Saturday, December 11, 2010

How to Build DPI Products? (Part V - Regular Expression Matching)

 
Continuing my "How to Build a DPI product?" series (see previous parts - I, II, III, IV) this time a paper by Fang Yu, UC Berkeley;  Zhifeng Chen Google Inc.; Yanlei Diao University of Massachusetts, Amherst (picture); T. V. Lakshman Bell Laboratories and Randy H. Katz, UC Berkeley.

See "Fast and Memory-Efficient Regular Expression Matching for Deep Packet Inspection Matching for Deep Packet Inspection" - here.

ABSTRACT

Packet content scanning at high speed has become extremely important due to its applications in network security, network monitoring, HTTP load balancing, etc. In content scanning, the packet payload is compared against a set of patterns specified as regular expressions.

In this paper, we first show that memory requirements using traditional methods are prohibitively high for many patterns used in packet scanning applications. We then propose regular expression rewrite techniques that can effectively reduce memory usage. Further, we develop a grouping scheme that can strategically compile a set of regular expressions into several engines, resulting in remarkable improvement of regular expression matching speed without much increase in memory usage.

We implement a new DFA-based packet scanner using the above techniques. Our experimental results using real-world traffic and patterns show that our implementation achieves a factor of 12 to 42 performance improvement over a commonly used DFAbased scanner. Compared to the state-of-art NFA-based implementation, our DFA-based packet scanner achieves 50 to 700 times speedup.

19 comments:

  1. Thank you for taking the time to publish this information very useful!
    data scientist training in hyderabad

    ReplyDelete
  2. This is an excellent post I seen thanks to share it. It is really what I wanted to see hope in future you will continue for sharing such a excellent post.
    data science course

    ReplyDelete
  3. This comment has been removed by the author.

    ReplyDelete

  4. Infycle Technologies, the top software training institute and placement center in Chennai offers the best
    Data science training in Chennai
    for freshers, students, and tech professionals at the best offers. In addition to Digital Marketing, other in-demand courses such as DevOps, Big Data, Cyber Security, Python, Selenium, Big Data, Java, Power BI, Oracle will also be trained with 100% practical classes. Call 7504633633 to get more info and a free demo.

    ReplyDelete
  5. Tableau training institute in Hyderabad can be a ticket to your fortunate tableau career.Dashboards, tableau desktop, Tableau online,charts,and many other key features of tableau this is best for you have interest visit my website link http://tableautrainings.in/

    ReplyDelete
  6. React JS Training in Hyderabad

    ReplyDelete
  7. HI IAM CHARAN Tableau training institute in Hyderabad can be a ticket to your fortunate tableau career.Dashboards, tableau desktop, Tableau online,charts,and many other key features of tableau this is best for you have interest

    ReplyDelete
  8. Very Nice Blog…Thanks for sharing this information with us. Here am sharing some information about training institute.Andriod App Development Course in Chennai

    ReplyDelete
  9. This comment has been removed by the author.

    ReplyDelete
  10. A React course is a training program that teaches you how to use React, a JavaScript library for building user interfaces. React is one of the most popular JavaScript libraries in the world, and it is used by many large companies, such as Facebook, Airbnb, and Netflix.

    A React course typically covers the following topics:

    The basics of React, including components, state, and props
    Advanced React topics, such as routing, Redux, and testing
    How to build real-world applications with React
    The best React courses will be well-structured, engaging, and easy to follow. They will also provide you with plenty of opportunities to practice what you learn.
    reactgeeks

    ReplyDelete
  11. Thank you for sharing This is a wonderful post

    ReplyDelete