Optimizing Application Performance in Large Multi-core Systems
Session information has not yet been published for this event.
One Line Summary
This presentation discusses various performance related kernel patches that can help improving performance and scalability in large multi-core systems and best practices to avoid this type of performance problems in user applications.
As more and more cores are cramming into a single CPU chip, even a commodity dual-socket server can now have dozens of cores/threads available for running applications. To efficiently utilize all the available cores, care must be taken to avoid excessive core-to-core synchronization and cacheline contention from becoming a performance bottleneck. Excessive cacheline contention also has an impact on system power consumption.
This presentation discusses various performance related kernel patches that have gone into the upstream kernel, are pending or being proposed that can help improving performance and scalability in large multi-core systems. It also discuss best practices to avoid this type of performance problems in user applications as well as tools available to diagnose them.
Waiman Long is an experienced software engineer working in the Linux Performance and Scalability team of HP Enterprise Server Group. He is responsible for investigating and resolving performance and scalability issues of the Linux kernel on large multi-node NUMA systems. He is also a major contributor in revamping the Linux kernel synchronization primitives in recent years.
He has multiple years of working experience on Linux, HP-UX and Tru64 UNIX in both the kernel and the C runtime library. He is also an expert in the field of software internationalization.