A deep reinforcement learning framework with meta-learning, safety constraints, and online updating tunes learned index parameters, cutting runtime by up to 98% and raising throughput 17x in reported experiments.
Learning to Optimize LSM-trees: Towards A Reinforcement Learning based Key-Value Store for Dynamic Workloads
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
LSM-trees are widely adopted as the storage backend of key-value stores. However, optimizing the system performance under dynamic workloads has not been sufficiently studied or evaluated in previous work. To fill the gap, we present RusKey, a key-value store with the following new features: (1) RusKey is a first attempt to orchestrate LSM-tree structures online to enable robust performance under the context of dynamic workloads; (2) RusKey is the first study to use Reinforcement Learning (RL) to guide LSM-tree transformations; (3) RusKey includes a new LSM-tree design, named FLSM-tree, for an efficient transition between different compaction policies -- the bottleneck of dynamic key-value stores. We justify the superiority of the new design with theoretical analysis; (4) RusKey requires no prior workload knowledge for system adjustment, in contrast to state-of-the-art techniques. Experiments show that RusKey exhibits strong performance robustness in diverse workloads, achieving up to 4x better end-to-end performance than the RocksDB system under various settings.
citation-role summary
background 1
citation-polarity summary
fields
cs.DB 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A New Paradigm in Tuning Learned Indexes: A Reinforcement Learning Enhanced Approach
A deep reinforcement learning framework with meta-learning, safety constraints, and online updating tunes learned index parameters, cutting runtime by up to 98% and raising throughput 17x in reported experiments.