Re: [PATCH v2 1/2] migration: Fix rdma migration failed

[Peter Xu]

On Tue, Oct 03, 2023 at 08:57:07PM +0200, Juan Quintela wrote:
> commit c638f66121ce30063fbf68c3eab4d7429cf2b209
> Author: Juan Quintela <quintela@redhat.com>
> Date:   Tue Oct 3 20:53:38 2023 +0200
> 
>     migration: Non multifd migration don't care about multifd flushes
>     
>     RDMA was having trouble because
>     migrate_multifd_flush_after_each_section() can only be true or false,
>     but we don't want to send any flush when we are not in multifd
>     migration.
>     
>     CC: Fabiano Rosas <farosas@suse.de
>     Reported-by: Li Zhijian <lizhijian@fujitsu.com>
>     Signed-off-by: Juan Quintela <quintela@redhat.com>
> 
> diff --git a/migration/ram.c b/migration/ram.c
> index e4bfd39f08..716cef6425 100644
> --- a/migration/ram.c
> +++ b/migration/ram.c
> @@ -1387,7 +1387,8 @@ static int find_dirty_block(RAMState *rs, 
> PageSearchStatus *pss)
>          pss->page = 0;
>          pss->block = QLIST_NEXT_RCU(pss->block, next);
>          if (!pss->block) {
> -            if (!migrate_multifd_flush_after_each_section()) {
> +            if (migrate_multifd() &&
> +                !migrate_multifd_flush_after_each_section()) {
>                  QEMUFile *f = rs->pss[RAM_CHANNEL_PRECOPY].pss_channel;
>                  int ret = multifd_send_sync_main(f);
>                  if (ret < 0) {
> @@ -3064,7 +3065,7 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
>          return ret;
>      }
>  
> -    if (!migrate_multifd_flush_after_each_section()) {
> +    if (migrate_multifd() && !migrate_multifd_flush_after_each_section()) {
>          qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH);
>      }
>  
> @@ -3176,7 +3177,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
>  out:
>      if (ret >= 0
>          && migration_is_setup_or_active(migrate_get_current()->state)) {
> -        if (migrate_multifd_flush_after_each_section()) {
> +        if (migrate_multifd() && migrate_multifd_flush_after_each_section()) 
> {
>              ret = 
> multifd_send_sync_main(rs->pss[RAM_CHANNEL_PRECOPY].pss_channel);
>              if (ret < 0) {
>                  return ret;
> @@ -3253,7 +3254,7 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
>          return ret;
>      }
>  
> -    if (!migrate_multifd_flush_after_each_section()) {
> +    if (migrate_multifd() && !migrate_multifd_flush_after_each_section()) {
>          qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH);
>      }
>      qemu_put_be64(f, RAM_SAVE_FLAG_EOS);
> @@ -3760,7 +3761,7 @@ int ram_load_postcopy(QEMUFile *f, int channel)
>              break;
>          case RAM_SAVE_FLAG_EOS:
>              /* normal exit */
> -            if (migrate_multifd_flush_after_each_section()) {
> +            if (migrate_multifd() && 
> migrate_multifd_flush_after_each_section()) {
>                  multifd_recv_sync_main();
>              }
>              break;
> @@ -4038,7 +4039,8 @@ static int ram_load_precopy(QEMUFile *f)
>              break;
>          case RAM_SAVE_FLAG_EOS:
>              /* normal exit */
> -            if (migrate_multifd_flush_after_each_section()) {
> +            if (migrate_multifd() &&
> +                migrate_multifd_flush_after_each_section()) {
>                  multifd_recv_sync_main();
>              }
>              break;

Reviewed-by: Peter Xu <peterx@redhat.com>

Did you forget to send this out formally?  Even if f1de309792d6656e landed
(which, IMHO, shouldn't..), but IIUC rdma is still broken..

Thanks,

-- 
Peter Xu