Re: [PATCH v4 21/23] multifd: Zero pages transmission

["Dr. David Alan Gilbert" <dgilbert@redhat.com>]

* Juan Quintela (quintela@redhat.com) wrote:
> This implements the zero page dection and handling.
> 
> Signed-off-by: Juan Quintela <quintela@redhat.com>
> 
> ---
> 
> Add comment for offset (dave)
> ---
>  migration/multifd.h |  4 ++++
>  migration/multifd.c | 36 ++++++++++++++++++++++++++++++++++--
>  2 files changed, 38 insertions(+), 2 deletions(-)
> 
> diff --git a/migration/multifd.h b/migration/multifd.h
> index 4c6d29c954..d014747122 100644
> --- a/migration/multifd.h
> +++ b/migration/multifd.h
> @@ -54,6 +54,10 @@ typedef struct {
>      uint32_t unused32[1];    /* Reserved for future use */
>      uint64_t unused64[3];    /* Reserved for future use */
>      char ramblock[256];
> +    /* This array contains the pointers to:
> +       - normal pages (initial normal_pages entries)
> +       - zero pages (following zero_pages entries)
> +    */
>      uint64_t offset[];
>  } __attribute__((packed)) MultiFDPacket_t;
>  
> diff --git a/migration/multifd.c b/migration/multifd.c
> index cfa9f75d13..ded13289e7 100644
> --- a/migration/multifd.c
> +++ b/migration/multifd.c
> @@ -11,6 +11,7 @@
>   */
>  
>  #include "qemu/osdep.h"
> +#include "qemu/cutils.h"
>  #include "qemu/rcu.h"
>  #include "exec/target_page.h"
>  #include "sysemu/sysemu.h"
> @@ -277,6 +278,12 @@ static void multifd_send_fill_packet(MultiFDSendParams *p)
>  
>          packet->offset[i] = cpu_to_be64(temp);
>      }
> +    for (i = 0; i < p->zero_num; i++) {
> +        /* there are architectures where ram_addr_t is 32 bit */
> +        uint64_t temp = p->zero[i];
> +
> +        packet->offset[p->normal_num + i] = cpu_to_be64(temp);
> +    }
>  }
>  
>  static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp)
> @@ -362,6 +369,18 @@ static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp)
>          p->normal[i] = offset;
>      }
>  
> +    for (i = 0; i < p->zero_num; i++) {
> +        uint64_t offset = be64_to_cpu(packet->offset[p->normal_num + i]);
> +
> +        if (offset > (block->used_length - page_size)) {
> +            error_setg(errp, "multifd: offset too long %" PRIu64
> +                       " (max " RAM_ADDR_FMT ")",
> +                       offset, block->used_length);
> +            return -1;
> +        }
> +        p->zero[i] = offset;
> +    }
> +
>      return 0;
>  }
>  
> @@ -627,6 +646,8 @@ static void *multifd_send_thread(void *opaque)
>  {
>      MultiFDSendParams *p = opaque;
>      Error *local_err = NULL;
> +    /* qemu older than 7.0 don't understand zero page on multifd channel */
> +    bool use_zero_page = migrate_use_multifd_zero_page();
>      int ret = 0;
>  
>      trace_multifd_send_thread_start(p->id);
> @@ -655,8 +676,15 @@ static void *multifd_send_thread(void *opaque)
>              p->zero_num = 0;
>  
>              for (int i = 0; i < p->pages->num; i++) {
> -                p->normal[p->normal_num] = p->pages->offset[i];
> -                p->normal_num++;
> +                if (use_zero_page &&
> +                    buffer_is_zero(p->pages->block->host + p->pages->offset[i],
> +                                   qemu_target_page_size())) {
> +                    p->zero[p->zero_num] = p->pages->offset[i];
> +                    p->zero_num++;
> +                } else {
> +                    p->normal[p->normal_num] = p->pages->offset[i];
> +                    p->normal_num++;
> +                }
>              }
>  
>              if (p->normal_num) {
> @@ -1115,6 +1143,10 @@ static void *multifd_recv_thread(void *opaque)
>              }
>          }
>  
> +        for (int i = 0; i < p->zero_num; i++) {
> +            memset(p->host + p->zero[i], 0, qemu_target_page_size());
> +        }
> +

On the existing code, it tries to avoid doing the memset if the target
page size matches; that avoids allocating the zero pages on the
destination host; should we try and do the same here?

Dave

>          if (flags & MULTIFD_FLAG_SYNC) {
>              qemu_sem_post(&multifd_recv_state->sem_sync);
>              qemu_sem_wait(&p->sem_sync);
> -- 
> 2.34.1
> 
-- 
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK