مقاله


کد مقاله : 139511231448574966

عنوان مقاله : Towards Accelerating IP Lookups on Commodity PC Routers using Bloom Filter: Proposal of Bloom-Bird

نشریه شماره : 17 Winter 2017

مشاهده شده : 118

فایل های مقاله :


نویسندگان

  نام و نام خانوادگی پست الکترونیک مرتبه علمی مدرک تحصیلی مسئول
1 Bahram Bahrambeigy bahramwhh@gmail.com Graduate M.Sc
2 Mahmood Ahmadi m.ahmadi@razi.ac.ir Assistant Professor PhD
3 Mahmood Fazlali fazlali@sbu.ac.ir Assistant Professor PhD

چکیده مقاله

Nowadays, routers are the main backbone of computer networks specifically the Internet. Moreover, the need for high-performance and high-speed routers has become a fundamental issue due to significant growth of information exchange through the Internet and intranets. On the other hand, flexibility and configurability behind the open-source routers has extended their usage via the networks. Furthermore, after assigning the last remaining IPv4 address block in 2011, development and improvement of IPv6-enabled routers especially the open-sources has become one of the first priorities for network programmers and researchers. In IPv6 because of its 128-bits address space compared to 32-bits in IPv4, much more space and time are required to be stored and searched that might cause a speed bottleneck in lookup of routing tables. Therefore, in this paper, Bird as an example of existing open source router which supports both IPv4 and IPv6 addresses is selected and Bloom-Bird (our improved version of Bird) is proposed which uses an extra stage for its IP lookups using Bloom filter to accelerate IP lookup mechanism. Based on the best of our knowledge this is the first application of Bloom filter on Bird software router. Moreover, false positive errors are handled in an acceptable rate because Bloom-Bird scales its Bloom filter capacity. The Bloom-Bird using real-world IP prefixes and huge number of inserted prefixes into its internal FIB (Forwarding Information Base), shows up to 61% and 56% speedup for IPv4 and IPv6 lookups over standard Bird, respectively. Moreover, using manually generated prefix sets in the best case, up to 93% speedup is gained.