Liran Schour

Networking Architecture for Seamless Cloud Interoperability

Seamless cloud interoperability is highly desired but not yet easily attainable in the current cloud solutions market. This work tackles one aspect of achieving cloud interoperability, namely, inter-cloud networking. We list the requirements and propose an inter-cloud networking architecture for a case of independent clouds owned by different entities and powered by different cloud management and network virtualization technologies. Then we validate the proposed architecture by describing an example of working implementation for Open Stack cloud powered by Open Daylight Open DOVE SDN solution. Finally, we compare our architecture to the existing solutions.

BEACON: A Cloud Network Federation Framework

This paper presents the BEACON Framework, which will enable the provision and management of cross-site virtual networks for federated cloud infrastructures in order to support the automated deployment of applications and services across different clouds and datacenters. The proposed framework will support different federation architectures, going from tightly coupled (datacenter federation) to loosely coupled (cloud federation and multi-cloud orchestration) architectures, and will enable the creation of Layer 2 and Layer 3 overlay networks to interconnect remote resources located at different cloud sites. A high level description of the main components of the BEACON framework is also introduced.

NoEncap: overlay network virtualization with no encapsulation overheads

Overlay network virtualization quickly gains traction in todays multi-tenant data centers due to its ability to provide independent virtual networks, at scale, along with complete isolation from the underlying physical network. Despite the benefits, performance degradation due to the imposed perpacket encapsulation overhead is a serious impediment. Mitigation approaches are mostly hardware based and thus depend on costly networking gear upgrades and suffer from lesser flexibility and longer times to market, compared to software solutions. Software optimizations proposed so far are limited in scope, applicability, and interoperability. In this paper we present NoEncap, a software-only opt mization, capable of eliminating almost completely the overheads, while fully preserving the benefits of an overlay-based network virtualization.

Federated Networking Services in Multiple OpenStack Clouds

Cloud federation refers to a mesh of Cloud providers that are interconnected by using agreements and protocols necessary to provide a decentralized computing environment. Federation is raising many challenges in different research fields but is also creating new business opportunities. Nowadays, the combination between Cloud federation, Software Defined Networking (SDN), and Network Function Virtualization (NFV) technologies offers new business opportunities to Cloud providers that are able to offer new innovative federated Cloud networking services to customers. In this paper, we focus on federated Cloud networking services considering multiple OpenStack Clouds. In particular, we present a preliminary outcome of an innovative design of a Federation Management system acting as an external service provider dealing with federated networking services among multiple federated OpenStack Clouds. More specifically, we describe how virtual resources, virtual networking, and security management can be accomplished.

Combining optics and SDN to enable true hybrid integration of electronic and photonic switching solutions

We present two hybrid fabrics integrating optical and electronic switches with SDN, and a novel approach improving the scaling of fast optical switches. C-Share reroute flows through optical switches increasing network performance. E-WDM exploits the optical switch transparency by emulating wavelength switching in electronic switches.

CogNETive: insights and visualization for operations@scale

Operating a cloud-scale service is a huge challenge. There are millions of users worldwide and millions of requests per seconds. For example, Amazons Simple Storage Service (S3) in 2013 contained two trillion objects and its logs contained 1.1 million log lines per second, which are approximately 10 PB of log records per year (see [1]). Cloud scale implies thousands of servers and network elements, and hundreds of services from multiple cross-regional data centers. Cloud service operation data is scattered over various types of semi-structured and unstructured logs (e.g., application, error, debug), telemetry and network data, as well as customer service records. It is therefore extremely difficult for the multiple owners and administrators in such systems, coming from different units of the organization, to follow the possible paths and system alternatives in order to detect problems, solve issues and understand the service operation.