Benchmarking Methodology for IPv6 Transition Technologies

Bakai

2017

CIT

In the current phase of the IPv6 transition, it is a typical situation that IPv6-only clients should be enabled to communicate with IPv4-only servers. The DNS64+NAT64 tool suite is an excellent solution to this problem. Although several free software DNS64 implementations exist, we point out that there is room for further high performance and computation efficient multithreaded DNS64 implementations. MTD64 was designed to be able to utilize several CPU cores. Whereas MTD64 outperformed BIND more than five times, two critical issues (memory leaking and potential vulnerability to DoS attacks) were identified. Therefore MTD64 was redesigned under a new name: mtd64-ng (not capitalized). This paper is about the design, implementation and initial performance estimation of mtd64-ng. The usage of object oriented decomposition and the RAII (Resource Acquisition Is Initialization) idiom ensures that raw, sensitive resources (e.g. memory, sockets) are always released and it greatly simplifies exception handling. Using the new features of the C++11 standard enabled us to write more efficient and better readable code. The performance of mtd64-ng is compared to that of BIND and MTD64 and it is found that mtd64-ng outperforms even its predecessor, MTD64. ACM CCS (2012) Classification

Section: Introductionmentioning

confidence: 78%

Section: Performance Estimation Methodsmentioning

confidence: 99%

“…The Internet Draft is also required to perform a so called self-test to ensure that the tester itself is not a bottleneck, see subsection 9.2.1 of [7].…”

Section: Performance Estimation Methodsmentioning

confidence: 99%

Section: Initial Performance Estimationmentioning

confidence: 99%

“…This choice is justified in [14]. Thus the timeout value for the self-test was set to 0.25 second conforming to subsection 9.2.1 of [7].…”

Section: Measurements and Parametersmentioning

confidence: 99%

See 3 more Smart Citations

Design, Implementation and Performance Estimation of mtd64-ng, a New Tiny DNS64 Proxy

Bakai

2017

CIT

Towards the scalability comparison of the Jool implementation of the 464XLAT and of the MAP‐T IPv4aaS technologies

Nagy

2022

Int J Communication

Summary 464XLAT and MAP‐T are both IPv4‐as‐a‐Service technologies aiming to provide IPv4 service to the customers, while ISPs use only IPv6 in their access and core networks. The ISPs need to consider several different aspects, like scalability, compatibility with the applications, and efficiency of public IPv4 address sharing, when selecting the most appropriate IPv4aaS technology for their specific application scenario. The aim of our current effort is to make an initial step towards the comparison of the scalability of the 464XLAT and of the MAP‐T IPv4aaS technologies. We point out the gap between the most desirable measurement method and the available testing tools. We measure the scale‐up of the performance of the Jool implementation of 464XLAT and MAP‐T as a function of the number of active CPU cores up to 16 cores using an available testing tool called dns64perf++. We fully disclose our detailed measurement setup and our results, as well as the analysis of our results pointing out the bottleneck during the measurements. We also outline the directions of our future research

Benchmarking stateless NAT64 implementations with a standard tester

2020

Telecommun Syst

Self Cite

RFC 5180, the IPv6 update of RFC 2544, declared IPv6 transition technologies out of its scope. RFC 8219 defined a benchmarking methodology for IPv6 transition technologies including stateless NAT64 (more properly called SIIT) in the category of single translation solutions. Whereas several research papers have dealt with the performance of different stateful NAT64 implementations, none of them used RFC 8219 compliant measurements or addressed stateless NAT64 implementations. In this paper, we show, how stateless NAT64 implementations can be benchmarked carrying out the most important tests recommended by RFC 8219 without a special purpose NAT64 Tester, using simply an RFC 2544/RFC 5180 compliant legacy Tester. We carry out benchmarking measurements to examine the performance of three free software NAT64 implementations, namely: Jool, TAYGA and map646. All the details of our measurements are disclosed and their results are presented in the paper.