面向IP流测量的哈希算法研究

A Hash Algorithm for IP Flow Measurement

为了解决计算资源和高速网络流量之间的矛盾,需要对IP流进行抽样或负载均衡等处理,而哈希算法是资源代价的核心.首先提出评价哈希算法性能的随机测度;其次从理论上证明比特之间异或运算和位移运算能够提高哈希值的随机特性,提出比特流之间哈希算法的原则;然后分析IP报文的4个字段:源IP、宿IP、源端口和宿端口的特性,由此提出相关的哈希算法;最后使用CERNET主干流量和PMA的数据验证算法的性能,并与IPSX和CRC32算法进行比较.研究表明,基于异或、位移原则的比特流哈希算法的执行效率和哈希值的均匀性两方面具有较好的性质,能够满足高速网络流量测量需求.

In order to solve the problems with computing resource and high-speed network traffic, it is necessary to deal with the network traffic by some measuring technologies, such as sampling measurement and load balance, etc, while the hash algorithm is one of the key measuring technologies. In this paper, firstly, a random metric is provided to evaluate the performance of the hash algorithms. Secondly, the randomicity of XOR and shift operations are analyzed, and it is proved that the two operations can improve the bit randomicity. Thirdly, this paper analyzes the four fields of IP packet, such as source IP, destination IP, source port, and destination port, and a hash algorithm named XOR_SHIFT is provided based on the analysis. Finally, using the CERNET backbone traffic and PMA traffic, this paper analyzes the character of the XOR_SHIFT hash algorithm and compares with the performance among XOR_SHIFT, IPSX and CRC32 hash algorithms. This study shows that the XOR_SHIFT hash function provided in this paper has two advantages: algorithm performance and hash randomicity, and it can be applied to measure the high-speed network traffic.