Title | ||
---|---|---|
3D Fabric: Differential Deceleration and Detour for Congestion Free Data Center Networks |
Abstract | ||
---|---|---|
3D Fabric jointly uses two strategies for congestion avoidance: flow rate adjustment and path switch. 3D Fabric predicts flow's size and only decelerates large flows in case of light congestion. When the network is heavily congested, it starts to decelerate small flows as well, and meanwhile, considers to switch large flow's path with the help of a new artificial flowlet generation method. ns-3 simulation shows 3D Fabric's FCT outperforms DCTCP by more than 50% for small lows and 3% for large lows with low implementation cost. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1145/3123878.3131994 | SIGCOMM Posters and Demos |
Field | DocType | ISBN |
Computer science,Load balancing (computing),Simulation,Flow (psychology),Computer network,Real-time computing,Network congestion,Functional testing (manufacturing),Acceleration,Data center | Conference | 978-1-4503-5057-0 |
Citations | PageRank | References |
0 | 0.34 | 3 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Haoyu Song | 1 | 734 | 42.50 |
Zhigang Ji | 2 | 0 | 1.01 |
Yali Zhang | 3 | 7 | 6.51 |
Yinben Xia | 4 | 0 | 0.34 |