MySQL AI User Guide
You can monitor the status of AutoML by querying the
rapid_ml_status variable or by querying the
ML_STATUS column of the
performance_schema.rpd_nodes table.
The rapid_ml_status variable provides the
status of AutoML. Possible values are ON
and OFF.
ON: AutoML is up and running.
OFF: AutoML is down.
The following example queries the
rapid_ml_status status variable directly.
mysql> SHOW GLOBAL STATUS LIKE 'rapid_ml_status';
+-----------------+-------+
| Variable_name | Value |
+-----------------+-------+
| rapid_ml_status | ON |
+-----------------+-------+
The following example queries the
rapid_ml_status status through the
performance_schema.global_status
table.
mysql> SELECT VARIABLE_NAME, VARIABLE_VALUE
FROM performance_schema.global_status
WHERE VARIABLE_NAME LIKE 'rapid_ml_status';
+-----------------+----------------+
| VARIABLE_NAME | VARIABLE_VALUE |
+-----------------+----------------+
| rapid_ml_status | ON |
+-----------------+----------------+
The MySQL AI plugin writes AutoML status information to the
ML_STATUS column of the
performance_schema.rpd_nodes table after each
AutoML query. Possible values include:
UNAVAIL_MLSTATE: AutoML is not
available.
AVAIL_MLSTATE: AutoML is available.
DOWN_MLSTATE: AutoML is down.
ML_STATUS is reported for each node.
You can query the ML_STATUS column of the
performance_schema.rpd_nodes table.
To following example retrieves ID,
STATUS, and ML_STATUS for
each node from the
performance_schema.rpd_nodes table:
mysql> SELECT ID, STATUS, ML_STATUS FROM performance_schema.rpd_nodes;
+----+---------------+---------------+
| ID | STATUS | ML_STATUS |
+----+---------------+---------------+
| 0 | AVAIL_RNSTATE | AVAIL_MLSTATE |
+----+---------------+---------------+
If rapid_ml_status is OFF
or ML_STATUS reports
DOWN_MLSTATE for any node, you can restart
the MySQL server and Cluster. Be aware that restarting
interrupts any analytics queries that are running.
See the following to learn more:
Review Machine Learning Use Cases to create machine learning models with sample datasets.