CAPES: Unsupervised Storage Performance Tuning Using
Neural Network-Based Deep Reinforcement Learning
SessionPerformance Tuning
Event Type
Paper
Performance
TimeWednesday, November 15th4pm -
4:30pm
Location301-302-303
DescriptionParameter tuning is an important task of storage
performance optimization. Current practice usually
involves numerous tweak-benchmark cycles that are slow
and costly. We present CAPES, a model-less deep
reinforcement learning-based unsupervised parameter
tuning system driven by a deep neural network (DNN). It
is designed to find optimal values for computer systems
that have tunable parameters, from a simple
client-server system to a large data center, where human
tuning can be costly and often cannot achieve optimal
performance. CAPES takes periodic measurements of a
target computer system's state, and trains a DNN which
uses Q-learning to suggest changes to the system's
current parameter values. CAPES is minimally intrusive,
and can be deployed into a production system to collect
training data and suggest tuning actions during the
system's daily operation. Evaluation of a prototype on a
Lustre file system demonstrates an increase in I/O
throughput up to 45% at saturation point.
Download PDF:
here
