Modern data center nowadays leverages highly concurrent TCP connections between thousands of computer servers to achieve high system performance and service reliability. However, recent works have shown that, in the many-to-one and barrier-synchronized communication pattern, a large number of concurrent TCP connections suffer the TCP Incast problem due to packet drops in shallow-buffered Ethernet switches. This problem unavoidably leads to severe under-utilization of link capacity. In this work, we first reveal theoretically and empirically that controlling the IP packet size reduces the Incast probability much more effectively than controlling the congestion windows in the presence of severe congestion. We further present the design and implementation of Packet Slicing, a general supporting scheme that adjusts the packet size through a standard ICMP signaling method. Our method can be deployed on commodity switches with small firmware updates, while making no modification on end hosts. Another highlight of our work is Packet Slicing's broad applicability and effectiveness. We integrate Packet Slicing transparently (i.e., without modification) with three state-of-the-art TCP protocols designed for data centers on NS2 simulation and a physical testbed, respectively. The experimental results show that Packet Slicing remarkably improves network goodput across different TCP protocols by average 26x under severe congestion, while introducing little I/O performance impact on both switches and end hosts.
|Original language||English (US)|
|Title of host publication||Proceedings - 2015 IEEE 23rd International Conference on Network Protocols, ICNP 2015|
|Publisher||IEEE Computer Society|
|Number of pages||10|
|State||Published - Mar 18 2016|
|Event||23rd IEEE International Conference on Network Protocols, ICNP 2015 - San Francisco, United States|
Duration: Nov 10 2015 → Nov 13 2015
|Name||Proceedings - International Conference on Network Protocols, ICNP|
|Other||23rd IEEE International Conference on Network Protocols, ICNP 2015|
|Period||11/10/15 → 11/13/15|
Bibliographical noteFunding Information:
This work is supported by the National Natural Science Foundation of China (61103204, 61572530), the China Hunan Provincial Science and Technology Program (2012GK4106), the International Science and Technology Cooperation Program of China (2013DFB10070)
© 2015 IEEE.
- Congestion control
- Data center network