Accelerating forex trading system through transaction log compression

Abstract

In this paper, we propose the hardware architecture for high-speed transaction logging of forex trading system. In forex trading market, the trading volume of currencies is growing larger every year. In order to provide real-time processing of large volume and high availability service, we focused on the two types of the workload, where the bottleneck occurs, and conducted workload analysis. The bottleneck between the application server and the internal hard disk is caused by the overhead from storing the transaction logs, due to the bandwidth limitation of a hard disk. Our key idea is to suppress an overhead of the transaction logging through the compression of the transaction logs. Implementation result demonstrates the feasibility of our proposal for increasing the bandwidth through the log compression.

Energy Efficient and Low-Cost Server Architecture for Hadoop Storage Appliance

“…They verified the possibilities of realization on hardware by comparing area, frequency performance of LZRW (Lempel-Ziv Ross Williams) [19]. Jang et al improved the transfer logging speed of the forex trading system by implementation of the LZ4 algorithm on hardware compression accelerator [12]. However, the study of the LZ4 algorithm to address the power and cost issues of Hadoop is still needed.…”

“…LZ4 created by Yan Collet is a lossy, dictionary-based, and byte-oriented compression algorithm [11,12]. Since the LZ4 is based on LZ77 compression algorithm, dictionary is used for compression.…”

“…The LZ4 algorithm is used in Solid-State Driver(SSD) to improve the storage performance and lifetime [13]. And LZ4 is also used in forex trading system to improve the transfer logging speed [12].…”