Ben Vandiver, S. Prasad, Pratibha Rana, Eden Zik, Amin Saeidi, Pratyush Parimal, Styliani Pantela, J. Dave
{"title":"Eon Mode: Bringing the Vertica Columnar Database to the Cloud","authors":"Ben Vandiver, S. Prasad, Pratibha Rana, Eden Zik, Amin Saeidi, Pratyush Parimal, Styliani Pantela, J. Dave","doi":"10.1145/3183713.3196938","DOIUrl":null,"url":null,"abstract":"The Vertica Analytic Database is a powerful tool for high performance, large scale SQL analytics. Historically, Vertica has managed direct-attached disk for performance and reliability, at a cost of product complexity and scalability. Eon mode is a new architecture for Vertica that places the data on a reliable shared storage, matching the original architecture's performance on existing workloads and supporting new workloads. While the design reuses Vertica's optimizer and execution engine, the metadata, storage, and fault tolerance mechanisms are re-architected to enable and take advantage of shared storage. A sharding mechanism distributes load over the nodes while retaining the capability of running node-local table joins. Running on Amazon EC2 compute and S3 storage, Eon mode demonstrates good performance, superior scalability, and robust operational behavior. With these improvements, Vertica delivers on the promise of cloud economics, consuming only the compute and storage resources needed, while supporting efficient elasticity.","PeriodicalId":20430,"journal":{"name":"Proceedings of the 2018 International Conference on Management of Data","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2018-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"14","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2018 International Conference on Management of Data","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3183713.3196938","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 14
Abstract
The Vertica Analytic Database is a powerful tool for high performance, large scale SQL analytics. Historically, Vertica has managed direct-attached disk for performance and reliability, at a cost of product complexity and scalability. Eon mode is a new architecture for Vertica that places the data on a reliable shared storage, matching the original architecture's performance on existing workloads and supporting new workloads. While the design reuses Vertica's optimizer and execution engine, the metadata, storage, and fault tolerance mechanisms are re-architected to enable and take advantage of shared storage. A sharding mechanism distributes load over the nodes while retaining the capability of running node-local table joins. Running on Amazon EC2 compute and S3 storage, Eon mode demonstrates good performance, superior scalability, and robust operational behavior. With these improvements, Vertica delivers on the promise of cloud economics, consuming only the compute and storage resources needed, while supporting efficient elasticity.