Robust TCP Reassembly with a Hardware-Based Solution for Backbone Traffic

Memory-efficient TCP reassembly using FPGA

“…In this section, we do not compare our system with the system in [3] because that system use the method of out-of-order matching, and thus do not need to reorder out-of-sequence packets. We assume the network traffic conforms to the CAIDA_10G in [1]. These statistics are recorded by the Cooperative Association for Internet Data Analysis in 2009.…”

“…The length of a string, which matches an RE, cannot be priory known; Therefore, this technique is not applicable to RE. In another approach [1], the authors use a buffer for each out-ofsequence connection. The size of the buffer is fixed and every outof-sequence connection has only one buffer.…”

“…The reason that they decide to supports only one hole is based on their studies that more than 95% of out-ofsequence connections contain only one hole. However, newer studies in [1] show that number of 2-hole connections are 7.3% of out-of-sequence connections in CAIDA_10G, and even 17.8% in WA_1G. In this design, the buffer information is compressed to be stored in the connection record, so it is difficult to scale up the system, such as supporting multi-hole connections.…”

“…Turn back to the problem of number of holes simultaneously exist in a connection. Studies [1] show that about 99% out-of-sequence connections have less than 4 concurrent holes. If a connection has too many holes, buffering all out-ofsequence packets is not as efficient as dropping the packets so that the source machine will retransmit packets to fill some holes.…”

“…Moreover the network speed can reach 1Gbps or more, these NIDS systems can drop the packets. To overcome these problems, several researches has be proceeded to reassemble out-ofsequence TCP packets [1,3,4,5]. In these researches, FPGA is usually used as the development platform because it supports high speed processing and easy to update.…”