Data Center Networks present a novel, unique and rich environment for algorithm development and deployment. Projects are underway in the IEEE 802.1 standards body, especially in the Data Center Bridging Task Group, to define new switched Ethernet functions for data center use.
We describe recent work on one such project: IEEE 802.1Qau---Congestion Notification---whose aim is to develop an Ethernet congestion control algorithm for hardware implementation. We describe and present a model of QCN, for Quantized Congestion Notification, the algorithm developed for this purpose.
Secondly, we articulate the Averaging Principle: a simple method for making congestion control loops stable in the face of increasing lags.
This contrasts with two well-known methods of feedback compensation; namely, (i) sensing and feeding back higher-order derivatives of the queue state, and (ii) determining the lag and then choosing appropriate loop gains. Both methods have been applied in the congestion control literature to obtain stable algorithms for high bandwidth-delay product paths in the Internet. However, these methods are either undesirable or infeasible in the Ethernet context. The Averaging Principle provides a simple alternative, one which we are able to theoretically characterize.
Back to Workshop III: Beyond Internet MRA: Networks of Networks