Synchronized network snapshots

Abstract

When monitoring a network, operators rarely have a fine-grained and complete view of the network's state. Instead, today's network monitoring tools generally only measure a single device or path at a time; whole-network metrics are a composition of these independent measurements, i.e., an afterthought. Such tools fail to fully answer a wide range of questions. Is my load balancing algorithm taking advantage of all available paths evenly? How much of my network is concurrently loaded? Is application traffic synchronized? These types of concurrent network behavior are challenging to capture at fine granularity as they involve coordination across the entire network. At the same time, understanding them is essential to the design of network switches, architectures, and protocols. This paper presents the design of a Synchronized Network Snapshot protocol. The goal of our primitive is the collection of a network-wide set of measurements. To ensure that the measurements are meaningful, our design guarantees they are both causally consistent and approximately synchronous. We demonstrate with a Wedge100BF implementation the feasibility of our approach as well as its many potential uses.