CGPTuner: a contextual gaussian process bandit approach for the automatic tuning of IT configurations under varying workload conditions

AbstractProperly selecting the configuration of a database management system (DBMS) is essential to increase performance and reduce costs. However, the task is astonishingly tricky due to a large number of tunable configuration parameters and their inter-dependencies. Also, the optimal configuration depends upon the workload to which the DBMS is exposed. To extract the full potential of a DBMS, we must also consider the entire IT stack on which the DBMS is running, comprising layers like the Java virtual machine, the operating system and the physical machine. Each layer offers a multitude of parameters that we should take into account. The available parameters vary as new software versions are released, making it impractical to rely on historical knowledge bases. We present a novel tuning approach for the DBMS configuration auto-tuning that quickly finds a well-performing configuration of an IT stack and adapts it to workload variations, without having to rely on a knowledge base. We evaluate the proposed approach using the Cassandra and MongoDB DBMSs, showing that it adjusts the suggested configuration to the observed workload and is portable across different IT applications. We try to minimise the memory consumption without increasing the response time, showing that the proposed approach reduces the response time and increases the memory requirements only under heavy-load conditions, reducing it again when the load decreases.