdevBackup *arg, Error **errp)
>  {
> -    do_blockdev_backup(arg, NULL, errp);
> +    BlockJob *job;
> +    job = do_blockdev_backup(arg, NULL, errp);
> +    if (job) {
> +        block_job_start(job);
> +    }
>  }
>
>  /* Parameter check and block job starting for drive mirroring.
> diff --git a/include/block/block_int.h b/include/block/block_int.h
> index 686f6a8..738e4b4 100644
> --- a/include/block/block_int.h
> +++ b/include/block/block_int.h
> @@ -737,7 +737,7 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
>                    void *opaque, Error **errp);
>
>  /*
> - * backup_start:
> + * backup_job_create:
>   * @job_id: The id of the newly-created job, or %NULL to use the
>   * device name of @bs.
>   * @bs: Block device to operate on.
> @@ -751,17 +751,18 @@ void mirror_start(const char *job_id, BlockDriverState 
> *bs,
>   * @opaque: Opaque pointer value passed to @cb.
>   * @txn: Transaction that this job is part of (may be NULL).
>   *
> - * Start a backup operation on @bs.  Clusters in @bs are written to @target
> + * Create a backup operation on @bs.  Clusters in @bs are written to @target
>   * until the job is cancelled or manually completed.
>   */
> -void backup_start(const char *job_id, BlockDriverState *bs,
> -                  BlockDriverState *target, int64_t speed,
> -                  MirrorSyncMode sync_mode, BdrvDirtyBitmap *sync_bitmap,
> -                  bool compress,
> -                  BlockdevOnError on_source_error,
> -                  BlockdevOnError on_target_error,
> -                  BlockCompletionFunc *cb, void *opaque,
> -                  BlockJobTxn *txn, Error **errp);
> +BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
> +                            BlockDriverState *target, int64_t speed,
> +                            MirrorSyncMode sync_mode,
> +                            BdrvDirtyBitmap *sync_bitmap,
> +                            bool compress,
> +                            BlockdevOnError on_source_error,
> +                            BlockdevOnError on_target_error,
> +                            BlockCompletionFunc *cb, void *opaque,
> +                            BlockJobTxn *txn, Error **errp);
>
>  /**
>   * block_job_start: