Turning an open source project into a carrier grade vswitch for NFV: Vosyswitch challenges &amp; results

Paolino, Michele; Fanguede, Jeremy; Nikolaev, Nikolay; Raho, Daniel

doi:10.1109/icnidc.2016.7974529

Cited by 6 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(Tacker) OpenStack is an open-source software for cloud computing infrastructure management. Due to its high modularity, its use as a VIM (Virtual infrastructure Manager) for NFV deployments is popular among telecommunication service providers and enterprises [64], [65], [66], [67], [68], [69]. In its simplest deployment, it requires one or more compute nodes, which will host the virtual machines or containers, and a controller node, which will take care of the management of the VMs and of the network 3 .…”

Section: Openstack Deployments For Nfvmentioning

confidence: 99%

Strong Temporal Isolation Among Containers in OpenStack for NFV Services

Cucinotta

Abeni

Marinoni

et al. 2023

IEEE Trans. Cloud Comput.

View full text Add to dashboard Cite

In this paper, the problem of temporal isolation among containerized software components running in shared cloud infrastructures is tackled, proposing an approach based on hierarchical real-time CPU scheduling. This allows for reserving a precise share of the available computing power for each container deployed in a multi-core server, so to provide it with a stable performance, independently from the load of other co-located containers. The proposed technique enables the use of reliable modeling techniques for end-to-end service chains that are effective in controlling the application-level performance. An implementation of the technique within the well-known OpenStack cloud orchestration software is presented, focusing on a use-case framed in the context of network function virtualization. The modified OpenStack is capable of leveraging the special real-time scheduling features made available in the underlying Linux operating system through a patch to the in-kernel process scheduler. The effectiveness of the technique is validated by gathering performance data from two applications running in a real test-bed with the mentioned modifications to OpenStack and the Linux kernel. A performance model is developed that tightly models the application behavior under a variety of conditions. Extensive experimentation shows that the proposed mechanism is successful in guaranteeing isolation of individual containerized activities on the platform.

show abstract

Section: Openstack Deployments For Nfvmentioning

confidence: 99%

Strong Temporal Isolation Among Containers in OpenStack for NFV Services

Cucinotta

Abeni

Marinoni

et al. 2023

IEEE Trans. Cloud Comput.

View full text Add to dashboard Cite

show abstract

“…A similar work presented in [18] and later in [19] explore the efficiency of Linux bridges, OVS-DPDK, and OVS when chaining two VNFs and using flows of different packet sizes.The impact of OVS and OVS-DPDK was also considered in [20] for both containarized and VM-based chained VNF deployments. The authors in [21,22] also tried to study the impact of a single chain in an OVS-DPDK environment. Regarding SR-IOV and VNF chaining, a comparison against OVS-DPDK is presented in in [23].…”

Section: Related Workmentioning

confidence: 99%

VNF Chaining Performance Characterization under Multi-Feature and Oversubscription Using SR-IOV

et al. 2020

View full text Add to dashboard Cite

Network Function Virtualization (NFV) has revolutionized the way network services are offered, leading Enterprise and Service Providers to increasingly adapt their portfolio of network products in order to reap the benefits of flexible network service deployment and cost reduction promises. With this method, network services are offered in the form of software images instead of dedicated hardware. However, NFV presents several challenges, including standard networking challenges (e.g., security, resilience, and availability), management and orchestration challenges, resource allocation challenges, and performance trade-off challenges of using standard x86 servers instead of dedicated and proprietary hardware. The first three challenges are typical challenges found in virtualization environments and have been extensively addressed in the literature. However, the performance trade-off challenge can be the most impactful when offering networking services, negatively affecting the throughput and delay performance achieved. Thus, in this paper, we investigate and propose several configurations on a virtualized system for increasing the performance in terms of throughput and delay while chaining multiple virtual network functions (VNFs) in case of an undersubscribed and oversubscribed system, where the resource demands exceeds the physical resource capacity. Specifically, we use the Single Root Input Output Virtualization (SR-IOV) as our Input/Output (I/O) technology, and analyze the attainable throughput and delay when running multiple chained VNFs in a standard x86 server under various resource footprints and network features configurations. We show that the system throughput and delay in a multi-chained environment, offering multiple features, and under oversubscription can affect the overall performance of VNFs.

show abstract