J Jiang, S Ma, B Li, B Li - IEEE Transactions on Cloud …, 2016 - ieeexplore.ieee.org
Link utilization has received extensive attention since data centers become the most pervasive platform for data-parallel applications. A specific job of such applications involves …
J Jiang, S Ma, B Li, B Li - 2016 25th International Conference …, 2016 - ieeexplore.ieee.org
Tasks in a data-parallel job communicate with each other through a number of concurrent flows, which is described as a coflow. These flows are correlated in the sense that the …
S Luo, H Yu, L Li - 2016 IEEE International Conference on …, 2016 - ieeexplore.ieee.org
This paper presents D2-CAS, a novel decentralized coflow scheduling system, to minimize the rate of deadline missed coflow for datacenter networks. To design D2-CAS, we first …
S Luo, P Fan, H Xing, H Yu - IEEE/ACM Transactions on …, 2022 - ieeexplore.ieee.org
Recently, the abstraction of coflow is introduced to capture the collective data transmission patterns among modern distributed data-parallel applications. During processing, coflows …
H Zhang, X Shi, X Yin, Z Wang - 2017 IEEE 25th International …, 2017 - ieeexplore.ieee.org
Recently, coflow has been proposed as a new abstraction to capture the communication patterns in a rich set of data parallel applications in data centers. Coflows effectively model …
Datacenter networks routinely support the data transfers of distributed computing frameworks in the form of coflows, ie, sets of concurrent flows related to a common task. The …
Flow completion times (FCTs) are critical for many cloud applications. To minimize the average FCT, recent transport designs, such as pFabric, PASE, and PIAS, approximate the …
T Wang, H Xu, F Liu - Proceedings of the First Asia-Pacific Workshop on …, 2017 - dl.acm.org
Data center networks carry a mix of flows, some with deadlines and some without. Existing mix-flow transport designs assume prior knowledge of flow sizes, which may not hold in …
R Xu, W Li, K Li, X Zhou, H Qi - IEEE Transactions on Network …, 2020 - ieeexplore.ieee.org
Data-parallel applications generate a mix of coflows with and without deadlines. Deadline coflows are mission-critical and must be completed within deadlines, while the non-deadline …