MAPLE: a scalable architecture for maintaining packet latency measurements.

Myungjin Lee, Nick G. Duffield, Ramana Rao Kompella

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Latency has become an important metric for network monitoring since the emergence of new latency-sensitive applications (e.g., algorithmic trading and high-performance computing). To satisfy the need, researchers have proposed new architectures such as LDA and RLI that can provide fine-grained latency measurements. However, these architectures are fundamentally ossified in their design as they are designed to provide only a specific pre-configured aggregate measurement---either average latency across all packets (LDA) or per-flow latency measurements (RLI). Network operators, however, need latency measurements at both finer (e.g., packet) as well as flexible (e.g., flow subsets) levels of granularity. To bridge this gap, we propose an architecture called MAPLE that essentially stores packet-level latencies in routers and allows network operators to query the latency of arbitrary traffic sub-populations. MAPLE is built using scalable data structures with small storage needs (uses only 12.8 bits/packet), and uses a novel mechanism to reduce the query bandwidth significantly (by a factor of 17 compared to the naive method of sending packet queries individually).
Original languageEnglish
Title of host publicationIMC '12 Proceedings of the 2012 ACM conference on Internet measurement conference
EditorsJohn W. Byers, Jim Kurose, Ratul Mahajan, Alex C. Snoeren
PublisherACM
Pages101-114
Number of pages14
ISBN (Print)978-1-4503-1705-4
Publication statusPublished - 2012

Keywords

  • dblp

Fingerprint Dive into the research topics of 'MAPLE: a scalable architecture for maintaining packet latency measurements.'. Together they form a unique fingerprint.

Cite this