• Publications
  • Influence
Making Scheduling "Cool": Temperature-Aware Workload Placement in Data Centers
TLDR
This paper examines a theoretic thermodynamic formulation that uses information about steady state hot spots and cold spots in the data center and develops real-world scheduling algorithms, and develops an alternate approach to address the problem of heat management through temperature-aware workload placement.
Managing energy and server resources in hosting centers
TLDR
Experimental results from a prototype confirm that the system adapts to offered load and resource availability, and can reduce server energy usage by 29% or more for a typical Web workload.
Correlating Instrumentation Data to System States: A Building Block for Automated Diagnosis and Control
TLDR
Experimental results from a testbed show that TAN models involving small subsets of metrics capture patterns of performance behavior in a way that is accurate and yields insights into the causes of observed performance effects.
Balancing risk and reward in a market-based task service
TLDR
This work presents improved heuristics for value-based task scheduling using a simple but rich formulation of value, in which a task's yield decays linearly with its waiting time, and shows the importance of opportunity cost and the impact of risk due to uncertainty in the future job mix.
Automated control for elastic storage
TLDR
This paper addresses elastic control for multi-tier application services that allocate and release resources in discrete units, such as virtual server instances of predetermined sizes, by designing and implementing a new controller for elastic storage systems.
Automated control in cloud computing: challenges and opportunities
TLDR
This paper addresses the challenge of building an effective controller as a customer add-on outside of the cloud utility service itself, and explores proportional thresholding, a policy enhancement for feedback controllers that enables stable control across a wide range of guest cluster sizes using the coarse-grained control offered by popular virtual compute cloud services.
Scalability and accuracy in a large-scale network emulator
TLDR
The current ModelNet prototype is able to accurately subject thousands of instances of a distrbuted application to Internet-like conditions with gigabits of bisection bandwidth, including novel techniques to balance emulation accuracy against scalability.
Interposed proportional sharing for a storage service utility
TLDR
Interposed request scheduling is non-intrusive and views the server as a black box, so it is useful for complex services with no internal support for differentiated service quality, such as network storage servers.
Scalability and accuracy in a large-scale network emulator
TLDR
The current ModelNet prototype is able to accurately subject thousands of instances of a distrbuted application to Internet-like conditions with gigabits of bisection bandwidth, including novel techniques to balance emulation accuracy against scalability.
...
...