无忧视频

Databases鈥攅specially large-scale databases鈥攁re the 鈥渞eactor core鈥� powering today鈥檚 software services. The performance of large databases depends on many interactions between internal parameters and the varying external load they鈥檙e asked to handle. Our goal is to improve both the 鈥渟ensing鈥� and the 鈥渃ontrol鈥� of Cassandra, a large-scale open-source database, adapting its operation based on changing conditions. The pipeline will use machine learning to guide parameter-tuning for the database, depending on operational and query patterns.