diff mbox

[06/10] migraion: optimiztion xbzrle by reducing data copy

Message ID 1394542415-5152-7-git-send-email-arei.gonglei@huawei.com
State New
Headers show

Commit Message

Gonglei (Arei) March 11, 2014, 12:53 p.m. UTC 
From: ChenLiang <chenliang88@huawei.com>

Reducing data copy can reduce cpu overhead.

Signed-off-by: ChenLiang <chenliang88@huawei.com>
Signed-off-by: Gonglei <arei.gonglei@huawei.com>
---
 arch_init.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

Comments

Juan Quintela March 11, 2014, 8:56 p.m. UTC | #1 
<arei.gonglei@huawei.com> wrote:
> From: ChenLiang <chenliang88@huawei.com>
>
> Reducing data copy can reduce cpu overhead.
>
> Signed-off-by: ChenLiang <chenliang88@huawei.com>
> Signed-off-by: Gonglei <arei.gonglei@huawei.com>


Reviewed-by: Juan Quintela <quintela@redhat.com>
Juan Quintela March 11, 2014, 8:56 p.m. UTC | #2 
<arei.gonglei@huawei.com> wrote:
> From: ChenLiang <chenliang88@huawei.com>
>
> Reducing data copy can reduce cpu overhead.
>
> Signed-off-by: ChenLiang <chenliang88@huawei.com>
> Signed-off-by: Gonglei <arei.gonglei@huawei.com>

Reviewed-by: Juan Quintela <quintela@redhat.com>
Eric Blake March 11, 2014, 8:58 p.m. UTC | #3 
On 03/11/2014 06:53 AM, arei.gonglei@huawei.com wrote:
> From: ChenLiang <chenliang88@huawei.com>

s/migraion/migration/ in the subject (here and in 7/10)

s/optimiztion/optimize/ in the subject

> +++ b/arch_init.c
> @@ -381,11 +381,8 @@ static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
>  
>      prev_cached_page = get_cached_data(XBZRLE.cache, current_addr);
>  
> -    /* save current buffer into memory */
> -    memcpy(XBZRLE.current_buf, *current_data, TARGET_PAGE_SIZE);
> -
>      /* XBZRLE encoding (if there is no overflow) */
> -    encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf,
> +    encoded_len = xbzrle_encode_buffer(prev_cached_page, *current_data,
>                                         TARGET_PAGE_SIZE, XBZRLE.encoded_buf,
>                                         TARGET_PAGE_SIZE);
>      if (encoded_len == 0) {
> @@ -404,7 +401,8 @@ static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
>  
>      /* we need to update the data in the cache, in order to get the same data */
>      if (!last_stage) {
> -        memcpy(prev_cached_page, XBZRLE.current_buf, TARGET_PAGE_SIZE);
> +        xbzrle_decode_buffer(XBZRLE.encoded_buf, encoded_len, prev_cached_page,
> +                             TARGET_PAGE_SIZE);

So, is XBZRLE.current_buf even needed after this patch?  Oh, patch 7
kills it.  I guess splitting in two patches is okay, although I
personally would have squashed them into one.
diff mbox

Patch

diff --git a/arch_init.c b/arch_init.c
index d79535c..7ef3ebb 100644
--- a/arch_init.c
+++ b/arch_init.c
@@ -381,11 +381,8 @@  static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
 
     prev_cached_page = get_cached_data(XBZRLE.cache, current_addr);
 
-    /* save current buffer into memory */
-    memcpy(XBZRLE.current_buf, *current_data, TARGET_PAGE_SIZE);
-
     /* XBZRLE encoding (if there is no overflow) */
-    encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf,
+    encoded_len = xbzrle_encode_buffer(prev_cached_page, *current_data,
                                        TARGET_PAGE_SIZE, XBZRLE.encoded_buf,
                                        TARGET_PAGE_SIZE);
     if (encoded_len == 0) {
@@ -404,7 +401,8 @@  static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
 
     /* we need to update the data in the cache, in order to get the same data */
     if (!last_stage) {
-        memcpy(prev_cached_page, XBZRLE.current_buf, TARGET_PAGE_SIZE);
+        xbzrle_decode_buffer(XBZRLE.encoded_buf, encoded_len, prev_cached_page,
+                             TARGET_PAGE_SIZE);
     }
 
     /* Send XBZRLE based compressed page */