In this paper, we consider the challenges that arise from the need to scale virtualized network functions (VNFs) at 100 Gbps line speed and beyond. Traditional VNF designs are monolithic in state management and scheduling: internally maintaining all states and operations associated with them. Without proper design considerations, it suffers from limitations when scaling at 100 Gbps link speed and beyond: the inability of efficient utilization of the cache because of the contention due to the frequent control plane activities, computational/memory-intensive tasks taking up CPU times, shares states causing the synchronization among the cores. We address these limitations by arguing for the need to granularly decompose a VNF into data/control components that are co-located within a server but can be independently scaled among the cores. To realize the approach, we design a "serverless" programming framework with novel abstraction to optimize the data components that must process packets at the line speed, reduce the contention of the data states and enable run-time scheduling of different components for improved resource utilization. The abstractions, combined with the runtime system that we design, help NFV developers focus on the logic and correctness of VNF programming without worrying about how VNFs may be scaled in or out. We evaluate our platform by comparing it with monolithic approaches using different workloads and by analyzing its advantages of separation on scalability, performance determinism, and feature velocity.
more »
« less
Data-driven resource flexing for network functions visualization
Resource flexing is the notion of allocating resources on-demand as workload changes.
This is a key advantage of Virtualized Network Functions (VNFs) over their
non-virtualized counterparts. However, it is difficult to balance the timeliness and
resource efficiency when making resource flexing decisions due to unpredictable workloads and complex VNF processing logic.
In this work, we propose an Elastic resource flexing system for Network functions
VIrtualization (ENVI) that leverages a combination of VNF-level features and
infrastructure-level features to construct a neural-network-based scaling decision
engine for generating timely scaling decisions. To adapt to dynamic workloads,
we design a window-based rewinding mechanism to update the neural network with
emerging workload patterns and make accurate decisions in real time. Our experimental
results for real VNFs (IDS Suricata and caching proxy Squid) using workloads generated
based on real-world traces, show that ENVI provisions significantly fewer (up to 26%)
resources without violating service level objectives, compared to commonly used
rule-based scaling policies.
more »
« less
- NSF-PAR ID:
- 10066960
- Date Published:
- Journal Name:
- ANCS '18: Symposium on Architectures for Networking and Communications Systems, July 23--24, 2018, Ithaca, NY, USA
- Page Range / eLocation ID:
- 111 to 124
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Network function virtualization (NFV) offers the potential for both enhancing service delivery flexibility and reducing overall costs by virtualizing network functions that are traditionally implemented in dedicated hardware. However, the flexibility of NFV comes with considerable compromises since virtual machine carried functions could introduce significant performance overhead. In this paper, we present a novel high-performance framework called HYPER, which combines programmable hardware infrastructure and traditional software infrastructure in NFV to achieve both high performance and flexibility for supporting virtualized network functions (VNFs). In HYPER, we design a mediator layer to hide underlying infrastructure heterogeneity from the NFV orchestrator to simplify VNF management. In addition, we design a SLA-aware service chaining algorithm in HYPER to leverage the benefits of the hybrid infrastructure to fulfill both functional and performance requirements from service subscribers (or tenants). To optimize resource utilization efficiency, we also introduce a performance-aware VNF placement algorithm in HYPER, which accommodates both resource and performance requirements in placing VNFs. We implement HYPER in a testbed based on OpenStack and ONetCard. Experimental results show that HYPER reduces the forwarding latency of a service chain by 40% to 67% compared with data plane development kit -based implementation, while maintaining the flexibility of VNF management.more » « less
-
more » « less
The high reliability required by many future-generation network services can be enforced by proper resource assignments by means of logical partitions, i.e., network slices, applied in optical metro-aggregation networks. Different strategies can be applied to deploy the virtual network functions (VNFs) composing the slices over physical nodes, while providing different levels of resource isolation (among slices) and protection against failures, based on several available techniques. Considering that, in optical metro-aggregation networks, protection can be ensured at different layers, and the slice protection with traffic grooming calls for evolved multilayer protection approaches. In this paper, we investigate the problem of reliable slicing with protection at the lightpath layer for different levels of slice isolation and different VNF deployment strategies. We model the problem through an integer linear program (ILP), and we devise a heuristic for joint optimization of VNF placement and ligthpath selection. The heuristic maps nodes and links over the physical network in a coordinated manner and provides an effective placement of radio access network functions and the routing and wavelength assignment for the optical layer. The effectiveness of the proposed heuristic is validated by comparison with the optimal solution provided by the ILP. Our illustrative numerical results compare the impact of different levels of isolation, showing that higher levels of network and VNF isolation are characterized by higher costs in terms of optical and computation resources.
-
null (Ed.)Virtual Network Functions (VNFs) are software implementation of middleboxes (MBs) (e.g., firewalls) that provide performance and security guarantees for virtual machine (VM) cloud applications. In this paper we study a new flow migration problem in VNF-enabled cloud data centers where the traffic rates of VM flows are constantly changing. Our goal is to minimize the total network traffic (therefore optimizing the network resources such as bandwidth and energy) while considering that VNFs have limited processing capability. We formulate the flow migration problem and design two efficient benefit-based greedy algorithms. The simulations show that our algorithms are effective in reducing the network traffic as well as in achieving load balance among VNFs. In particular, our flow migration algorithms can reduce upto 15% network traffic compared to the case without flow migration.more » « less
-
null (Ed.)Network function virtualization (NFV) technologyattracts tremendous interests from telecommunication industryand data center operators, as it allows service providers to assignresource for Virtual Network Functions (VNFs) on demand,achieving better flexibility, programmability, and scalability. Toimprove server utilization, one popular practice is to deploy besteffort (BE) workloads along with high priority (HP) VNFs whenhigh priority VNF’s resource usage is detected to be low. The keychallenge of this deployment scheme is to dynamically balancethe Service level objective (SLO) and the total cost of ownership(TCO) to optimize the data center efficiency under inherentlyfluctuating workloads. With the recent advancement in deepreinforcement learning, we conjecture that it has the potential tosolve this challenge by adaptively adjusting resource allocationto reach the improved performance and higher server utilization.In this paper, we present a closed-loop automation systemRLDRM1to dynamically adjust Last Level Cache allocationbetween HP VNFs and BE workloads using deep reinforcementlearning. The results demonstrate improved server utilizationwhile maintaining required SLO for the HP VNFs.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3230718.3230725
