| Message ID | 1463227273-27523-3-git-send-email-den@openvz.org |
|---|---|
| State | New |
| Headers | show |
On 05/14/2016 06:01 AM, Denis V. Lunev wrote: > We should split requests even if they are less than write_zeroes_alignment. > For example we can have the following request: > offset 62k > size 4k > write_zeroes_alignment 64k > Original code will send 1 request covering 2 qcow2 clusters. One cluster > could be zeroed as a whole, another could not be. In this case we will have > both 2 clusters allocated. > > After the patch 2 requests to qcow2 layer will be sent and thus only one > cluster will be allocated. Grammar suggestion: The original code sent 1 request covering 2 qcow2 clusters, and resulted in both clusters being allocated. But by splitting the request, we can cater to the case where one of the two clusters can be zeroed as a whole, for only 1 cluster allocated after the operation. > > Signed-off-by: Denis V. Lunev <den@openvz.org> > CC: Kevin Wolf <kwolf@redhat.com> > --- > block/io.c | 6 +++--- > 1 file changed, 3 insertions(+), 3 deletions(-) > > num -= sector_num % bs->bl.write_zeroes_alignment; > - } else if ((sector_num + num) % bs->bl.write_zeroes_alignment != 0) { > + } else if (num > bs->bl.write_zeroes_alignment && > + (sector_num + num) % bs->bl.write_zeroes_alignment != 0) { Alignment looks off. Also, if it were me, I'd write 'a % b' rather than 'a % b != 0'.
diff --git a/block/io.c b/block/io.c index cd6d71a..2d6f48f 100644 --- a/block/io.c +++ b/block/io.c @@ -1172,13 +1172,13 @@ static int coroutine_fn bdrv_co_do_write_zeroes(BlockDriverState *bs, /* Align request. Block drivers can expect the "bulk" of the request * to be aligned. */ - if (bs->bl.write_zeroes_alignment - && num > bs->bl.write_zeroes_alignment) { + if (bs->bl.write_zeroes_alignment) { if (sector_num % bs->bl.write_zeroes_alignment != 0) { /* Make a small request up to the first aligned sector. */ num = bs->bl.write_zeroes_alignment; num -= sector_num % bs->bl.write_zeroes_alignment; - } else if ((sector_num + num) % bs->bl.write_zeroes_alignment != 0) { + } else if (num > bs->bl.write_zeroes_alignment && + (sector_num + num) % bs->bl.write_zeroes_alignment != 0) { /* Shorten the request to the last aligned sector. num cannot * underflow because num > bs->bl.write_zeroes_alignment. */
We should split requests even if they are less than write_zeroes_alignment. For example we can have the following request: offset 62k size 4k write_zeroes_alignment 64k Original code will send 1 request covering 2 qcow2 clusters. One cluster could be zeroed as a whole, another could not be. In this case we will have both 2 clusters allocated. After the patch 2 requests to qcow2 layer will be sent and thus only one cluster will be allocated. Signed-off-by: Denis V. Lunev <den@openvz.org> CC: Kevin Wolf <kwolf@redhat.com> --- block/io.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)