Distributed state monitoring plays a critical role in industrial Cloud datacenter management. One fundamental problem in distributed state monitoring is to minimize the monitoring cost while maximizing the monitoring accuracy at the same time. In this paper, we present Volley, a violation likelihood based approach for efficient distributed state monitoring in Cloud datacenters. Volley achieves ...

Virtually all public clouds today are run by single providers, and this creates near-monopolies, inefficient markets, and hinders innovation at the infrastructure level. There are current proposals to change this, by creating open architectures that allow providers of computing and storage resources to compete for tenant services at multiple levels, all the way down to the bare metal. Networkin...

The datacenter network is shared among untrusted tenants in a public cloud, and hundreds of services in a private cloud. Today we lack fine-grained control over network bandwidth partitioning across tenants. In this paper we present EyeQ, a simple and practical system that provides tenants with bandwidth guarantees as if their endpoints were connected to a dedicated switch. To realize this goal...

Large cloud companies manage dozens of datacenters across the globe connected using dedicated inter-datacenter networks. An important application of these networks is data replication which is done for purposes such as increased resiliency via making backup copies, getting data closer to users for reduced delay and WAN bandwidth usage, and global load balancing. These replications usually lead ...

Abstract Today’s datacenter networks (DCNs) scale is rapidly increasing because of the wide deployment cloud services and rapid rise edge computing. The bandwidth consumption cost a DCN are growing sharply with extensions network size. Thus, how to keep traffic balanced key challenging issue. However, traditional load balancing algorithms such as Equal-Cost Multi-Path routing (ECMP) not suitabl...

Quickly exploring massive datasets for insights requires an efficient data processing platform. Parallel database management systems were originally designed to scale only to a handful of nodes, where each node keeps recent (“hot”) data in memory and has directlyattached hard disk storage for infrequently accessed (“cold”) data. To keep pace with the growing data volumes, the research focus has...

The Cloud Computing model leverages virtualization of computing resources allowing customers to provision resources on-demand on a pay-as-you-go basis. During recent years, the power consumption of datacenters in cloud environment attracted researchers. Optimization of energy consumption can be performed by different methods including virtual machine (VM) consolidation. This technique can reduc...