Packet Classification using Tuple Space Search Author V

Packet Classification using Tuple Space Search Author: V. Srinivasan, S. Suri, G. Vargheset Publisher: ACM SIGCOMM 1999 Presenter: Sih-An Pan Date: 2013/11/27

Tuple Space Search n Our scheme is motivated by the observation that while filter databases contain many different prefixes or ranges, the number of distinct prefix lengths tends to be small. n Suppose we have a filter database FD with N filters, and these filters result in m distinct tuples. n Since m tends to be much smaller than N in practice, even a linear search through the tuple set is likely to greatly outperform the linear search through the filter database.

Tuple Space Search n We can define a tuple for each combination of field length, and call the resulting set tuple space. n By concatenating these bits in order we can create a hash key, which can then be used to map filters of that tuple into a hash table.

Tuple Space Search n The port numbers, however, are often specified using ranges, and the number of bits specified is not clear. n To get around this, we define the length of a port range to be its nesting level. Range. ID Level 0 1 2

Tuple Pruning Algorithm Packet = {0000, 01*} Source Trie Destination Trie Source Tuple List = {[0, 0], [0, 4], [2, 3], [4, 1], [4, 4]} Destination Tuple List = {[0, 0], [4, 1], [3, 2]} Intersected Tuple List = {[0, 0], [4, 1]}

Tuple Pruning Algorithm

Markers and Precomputation •

Markers and Precomputation

Markers

Precomputation

Rectangle Search n The search terminates when the we reach the rightmost column or the first row. n Since there are W rows and W columns, the number of probes needed is at most 2 W - 1

Rectangle Search

Storage Efficiency

Throughput (Worst Case)

Throughput (Avg. Case)