A Perfect Knob to Scale Thread Pool on Runtime

What is it about?

This article focuses on improving scalability and performance of software intensive systems or server-side-apps. We presented a workload profiling based frequency-oriented thread pool system, that focused on the knob to scale thread pool on runtime. The knob is the combination of request size (service time) and the request rate to represent the real load on the server. The real load is used to set an optimal thread pool size of frequency-oriented thread pool system on runtime. We enhances on how server applications manage their thread pools to handle changing workloads more efficiently. Specifically, it proposes an enhanced thread pool system that doesn't just rely on how many requests are coming in (request rate), but also considers how heavy each request is (request size or service time). This dual consideration helps scale the thread pool more accurately during runtime. The paper compares this new system with Oracle's thread pool system using a simulator and shows better results in response time and throughput.

Featured Image

Photo by Todd Rhines on Unsplash

Photo by Todd Rhines on Unsplash

Why is it important?

Our work improves the scalability and performance of server-side applications including web-servers, application servers, IoT servers, Cloud servers etc. Consequently, the clients of the service will get prompt response times along with increased throughput of servers.

Perspectives