Run Petabyte-Scale Clusters on Amazon Elasticsearch Service Using I3 instances
Amazon Elasticsearch Service now supports I3 instances, allowing you to store up to 1.5 petabytes of data in a single Elasticsearch cluster for large log analytics workloads. Using I3 instances, you can store up to 15 terabytes of data in each node and gain up to 3x increase in indexing throughput for less than 50% of the cost of the previous generation I2 instances.
With petabyte-scale support, you can log a lot more data than before and significantly expand the duration for which you retain data for analytics. In addition, the increased performance of I3 instances (up to 3.3 million IOPS and 16 GB/second of sequential disk throughput) enables you to support more demanding workloads, delivering higher ingestion rates and lower query response times compared to other instance types. Also, with the enhanced networking offered by I3 instances, shard relocation is faster, which reduces the time for cluster updates and instance recovery. You can also enable Amazon Elasticsearch Service’s encryption-at-rest capability on the I3 instances. Furthermore, with the increased storage capacity per node you can do more with fewer instances, which can translate into additional cost savings. To learn more, see the Amazon Elasticsearch Service Developer Guide and the Amazon Elasticsearch Service pricing page.
I3 instances for Amazon Elasticsearch Service are available in 14 regions globally: US East (N. Virginia), US East (Ohio), US West (Oregon), US West (N. California), Canada (Central), South America (Sao Paulo), EU (Ireland), EU (London), EU (Frankfurt), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Asia Pacific (Seoul), and Asia Pacific (Mumbai).