Posted On: Jan 8, 2019
Today we are introducing partition placement groups, a new Amazon EC2 placement strategy that helps reduce the likelihood of correlated failures for large distributed and replicated workloads such as HDFS, HBase and Cassandra running on EC2. Partition placement groups spread EC2 instances across logical partitions and ensure that instances in different partitions do not share the same underlying hardware, thus containing the impact of hardware failure to a single partition. In addition, partition placement groups offer visibility into the partitions and allow topology aware applications to use this information to make intelligent data replication decisions, increasing data availability and durability.
Partition placement groups are available to customers through Amazon API and CLI at no additional charge and is offered in US East (N. Virginia), US East (Ohio), US West (N. California), US West (Oregon), Asia Pacific (Mumbai), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Canada (Central), EU (Frankfurt), EU (Ireland), EU (London), EU (Paris), South America (São Paulo), Amazon Web Services China (Beijing) region, operated by Sinnet and Amazon Web Services China (Ningxia) region, operated by NWCD.
To learn more about partition placement groups, see the User Guide for EC2 Placement Groups.