Re: [PULL 20/30] migration: Update error description whenever migration fails

[Tejus GK]

On 22/06/23 7:43 am, Juan Quintela wrote:
> From: Tejus GK <tejus.gk@nutanix.com>
> 
> There are places in migration.c where the migration is marked failed with
> MIGRATION_STATUS_FAILED, but the failure reason is never updated. Hence
> libvirt doesn't know why the migration failed when it queries for it.
> 
> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com
> Reviewed-by: Juan Quintela <quintela@redhat.com>
> Acked-by: Peter Xu <peterx@redhat.com>
> Signed-off-by: Tejus GK <tejus.gk@nutanix.com>
> Message-ID: <20230621130940.178659-2-tejus.gk@nutanix.com>
> Signed-off-by: Juan Quintela <quintela@redhat.com>
> ---
>  migration/migration.c | 19 ++++++++++++-------
>  1 file changed, 12 insertions(+), 7 deletions(-)
> 
> diff --git a/migration/migration.c b/migration/migration.c
> index 719f91573f..e6bff2e848 100644
> --- a/migration/migration.c
> +++ b/migration/migration.c
> @@ -1679,7 +1679,7 @@ void qmp_migrate(const char *uri, bool has_blk, bool 
> blk,
>          if (!(has_resume && resume)) {
>              yank_unregister_instance(MIGRATION_YANK_INSTANCE);
>          }
> -        error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "uri",
> +        error_setg(&local_err, QERR_INVALID_PARAMETER_VALUE, "uri",
>                     "a valid migration protocol");
>          migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
>                            MIGRATION_STATUS_FAILED);
> @@ -2066,7 +2066,7 @@ migration_wait_main_channel(MigrationState *ms)
>   * Switch from normal iteration to postcopy
>   * Returns non-0 on error
>   */
> -static int postcopy_start(MigrationState *ms)
> +static int postcopy_start(MigrationState *ms, Error **errp)
>  {
>      int ret;
>      QIOChannelBuffer *bioc;
> @@ -2176,7 +2176,7 @@ static int postcopy_start(MigrationState *ms)
>       */
>      ret = qemu_file_get_error(ms->to_dst_file);
>      if (ret) {
> -        error_report("postcopy_start: Migration stream errored (pre 
> package)");
> +        error_setg(errp, "postcopy_start: Migration stream errored (pre 
> package)");
>          goto fail_closefb;
>      }
>  
> @@ -2213,7 +2213,7 @@ static int postcopy_start(MigrationState *ms)
>  
>      ret = qemu_file_get_error(ms->to_dst_file);
>      if (ret) {
> -        error_report("postcopy_start: Migration stream errored");
> +        error_setg(errp, "postcopy_start: Migration stream errored");
>          migrate_set_state(&ms->state, MIGRATION_STATUS_POSTCOPY_ACTIVE,
>                                MIGRATION_STATUS_FAILED);
>      }
> @@ -2720,6 +2720,7 @@ typedef enum {
>  static MigIterateState migration_iteration_run(MigrationState *s)
>  {
>      uint64_t must_precopy, can_postcopy;
> +    Error *local_err = NULL;
>      bool in_postcopy = s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE;
>  
>      qemu_savevm_state_pending_estimate(&must_precopy, &can_postcopy);
> @@ -2742,8 +2743,9 @@ static MigIterateState 
> migration_iteration_run(MigrationState *s)
>      /* Still a significant amount to transfer */
>      if (!in_postcopy && must_precopy <= s->threshold_size &&
>          qatomic_read(&s->start_postcopy)) {
> -        if (postcopy_start(s)) {
> -            error_report("%s: postcopy failed to start", __func__);
> +        if (postcopy_start(s, &local_err)) {
> +            migrate_set_error(s, local_err);
> +            error_report_err(local_err);
>          }
>          return MIG_ITERATE_SKIP;
>      }
> @@ -3234,8 +3236,10 @@ void migrate_fd_connect(MigrationState *s, Error 
> *error_in)
>       */
>      if (migrate_postcopy_ram() || migrate_return_path()) {
>          if (open_return_path_on_source(s, !resume)) {
> -            error_report("Unable to open return-path for postcopy");
> +            error_setg(&local_err, "Unable to open return-path for 
> postcopy");
>              migrate_set_state(&s->state, s->state, MIGRATION_STATUS_FAILED);
> +            migrate_set_error(s, local_err);
> +            error_report_err(local_err);
>              migrate_fd_cleanup(s);
>              return;
>          }
> @@ -3259,6 +3263,7 @@ void migrate_fd_connect(MigrationState *s, Error 
> *error_in)
>      }
>  
>      if (multifd_save_setup(&local_err) != 0) {
> +        migrate_set_error(s, local_err);
>          error_report_err(local_err);
>          migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
>                            MIGRATION_STATUS_FAILED);

Hi Juan,

I can see that the "Acked-by" by Peter has been added to this patch ( and the 
next one in queue ), however, Peter hadn't Acked this patchset, but had "Acked" 
a different but similar patchset which is still under review: 
https://lists.gnu.org/archive/html/qemu-devel/2023-06/msg04184.html

Regards,
Tejus