007: Democratically Finding The Cause of Packet Drops
Published in
Symposium on Networked Systems Design and Imple...(2018)External Links:
TL
TL;DR
During its two month deployment in a tier-1 datacenter, 007 detected every problem found by previously deployed monitoring tools while also finding the sources of other problems previously undetected.
Abstract
Network failures continue to plague datacenter operators as their symptoms may not have direct correlation with where or why they occur. We introduce 007, a lightweight, always-on diagnosis application that can find problematic links and also pinpoint problems for each TCP connection. 007 is completely contained within the end host. During its two month deployment in a tier-1 datacenter, it detected every problem found by previously deployed monitoring tools while also finding the sources of other problems previously undetected.
References84 items
1
Understanding and Mitigating Packet Corruption in Data Center Networks
2
Language-Directed Hardware Design for Network Performance Monitoring
3
VFP: A Virtual Switch Platform for Host SDN in the Public Cloud
4
RAIL: A Case for Redundant Arrays of Inexpensive Links in Data Center Networks
5