http://hdl.handle.net/2144/1455 2013-05-25T23:54:22Z 2013-05-25T23:54:22Z Danish, Matthew Li, Ye West, Rich http://hdl.handle.net/2144/3810 2012-05-23T13:07:12Z 2010-11-10T00:00:00Z

Virtual-CPU Scheduling in the Quest Operating System Danish, Matthew; Li, Ye; West, Rich This paper describes the scheduling framework for a new operating system called "Quest". The three main goals of Quest are to ensure safety, predictability and efficiency of software execution. For this paper, we focus on one aspect of predictability, involving the integrated management of tasks and I/O events such as interrupts. Quest's scheduling infrastructure is based around the concept of a virtual CPU (VCPU). Using both Main and I/O VCPUs, we are able to separate the CPU bandwidth consumed by tasks from that used to complete I/O processing. We introduce a priority-inheritance bandwidth-preserving server policy for I/O management, called PIBS. We show how PIBS operates with lower cost and higher throughput than a comparable Sporadic Server for managing I/O transfers that require small bursts of CPU time. Using a hybrid system of Sporadic Servers for Main VCPUs, and PIBS for I/O VCPUs, we show how to maintain temporal isolation between multiple tasks and I/O transfers from different devices. We believe Quest's VCPU scheduling infrastructure is scalable enough to operate on future multi- and many-core systems supporting large numbers of threads. For a system of 24 VCPUs, we observe a CPU scheduling overhead of approximately 0.3% when VCPU budget is managed in 1ms units.

2010-11-10T00:00:00Z Gursun, Gonca Crovella, Mark Matta, Ibrahim http://hdl.handle.net/2144/3811 2012-05-23T13:07:12Z 2010-11-10T00:00:00Z

Describing and Forecasting Video Access Patterns Gursun, Gonca; Crovella, Mark; Matta, Ibrahim Computer systems are increasingly driven by workloads that reflect large-scale social behavior, such as rapid changes in the popularity of media items like videos. Capacity planners and system designers must plan for rapid, massive changes in workloads when such social behavior is a factor. In this paper we make two contributions intended to assist in the design and provisioning of such systems.We analyze an extensive dataset consisting of the daily access counts of hundreds of thousands of YouTube videos. In this dataset, we find that there are two types of videos: those that show rapid changes in popularity, and those that are consistently popular over long time periods. We call these two types rarely-accessed and frequently-accessed videos, respectively. We observe that most of the videos in our data set clearly fall in one of these two types. For each type of video we ask two questions: first, are there relatively simple models that can describe its daily access patterns? And second, can we use these simple models to predict the number of accesses that a video will have in the near future, as a tool for capacity planning? To answer these questions we develop two different frameworks for characterization and forecasting of access patterns. We show that for frequently-accessed videos, daily access patterns can be extracted via principal component analysis, and used efficiently for forecasting. For rarely-accessed videos, we demonstrate a clustering method that allows one to classify bursts of popularity and use those classifications for forecasting.

2010-11-10T00:00:00Z Magee, John Epstein, Samuel Missimer, Eric Betke, Margrit http://hdl.handle.net/2144/3805 2012-05-23T13:07:11Z 2010-09-06T00:00:00Z

Adaptive mappings for mouse-replacement interfaces Magee, John; Epstein, Samuel; Missimer, Eric; Betke, Margrit Users of mouse-replacement interfaces may have difficulty conforming to the motion requirements of their interfacesystem. We have observed users with severe motor disabilities who controlled the mouse pointer with a head tracking interface. Our analysis shows that some users may be able to move in some directions easier than other directions. We propose several mouse pointer mappings that adapt to the user's movement abilities. These mappings will take into account the user's motions in two-or three-dimensions to move the mouse pointer in the intended direction.

2010-09-06T00:00:00Z Wu, Zheng Hristov, Nickolay Swartz, Sharon Kunz, Thomas Betke, Margrit http://hdl.handle.net/2144/3806 2012-05-23T13:07:11Z 2010-09-06T00:00:00Z

Tracking-Reconstruction or Reconstruction-Tracking? Wu, Zheng; Hristov, Nickolay; Swartz, Sharon; Kunz, Thomas; Betke, Margrit We developed two methods for tracking multiple objects using several camera views. The methods use the Multiple Hypothesis Tracking (MHT) framework to solve both the across-view data association problem (i.e., finding object correspondences across several views) and the across-time data association problem (i.e., the assignment of current object measurements to previously established object tracks). The "tracking-reconstruction method" establishes two-dimensional (2D) objects tracks for each view and then reconstructs their three-dimensional (3D) motion trajectories. The "reconstruction-tracking method" assembles 2D object measurements from all views, reconstructs 3D object positions, and then matches these 3D positions to previously established 3D object tracks to compute 3D motion trajectories. For both methods, we propose techniques for pruning the number of association hypotheses and for gathering track fragments. We tested and compared the performance of our methods on thermal infrared video of bats using several performance measures. Our analysis of video sequences with different levels of densities of flying bats reveals that the reconstruction-tracking method produces fewer track fragments than the tracking-reconstruction method but creates more false positive 3D tracks.

2010-09-06T00:00:00Z