Towards practical page coloring-based multicore cache management

Modern multi-core processors present new resource man-agement challenges due to the subtle interactions of simulta-neously executing processes sharing on-chip resources (par-ticularly the L2 cache). Recent research demonstrates that the operating system may use the page coloring mechanism to control cache partitioning, and consequently to achieve fair and efficient cache utilization. However, page coloring places additional constraints on memory space allocation, which may conflict with application memory needs. Fur-ther, adaptive adjustments of cache partitioning policies in a multi-programmed execution environment may incur sub-stantial overhead for page recoloring (or copying). This paper proposes a hot-page coloring approach— enforcing coloring on only a small set of frequently accessed (or hot) pages for each process. The cost of identifying hot pages online is reduced by leveraging the knowledge of spa-tial locality during a page table scan of access bits. Our re-sults demonstrate that hot page identification and selective coloring can significantly alleviate the coloring-induced ad-verse effects in practice. However, we also reach the some-what negative conclusion that without additional hardware support, adaptive page coloring is only beneficial when re-coloring is performed infrequently (meaning long schedul-ing time quanta in multi-programmed executions)