Decentralized Task-Aware Scheduling for Data Center Networks

被引:160
作者
Dogar, Fahad R. [1 ]
Karagiannis, Thomas [1 ]
Ballani, Hitesh [1 ]
Rowstron, Antony [1 ]
机构
[1] Microsoft Res, Redmond, WA 98052 USA
关键词
datacenter; transport; scheduling; response time;
D O I
10.1145/2740070.2626322
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Many data center applications perform rich and complex tasks (e.g., executing a search query or generating a user's news-feed). From a network perspective, these tasks typically comprise multiple flows, which traverse different parts of the network at potentially different times. Most network resource allocation schemes, however, treat all these flows in isolation rather than as part of a task and therefore only optimize flow-level metrics. In this paper, we show that task-aware network scheduling, which groups flows of a task and schedules them together, can reduce both the average as well as tail completion time for typical data center applications. To achieve these benefits in practice, we design and implement Baraat, a decentralized task-awn re scl led tdi rig system. Baran t sched tiles tasks in a FIFO order but avoids head-of-line blocking by dynamically changing the level of multiplexing in the network. Through experiments with Memcached on a small testbed and large-scale simulations, we show that Baraat outperforms state-of-the-art decentralized schemes (e.g., pFabric) as well as centralized schedulers (e.g., Orchestra) for a wide range of workloads (e.g., search, analytics, etc).
引用
收藏
页码:431 / 442
页数:12
相关论文
共 27 条
[1]  
Al-Fares M., 2010, Hedera: dynamic flow scheduling for data center networks, P19
[2]  
Alizadeh M., 2010, P SIGCOMM
[3]  
Ananthanarayanan G., 2012, P NSDI
[4]  
Ananthanarayanan G., 2010, P OSDI
[5]  
[Anonymous], 2011, P MASCOTS
[6]  
[Anonymous], 2011, PROC USENIX C NETWOR
[7]  
[Anonymous], 2011, P ACM SIGCOMM
[8]  
[Anonymous], 1979, Computers and Intractablity: A Guide to the Theory of NP-Completeness
[9]  
[Anonymous], 2013, MSRTR201396
[10]  
[Anonymous], 2007, THESIS STANFORD U