OS Scheduling Algorithms for Memory Intensive Workloads in Multi-socket Multi-core servers

TL;DR

This paper introduces new OS scheduling algorithms for multi-socket, multi-core servers that reduce remote memory accesses, significantly improving performance by up to 55% in synthetic workload tests.

Contribution

The paper proposes three novel scheduling algorithms, including an adaptation of the Hungarian algorithm, to optimize thread scheduling based on DRAM access patterns in multi-socket systems.

Findings

Algorithms reduce DRAM access latency by up to 55%.

Higher complexity algorithms yield greater performance gains.

Two algorithms offer a good balance between complexity and performance.

Abstract

Major chip manufacturers have all introduced multicore microprocessors. Multi-socket systems built from these processors are routinely used for running various server applications. Depending on the application that is run on the system, remote memory accesses can impact overall performance. This paper presents a new operating system (OS) scheduling optimization to reduce the impact of such remote memory accesses. By observing the pattern of local and remote DRAM accesses for every thread in each scheduling quantum and applying different algorithms, we come up with a new schedule of threads for the next quantum. This new schedule potentially cuts down remote DRAM accesses for the next scheduling quantum and improves overall performance. We present three such new algorithms of varying complexity followed by an algorithm which is an adaptation of Hungarian algorithm. We used three different synthetic workloads to evaluate the algorithm. We also performed sensitivity analysis with respect to varying DRAM latency. We show that these algorithms can cut down DRAM access latency by up to 55% depending on the algorithm used. The benefit gained from the algorithms is dependent upon their complexity. In general higher the complexity higher is the benefit. Hungarian algorithm results in an optimal solution. We find that two out of four algorithms provide a good trade-off between performance and complexity for the workloads we studied.