Re: [PATCH 3/3] migration/ram: Optimize ram_save_host_page()

[David Edmondson <dme@dme.org>]

On Tuesday, 2021-02-23 at 10:16:45 +08, Kunkun Jiang wrote:

> Starting from pss->page, ram_save_host_page() will check every page
> and send the dirty pages up to the end of the current host page or
> the boundary of used_length of the block. If the host page size is
> a huge page, the step "check" will take a lot of time.
>
> This will improve performance to use migration_bitmap_find_dirty().
>
> Signed-off-by: Keqian Zhu <zhukeqian1@huawei.com>
> Signed-off-by: Kunkun Jiang <jiangkunkun@huawei.com>
> ---
>  migration/ram.c | 14 ++++++++------
>  1 file changed, 8 insertions(+), 6 deletions(-)
>
> diff --git a/migration/ram.c b/migration/ram.c
> index c7e18dc2fc..c7a2350198 100644
> --- a/migration/ram.c
> +++ b/migration/ram.c
> @@ -1994,6 +1994,8 @@ static int ram_save_host_page(RAMState *rs, PageSearchStatus *pss,
>      int tmppages, pages = 0;
>      size_t pagesize_bits =
>          qemu_ram_pagesize(pss->block) >> TARGET_PAGE_BITS;
> +    unsigned long hostpage_boundary =
> +        QEMU_ALIGN_UP(pss->page + 1, pagesize_bits);
>      unsigned long start_page = pss->page;
>      int res;
>  
> @@ -2005,8 +2007,7 @@ static int ram_save_host_page(RAMState *rs, PageSearchStatus *pss,
>      do {
>          /* Check the pages is dirty and if it is send it */
>          if (!migration_bitmap_clear_dirty(rs, pss->block, pss->page)) {
> -            pss->page++;
> -            continue;
> +            goto find_next;
>          }
>  
>          tmppages = ram_save_target_page(rs, pss, last_stage);
> @@ -2015,16 +2016,17 @@ static int ram_save_host_page(RAMState *rs, PageSearchStatus *pss,
>          }
>  
>          pages += tmppages;
> -        pss->page++;
>          /* Allow rate limiting to happen in the middle of huge pages */
>          if (pagesize_bits > 1) {
>              migration_rate_limit();
>          }
> -    } while ((pss->page & (pagesize_bits - 1)) &&
> +find_next:
> +        pss->page = migration_bitmap_find_dirty(rs, pss->block, pss->page);
> +    } while ((pss->page < hostpage_boundary) &&
>               offset_in_ramblock(pss->block,
>                                  ((ram_addr_t)pss->page) << TARGET_PAGE_BITS));

This ends up looking very messy, with a goto inside the loop.

Wouldn't it be cleaner to invert the sense of the
migration_bitmap_clear_dirty() test, such that
migration_bitmap_find_dirty() is called after the body of the test?

> -    /* The offset we leave with is the last one we looked at */
> -    pss->page--;
> +    /* The offset we leave with is the min boundary of host page and block */
> +    pss->page = MIN(pss->page, hostpage_boundary) - 1;
>  
>      res = ram_save_release_protection(rs, pss, start_page);
>      return (res < 0 ? res : pages);
> -- 
> 2.23.0

dme.
-- 
Oliver darling, call Mister Haney, I think our speakers are blown.