Re: [RFC v2 1/1] migration: Update error description whenever migration fails

[Tejus GK]

On 09/05/23 3:46 pm, Juan Quintela wrote:
> "tejus.gk" <tejus.gk@nutanix.com> wrote:
>> There are places in the code where the migration is marked failed with
>> MIGRATION_STATUS_FAILED, but the failiure reason is never updated. Hence
>> libvirt doesn't know why the migration failed when it queries for it.
>>
>> Signed-off-by: tejus.gk <tejus.gk@nutanix.com>
>> ---
>>  migration/migration.c | 24 +++++++++++-------------
>>  1 file changed, 11 insertions(+), 13 deletions(-)
>>
>> diff --git a/migration/migration.c b/migration/migration.c
>> index 232e387109..87101eed5c 100644
>> --- a/migration/migration.c
>> +++ b/migration/migration.c
>> @@ -1660,15 +1660,9 @@ void qmp_migrate(const char *uri, bool has_blk, bool 
>> blk,
>>      } else if (strstart(uri, "fd:", &p)) {
>>          fd_start_outgoing_migration(s, p, &local_err);
>>      } else {
>> -        if (!(has_resume && resume)) {
>> -            yank_unregister_instance(MIGRATION_YANK_INSTANCE);
>> -        }
> 
> Why are you removing this yank_unregister()?
As recommended by Daniel in the previous patchset, most of the stuff in this 
else block is duplicating the contents of the "if (local_error)" block below

    if (local_err) {
        if (!(has_resume && resume)) {
            yank_unregister_instance(MIGRATION_YANK_INSTANCE);
        }

So now, after local_error gets set through error_setg(), it falls to this block 
where yank_unregister() will be called as before. 
> 
>> -        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);
>>          block_cleanup_parameters();
>> -        return;
>>      }
>>  
>>      if (local_err) {
>> @@ -2050,7 +2044,7 @@ 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;
>> @@ -2165,7 +2159,7 @@ 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;
>>      }
>>  
>> @@ -2202,7 +2196,7 @@ 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);
>>      }
>> @@ -2719,6 +2713,7 @@ 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);
>> @@ -2741,8 +2736,9 @@ 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;
>>      }
>> @@ -3232,8 +3228,10 @@ 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;
>>          }
> 
> The rest of the patch looks right to me.
> 
> Later, Juan.
>