Predictable Performance Management
RAD-Flows: Buffer Management for Predictable Communication
Members: Roberto Pineiro, Scott Brandt, Carlos Maltzahn, Kleoni Ioannidou
Real-time systems and applications are becoming increasingly complex and often comprise multiple communicating tasks. The management of the individual tasks is well-understood, but the interaction of communicating tasks with different timing characteristics is less well-understood. We address several representative inter-task communication flows via reserved memory buffers (possibly interconnected via a real-time network) and present RAD-Flows, a model for managing these interactions. We provide proofs and simulation results demonstrating the correctness and effectiveness of RAD-Flows, allowing system designers to determine the amount of memory required based upon the characteristics of the interacting tasks and to guarantee real-time operation of the system as a whole.
Radon: Efficient Performance Guarantees on Storage Networks
Members: Andrew Shewmaker, Scott Brandt, Carlos Maltzahn
Traditional Ethernet storage networks provide poor Quality of Service because traditional congestion control protocols gain their efficiency by avoiding global coordination. If the hardware allows it, the simplest approach to providing guaranteed performance is to maximize statistical multiplexing on the switch fabric by shaping the traffic on the sending side. Current hardware can accomplish this at gigabit speeds, but processor clocks cannot provide accurate timing between small packets at 10 to 100 times faster speeds. This research is developing algorithms to deliver the benefits of traffic shaping with congestion control algorithms that are intended to provide guaranteed performance, unlike existing protocols.
Fahrrad: Efficient Performance Guarantees on Storage Devices
Members: Dimitris Skourtis, Scott Brandt, Carlos Maltzahn, Kleoni Ioannidou
Alumni: Tim Kaldewey, Anna Povzner
Guaranteed I/O performance is needed for a variety of applications ranging from real-time data collection to desktop multimedia to large-scale scientific simulations. Reservations on throughput, the standard measure of disk performance, fail to effectively manage disk performance due to the orders of magnitude difference between best-, average-, and worst-case response times, allowing reservation of less than 0.01% of the achievable bandwidth. We show that by reserving disk resources in terms of utilization it is possible to create a disk scheduler that supports reservation of nearly 100% of the disk resources, provides arbitrarily hard or soft guarantees depending upon application needs, and yields efficiency as good or better than best-effort disk schedulers tuned for performance. We present the architecture of our scheduler, prove the correctness of its algorithms, and provide results demonstrating its effectiveness.