Re: [Qemu-devel] [PATCH v7 14/42] Return path: Send responses from destination to source

[Juan Quintela]

"Dr. David Alan Gilbert (git)" <address@hidden> wrote:
> From: "Dr. David Alan Gilbert" <address@hidden>
>
> Add migrate_send_rp_message to send a message from destination to source 
> along the return path.
>   (It uses a mutex to let it be called from multiple threads)
> Add migrate_send_rp_shut to send a 'shut' message to indicate
>   the destination is finished with the RP.
> Add migrate_send_rp_ack to send a 'PONG' message in response to a PING
>   Use it in the MSG_RP_PING handler
>
> Signed-off-by: Dr. David Alan Gilbert <address@hidden>
> ---
>  include/migration/migration.h | 17 ++++++++++++++++
>  migration/migration.c         | 45 
> +++++++++++++++++++++++++++++++++++++++++++
>  migration/savevm.c            |  2 +-
>  trace-events                  |  1 +
>  4 files changed, 64 insertions(+), 1 deletion(-)
>
> diff --git a/include/migration/migration.h b/include/migration/migration.h
> index 65fe5db..36caab9 100644
> --- a/include/migration/migration.h
> +++ b/include/migration/migration.h
> @@ -42,12 +42,20 @@ struct MigrationParams {
>      bool shared;
>  };
>  
> +/* Messages sent on the return path from destination to source */
> +enum mig_rp_message_type {
> +    MIG_RP_MSG_INVALID = 0,  /* Must be 0 */
> +    MIG_RP_MSG_SHUT,         /* sibling will not send any more RP messages */
> +    MIG_RP_MSG_PONG,         /* Response to a PING; data (seq: be32 ) */
> +};
> +
>  typedef QLIST_HEAD(, LoadStateEntry) LoadStateEntry_Head;
>  /* State for the incoming migration */
>  struct MigrationIncomingState {
>      QEMUFile *file;
>  
>      QEMUFile *return_path;
> +    QemuMutex      rp_mutex;    /* We send replies from multiple threads */
>  
>      /* See savevm.c */
>      LoadStateEntry_Head loadvm_handlers;
> @@ -179,6 +187,15 @@ int migrate_compress_level(void);
>  int migrate_compress_threads(void);
>  int migrate_decompress_threads(void);
>  
> +/* Sending on the return path - generic and then for each message type */
> +void migrate_send_rp_message(MigrationIncomingState *mis,
> +                             enum mig_rp_message_type message_type,
> +                             uint16_t len, void *data);
> +void migrate_send_rp_shut(MigrationIncomingState *mis,
> +                          uint32_t value);
> +void migrate_send_rp_pong(MigrationIncomingState *mis,
> +                          uint32_t value);
> +
>  void ram_control_before_iterate(QEMUFile *f, uint64_t flags);
>  void ram_control_after_iterate(QEMUFile *f, uint64_t flags);
>  void ram_control_load_hook(QEMUFile *f, uint64_t flags);
> diff --git a/migration/migration.c b/migration/migration.c
> index 295f15a..afb19a1 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -85,6 +85,7 @@ MigrationIncomingState 
> *migration_incoming_state_new(QEMUFile* f)
>      mis_current = g_malloc0(sizeof(MigrationIncomingState));
>      mis_current->file = f;
>      QLIST_INIT(&mis_current->loadvm_handlers);
> +    qemu_mutex_init(&mis_current->rp_mutex);
>  
>      return mis_current;
>  }
> @@ -182,6 +183,50 @@ void process_incoming_migration(QEMUFile *f)
>      qemu_coroutine_enter(co, f);
>  }
>  
> +/*
> + * Send a message on the return channel back to the source
> + * of the migration.
> + */
> +void migrate_send_rp_message(MigrationIncomingState *mis,
> +                             enum mig_rp_message_type message_type,
> +                             uint16_t len, void *data)
> +{
> +    trace_migrate_send_rp_message((int)message_type, len);
> +    qemu_mutex_lock(&mis->rp_mutex);
> +    qemu_put_be16(mis->return_path, (unsigned int)message_type);
> +    qemu_put_be16(mis->return_path, len);
if (len) {

> +    qemu_put_buffer(mis->return_path, data, len);
}


?

We check for zero sized command on control commands but not on
responses?

> +    qemu_fflush(mis->return_path);
> +    qemu_mutex_unlock(&mis->rp_mutex);
> +}
> +
> +/*
> + * Send a 'SHUT' message on the return channel with the given value
> + * to indicate that we've finished with the RP.  Non-0 value indicates
> + * error.
> + */
> +void migrate_send_rp_shut(MigrationIncomingState *mis,
> +                          uint32_t value)
> +{
> +    uint32_t buf;
> +
> +    buf = cpu_to_be32(value);
> +    migrate_send_rp_message(mis, MIG_RP_MSG_SHUT, sizeof(buf), &buf);
> +}
> +
> +/*
> + * Send a 'PONG' message on the return channel with the given value
> + * (normally in response to a 'PING')
> + */
> +void migrate_send_rp_pong(MigrationIncomingState *mis,
> +                          uint32_t value)
> +{
> +    uint32_t buf;
> +
> +    buf = cpu_to_be32(value);
> +    migrate_send_rp_message(mis, MIG_RP_MSG_PONG, sizeof(buf), &buf);
> +}
> +
>  /* amount of nanoseconds we are willing to wait for migration to be down.
>   * the choice of nanoseconds is because it is the maximum resolution that
>   * get_clock() can achieve. It is an internal measure. All user-visible
> diff --git a/migration/savevm.c b/migration/savevm.c
> index a995014..d424c2a 100644
> --- a/migration/savevm.c
> +++ b/migration/savevm.c
> @@ -1071,7 +1071,7 @@ static int loadvm_process_command(QEMUFile *f)
>                           tmp32);
>              return -1;
>          }
> -        /* migrate_send_rp_pong(mis, tmp32); TODO: gets added later */
> +        migrate_send_rp_pong(mis, tmp32);
>          break;
>  
>      default:
> diff --git a/trace-events b/trace-events
> index 5967fdf..5738e3f 100644
> --- a/trace-events
> +++ b/trace-events
> @@ -1399,6 +1399,7 @@ migrate_fd_cleanup(void) ""
>  migrate_fd_error(void) ""
>  migrate_fd_cancel(void) ""
>  migrate_pending(uint64_t size, uint64_t max) "pending size %" PRIu64 " max 
> %" PRIu64
> +migrate_send_rp_message(int msg_type, uint16_t len) "%d: len %d"
>  migrate_transferred(uint64_t tranferred, uint64_t time_spent, double 
> bandwidth, uint64_t size) "transferred %" PRIu64 " time_spent %" PRIu64 " 
> bandwidth %g max_size %" PRId64
>  
>  # migration/rdma.c