[Qemu-devel] [PATCH 0/2] use blk_pwrite_zeroes for each zero cluster

[Qemu-devel] [PATCH 0/2] use blk_pwrite_zeroes for each zero cluster

[jemmy858585]

From: Lidong Chen <lidongchen@tencent.com>

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.

Lidong Chen (2):
  block: make bdrv_get_cluster_size public
  migration/block: use blk_pwrite_zeroes for each zero cluster

 block/io.c            |  2 +-
 include/block/block.h |  1 +
 migration/block.c     | 34 ++++++++++++++++++++++++++++++++--
 3 files changed, 34 insertions(+), 3 deletions(-)

-- 
1.8.3.1

[Qemu-devel] [PATCH 1/2] block: make bdrv_get_cluster_size public

[jemmy858585]

From: Lidong Chen <lidongchen@tencent.com>

The bdrv_get_cluster_size function is need by block migration
to optimize zero cluster.

Signed-off-by: Lidong Chen <lidongchen@tencent.com>
---
 block/io.c            | 2 +-
 include/block/block.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/block/io.c b/block/io.c
index 2709a70..1c31c2b 100644
--- a/block/io.c
+++ b/block/io.c
@@ -459,7 +459,7 @@ void bdrv_round_to_clusters(BlockDriverState *bs,
     }
 }
 
-static int bdrv_get_cluster_size(BlockDriverState *bs)
+int bdrv_get_cluster_size(BlockDriverState *bs)
 {
     BlockDriverInfo bdi;
     int ret;
diff --git a/include/block/block.h b/include/block/block.h
index 5149260..a0d78fc 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -473,6 +473,7 @@ void bdrv_round_to_clusters(BlockDriverState *bs,
                             int64_t offset, unsigned int bytes,
                             int64_t *cluster_offset,
                             unsigned int *cluster_bytes);
+int bdrv_get_cluster_size(BlockDriverState *bs);
 
 const char *bdrv_get_encrypted_filename(BlockDriverState *bs);
 void bdrv_get_backing_filename(BlockDriverState *bs,
-- 
1.8.3.1

[Qemu-devel] [PATCH 2/2] migration/block: use blk_pwrite_zeroes for each zero cluster

[jemmy858585]

From: Lidong Chen <lidongchen@tencent.com>

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 <lidongchen@tencent.com>
---
 migration/block.c | 34 ++++++++++++++++++++++++++++++++--
 1 file changed, 32 insertions(+), 2 deletions(-)

diff --git a/migration/block.c b/migration/block.c
index 7734ff7..1fce9b9 100644
--- a/migration/block.c
+++ b/migration/block.c
@@ -885,6 +885,10 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
     int64_t total_sectors = 0;
     int nr_sectors;
     int ret;
+    int i;
+    int cluster_size;
+    int64_t addr_offset;
+    uint8_t *buf_offset;
 
     do {
         addr = qemu_get_be64(f);
@@ -934,8 +938,34 @@ 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);
+
+                cluster_size = bdrv_get_cluster_size(blk_bs(blk));
+
+                if (cluster_size > 0) {
+                    for (i = 0; i < BLOCK_SIZE / cluster_size; i++) {
+                        addr_offset = addr * BDRV_SECTOR_SIZE
+                                        + i * cluster_size;
+                        buf_offset = buf + i * cluster_size;
+
+                        if (buffer_is_zero(buf_offset, cluster_size)) {
+                            ret = blk_pwrite_zeroes(blk, addr_offset,
+                                                    cluster_size,
+                                                    BDRV_REQ_MAY_UNMAP);
+                        } else {
+                            ret = blk_pwrite(blk, addr_offset,
+                                             buf_offset, cluster_size, 0);
+                        }
+
+                        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

Re: [Qemu-devel] [PATCH 0/2] use blk_pwrite_zeroes for each zero cluster

[858585 jemmy]

the test result for this patch:

the migration command :
virsh migrate --live 165cf436-312f-47e7-90f2-f8aa63f34893
--copy-storage-all qemu+ssh://10.59.163.38/system

the qemu-img info on source host:
qemu-img info /instanceimage/165cf436-312f-47e7-90f2-f8aa63f34893/165cf436-312f-47e7-90f2-f8aa63f34893_vda.qcow2
image: /instanceimage/165cf436-312f-47e7-90f2-f8aa63f34893/165cf436-312f-47e7-90f2-f8aa63f34893_vda.qcow2
file format: qcow2
virtual size: 1.0T (1095216660480 bytes)
disk size: 1.5G (1638989824 bytes)
cluster_size: 65536
backing file: /baseimage/img2016042213665396/img2016042213665396.qcow2

