"Agoda started utilizing ChatGPT to optimize SQL stored procedures (SP) as part of their CI/CD process. After introducing the automated LLM-assisted step, the company observed shortened stored procedure optimization times, which lightened the load on DB developers. Agora works on making ChatGPT more accessible for SP optimization outside of the CI/CD pipeline. Agoda's DB developers have been spending approximately 366 person-days on SP optimization, of which 320 person-days were dedicated to analyzing SP changes that resulted in performance test failures, reported by the CI/CD pipeline."
"To reduce manual effort and accelerate SP tuning, we integrated GPT into our development workflow. Our goal was to reduce manual review time, speed up MR approvals, and give developers access to self-service tools for performance tuning. Inefficient SPs and SQL in general impacted performance, cost, and scalability for the company, potentially resulting in slow response times and frustrated users, higher resource utilization, and scalability bottlenecks."
Agoda integrated ChatGPT into the CI/CD pipeline to generate automated optimization recommendations for SQL stored procedures. The LLM step submits stored procedure SQL, table schemas, indexes, and performance test reports to produce rewritten queries and index-change suggestions. Engineers previously spent about 366 person-days on SP tuning, with 320 person-days analyzing CI/CD-reported performance test failures and a 90th-percentile MR approval time of 4.1 hours. The integration reduced manual review effort, shortened optimization times, and eased DB developer workload. Efforts are underway to expand LLM-assisted tuning outside CI/CD to enable developer self-service for performance improvements.
Read at InfoQ
Unable to calculate read time
Collection
[
|
...
]