Re: [Qemu-devel] [PATCH v3] migration/block: use blk_pwrite_zeroes for each zero cluster

[Stefan Hajnoczi]

On Sun, Apr 09, 2017 at 08:37:40PM +0800, address@hidden wrote:
> From: Lidong Chen <address@hidden>
> 
> BLOCK_SIZE is (1 << 20), qcow2 cluster size is 65536 by default,
> this maybe cause the qcow2 file size is bigger after migration.
> This patch check each cluster, use blk_pwrite_zeroes for each
> zero cluster.
> 
> Signed-off-by: Lidong Chen <address@hidden>
> ---
>  migration/block.c | 38 ++++++++++++++++++++++++++++++++++++--
>  1 file changed, 36 insertions(+), 2 deletions(-)
> 
> diff --git a/migration/block.c b/migration/block.c
> index 7734ff7..fe613db 100644
> --- a/migration/block.c
> +++ b/migration/block.c
> @@ -885,6 +885,8 @@ static int block_load(QEMUFile *f, void *opaque, int 
> version_id)
>      int64_t total_sectors = 0;
>      int nr_sectors;
>      int ret;
> +    BlockDriverInfo bdi;
> +    int cluster_size;
>  
>      do {
>          addr = qemu_get_be64(f);
> @@ -934,8 +936,40 @@ static int block_load(QEMUFile *f, void *opaque, int 
> version_id)
>              } else {
>                  buf = g_malloc(BLOCK_SIZE);
>                  qemu_get_buffer(f, buf, BLOCK_SIZE);
> -                ret = blk_pwrite(blk, addr * BDRV_SECTOR_SIZE, buf,
> -                                 nr_sectors * BDRV_SECTOR_SIZE, 0);
> +
> +                ret = bdrv_get_info(blk_bs(blk), &bdi);
> +                cluster_size = bdi.cluster_size;
> +
> +                if (ret == 0 && cluster_size > 0 &&
> +                    cluster_size <= BLOCK_SIZE &&
> +                    BLOCK_SIZE % cluster_size == 0) {

How about:

  if (blk != blk_prev) {
      blk_prev = blk;
      total_sectors = blk_nb_sectors(blk);
      if (total_sectors <= 0) {
          error_report("Error getting length of block device %s",
                       device_name);
          return -EINVAL;
      }

      blk_invalidate_cache(blk, &local_err);
      if (local_err) {
          error_report_err(local_err);
          return -EINVAL;
      }

+     ret = bdrv_get_info(blk_bs(blk), &bdi);
+     if (ret == 0 && cluster_size > 0 && cluster_size <= BLOCK_SIZE &&
+         BLOCK_SIZE % cluster_size == 0) {
+         zero_cluster_size = bdi.cluster_size;
+     } else {
+         zero_cluster_size = 0;
+     }
  }

That way we only fetch the cluster size once per device.

When processing a block we do without repeatedly fetching the cluster
size:

  if (zero_cluster_size) {
     ...detect zeroes...
  }

> +                    int i;
> +                    int64_t cur_addr;
> +                    uint8_t *cur_buf;
> +
> +                    for (i = 0; i < BLOCK_SIZE / cluster_size; i++) {
> +                        cur_addr = addr * BDRV_SECTOR_SIZE
> +                                        + i * cluster_size;
> +                        cur_buf = buf + i * cluster_size;
> +
> +                        if (buffer_is_zero(cur_buf, cluster_size)) {
> +                            ret = blk_pwrite_zeroes(blk, cur_addr,
> +                                                    cluster_size,
> +                                                    BDRV_REQ_MAY_UNMAP);
> +                        } else {
> +                             ret = blk_pwrite(blk, cur_addr, cur_buf,
> +                                              cluster_size, 0);

Indentation is off here.

> +                        }
> +
> +                        if (ret < 0) {
> +                            g_free(buf);
> +                            return ret;
> +                        }
> +                    }
> +                } else {
> +                    ret = blk_pwrite(blk, addr * BDRV_SECTOR_SIZE, buf,
> +                                     nr_sectors * BDRV_SECTOR_SIZE, 0);
> +                }
>                  g_free(buf);
>              }
>  
> -- 
> 1.8.3.1
>

signature.asc
Description: PGP signature