the qemu-img info on dest host(before apply patch):
qemu-img info /instanceimage/165cf436-312f-47e7-90f2-f8aa63f34893/165cf436-312f-47e7-90f2-f8aa63f34893_vda.qcow2
image: /instanceimage/165cf436-312f-47e7-90f2-f8aa63f34893/165cf436-312f-47e7-90f2-f8aa63f34893_vda.qcow2
file format: qcow2
virtual size: 40G (42949672960 bytes)
disk size: 4.1G (4423286784 bytes)
cluster_size: 65536
backing file: /baseimage/img2016042213665396/img2016042213665396.qcow2

the qemu-img info on dest host(after apply patch):
qemu-img info /instanceimage/165cf436-312f-47e7-90f2-f8aa63f34893/165cf436-312f-47e7-90f2-f8aa63f34893_vda.qcow2
image: /instanceimage/165cf436-312f-47e7-90f2-f8aa63f34893/165cf436-312f-47e7-90f2-f8aa63f34893_vda.qcow2
file format: qcow2
virtual size: 40G (42949672960 bytes)
disk size: 2.3G (2496200704 bytes)
cluster_size: 65536
backing file: /baseimage/img2016042213665396/img2016042213665396.qcow2

the disk size reduce from 4.1G to 2.3G.


On Thu, Apr 6, 2017 at 9:15 PM,  <jemmy858585@gmail.com> wrote:
> From: Lidong Chen <lidongchen@tencent.com>
>
> 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.
>
> Lidong Chen (2):
>   block: make bdrv_get_cluster_size public
>   migration/block: use blk_pwrite_zeroes for each zero cluster
>
>  block/io.c            |  2 +-
>  include/block/block.h |  1 +
>  migration/block.c     | 34 ++++++++++++++++++++++++++++++++--
>  3 files changed, 34 insertions(+), 3 deletions(-)
>
> --
> 1.8.3.1
>

Re: [Qemu-devel] [PATCH 0/2] use blk_pwrite_zeroes for each zero cluster

[858585 jemmy]

On Fri, Apr 7, 2017 at 1:22 PM, 858585 jemmy <jemmy858585@gmail.com> wrote:
> the test result for this patch:
>
> the migration command :
> virsh migrate --live 165cf436-312f-47e7-90f2-f8aa63f34893
> --copy-storage-all qemu+ssh://10.59.163.38/system
>
> the qemu-img info on source host:
> qemu-img info /instanceimage/165cf436-312f-47e7-90f2-f8aa63f34893/165cf436-312f-47e7-90f2-f8aa63f34893_vda.qcow2
> image: /instanceimage/165cf436-312f-47e7-90f2-f8aa63f34893/165cf436-312f-47e7-90f2-f8aa63f34893_vda.qcow2
> file format: qcow2
> virtual size: 1.0T (1095216660480 bytes)
> disk size: 1.5G (1638989824 bytes)
> cluster_size: 65536
> backing file: /baseimage/img2016042213665396/img2016042213665396.qcow2
>
> the qemu-img info on dest host(before apply patch):
> qemu-img info /instanceimage/165cf436-312f-47e7-90f2-f8aa63f34893/165cf436-312f-47e7-90f2-f8aa63f34893_vda.qcow2
> image: /instanceimage/165cf436-312f-47e7-90f2-f8aa63f34893/165cf436-312f-47e7-90f2-f8aa63f34893_vda.qcow2
> file format: qcow2
> virtual size: 40G (42949672960 bytes)
> disk size: 4.1G (4423286784 bytes)
> cluster_size: 65536
> backing file: /baseimage/img2016042213665396/img2016042213665396.qcow2
>
> the qemu-img info on dest host(after apply patch):
> qemu-img info /instanceimage/165cf436-312f-47e7-90f2-f8aa63f34893/165cf436-312f-47e7-90f2-f8aa63f34893_vda.qcow2
> image: /instanceimage/165cf436-312f-47e7-90f2-f8aa63f34893/165cf436-312f-47e7-90f2-f8aa63f34893_vda.qcow2
> file format: qcow2
> virtual size: 40G (42949672960 bytes)
> disk size: 2.3G (2496200704 bytes)
> cluster_size: 65536
> backing file: /baseimage/img2016042213665396/img2016042213665396.qcow2
>
> the disk size reduce from 4.1G to 2.3G.
>

I find a bug for my patch.
unfortunately, when use raw format , bdrv_get_cluster_size return 1.
the raw format cluster size is 1.
and will reduce migration speed.

bdrv_get_cluster_size return bs->bl.request_alignment when cluster_size is zero.
and bs->bl.request_alignment is 1 when use raw format.

static int bdrv_get_cluster_size(BlockDriverState *bs)
{
    BlockDriverInfo bdi;
    int ret;

    ret = bdrv_get_info(bs, &bdi);
    if (ret < 0 || bdi.cluster_size == 0) {
        return bs->bl.request_alignment;
    } else {
        return bdi.cluster_size;
    }
}

so i will change to use bdrv_get_info function to get cluster_size.
and bdrv_get_cluster_size is not need to be public.

