itmBench: Generalized API for Internet Traffic Managers

Internet Traffic Managers (ITMs) are special machines placed at strategic places in the Internet. itmBench is an interface that allows users (e.g. network managers, service providers, or experimental researchers) to register different traffic control functionalities to run on one ITM or an overlay of ITMs. Thus itmBench offers a tool that is extensible and powerful yet easy to maintain. ITM traffic control applications could be developed either using a kernel API so they run in kernel space, or using a user-space API so they run in user space. We demonstrate the flexibility of itmBench by showing the implementation of both a kernel module that provides a differentiated network service, and a user-space module that provides an overlay routing service. Our itmBench Linux-based prototype is free software and can be obtained from http://www.cs.bu.edu/groups/itm/.

Efficient End-Host Architecture for High Performance Communication Using User-level Sandboxing

Current low-level networking abstractions on modern operating systems are commonly implemented in the kernel to provide sufficient performance for general purpose applications. However, it is desirable for high performance applications to have more control over the networking subsystem to support optimizations for their specific needs. One approach is to allow networking services to be implemented at user-level. Unfortunately, this typically incurs costs due to scheduling overheads and unnecessary data copying via the kernel. In this paper, we describe a method to implement efficient application-specific network service extensions at user-level, that removes the cost of scheduling and provides protected access to lower-level system abstractions. We present a networking implementation that, with minor modifications to the Linux kernel, passes data between "sandboxed" extensions and the Ethernet device without copying or processing in the kernel. Using this mechanism, we put a customizable networking stack into a user-level sandbox and show how it can be used to efficiently process and forward data via proxies, or intermediate hosts, in the communication path of high performance data streams. Unlike other user-level networking implementations, our method makes no special hardware requirements to avoid unnecessary data copies. Results show that we achieve a substantial increase in throughput over comparable user-space methods using our networking stack implementation.

A Virtual Deadline Scheduler for Window-Constrained Service Guarantees

This paper presents a new approach to window-constrained scheduling, suitable for multimedia and weakly-hard real-time systems. We originally developed an algorithm, called Dynamic Window-Constrained Scheduling (DWCS), that attempts to guarantee no more than x out of y deadlines are missed for real-time jobs such as periodic CPU tasks, or delay-constrained packet streams. While DWCS is capable of generating a feasible window-constrained schedule that utilizes 100% of resources, it requires all jobs to have the same request periods (or intervals between successive service requests). We describe a new algorithm called Virtual Deadline Scheduling (VDS), that provides window-constrained service guarantees to jobs with potentially different request periods, while still maximizing resource utilization. VDS attempts to service m out of k job instances by their virtual deadlines, that may be some finite time after the corresponding real-time deadlines. Notwithstanding, VDS is capable of outperforming DWCS and similar algorithms, when servicing jobs with potentially different request periods. Additionally, VDS is able to limit the extent to which a fraction of all job instances are serviced late. Results from simulations show that VDS can provide better window-constrained service guarantees than other related algorithms, while still having as good or better delay bounds for all scheduled jobs. Finally, an implementation of VDS in the Linux kernel compares favorably against DWCS for a range of scheduling loads.

Measuring the Behavior of a World-Wide Web Server

Server performance has become a crucial issue for improving the overall performance of the World-Wide Web. This paper describes Webmonitor, a tool for evaluating and understanding server performance, and presents new results for a realistic workload. Webmonitor measures activity and resource consumption, both within the kernel and in HTTP processes running in user space. Webmonitor is implemented using an efficient combination of sampling and event-driven techniques that exhibit low overhead. Our initial implementation is for the Apache World-Wide Web server running on the Linux operating system. We demonstrate the utility of Webmonitor by measuring and understanding the performance of a Pentium-based PC acting as a dedicated WWW server. Our workload uses a file size distribution with a heavy tail. This captures the fact that Web servers must concurrently handle some requests for large audio and video files, and a large number of requests for small documents, containing text or images. Our results show that in a Web server saturated by client requests, over 90% of the time spent handling HTTP requests is spent in the kernel. Furthermore, keeping TCP connections open, as required by TCP, causes a factor of 2-9 increase in the elapsed time required to service an HTTP request. Data gathered from Webmonitor provide insight into the causes of this performance penalty. Specifically, we observe a significant increase in resource consumption along three dimensions: the number of HTTP processes running at the same time, CPU utilization, and memory utilization. These results emphasize the important role of operating system and network protocol implementation in determining Web server performance.

