Re: [PATCH v2 15/29] migration/ram: Add support for 'fixed-ram' outgoing migration

[Peter Xu]

On Mon, Oct 23, 2023 at 05:35:54PM -0300, Fabiano Rosas wrote:
> From: Nikolay Borisov <nborisov@suse.com>
> 
> Implement the outgoing migration side for the 'fixed-ram' capability.
> 
> A bitmap is introduced to track which pages have been written in the
> migration file. Pages are written at a fixed location for every
> ramblock. Zero pages are ignored as they'd be zero in the destination
> migration as well.
> 
> The migration stream is altered to put the dirty pages for a ramblock
> after its header instead of having a sequential stream of pages that
> follow the ramblock headers. Since all pages have a fixed location,
> RAM_SAVE_FLAG_EOS is no longer generated on every migration iteration.
> 
> Without fixed-ram (current):
> 
> ramblock 1 header|ramblock 2 header|...|RAM_SAVE_FLAG_EOS|stream of
>  pages (iter 1)|RAM_SAVE_FLAG_EOS|stream of pages (iter 2)|...
> 
> With fixed-ram (new):
> 
> ramblock 1 header|ramblock 1 fixed-ram header|ramblock 1 pages (fixed
>  offsets)|ramblock 2 header|ramblock 2 fixed-ram header|ramblock 2
>  pages (fixed offsets)|...|RAM_SAVE_FLAG_EOS
> 
> where:
>  - ramblock header: the generic information for a ramblock, such as
>    idstr, used_len, etc.
> 
>  - ramblock fixed-ram header: the new information added by this
>    feature: bitmap of pages written, bitmap size and offset of pages
>    in the migration file.
> 
> Signed-off-by: Nikolay Borisov <nborisov@suse.com>
> Signed-off-by: Fabiano Rosas <farosas@suse.de>
> ---
>  include/exec/ramblock.h |  8 ++++
>  migration/options.c     |  3 --
>  migration/ram.c         | 98 ++++++++++++++++++++++++++++++++++++-----
>  3 files changed, 96 insertions(+), 13 deletions(-)
> 
> diff --git a/include/exec/ramblock.h b/include/exec/ramblock.h
> index 69c6a53902..e0e3f16852 100644
> --- a/include/exec/ramblock.h
> +++ b/include/exec/ramblock.h
> @@ -44,6 +44,14 @@ struct RAMBlock {
>      size_t page_size;
>      /* dirty bitmap used during migration */
>      unsigned long *bmap;
> +    /* shadow dirty bitmap used when migrating to a file */
> +    unsigned long *shadow_bmap;
> +    /*
> +     * offset in the file pages belonging to this ramblock are saved,
> +     * used only during migration to a file.
> +     */
> +    off_t bitmap_offset;
> +    uint64_t pages_offset;
>      /* bitmap of already received pages in postcopy */
>      unsigned long *receivedmap;
>  
> diff --git a/migration/options.c b/migration/options.c
> index 2622d8c483..9f693d909f 100644
> --- a/migration/options.c
> +++ b/migration/options.c
> @@ -271,12 +271,9 @@ bool migrate_events(void)
>  
>  bool migrate_fixed_ram(void)
>  {
> -/*
>      MigrationState *s = migrate_get_current();
>  
>      return s->capabilities[MIGRATION_CAPABILITY_FIXED_RAM];
> -*/
> -    return false;
>  }
>  
>  bool migrate_ignore_shared(void)
> diff --git a/migration/ram.c b/migration/ram.c
> index 92769902bb..152a03604f 100644
> --- a/migration/ram.c
> +++ b/migration/ram.c
> @@ -1157,12 +1157,18 @@ static int save_zero_page(RAMState *rs, 
> PageSearchStatus *pss,
>          return 0;
>      }
>  
> +    stat64_add(&mig_stats.zero_pages, 1);

Here we keep zero page accounting, but..

> +
> +    if (migrate_fixed_ram()) {
> +        /* zero pages are not transferred with fixed-ram */
> +        clear_bit(offset >> TARGET_PAGE_BITS, pss->block->shadow_bmap);
> +        return 1;
> +    }
> +
>      len += save_page_header(pss, file, pss->block, offset | 
> RAM_SAVE_FLAG_ZERO);
>      qemu_put_byte(file, 0);
>      len += 1;
>      ram_release_page(pss->block->idstr, offset);
> -
> -    stat64_add(&mig_stats.zero_pages, 1);
>      ram_transferred_add(len);
>  
>      /*
> @@ -1220,14 +1226,20 @@ static int save_normal_page(PageSearchStatus *pss, 
> RAMBlock *block,
>  {
>      QEMUFile *file = pss->pss_channel;
>  
> -    ram_transferred_add(save_page_header(pss, pss->pss_channel, block,
> -                                         offset | RAM_SAVE_FLAG_PAGE));
> -    if (async) {
> -        qemu_put_buffer_async(file, buf, TARGET_PAGE_SIZE,
> -                              migrate_release_ram() &&
> -                              migration_in_postcopy());
> +    if (migrate_fixed_ram()) {
> +        qemu_put_buffer_at(file, buf, TARGET_PAGE_SIZE,
> +                           block->pages_offset + offset);
> +        set_bit(offset >> TARGET_PAGE_BITS, block->shadow_bmap);
>      } else {
> -        qemu_put_buffer(file, buf, TARGET_PAGE_SIZE);
> +        ram_transferred_add(save_page_header(pss, pss->pss_channel, block,
> +                                             offset | RAM_SAVE_FLAG_PAGE));

.. here we ignored normal page accounting.

I think we should have the same behavior on both, perhaps keep them always?

