Postgres 18 introduces Asynchronous I/O (AIO) that can dramatically improve read performance, especially in the cloud. Learn how these changes and the new io_method setting work and see why our benchmark results show that io_uring is the recommended setting for maximizing I/O performance in Postgres 18 over the default setting 'worker'.

pganalyze's platform is a resource for database administrators, software engineers, and PostgreSQL users, offering insights into database performance optimization, query tuning, and database monitoring. Through articles, tutorials, and case studies, pganalyze offers insights into PostgreSQL internals, query execution plans, and database indexing strategies. Readers can learn about PostgreSQL configuration, performance troubleshooting techniques, and database optimization best practices to improve the efficiency and reliability of their PostgreSQL deployments. Additionally, pganalyze provides updates on the latest PostgreSQL releases, database management tools, and industry trends to help users stay informed and maximize the performance of their PostgreSQL databases.

pganalyze

Postgres 18 introduces asynchronous I/O to boost read performance, especially in cloud environments with latency issues. While write operations remain synchronous, async reads enable substantial performance gains. The new 'io_method' setting offers choices like 'worker' and 'io_uring', with benchmarks showing up to 2-3x better throughput for reads compared to previous versions. Future versions might extend async capabilities to write operations.

Waiting for Postgres 18: Accelerating Disk Reads with Asynchronous I/O

Heads Up: Async I/O makes I/O timing information hard to interpret