Multi-dimensional auto scaling of container-based clusters

A system comprising:

• one or more processors;
• and
• at least one memory, the one or more processors and the at least one memory configured to:
• train a model on a plurality of training data instances to generate the plurality of candidate configurations, wherein each of the plurality of training data instances comprises:
• a training input comprising information about configuration settings applied to the container-based cluster and information about one or more loads generated for the container-based cluster;
• and
• a training output comprising at least one of performance metrics or resource utilization metrics gathered for the container-based cluster when the corresponding configuration settings are applied and the corresponding one or more loads are generated;
• determine, by a virtualization management platform configured to manage components of a container-based cluster, a current state of the container-based cluster;
• determine, by the virtualization management platform, at least one of performance metrics or resource utilization metrics for the container-based cluster based on the current state of the container-based cluster;
• process, with the model, the current state and at least one of the performance metrics or the resource utilization metrics and thereby generate the plurality of candidate configurations;
• calculate a reward score for each of the plurality of candidate configurations;
• select a target configuration from the plurality of candidate configurations based on the reward score of the target configuration;
• and
• adjust configuration settings for the container-based cluster based on the target configuration to alter the current state of the container-based cluster.

A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations for determining a target configuration for a container-based cluster, the operations comprising:

• training a model on a plurality of training data instances to generate the plurality of candidate configurations, wherein each of the plurality of training data instances comprises:
• a training input comprising information about configuration settings applied to the container-based cluster and information about one or more loads generated for the container-based cluster;
• and
• a training output comprising at least one of performance metrics or resource utilization metrics gathered for the container-based cluster when the corresponding configuration settings are applied and the corresponding one or more loads are generated;
• determining, by a virtualization management platform configured to manage components of the container-based cluster, a current state of the container-based cluster;
• determining, by the virtualization management platform, at least one of performance metrics or resource utilization metrics for the container-based cluster based on the current state of the container-based cluster;
• processing, the model, the current state and at least one of the performance metrics or the resource utilization metrics and thereby generate the plurality of candidate configurations;
• calculating a reward score for each of the plurality of candidate configurations;
• selecting a target configuration from the plurality of candidate configurations based on the reward score of the target configuration;
• and
• adjusting configuration settings for the container-based cluster based on the target configuration to alter the current state of the container-based cluster.