Enabling low latency and high reliability for IMS-NFV

Network Functions Virtualization (NFV) allows service providers to deliver new services to their customers more quickly by adopting software centric network functions implementation over commercial, off-the-shelf hardwares. IP Multimedia Subsystem (IMS) which is one of the most complex NFV instances requires extremely low end-to-end latency (up to 40 msec), and demands system availability as high as five nines. We discover that highly modular 3GPP standardized IMS network functions implementation over virtualized platform (1) incurs latencies, and (2) does not tolerate faults. NFV-based IMS modules incur high latencies by creating a feedback loop among each other while executing delay sensitive data-plane traffic. These IMS modules are also susceptible to failures, causing the control-plane to terminate the application session while keeping the data-plane to forward data packets. To address these issues, we propose to refactor network function modules. We reduce latencies by pipelining the communication between IMS modules, and achieve fault tolerance by reconfiguring their neighboring modules. We build our system prototype of open source 3GPP compliant IMS over OpenStack platform. Our results show that our scheme reduces latencies and failure recovery time upto 12X and 10X, respectively, when compared to the stat-of-the-art 3GPP compliant virtualized IMS implementation.