"AWS recently updated Amazon Aurora Serverless with a new platform version that improves scaling behavior and runtime efficiency. According to the cloud provider, capacity can now scale up about 45% faster during demand spikes, and database performance improves by up to 30% through better resource scheduling and workload-aware scaling decisions."
"Platform version 4 introduces improved runtime efficiency and a smarter scaling algorithm, enabling faster capacity scaling and higher database performance for Aurora Serverless clusters. Generally available for four years, Amazon Aurora Serverless is an on-demand, automatically scaling configuration for Aurora that adjusts database capacity based on application demand."
"For both database engines supported on serverless, Aurora MySQL and Aurora PostgreSQL, platform version 4 delivers 27-34% higher NOPM compared to platform version 3. A HammerDB TPROC-C benchmark was used to measure performance across three Aurora Serverless platform versions with 1,024 virtual users."
"A Sysbench benchmark compared three Aurora Serverless clusters running platform versions 2, 3, and 4, with identical capacity settings ranging from 0.5 to 256 ACUs and faster scaling enabled. After loading 250 tables totaling 16 GB, a read-heavy workload executed 50 million queries with 512 threads. Evaluating the CloudWatch ServerlessDatabaseCapacity metric to compare capacity across versions, Yan, Kurakula, and Safa conclude:"
Amazon Aurora Serverless received a new platform version that improves scaling behavior and runtime efficiency. Capacity can scale up about 45% faster during demand spikes. Database performance improves by up to 30% through better resource scheduling and workload-aware scaling decisions. Platform version 4 adds improved runtime efficiency and a smarter scaling algorithm for faster capacity scaling and higher performance. Aurora Serverless is an on-demand, automatically scaling Aurora configuration that adjusts capacity based on application demand and can scale down to zero when idle. Benchmarks using HammerDB TPROC-C and Sysbench compare platform versions 2, 3, and 4 under identical capacity settings and workloads, showing higher throughput and better results for platform version 4.
Read at InfoQ
Unable to calculate read time
Collection
[
|
...
]