In this test, the configuration changes that PGTune recommended increased throughput (transactions per second) by 41.9%. Result: OtterTune more than doubles performance (throughput) We ran the tests on an Amazon db.m5.4xlarge RDS instance equipped with:įor PGTune, we applied the configuration recommended by PGTune to the database: max_connections = 300 Specifically, for Amazon RDS PostgreSQL, we optimized for the xact_commit metric (the number of transaction commits in the database). We collected runtime metrics from the database, and calculated the throughput based on those metrics. To run the test, we used the OLTP-bench framework to run the TPC-C benchmark, a well-known transactional workload. To help answer those questions, we ran an experiment to test Amazon RDS PostgreSQL performance with three database configurations: a) Default Amazon RDS knob settings b) Knob setting recommendations from PGTune c) Knob setting recommendations from OtterTune’s machine learning algorithms The question you’re probably not asking (yet) is “Can machine learning auto-tune my database knob settings to optimize its performance?” ![]() ![]() The question you’re probably asking is “how far off the mark could my Amazon RDS knob settings be?” Putting Amazon RDS PostgreSQL knob settings to the test If you run Amazon RDS PostgreSQL and you lack (1) or (2) above, or if your workload changes over time (thus requiring re-tuning), you’ll likely pay higher cloud costs than you ought to for your database. Time to iteratively make changes and test the impact of the change on performance until it is optimized (i.e., trial-and-error). ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |