A Element based Framework The NFs we discuss above either hardware thread based

A element based framework the nfs we discuss above

This preview shows page 4 - 6 out of 6 pages.

A. Element-based Framework The NFs we discuss above, either hardware, thread-based or VM-based, which vertically integrate basic modules (e.g., pro- tocol parse, encryption/decryption), can independently com- plete a particular packet processing task. On the other hand, Slick [3] takes another way which allows the operators to implement NFs as a chain of lightweight functions (e.g, checksums) which are placed across the network for reuse. These lightweight functions, referred as elements in Slick, are able to be reconfigured at runtime. The placement consists of two steps. The first step is to consolidate elements if necessary. The Slick controller decide whether to consolidate contiguous elements onto a single machine or distribute them across multiple machines based on each element’s inflation factor, which is defined as log ( f out / f in ) where f out and f in denote its output and input traffic volumes respectively. To reduce the link bandwidth consumption, it is intuitive to place elements with negative inflation factors near the sources and others near the desti- nation. Therefore, the controller breaks the element list into sub-lists, each of which is placed in a single machine, such that the bandwidth consumption is minimized. The second step is to place consolidated elements. The placement strategy is that consolidated elements with negative (positive) inflation factors are placed onto the node on the longest common path of all traffic closed to sources (destinations). The rest consolidated elements are placed in a way such that the average path length for all traffic is minimized. Unlike CoMb [25] using monolithic consolidating, the placement strategy of Slick is partial consolidating. B. Distributed NFs Nowadays, most NFs are resided at certain locations in the network, each responsible for a static portion of the flow space. With ever growing network scale and traffic volume, these centralized NFs become the performance bottleneck. Moreover, steering traffic to them incurs non-trivial overhead.
Image of page 4

Subscribe to view the full document.

CSamp [27] is a brave endeavour towards scalability by employing a system-wide approach to coordinate distributed NFs for fined-grained flow level monitoring. In CSamp, the monitor NFs are implemented as applications inside routers. To avoid duplicated sampling due to multiple monitor NFs on the routing path, CSamp uses a hash-based packet selection to achieve the coordination while obviating the overhead of explicit communication. When these distributed NFs are placed, a network-wide goal, such as maximizing the coverage, is achieved by distributing the workload to monitor NFs across the network while respecting the resource constraints. Apart from distributed monitoring, distributed redundant elimination [2] and distributed IDS/IPS [26] have already been implemented. C. Host-based Framework The NFs we have talked about are all residing inside the network, and that is why we also call them ”middleboxes” too.
Image of page 5
Image of page 6
  • Spring '16

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern

Ask Expert Tutors You can ask bonus questions You can ask questions ( expire soon) You can ask questions (will expire )
Answers in as fast as 15 minutes