Re: [Qemu-devel] [PATCH v4 20/32] migration: synchronize dirty bitmap for resume

[Dr. David Alan Gilbert]

* Peter Xu (address@hidden) wrote:
> This patch implements the first part of core RAM resume logic for
> postcopy. ram_resume_prepare() is provided for the work.
> 
> When the migration is interrupted by network failure, the dirty bitmap
> on the source side will be meaningless, because even the dirty bit is
> cleared, it is still possible that the sent page was lost along the way
> to destination. Here instead of continue the migration with the old
> dirty bitmap on source, we ask the destination side to send back its
> received bitmap, then invert it to be our initial dirty bitmap.
> 
> The source side send thread will issue the MIG_CMD_RECV_BITMAP requests,
> once per ramblock, to ask for the received bitmap. On destination side,
> MIG_RP_MSG_RECV_BITMAP will be issued, along with the requested bitmap.
> Data will be received on the return-path thread of source, and the main
> migration thread will be notified when all the ramblock bitmaps are
> synchronized.
> 
> Signed-off-by: Peter Xu <address@hidden>

Reviewed-by: Dr. David Alan Gilbert <address@hidden>

> ---
>  migration/migration.c  |  3 +++
>  migration/migration.h  |  1 +
>  migration/ram.c        | 47 +++++++++++++++++++++++++++++++++++++++++++++++
>  migration/trace-events |  4 ++++
>  4 files changed, 55 insertions(+)
> 
> diff --git a/migration/migration.c b/migration/migration.c
> index 4dc34ed8ce..5b1fbe5b98 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -2843,6 +2843,7 @@ static void migration_instance_finalize(Object *obj)
>      g_free(params->tls_hostname);
>      g_free(params->tls_creds);
>      qemu_sem_destroy(&ms->pause_sem);
> +    qemu_sem_destroy(&ms->rp_state.rp_sem);
>  }
>  
>  static void migration_instance_init(Object *obj)
> @@ -2871,6 +2872,8 @@ static void migration_instance_init(Object *obj)
>      params->has_x_multifd_channels = true;
>      params->has_x_multifd_page_count = true;
>      params->has_xbzrle_cache_size = true;
> +
> +    qemu_sem_init(&ms->rp_state.rp_sem, 0);
>  }
>  
>  /*
> diff --git a/migration/migration.h b/migration/migration.h
> index 11fbfebba1..82dd7d9820 100644
> --- a/migration/migration.h
> +++ b/migration/migration.h
> @@ -108,6 +108,7 @@ struct MigrationState
>          QEMUFile     *from_dst_file;
>          QemuThread    rp_thread;
>          bool          error;
> +        QemuSemaphore rp_sem;
>      } rp_state;
>  
>      double mbps;
> diff --git a/migration/ram.c b/migration/ram.c
> index b30c669476..49627ca9fc 100644
> --- a/migration/ram.c
> +++ b/migration/ram.c
> @@ -49,6 +49,7 @@
>  #include "qemu/rcu_queue.h"
>  #include "migration/colo.h"
>  #include "migration/block.h"
> +#include "savevm.h"
>  
>  /***********************************************************/
>  /* ram save/restore */
> @@ -3049,6 +3050,38 @@ static bool ram_has_postcopy(void *opaque)
>      return migrate_postcopy_ram();
>  }
>  
> +/* Sync all the dirty bitmap with destination VM.  */
> +static int ram_dirty_bitmap_sync_all(MigrationState *s, RAMState *rs)
> +{
> +    RAMBlock *block;
> +    QEMUFile *file = s->to_dst_file;
> +    int ramblock_count = 0;
> +
> +    trace_ram_dirty_bitmap_sync_start();
> +
> +    RAMBLOCK_FOREACH(block) {
> +        qemu_savevm_send_recv_bitmap(file, block->idstr);
> +        trace_ram_dirty_bitmap_request(block->idstr);
> +        ramblock_count++;
> +    }
> +
> +    trace_ram_dirty_bitmap_sync_wait();
> +
> +    /* Wait until all the ramblocks' dirty bitmap synced */
> +    while (ramblock_count--) {
> +        qemu_sem_wait(&s->rp_state.rp_sem);
> +    }
> +
> +    trace_ram_dirty_bitmap_sync_complete();
> +
> +    return 0;
> +}
> +
> +static void ram_dirty_bitmap_reload_notify(MigrationState *s)
> +{
> +    qemu_sem_post(&s->rp_state.rp_sem);
> +}
> +
>  /*
>   * Read the received bitmap, revert it as the initial dirty bitmap.
>   * This is only used when the postcopy migration is paused but wants
> @@ -3123,12 +3156,25 @@ int ram_dirty_bitmap_reload(MigrationState *s, 
> RAMBlock *block)
>  
>      trace_ram_dirty_bitmap_reload_complete(block->idstr);
>  
> +    /*
> +     * We succeeded to sync bitmap for current ramblock. If this is
> +     * the last one to sync, we need to notify the main send thread.
> +     */
> +    ram_dirty_bitmap_reload_notify(s);
> +
>      ret = 0;
>  out:
>      free(le_bitmap);
>      return ret;
>  }
>  
> +static int ram_resume_prepare(MigrationState *s, void *opaque)
> +{
> +    RAMState *rs = *(RAMState **)opaque;
> +
> +    return ram_dirty_bitmap_sync_all(s, rs);
> +}
> +
>  static SaveVMHandlers savevm_ram_handlers = {
>      .save_setup = ram_save_setup,
>      .save_live_iterate = ram_save_iterate,
> @@ -3140,6 +3186,7 @@ static SaveVMHandlers savevm_ram_handlers = {
>      .save_cleanup = ram_save_cleanup,
>      .load_setup = ram_load_setup,
>      .load_cleanup = ram_load_cleanup,
> +    .resume_prepare = ram_resume_prepare,
>  };
>  
>  void ram_mig_init(void)
> diff --git a/migration/trace-events b/migration/trace-events
> index eadabf03e8..804f18d492 100644
> --- a/migration/trace-events
> +++ b/migration/trace-events
> @@ -82,8 +82,12 @@ ram_load_postcopy_loop(uint64_t addr, int flags) "@%" 
> PRIx64 " %x"
>  ram_postcopy_send_discard_bitmap(void) ""
>  ram_save_page(const char *rbname, uint64_t offset, void *host) "%s: offset: 
> 0x%" PRIx64 " host: %p"
>  ram_save_queue_pages(const char *rbname, size_t start, size_t len) "%s: 
> start: 0x%zx len: 0x%zx"
> +ram_dirty_bitmap_request(char *str) "%s"
>  ram_dirty_bitmap_reload_begin(char *str) "%s"
>  ram_dirty_bitmap_reload_complete(char *str) "%s"
> +ram_dirty_bitmap_sync_start(void) ""
> +ram_dirty_bitmap_sync_wait(void) ""
> +ram_dirty_bitmap_sync_complete(void) ""
>  
>  # migration/migration.c
>  await_return_path_close_on_source_close(void) ""
> -- 
> 2.13.6
> 
--
Dr. David Alan Gilbert / address@hidden / Manchester, UK