> +        if (async) {
> +            qemu_put_buffer_async(file, buf, TARGET_PAGE_SIZE,
> +                                  migrate_release_ram() &&
> +                                  migration_in_postcopy());
> +        } else {
> +            qemu_put_buffer(file, buf, TARGET_PAGE_SIZE);
> +        }
>      }
>      ram_transferred_add(TARGET_PAGE_SIZE);
>      stat64_add(&mig_stats.normal_pages, 1);
> @@ -2475,6 +2487,8 @@ static void ram_save_cleanup(void *opaque)
>          block->clear_bmap = NULL;
>          g_free(block->bmap);
>          block->bmap = NULL;
> +        g_free(block->shadow_bmap);
> +        block->shadow_bmap = NULL;
>      }
>  
>      xbzrle_cleanup();
> @@ -2842,6 +2856,7 @@ static void ram_list_init_bitmaps(void)
>               */
>              block->bmap = bitmap_new(pages);
>              bitmap_set(block->bmap, 0, pages);
> +            block->shadow_bmap = bitmap_new(block->used_length >> 
> TARGET_PAGE_BITS);

AFAICT bmap should also use used_length.  How about adding one more patch
to change that, then you can use "pages" here?

See ram_mig_ram_block_resized() where we call migration_cancel() if resized.

>              block->clear_bmap_shift = shift;
>              block->clear_bmap = bitmap_new(clear_bmap_size(pages, shift));
>          }
> @@ -2979,6 +2994,44 @@ void qemu_guest_free_page_hint(void *addr, size_t len)
>      }
>  }
>  
> +#define FIXED_RAM_HDR_VERSION 1
> +struct FixedRamHeader {
> +    uint32_t version;
> +    uint64_t page_size;
> +    uint64_t bitmap_offset;
> +    uint64_t pages_offset;
> +    /* end of v1 */
> +} QEMU_PACKED;
> +
> +static void fixed_ram_insert_header(QEMUFile *file, RAMBlock *block)
> +{
> +    g_autofree struct FixedRamHeader *header;
> +    size_t header_size, bitmap_size;
> +    long num_pages;
> +
> +    header = g_new0(struct FixedRamHeader, 1);
> +    header_size = sizeof(struct FixedRamHeader);
> +
> +    num_pages = block->used_length >> TARGET_PAGE_BITS;
> +    bitmap_size = BITS_TO_LONGS(num_pages) * sizeof(unsigned long);
> +
> +    /*
> +     * Save the file offsets of where the bitmap and the pages should
> +     * go as they are written at the end of migration and during the
> +     * iterative phase, respectively.
> +     */
> +    block->bitmap_offset = qemu_get_offset(file) + header_size;
> +    block->pages_offset = ROUND_UP(block->bitmap_offset +
> +                                   bitmap_size, 0x100000);
> +
> +    header->version = cpu_to_be32(FIXED_RAM_HDR_VERSION);
> +    header->page_size = cpu_to_be64(TARGET_PAGE_SIZE);

This is the "page size" for the shadow bitmap, right?  Shall we state it
somewhere (e.g. explaining why it's not block->page_size)?

It's unfortunate that we already have things like:

            if (migrate_postcopy_ram() && block->page_size !=
                                          qemu_host_page_size) {
                qemu_put_be64(f, block->page_size);
            }

But indeed we can't merge them because they seem to service different
purpose.

> +    header->bitmap_offset = cpu_to_be64(block->bitmap_offset);
> +    header->pages_offset = cpu_to_be64(block->pages_offset);
> +
> +    qemu_put_buffer(file, (uint8_t *) header, header_size);
> +}
> +
>  /*
>   * Each of ram_save_setup, ram_save_iterate and ram_save_complete has
>   * long-running RCU critical section.  When rcu-reclaims in the code
> @@ -3028,6 +3081,12 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
>              if (migrate_ignore_shared()) {
>                  qemu_put_be64(f, block->mr->addr);
>              }
> +
> +            if (migrate_fixed_ram()) {
> +                fixed_ram_insert_header(f, block);
> +                /* prepare offset for next ramblock */
> +                qemu_set_offset(f, block->pages_offset + block->used_length, 
> SEEK_SET);
> +            }
>          }
>      }
>  
> @@ -3061,6 +3120,20 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
>      return 0;
>  }
>  
> +static void ram_save_shadow_bmap(QEMUFile *f)
> +{
> +    RAMBlock *block;
> +
> +    RAMBLOCK_FOREACH_MIGRATABLE(block) {
> +        long num_pages = block->used_length >> TARGET_PAGE_BITS;
> +        long bitmap_size = BITS_TO_LONGS(num_pages) * sizeof(unsigned long);
> +        qemu_put_buffer_at(f, (uint8_t *)block->shadow_bmap, bitmap_size,
> +                           block->bitmap_offset);
> +        /* to catch any thread late sending pages */
> +        block->shadow_bmap = NULL;

What is this for?  Wouldn't this leak the buffer already?

> +    }
> +}
> +
>  /**
>   * ram_save_iterate: iterative stage for migration
>   *
> @@ -3179,7 +3252,6 @@ out:
>          qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
>          qemu_fflush(f);
>          ram_transferred_add(8);
> -
>          ret = qemu_file_get_error(f);
>      }
>      if (ret < 0) {
> @@ -3256,7 +3328,13 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
>      if (migrate_multifd() && !migrate_multifd_flush_after_each_section()) {
>          qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH);
>      }
> +
> +    if (migrate_fixed_ram()) {
> +        ram_save_shadow_bmap(f);
> +    }
> +
>      qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
> +
>      qemu_fflush(f);
>  
>      return 0;
> -- 
> 2.35.3
> 

-- 
Peter Xu