Le Friday 17 Jan 2014 à 15:15:02 (+0100), Kevin Wolf a écrit :
> First waiting for all COR requests to complete and calling the
> throttling function afterwards means that the request could be delayed
> and we still need to wait for the COR request even if it was issued only
> after the throttled write request.
>
> Signed-off-by: Kevin Wolf <kw...@redhat.com>
> Reviewed-by: Max Reitz <mre...@redhat.com>
> ---
> block.c | 8 ++++----
> 1 file changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/block.c b/block.c
> index 70b72f0..fe55217 100644
> --- a/block.c
> +++ b/block.c
> @@ -2979,6 +2979,10 @@ static int coroutine_fn
> bdrv_aligned_pwritev(BlockDriverState *bs,
> assert((offset & (BDRV_SECTOR_SIZE - 1)) == 0);
> assert((bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
>
> + if (bs->copy_on_read_in_flight) {
> + wait_for_overlapping_requests(bs, sector_num, nb_sectors);
> + }
> +
> tracked_request_begin(&req, bs, sector_num, nb_sectors, true);
>
> ret = notifier_with_return_list_notify(&bs->before_write_notifiers,
> &req);
> @@ -3028,10 +3032,6 @@ static int coroutine_fn
> bdrv_co_do_writev(BlockDriverState *bs,
> return -EIO;
> }
>
> - if (bs->copy_on_read_in_flight) {
> - wait_for_overlapping_requests(bs, sector_num, nb_sectors);
> - }
> -
> /* throttling disk I/O */
> if (bs->io_limits_enabled) {
> bdrv_io_limits_intercept(bs, nb_sectors, true);
> --
> 1.8.1.4
>
>
Reviewed-by: Benoit Canet <ben...@irqsave.net>