On the Interaction Between an Operating System and Web Server

This paper examines how and why web server performance changes as the workload at the server varies. We measure the performance of a PC acting as a standalone web server, running Apache on top of Linux. We use two important tools to understand what aspects of software architecture and implementation determine performance at the server. The first is a tool that we developed, called WebMonitor, which measures activity and resource consumption, both in the operating system and in the web server. The second is the kernel profiling facility distributed as part of Linux. We vary the workload at the server along two important dimensions: the number of clients concurrently accessing the server, and the size of the documents stored on the server. Our results quantify and show how more clients and larger files stress the web server and operating system in different and surprising ways. Our results also show the importance of fixed costs (i.e., opening and closing TCP connections, and updating the server log) in determining web server performance.

PeriScope: An Active Internet Probing and Measurement API

Growing interest in inference and prediction of network characteristics is justified by its importance for a variety of network-aware applications. One widely adopted strategy to characterize network conditions relies on active, end-to-end probing of the network. Active end-to-end probing techniques differ in (1) the structural composition of the probes they use (e.g., number and size of packets, the destination of various packets, the protocols used, etc.), (2) the entity making the measurements (e.g. sender vs. receiver), and (3) the techniques used to combine measurements in order to infer specific metrics of interest. In this paper, we present Periscope: a Linux API that enables the definition of new probing structures and inference techniques from user space through a flexible interface. PeriScope requires no support from clients beyond the ability to respond to ICMP ECHO REQUESTs and is designed to minimize user/kernel crossings and to ensure various constraints (e.g., back-to-back packet transmissions, fine-grained timing measurements) We show how to use Periscope for two different probing purposes, namely the measurement of shared packet losses between pairs of endpoints and for the measurement of subpath bandwidth. Results from Internet experiments for both of these goals are also presented.

Multiplicative Kernels: Object Detection, Segmentation and Pose Estimation

Object detection is challenging when the object class exhibits large within-class variations. In this work, we show that foreground-background classification (detection) and within-class classification of the foreground class (pose estimation) can be jointly learned in a multiplicative form of two kernel functions. One kernel measures similarity for foreground-background classification. The other kernel accounts for latent factors that control within-class variation and implicitly enables feature sharing among foreground training samples. Detector training can be accomplished via standard SVM learning. The resulting detectors are tuned to specific variations in the foreground class. They also serve to evaluate hypotheses of the foreground state. When the foreground parameters are provided in training, the detectors can also produce parameter estimate. When the foreground object masks are provided in training, the detectors can also produce object segmentation. The advantages of our method over past methods are demonstrated on data sets of human hands and vehicles.

An alignment based similarity measure for hand detection in cluttered sign language video

Locating hands in sign language video is challenging due to a number of factors. Hand appearance varies widely across signers due to anthropometric variations and varying levels of signer proficiency. Video can be captured under varying illumination, camera resolutions, and levels of scene clutter, e.g., high-res video captured in a studio vs. low-res video gathered by a web cam in a user’s home. Moreover, the signers’ clothing varies, e.g., skin-toned clothing vs. contrasting clothing, short-sleeved vs. long-sleeved shirts, etc. In this work, the hand detection problem is addressed in an appearance matching framework. The Histogram of Oriented Gradient (HOG) based matching score function is reformulated to allow non-rigid alignment between pairs of images to account for hand shape variation. The resulting alignment score is used within a Support Vector Machine hand/not-hand classifier for hand detection. The new matching score function yields improved performance (in ROC area and hand detection rate) over the Vocabulary Guided Pyramid Match Kernel (VGPMK) and the traditional, rigid HOG distance on American Sign Language video gestured by expert signers. The proposed match score function is computationally less expensive (for training and testing), has fewer parameters and is less sensitive to parameter settings than VGPMK. The proposed detector works well on test sequences from an inexpert signer in a non-studio setting with cluttered background.

