Shriram Rajagopalan

A look at the dynamics of the JavaScript package ecosystem

The node package manager (npm) serves as the frontend to a large repository of JavaScript-based software packages, which foster the development of currently huge amounts of server-side Node.js and client-side JavaScript applications. In a span of 6 years since its inception, npm has grown to become one of the largest software ecosystems, hosting more than 230, 000 packages, with hundreds of millions of package installations every week. In this paper, we examine the npm ecosystem from two complementary perspectives: 1) we look at package descriptions, the dependencies among them, and download metrics, and 2) we look at the use of npm packages in publicly available applications hosted on GitHub. In both perspectives, we consider historical data, providing us with a unique view on the evolution of the ecosystem. We present analyses that provide insights into the ecosystem’s growth and activity, into conflicting measures of package popularity, and into the adoption of package versions over time. These insights help understand the evolution of npm, design better package recommendation engines, and can help developers understand how their packages are being used.

Gremlin: Systematic Resilience Testing of Microservices

Modern Internet applications are being disaggregated into a microservice-based architecture, with services being updated and deployed hundreds of times a day. The accelerated software life cycle and heterogeneity of language runtimes in a single application necessitates a new approach for testing the resiliency of these applications in production infrastructures. We present Gremlin, a framework for systematically testing the failure-handling capabilities of microservices. Gremlin is based on the observation that microservices are loosely coupled and thus rely on standard message-exchange patterns over the network. Gremlin allows the operator to easily design tests and executes them by manipulating inter-service messages at the network layer. We show how to use Gremlin to express common failure scenarios and how developers of an enterprise application were able to discover previously unknown bugs in their failure-handling code without modifying the application.

Flurries: Countless Fine-Grained NFs for Flexible Per-Flow Customization

The combination of Network Function Virtualization (NFV) and Software Defined Networking (SDN) allows flows to be flexibly steered through efficient processing pipelines. As deployment of NFV becomes more prevalent, the need to provide fine-grained customization of service chains and flow-level performance guarantees will increase, even as the diversity of Network Functions (NFs) rises. Existing NFV approaches typically route wide classes of traffic through pre-configured service chains. While this aggregation improves efficiency, it prevents flexibly steering and managing performance of flows at a fine granularity. To provide both efficiency and flexibility, we present Flurries, an NFV platform designed to support large numbers of short-lived lightweight NFs, potentially running a unique NF for each flow. Flurries maintains a pool of Docker container NFs--several thousand on each host--and resets NF memory state between flows for fast reuse. Flurries uses a hybrid of polling and interrupts to improve throughput and latency while allowing multiple NFs to efficiently share CPU cores. By assigning each NF an individual flow or a small set of flows, it becomes possible to dynamically manage the QoS and service chain functionality for flows at a very fine granularity. Our Flurries prototype demonstrates the potential for this approach to run as many as 80,000 Flurry NFs during a one second interval, while forwarding over 30Gbps of traffic, dramatically increasing data plane customizability.

NFVnice: Dynamic Backpressure and Scheduling for NFV Service Chains

Managing Network Function (NF) service chains requires careful system resource management. We propose NFVnice, a user space NF scheduling and service chain management framework to provide fair, efficient and dynamic resource scheduling capabilities on Network Function Virtualization (NFV) platforms. The NFVnice framework monitors load on a service chain at high frequency (1000Hz) and employs backpressure to shed load early in the service chain, thereby preventing wasted work. Borrowing concepts such as rate proportional scheduling from hardware packet schedulers, CPU shares are computed by accounting for heterogeneous packet processing costs of NFs, I/O, and traffic arrival characteristics. By leveraging cgroups, a user space process scheduling abstraction exposed by the operating system, NFVnice is capable of controlling when network functions should be scheduled. NFVnice improves NF performance by complementing the capabilities of the OS scheduler but without requiring changes to the OSs scheduling mechanisms. Our controlled experiments show that NFVnice provides the appropriate rate-cost proportional fair share of CPU to NFs and significantly improves NF performance (throughput and loss) by reducing wasted work across an NF chain, compared to using the default OS scheduler. NFVnice achieves this even for heterogeneous NFs with vastly different computational costs and for heterogeneous workloads.

Performance management challenges for virtual network functions

Networks increasingly incorporate complex functionality, going beyond simple forwarding. Packet flows require processing through a complex set of services, that may often be provided in the cloud or on commercial off the shelf (COTS) hardware. This paper investigates the problem of scheduling network functions in different service chains, on a single physical host. Stock operating system (OS) schedulers are ill-equipped to handle the strict performance required - high throughput AND low latency across multiple functions - by network function virtualization (NFV) platforms. Our experimental results show that the standard Linux scheduler can cause a 50% drop in throughput when subjected to diverse NFV workloads. We argue that the OS scheduler needs to be enhanced to be NFV-aware in order to handle service chains, while maintaining line-rate performance. We describe the challenges in designing a network function service chain friendly scheduler and present some early results based on our ongoing research in this area.