The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Nearly 50% of the energy overhead in today's datacenters comes from host-to-host data transfers, which largely depend on the transport layer performance. Multipath TCP (MPTCP) has recently been suggested as a promising transport protocol to improve datacenter network throughput, yet it also increases the host CPU power consumption. It remains unclear whether datacenters can indeed benefit from using...
RAM-based storage aggregates the RAM of servers in data center networks (DCN) to provide extremely high storage performance. For quick recovery of storage server failures, Mem-Cube [1] exploits the proximity of the BCube network to limit the recovery traffic to the recovery servers' 1-hop neighborhood. However, previous design is applicable only to BCube, and has suboptimal recovery performance due...
Communication networks are large distributed systems designed to send messages from one location to another. Messages are generated by a source and transmitted through a server to their destinations. Servers are connected by the transmission links through which the data flows, and each server has a certain queue capacity. When the number of incoming messages exceeds the capacity of the server or the...
The Dynamic Adaptive Streaming over HTTP (DASH) is specified to cope with the changing network conditions and provide an adaptive bit-rate HTTP-based streaming solution. While there have been many researches of rate adaptation algorithms on adaptive HTTP streaming, much of the work is focused on Video on Demand (VoD) service — which is not same as live streaming. It is generally preferred to minimize...
Due to the expensive hardware and complex management of the traditional middlebox, a concerted effort towards the virtualized middlebox has been launched in both academia and industry. In this paper, we propose a unified middlebox model, MBBrick, which is composed of three operation modules (classifier, rewriter, forwarder) and a control module (the mcontroller). We then design a language, MG, to...
Thanks to the abundant available bandwidth and multiple paths on wide-area links that interconnect datacenters on major cloud platforms, it is conceivable that bandwidth-intensive applications may improve their performance by relaying their traffic through such an inter-datacenter network. We propose Stemflow, a new systems framework that provides Inter-Datacenter Overlay as a Service. It is provided...
Network Function Virtualization (NFV) is a novel paradigm that enables flexible and scalable implementation of network services on cloud infrastructure. An important enabler for the NFV paradigm is software switching, which should satisfy rigid network requirements such as high throughput and low latency. Despite recent research activities in the field of NFV, not much attention was given to understand...
Recently, there has been a growing interest in enabling fast data analytics by leveraging system capabilities from large-scale high-performance computing (HPC) systems. OpenSHMEM is a popular run-time system on HPC systems that has been used for large-scale compute-intensive scientific applications. In this paper, we propose to leverage OpenSHMEM to design a distributed in-memory key-value store for...
This paper presents how the throughput of a server is influenced by the applying a vertical scalability. The paper studies the results obtained in measuring the response time of the server and the processing time of the server when dealing with a large number of requests by modifying the configuration of the machine, increasing the number of cores the machine has and increasing the RAM capacity. This...
Designing a cost-effective network for data centers that can deliver sufficient bandwidth and provide high availability has drawn tremendous attentions recently. In this paper, we propose a novel server-centric network structure called RCube, which is energy efficient and can deploy a redundancy scheme to improve the availability of data centers. Moreover, RCube shares many good properties with BCube,...
Downlink data rates can vary significantly in cellular networks, with a potentially non-negligible effect on the user experience. Content providers address this problem by using different representations (e.g., picture resolution, video resolution and rate) of the same content and switch among these based on measurements collected during the connection. If it were possible to know the achievable data...
Multi-Path TCP (MPTCP) boosts network performance of applications by aggregating bandwidth over multiple paths using sub-flows of the same TCP connection. However, MPTCP suffers from three limitations: (1) it is an end-to-end protocol with no control over the network routes, and sub-flows might end up traversing the same links, (2) it has no dynamic control over choosing the optimal number of sub-flows...
For distributed complex event processing systems, handling high volume and continuous data streams with high throughput are required for further decision support. Due to the specific properties of pattern operators, it is difficult to process the data streams in parallel over complex event processing systems. To address the issue, a novel parallel processing strategy is proposed. The proposed method...
Virtual Private Networks (VPN) are an established technology that provides users a way to achieve secure communication over an insecure communication channel, such as the public Internet. It has been widely accepted due to its flexibility and availability on many platforms. It is often used as an alternative to expensive leased lines. In traditional setups, VPN endpoints are set up in hardware appliances,...
Many services used in large scale web applications should be able to tolerate faults without impacting their performance. State machine replication is a well-known approach to implementing fault-tolerant services, providing high availability and strong consistency. To boost the performance of state machine replication, recent proposals have introduced parallel execution of commands. In parallel state...
The Trafïîc Flow Description (TFD) option is an experimental option of the IP protocol, designed by the Authors, able to assure signaling for QoS purposes. The option is used as a carrier of knowledge about forthcoming traffic. If planning horizons are short enough, this knowledge can be used for dynamic bandwidth allocation. In the paper an analysis of QoS assurance using the TFD option is presented...
Computer architects use a variety of workloads to measure system performance. For many workloads, the workload configuration determines the stress applied to the system and the corresponding performance behavior. Therefore, architects must make great efforts to explore and find the correct workload configuration before performing detailed analysis. However, such explorations become impossible for...
This paper describes the design, microarchitecture, and performance of the latest Fujitsu SPARC64 XII 12 core microprocessor which has been developed for high performance, mission critical servers. Dual instruction pipelines, 8-way SMT (Simultaneous Multi-Threading), a high CPU frequency of over 4 GHz, and a 12 core design have doubled the chip performance compared with the previous SPARC64 X+, while...
Data centers are experiencing tremendous growth in the number of servers and networking devices with an increase in traffic to cloud infrastructures. Data center network (DCN) topology plays an important role in providing acceptable level of performance to cloud applications. This paper presents the results of a simulation studies comparing the performance of several well-known DCN topologies under...
This demonstration introduces the database community to state-of-the-art cryptographic methods that ensure efficient oblivious access to cloud data. In particular, we explore oblivious storage systems which hide both the content of data and data access patterns from an untrusted cloud provider. The demo considers the popular and realistic setting where multiple users from a trusted group asynchronously...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.