>
> On Thu, Apr 6, 2017 at 9:15 PM,  <jemmy858585@gmail.com> wrote:
>> From: Lidong Chen <lidongchen@tencent.com>
>>
>> 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.
>>
>> Lidong Chen (2):
>>   block: make bdrv_get_cluster_size public
>>   migration/block: use blk_pwrite_zeroes for each zero cluster
>>
>>  block/io.c            |  2 +-
>>  include/block/block.h |  1 +
>>  migration/block.c     | 34 ++++++++++++++++++++++++++++++++--
>>  3 files changed, 34 insertions(+), 3 deletions(-)
>>
>> --
>> 1.8.3.1
>>

Re: [Qemu-devel] [PATCH 2/2] migration/block: use blk_pwrite_zeroes for each zero cluster

[Fam Zheng]

On Thu, 04/06 21:15, jemmy858585@gmail.com wrote:
> From: Lidong Chen <lidongchen@tencent.com>
> 
> 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 <lidongchen@tencent.com>
> ---
>  migration/block.c | 34 ++++++++++++++++++++++++++++++++--
>  1 file changed, 32 insertions(+), 2 deletions(-)
> 
> diff --git a/migration/block.c b/migration/block.c
> index 7734ff7..1fce9b9 100644
> --- a/migration/block.c
> +++ b/migration/block.c
> @@ -885,6 +885,10 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
>      int64_t total_sectors = 0;
>      int nr_sectors;
>      int ret;
> +    int i;
> +    int cluster_size;
> +    int64_t addr_offset;
> +    uint8_t *buf_offset;
>  
>      do {
>          addr = qemu_get_be64(f);
> @@ -934,8 +938,34 @@ 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);
> +
> +                cluster_size = bdrv_get_cluster_size(blk_bs(blk));
> +
> +                if (cluster_size > 0) {
> +                    for (i = 0; i < BLOCK_SIZE / cluster_size; i++) {

Should we check that cluster_size < BLOCK_SIZE and (BLOCK_SIZE % cluster_size ==
0)?

Fam

> +                        addr_offset = addr * BDRV_SECTOR_SIZE
> +                                        + i * cluster_size;
> +                        buf_offset = buf + i * cluster_size;
> +
> +                        if (buffer_is_zero(buf_offset, cluster_size)) {
> +                            ret = blk_pwrite_zeroes(blk, addr_offset,
> +                                                    cluster_size,
> +                                                    BDRV_REQ_MAY_UNMAP);
> +                        } else {
> +                            ret = blk_pwrite(blk, addr_offset,
> +                                             buf_offset, cluster_size, 0);
> +                        }
> +
> +                        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
> 

Re: [Qemu-devel] [PATCH 2/2] migration/block: use blk_pwrite_zeroes for each zero cluster

[858585 jemmy]

On Fri, Apr 7, 2017 at 3:08 PM, Fam Zheng <famz@redhat.com> wrote:
> On Thu, 04/06 21:15, jemmy858585@gmail.com wrote:
>> From: Lidong Chen <lidongchen@tencent.com>
>>
>> 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 <lidongchen@tencent.com>
>> ---
>>  migration/block.c | 34 ++++++++++++++++++++++++++++++++--
>>  1 file changed, 32 insertions(+), 2 deletions(-)
>>
>> diff --git a/migration/block.c b/migration/block.c
>> index 7734ff7..1fce9b9 100644
>> --- a/migration/block.c
>> +++ b/migration/block.c
>> @@ -885,6 +885,10 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
>>      int64_t total_sectors = 0;
>>      int nr_sectors;
>>      int ret;
>> +    int i;
>> +    int cluster_size;
>> +    int64_t addr_offset;
>> +    uint8_t *buf_offset;
>>
>>      do {
>>          addr = qemu_get_be64(f);
>> @@ -934,8 +938,34 @@ 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);
>> +
>> +                cluster_size = bdrv_get_cluster_size(blk_bs(blk));
>> +
>> +                if (cluster_size > 0) {
>> +                    for (i = 0; i < BLOCK_SIZE / cluster_size; i++) {
>
> Should we check that cluster_size < BLOCK_SIZE and (BLOCK_SIZE % cluster_size ==
> 0)?
I think this is necessary.
Thanks.

>
> Fam
>
>> +                        addr_offset = addr * BDRV_SECTOR_SIZE
>> +                                        + i * cluster_size;
>> +                        buf_offset = buf + i * cluster_size;
>> +
>> +                        if (buffer_is_zero(buf_offset, cluster_size)) {
>> +                            ret = blk_pwrite_zeroes(blk, addr_offset,
>> +                                                    cluster_size,
>> +                                                    BDRV_REQ_MAY_UNMAP);
>> +                        } else {
>> +                            ret = blk_pwrite(blk, addr_offset,
>> +                                             buf_offset, cluster_size, 0);
>> +                        }
>> +
>> +                        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
>>