Amazon Redshift now delivers better cold query performance by significantly improving compilation times
Amazon Redshift now processes queries 2x faster when they need to be compiled. This improvement gives you better query performance when you create a new Redshift cluster, onboard a new workload on an existing cluster, or after a software update of an existing cluster. These query performance improvements are available at no extra charge to you, and no action is needed to enable it on your clusters.
With this update, query compilations are now scaled to a serverless compilation service beyond the compute resources of the leader node of your cluster. We are also releasing an unlimited cache to store compiled objects to increase cache hits, from 99.60% to 99.95%, when your mission-critical queries are submitted to Redshift.
When queries are sent to Amazon Redshift, the query execution engine compiles the query into machine code and distributes it to the cluster nodes. The compiled code executes faster because it eliminates the overhead of using an interpreter. For a new cluster with no code cache or after an existing cluster is upgraded with the latest release, code cache is flushed, and queries must undergo query compilation. As a result, the latency of a query may vary, which may not meet the requirements of some workloads. With this update, unlimited cache minimizes the need to compile code, and when compilation is needed, a scalable compilation farm compiles it in parallel to speed up your workloads. The magnitude of workload speed up depends on its complexity and concurrency. To learn more about code compilation, see Query Processing under the Database developer guide.
These query performance improvements are now automatically enabled with release number 1.0.13751 in US East (Ohio), US East (N. Virginia), US West (N. California), US West (Oregon), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), EU (Frankfurt), EU (Ireland), and EU (London) regions.