Impact of processing costs on service chain placement in network functions virtualization

Abstract

Abstract-The Network Functions Virtualization (NFV) paradigm is the most promising technique to help network providers in the reduction of capital and energy costs. The deployment of virtual network functions (VNFs) running on generic x86 hardware allows higher flexibility than the classical middleboxes approach. NFV also reduces the complexity in the deployment of network services through the concept of service chaining, which defines how multiple VNFs can be chained together to provide a specific service. As a drawback, hosting multiple VNFs in the same hardware can lead to scalability issues, especially in the processing-resource sharing. In this paper, we evaluate the impact of two different types of costs that must be taken into account when multiple chained VNFs share the same processing resources: the upscaling costs and the context switching costs. Upscaling costs are incurred by VNFs multicore implementations, since they suffer a penalty due to the needs of load balancing among cores. Context switching costs arise when multiple VNFs share the same CPU and thus require the loading/saving of their context. We model through an ILP problem the evaluation of such costs and we show their impact in a VNFs consolidation scenario, when the x86 hardware deployed in the network is minimized.

Wireless-Optical Network Convergence: Enabling the 5G Architecture to Support Operational and End-User Services

“…Examples of features that enable these benefits include the option to virtualize the separate control plane, using NFV and deploy Virtual Network Functions (VNFs) [11]. VNFs are controlled by the SDN controller, to allow on-demand resource allocation and dynamically changing workloads [6].…”

“…, Markos Anastasopoulos (1) , Dimitra Simeonidou (1) , Ignacio Berberana (2) , Dimitris Syrivelis (3) , Paris Flegkas (3) ,Thanasis Korakis (3) , Daniel Camps Mur (4) , Ilker Demirkol (5) , Jesús Gutiérrez (6) , Eckhard Grass (6) , Qing Wei (7) , Emmanouil Pateromichelakis (7) , Nikola Vucic (7) , Albrecht Fehske (8) , Michael Grieger (8) , Michael Eiselt (9) , Jens Bartelt (10) , Gerhard Fettweis (10) , George Lyberopoulos (11) , Eleni Theodoropoulou (11) Initiative (OBSAI) and the Open Radio Interface (ORI), with CPRI currently being the most widely used standard. FH is responsible to carry the RU wireless signals, typically over an optical transport network, using either digital transmission (e.g.…”

QoS-driven function placement reducing expenditures in NFV deployments

“…The authors in [6] show that service chains with virtual network functions, despite having the larger processing delay, can provide lower end to end delay compared to the traditional infrastructures. The increase of the processing delay specific for virtualization of network functions has been studied in [7] and [8]. The increase of the processing delay caused by the side effects of multicore deployment and effects of multiple network functions sharing the same physical hardware are analyzed in [7], while the dependency between the load and the forwarding latency are presented in [8].…”

“…The increase of the processing delay specific for virtualization of network functions has been studied in [7] and [8]. The increase of the processing delay caused by the side effects of multicore deployment and effects of multiple network functions sharing the same physical hardware are analyzed in [7], while the dependency between the load and the forwarding latency are presented in [8]. The study in [9] show a trade-off between the service chain latency, the number of deployed host nodes in the network and the remaining data rate on network links.…”

“…Models of virtual network functions and service mix used in the simulations were based on the study in [7]. Considered functions were Network Address Translation (NAT), firewall (FW), traffic monitor (TM), WAN Optimization Controller (WOC), Video Optimization Controller (VOC) and Intrusion Detection System (IDS).…”