When an application reads data from AWS S3 or Alibaba Cloud OSS, it usually has serious performance problems, after all, it is through a remote network. Alluxio can provide a transparent data cache layer, automatic cache needs to read remote OSS/S3 data, but when does Alluxio itself pull remote data? Default all cache? Still on-demand caching? This PPT will introduce Alluxio’s hierarchical storage concept, combined with the ZFS system to maximize performance and reduce application development.
See results of 10x performance in Spark and Hive jobs that are running on AWS S3. Plus, learn how real world user Bazaarvoice implemented a tiered storage architecture for a boost in performance, enabling them to handle data at massive Internet-scale to serve its customers.