Randomized Load-balanced Routing for Fat-tree Networks
نویسندگان
چکیده
Fat-tree networks have been widely adopted to High Performance Computing (HPC) clusters and to Data Center Networks (DCN). These parallel systems usually have a large number of servers and hosts, which generate large volumes of highly-volatile traffic. Thus, distributed load-balancing routing design becomes critical to achieve high bandwidth utilization, and low-latency packet delivery. Existing distributed designs rely on remote congestion feedbacks to address congestion, which add overheads to collect and react to network-wide congestion information. In contrast, we propose a simple but effective load-balancing scheme, called Dynamic Randomized load-Balancing (DRB), to achieve network-wide low levels of path collisions through local-link adjustment which is free of communications and cooperations between switches. First, we use D-mod-k path selection scheme to allocate default paths to all source-destination (S-D) pairs in a fat-tree network, guaranteeing low levels of path collision over downlinks for any set of active S-D pairs. Then, we propose Threshold-based Two-Choice (TTC) randomized technique to balance uplink traffic through local uplink adjustment at each switch. We theoretically show that the proposed TTC for the uplink-load balancing in a fat-tree network have a similar performance as the two-choice technique in the area of randomized load balancing. Simulation results show that DRB with TTC technique achieves a significant improvement over many randomized routing schemes for fat-tree networks.
منابع مشابه
Randomized Routing on Fat-Trees
Fat-trees are a class of routing networks for hardware-efficient parallel computation. This paper presents a randomized algorithm for routing messages on a fat-tree. The quality of the algorithm is measured in terms of the load factor of a set of messages to be routed, which is a lower bound on the time required to deliver the messages. We show that if a set of messages has load factor λ on a f...
متن کاملStatic load-balanced routing for slimmed fat-trees
Slimmed fat-trees have recently been proposed and deployed to reduce costs in High Performance Computing (HPC) clusters. While existing static routing schemes such as destination-mod-k (D-modk) routing are load-balanced and effective for full bisection bandwidth fat-trees, they incur significant load imbalance in many slimmed fat-trees. In this work, we propose a static load balanced routing sc...
متن کاملOpenFlow based Load Balancing for Fat-Tree Networks with Multipath Support
Data center networks are designed for satisfying the data transmission demand of densely interconnected hosts in the data center. The network topology and routing mechanism can affect the performance and latency significantly. Nowadays, the fat-tree network is one of the most widely used topologies for data center networks. Network engineers also adopt load balancing methods in the design of ro...
متن کاملDeterministic On-Line Routing on Area-Universal Networks (Extended Abstract)
We present two deterministic routing networks, the pruned butterfly and the sorting fat-tree. Both networks are area-universal, i.e., they can simulate any other routing network fitting in similar area with polylogarithmic slowdown. Previous area-universal networks were either for the off-line problem, where the message set to be routed is known in advance and substantial precomputation is perm...
متن کاملImplementing Load-Balanced Switches With Fat-Tree Networks
Load-balanced switches have received a lot of attention lately as they are much more scalable than other existing switch architectures in the literature. One of the most salient features of load-balanced switches is the simplicity of implementing deterministic and periodic connection patterns for its switch fabrics. In this paper, we propose to use fat-tree networks as the switch fabrics in loa...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1708.09135 شماره
صفحات -
تاریخ انتشار 2017