Detail View

Kernel samepage merging (KSM) in Linux kernel archive is a memory deduplication scheme that finds duplicate pages and shares the page in order to alleviate memory bottleneck in cloud. However, because the KSM has to scan all pages in memory to find duplicate pages, KSM consumes high CPU cycles and so causes virtual machines (VMs) performance degradation [5]. This degradation of VMs performance is an obstacle in cloud to service real-time applications (i.e. Netflix) [6]. A previous work, CMD [5] proposed page grouping scheme to reduce page comparisons, but it requires special monitoring hardware, XLH [3] enhanced page sharing with the information of guest VM I/O operation. However, the CPU overhead of XLH is still very high - similar to the default KSM. To make KSM more useful, we need an optimization scheme that consume less CPU cycles. Therefore, we first profile the CPU cycle consumption of KSM and the results show that page comparison (28.77%) and page checksum (26.14%) take most of cycles. Based on the results, we propose improved KSM based hash value for cloud computing (IKC) that consumes less CPU cycles than the default KSM. To reduce the number of page comparisons, we apply checksum based RB-tree structure. In addition, IKC decreases page checksum overhead with hardware-accelerated crc32 hash function.

1	INTRODUCTION	5
2	BACKGROUND & PROBLEM of KSM	7
2.1	Kernel Samepage Merging (KSM)	7
2.2	Problem of KSM	9
3	DESIGNS	11
3.1	Overview	13
3.2	Checksum based red-black tree	14
3.3	Advanced checksum hash function	15
4	EVALUATION	16
4.1	Experimental setup	17
4.2	Experimental results	20
4.3	Overhead & Trade off	27
5	RELATED WORK	29
6	CONCLUSION	31
7	REFERENCES	32