Algorithms for congestion control and bandwidth-partitioning in data centers
Abstract/Contents
- Abstract
- Data Center Networks represent the convergence of computing and networking, of data and storage networks, and of packet transport mechanisms in Layers 2 and 4. These networks provide a rich opportunity for developing new algorithms and architectures. In this thesis, we propose a Layer 2 congestion management algorithm called QCN (Quantized Congestion Notification), which we have developed for the IEEE 802.1Qau Congestion Notification standard for Data Center Ethernet. QCN has been designed to be stable, responsive, and simple to implement. This thesis also introduces ECN-hat, a slightly modified version of the TCP algorithm that mimics QCN's multi-bit rate cuts, leading to significantly higher utilization and lower latency. It does this by using the ECN marks in the acks of packets in a non-traditional way, one which extracts more information about the congestion in network. We also show how QCN and Data Center TCP (DCTCP) can be easily extended via light-weight switch modifications to provide programmable bandwidth partitioning in multi-tenanted Cloud Computing and Data Center environments. Our Approximately Fair extensions, AF-QCN and AF-DCTCP, achieve weighted fairness at the granularity of a few milliseconds while retaining the good properties of QCN and DCTCP (stability, responsiveness, and simplicity).
Description
| Type of resource | text |
|---|---|
| Form | electronic; electronic resource; remote |
| Extent | 1 online resource. |
| Publication date | 2011 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Associated with | Kabbani, Abdul Kader |
|---|---|
| Associated with | Stanford University, Department of Electrical Engineering |
| Primary advisor | Prabhakar, Balaji, 1967- |
| Thesis advisor | Prabhakar, Balaji, 1967- |
| Thesis advisor | McKeown, Nick |
| Thesis advisor | Tobagi, Fouad A, 1947- |
| Advisor | McKeown, Nick |
| Advisor | Tobagi, Fouad A, 1947- |
Subjects
| Genre | Theses |
|---|
Bibliographic information
| Statement of responsibility | Abdul Kabbani. |
|---|---|
| Note | Submitted to the Department of Electrical Engineering. |
| Thesis | Ph. D. Stanford University 2011 |
| Location | electronic resource |
Access conditions
- Copyright
- © 2011 by Abdul Kader Kabbani
Also listed in
Loading usage metrics...