Talk on "Resource Management for Efficient, Scalable and Resilient Network Function Chains"
Speaker:Dr. Sameer Kulkarni (Postdoc, University of California, Riverside).
Title: Resource Management for Efficient, Scalable and Resilient Network Function Chains
Abstarct:
Networks, the basis of the modern connected world, have evolved beyond the connectivity services. Network Functions (NFs) or traditionally the middleboxes are the basis of realizing different types of in-network services such as security, optimization functions, and value-added services. Typically, multiple NFs are chained together (also known as Service Function Chaining) to realize distinct network services, which are pivotal in providing policy enforcement and performance in networks. Network Function Virtualization (NFV) is becoming more prevalent and enabling the softwarized NFs to fast replace the traditional dedicated hardware-based middleboxes in Communication Service Provider (CSP) networks. However, Virtualized Network Function (VNF) chains posit several systems and network level resource management and failure resiliency challenges: to ensure optimal resource utilization and performance at the system level; and at the network-level to address optimal NF placement and routing for service chains, traffic engineering, and load balancing the traffic across Virtualized Network Function Instances (VNFIs); and to provide High Availability (HA), Fault Tolerance (FT) and Disaster Recovery (DR) guarantees.
This talk presents an NFV resource management framework to realize efficient, scalable and resilient network service chaining. The presented solutions enable to improve scalability, performance, resource-utilization efficiency, and resiliency of deploying the NF chains in SDN/NFV ecosystem and are based on the standardized ETSI MANO NFV reference architecture. We address system-level NF resource utilization, performance, and scale challenges by designing a userspace NF scheduling framework for service function chains. We present a novel rate-cost proportional scheduler and chain-aware backpressure mechanisms to optimize the resource utilization through judicious Central Processing Unit (CPU) allocation to the NFs and improve on the chain-wide performance. We address network-level challenges i.e. orchestration and management of NF chains through a semi-distributed resource management framework that can efficiently instantiate, place and relocate the network functions and to distribute traffic across the active NF instances to optimize both the utilization of network links and NFs. We address HA and FT for NF chains through a novel NF state replication strategy and distinct mechanisms to provide timely detection of NFs, hardware node (Virtualized Network Function Manager), and network link failures. We exploit the concept of external synchrony and rollback recovery to address non-determinism and significantly reduce the amount of state transfer required to maintain consistent chain-wide state updates. We provide distinct failover mechanisms for individual NF failures and global service chain-wide failures with strict correctness guarantees.
Speaker Bio: Sameer G. Kulkarni is a post doctoral researcher at the University of California, Riverside. His work focuses on the resource management aspects towards building Efficient, Scalable and Resilient NFV platform. He recently received the IEEE TCSC Best Dissertation Award 2019.
He received Ph.D. degree in Computer Science from the University of Göttingen, Germany in July 2018. He received his M.S. degree in Computer Engineering from the University of Southern California, in 2010, and B.E. degree in Computer Science and Engineering from National Institute of Engineering, Mysore, in 2004. His research interests include Software Defined Networking, Network Function Virtualization, Edge Cloud Platforms, Distributed systems, and Disaster Management. His research publications include SIGCOMM, CoNEXT, IFIP Networking, NFV-SDN, EuCNC, LANMAN, ICIN conferences and Infocom workshop.
He has nearly a decade of Industrial experience. He worked at Qualcomm, San Diego (2009-2014), in the Multimedia Audio group, with core focus on design and development of entire audio software stack (middleware, drivers and DSP) for the Qualcomm Application processors. He also worked at Tata Elxsi Ltd., Bangalore, in the Product Research and Design for Embedded and Multimedia Systems (2004-2008). He has worked on development of the embedded software and systems for the Mobile devices, Set-Top-Box and Hi-Definition Televisions.
Event Date: 27th September, 2019(Friday)
Event Time: 02:30PM to 03:30 PM
Venue: Room No. 21