On 12.10.20 19:43, Andrey Shinkevich wrote:
> Modify the comment for the flag BDRV_REQ_PREFETCH as we are going to
> use it alone and pass it to the COR-filter driver for further
> processing.
>
> Signed-off-by: Andrey Shinkevich <andrey.shinkevich@xxxxxxxxxxxxx>
> ---
> include/block/block.h | 7 ++++---
> 1 file changed, 4 insertions(+), 3 deletions(-)
>
> diff --git a/include/block/block.h b/include/block/block.h
> index 981ab5b..2b7efd1 100644
> --- a/include/block/block.h
> +++ b/include/block/block.h
> @@ -71,9 +71,10 @@ typedef enum {
> BDRV_REQ_NO_FALLBACK = 0x100,
>
> /*
> - * BDRV_REQ_PREFETCH may be used only together with BDRV_REQ_COPY_ON_READ
> - * on read request and means that caller doesn't really need data to be
> - * written to qiov parameter which may be NULL.
> + * BDRV_REQ_PREFETCH may be used together with the BDRV_REQ_COPY_ON_READ
> + * flag or when the COR-filter applied to read operations and means that
There’s some word missing here, but I’m not sure what it is... At least
an “is” before “applied”. Perhaps something like ”or when a COR filter
is involved (in read operations)” would be better.
> + * caller doesn't really need data to be written to qiov parameter which
And this “written to” confused me for a second, because we’re reading
into qiov. Technically, that means writing into the buffer, but, you know.
Could we rewrite the whole thing, perhaps? Something like
“BDRV_REQ_PREFETCH makes sense only in the context of copy-on-read
(i.e., together with the BDRV_REQ_COPY_ON_READ flag or when there is a
COR filter), in which case it signals that the COR operation need not
read the data into memory (qiov), but only ensure it is copied to the
top layer (i.e., that COR is done).”
I don’t know.
Max
> + * may be NULL.
> */
> BDRV_REQ_PREFETCH = 0x200,
> /* Mask of valid flags */
>
Attachment:
signature.asc
Description: OpenPGP digital signature
