Ilari Shafer

Learn More
Mobile phone services based on the location of a user have increased in popularity and importance, particularly with the proliferation of feature-rich smartphones. One major obstacle to the widespread use of location-based services is the limited battery life of these mobile devices and the high power costs of many existing approaches. We demonstrate the(More)
Metrics like disk activity and network traffic are widespread sources of diagnosis and monitoring information in datacenters and networks. However, as the scale of these systems increases, examining the raw data yields diminishing insight. We present RainMon, a novel end-to-end approach for mining timeseries monitoring data designed to handle its size and(More)
End-to-end tracing captures the workžow of causally-related activity (e.g., work done to process a request) within and among the components of a distributed system. As distributed systems grow in scale and complexity, such tracing is becoming a critical tool for management tasks like diagnosis and resource accounting. Drawing upon our experiences building(More)
Distributed systems are complex to develop and administer, and performance problem diagnosis is particularly challenging. When performance degrades, the problem might be in any of the system's many components or could be a result of poor interactions among them. Recent research efforts have created tools that automatically localize the problem to a small(More)
Identifying the “semantic” location of a phone — for example, determining if it is resting on a desk, in a pocket, or on a chair — is a growing area of interest as smartphones become more prevalent. Taking advantage of the accelerometers and vibrators common in these devices, we use a machine learning approach to classify semantic location of a phone, even(More)
Workflow-centric tracing captures the workflow of causally-related events (e.g., work done to process a request) within and among the components of a distributed system. As distributed systems grow in scale and complexity, such tracing is becoming a critical tool for understanding distributed system behavior. Yet, there is a fundamental lack of clarity(More)
Workžow-centric tracing captures the workžow of causallyrelated events (e.g., work done to process a request) within and among the components of a distributed system. As distributed systems grow in scale and complexity, such tracing is becoming a critical tool for understanding distributed system behavior. Yet, there is a fundamental lack of clarity about(More)