Farnaz Moradi

Monitoring Transport and Cloud for Network Functions Virtualization

In this demonstration, we present a monitoring framework for VNFs running inside containers in a cloud system consisting of multiple data centers. We illustrate a use case for the monitoring framework by demonstrating VNF scaling based on monitoring information from both cloud resources and the transport network.

ConMon: An automated container based network performance monitoring system

The popularity of container technologies and their widespread usage for building microservices demands solutions dedicated for efficient monitoring of containers and their interactions. In this paper we present ConMon, an automated system for monitoring the network performance of container-based applications. It automatically identifies newly instantiated application containers and observes passively their traffic. Based on these observations, it configures and executes monitoring functions inside adjacent monitoring containers. The system adapts the monitoring containers to changes driven by either the application or the execution platform. The evaluation results validate the feasibility of the ConMon approach and illustrate its scalability in terms of low overhead on compute resources, moderate impact on applications, and negligible impact on the background network traffic.

Meeting the observability challenges for VNFs in 5G systems

5G mobile communication systems will need to accommodate a variety of use-cases, resulting in a diverse set of requirements. To meet these requirements, 5G systems take advantage of modern virtualization possibilities offered by Network Function Virtualization (NFV), enabling deployment agility and dynamicity of virtualized network functions. With the transformation of telecom towards virtualized environments, advanced observability possibilities gain increasing importance as one of the essential prerequisites, especially for successful DevOps operations. However, deployment agility also puts specific requirements on monitoring solutions in order to adapt automatically and continuously to frequent changes in service deployments. In this short-paper, we establish and discuss essential properties of observability systems for virtual network functions in a 5G context. We take these properties as guiding design principles for our software-defined monitoring framework and outline how to evolve our existing components towards a flexible, scalable, and programmable observability solution for microservice-based NFV with features for increased manageability.

On time-stamp accuracy of passive monitoring in a container execution environment

Passive monitoring of network performance parameters is experiencing a revival due to widespread adoption of virtualization and software-based implementation of network functions. Timestamping is one of the most challenging operations needed for passively monitoring network traffic performance parameters such as latency and jitter. We develop a setup whereby functions that monitor the network traffic are deployed in monitoring containers adjacently to, and interconnected through a virtual switch with the monitored Virtual Network Function instance. In this scenario, we evaluate the effects of container virtualization and virtual switch mirroring of traffic on the measurement of latency. The evaluation results indicate very low measurement errors (a few microseconds in our testbed) which are consistent over different measurement scenarios, thus validating the feasibility of this technique for passively monitoring latency.

Real-time resource prediction engine for cloud management

Predicting resource requirements for cloud services is critical for dimensioning, anomaly detection and service assurance. We demonstrate a system for real-time estimation of the needed amount of infrastructure resources, such as CPU and memory, for a given service. Statistical learning methods on server statistics and load parameters of the service are used for learning a resource prediction model. The model can be used as a guideline for service deployment and for real-time identification of resource bottlenecks.

Online approach to performance fault localization for cloud and datacenter services

Automated detection and diagnosis of the performance faults in cloud and datacenter environments is a crucial task to maintain smooth operation of different services and minimize downtime. We demonstrate an effective machine learning approach based on detecting metric correlation stability violations (CSV) for automated localization of performance faults for datacenter services running under dynamic load conditions.