Re: [PATCH RFC 06/14] migration/rdma: Transmit initial packet

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

* Zhimin Feng (fengzhimin1@huawei.com) wrote:
> Transmit initial packet through the multifd RDMA channels,
> so that we can identify the multifd channels.
> 
> Signed-off-by: Zhimin Feng <fengzhimin1@huawei.com>
> ---
>  migration/multifd.c | 33 +++++++++++++++++++++------------
>  migration/rdma.c    |  2 ++
>  2 files changed, 23 insertions(+), 12 deletions(-)
> 
> diff --git a/migration/multifd.c b/migration/multifd.c
> index acdfd3d5b3..a57d7a2eab 100644
> --- a/migration/multifd.c
> +++ b/migration/multifd.c
> @@ -483,6 +483,13 @@ void multifd_send_sync_main(QEMUFile *f)
>  static void *multifd_rdma_send_thread(void *opaque)
>  {
>      MultiFDSendParams *p = opaque;
> +    Error *local_err = NULL;
> +
> +    trace_multifd_send_thread_start(p->id);
> +
> +    if (multifd_send_initial_packet(p, &local_err) < 0) {
> +        goto out;
> +    }
>  
>      while (true) {
>          qemu_mutex_lock(&p->mutex);
> @@ -494,6 +501,12 @@ static void *multifd_rdma_send_thread(void *opaque)
>          qemu_sem_wait(&p->sem);
>      }
>  
> +out:
> +    if (local_err) {
> +        trace_multifd_send_error(p->id);
> +        multifd_send_terminate_threads(local_err);
> +    }
> +
>      qemu_mutex_lock(&p->mutex);
>      p->running = false;
>      qemu_mutex_unlock(&p->mutex);
> @@ -964,18 +977,14 @@ bool multifd_recv_new_channel(QIOChannel *ioc, Error **errp)
>      Error *local_err = NULL;
>      int id;
>  
> -    if (migrate_use_rdma()) {
> -        id = multifd_recv_state->count;
> -    } else {
> -        id = multifd_recv_initial_packet(ioc, &local_err);
> -        if (id < 0) {
> -            multifd_recv_terminate_threads(local_err);
> -            error_propagate_prepend(errp, local_err,
> -                    "failed to receive packet"
> -                    " via multifd channel %d: ",
> -                    atomic_read(&multifd_recv_state->count));
> -            return false;
> -        }
> +    id = multifd_recv_initial_packet(ioc, &local_err);
> +    if (id < 0) {
> +        multifd_recv_terminate_threads(local_err);
> +        error_propagate_prepend(errp, local_err,
> +                "failed to receive packet"
> +                " via multifd channel %d: ",
> +                atomic_read(&multifd_recv_state->count));
> +        return false;

I'm confused; hasn't that just undone part of patch 5 ?

Dave

>      }
>  
>      trace_multifd_recv_new_channel(id);
> diff --git a/migration/rdma.c b/migration/rdma.c
> index 48615fcaad..2f1e69197f 100644
> --- a/migration/rdma.c
> +++ b/migration/rdma.c
> @@ -4003,6 +4003,8 @@ int multifd_channel_rdma_connect(void *opaque)
>          goto out;
>      }
>  
> +    p->c = QIO_CHANNEL(getQIOChannel(p->file));
> +
>  out:
>      if (local_err) {
>          trace_multifd_send_error(p->id);
> -- 
> 2.19.1
> 
> 
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK