MedusaVM: Decentralizing Virtual Memory System for Multithreaded Applications on Many-core

Miao Cai, Shenming Liu, Weiyong Yang, Hao Huang

Abstract: Virtual memory system multiplexes the single physical memory for multiple running processes with two centralized resources, i.e., virtual memory space and page table hierarchy. However, for multithreaded applications running a single address space, current centralized VM system design encounters severe scalability bottlenecks and significantly impedes the application speedup increment on many-core systems. This paper proposes a novel VM system called MedusaVM to scale VM system to many cores. To this end, MedusaVM partitions the global virtual memory space and page table tree in a memory-efficient way, eliminating performance interference and lock contention between cores. Moreover, MedusaVM also provides a traditional shared memory interface for multithreaded applications. Our prototype system is implemented based on Linux kernel 4.4.0 and glibc 2.23. Experimental results evaluated on a 32-core machine demonstrate that MedusaVM scales much better than Linux kernel and uses 22 $$\times $$ less memory compared with the state-of-art approach. For microbenchmarks experiments, MedusaVM achieves nearly linear performance speedup. In multithreaded applications Metis and Psearchy, MedusaVM also significantly outperforms Linux kernel by up to a factor of 2.5 $$\times $$ .