[2/6] block: split write_zeroes always
diff mbox

Message ID 1463227273-27523-3-git-send-email-den@openvz.org
State New
Headers show

Commit Message

Denis V. Lunev May 14, 2016, 12:01 p.m. UTC
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(-)

Comments

Eric Blake May 16, 2016, 4:13 p.m. UTC | #1
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'.

Patch
diff mbox

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.
                  */