Learning a Family of Detectors

Object detection and recognition are important problems in computer vision. The challenges of these problems come from the presence of noise, background clutter, large within class variations of the object class and limited training data. In addition, the computational complexity in the recognition process is also a concern in practice. In this thesis, we propose one approach to handle the problem of detecting an object class that exhibits large within-class variations, and a second approach to speed up the classification processes. In the first approach, we show that foreground-background classification (detection) and within-class classification of the foreground class (pose estimation) can be jointly solved with using a multiplicative form of two kernel functions. One kernel measures similarity for foreground-background classification. The other kernel accounts for latent factors that control within-class variation and implicitly enables feature sharing among foreground training samples. For applications where explicit parameterization of the within-class states is unavailable, a nonparametric formulation of the kernel can be constructed with a proper foreground distance/similarity measure. Detector training is accomplished via standard Support Vector Machine learning. The resulting detectors are tuned to specific variations in the foreground class. They also serve to evaluate hypotheses of the foreground state. When the image masks for foreground objects are provided in training, the detectors can also produce object segmentation. Methods for generating a representative sample set of detectors are proposed that can enable efficient detection and tracking. In addition, because individual detectors verify hypotheses of foreground state, they can also be incorporated in a tracking-by-detection frame work to recover foreground state in image sequences. To run the detectors efficiently at the online stage, an input-sensitive speedup strategy is proposed to select the most relevant detectors quickly. The proposed approach is tested on data sets of human hands, vehicles and human faces. On all data sets, the proposed approach achieves improved detection accuracy over the best competing approaches. In the second part of the thesis, we formulate a filter-and-refine scheme to speed up recognition processes. The binary outputs of the weak classifiers in a boosted detector are used to identify a small number of candidate foreground state hypotheses quickly via Hamming distance or weighted Hamming distance. The approach is evaluated in three applications: face recognition on the face recognition grand challenge version 2 data set, hand shape detection and parameter estimation on a hand data set, and vehicle detection and estimation of the view angle on a multi-pose vehicle data set. On all data sets, our approach is at least five times faster than simply evaluating all foreground state hypotheses with virtually no loss in classification accuracy.

The Cyclone Server Architecture: Streamlining Delivery of Popular Content

We propose a new technique for efficiently delivering popular content from information repositories with bounded file caches. Our strategy relies on the use of fast erasure codes (a.k.a. forward error correcting codes) to generate encodings of popular files, of which only a small sliding window is cached at any time instant, even to satisfy an unbounded number of asynchronous requests for the file. Our approach capitalizes on concurrency to maximize sharing of state across different request threads while minimizing cache memory utilization. Additional reduction in resource requirements arises from providing for a lightweight version of the network stack. In this paper, we describe the design and implementation of our Cyclone server as a Linux kernel subsystem.

An Efficient User-Level Shared Memory Mechanism for Application-Specific Extensions

This paper focuses on an efficient user-level method for the deployment of application-specific extensions, using commodity operating systems and hardware. A sandboxing technique is described that supports multiple extensions within a shared virtual address space. Applications can register sandboxed code with the system, so that it may be executed in the context of any process. Such code may be used to implement generic routines and handlers for a class of applications, or system service extensions that complement the functionality of the core kernel. Using our approach, application-specific extensions can be written like conventional user-level code, utilizing libraries and system calls, with the advantage that they may be executed without the traditional costs of scheduling and context-switching between process-level protection domains. No special hardware support such as segmentation or tagged translation look-aside buffers (TLBs) is required. Instead, our ``user-level sandboxing'' mechanism requires only paged-based virtual memory support, given that sandboxed extensions are either written by a trusted source or are guaranteed to be memory-safe (e.g., using type-safe languages). Using a fast method of upcalls, we show how our mechanism provides significant performance improvements over traditional methods of invoking user-level services. As an application of our approach, we have implemented a user-level network subsystem that avoids data copying via the kernel and, in many cases, yields far greater network throughput than kernel-level approaches.

On classical and other methods of discriminant analysis and estimation of log-odds

For two multinormal populations with equal covariance matrices the likelihood ratio discriminant function, an alternative allocation rule to the sample linear discriminant function when n1 ≠ n2 ,is studied analytically. With the assumption of a known covariance matrix its distribution is derived and the expectation of its actual and apparent error rates evaluated and compared with those of the sample linear discriminant function. This comparison indicates that the likelihood ratio allocation rule is robust to unequal sample sizes. The quadratic discriminant function is studied, its distribution reviewed and evaluation of its probabilities of misclassification discussed. For known covariance matrices the distribution of the sample quadratic discriminant function is derived. When the known covariance matrices are proportional exact expressions for the expectation of its actual and apparent error rates are obtained and evaluated. The effectiveness of the sample linear discriminant function for this case is also considered. Estimation of true log-odds for two multinormal populations with equal or unequal covariance matrices is studied. The estimative, Bayesian predictive and a kernel method are compared by evaluating their biases and mean square errors. Some algebraic expressions for these quantities are derived. With equal covariance matrices the predictive method is preferable. Where it derives this superiority is investigated by considering its performance for various levels of fixed true log-odds. It is also shown that the predictive method is sensitive to n1 ≠ n2. For unequal but proportional covariance matrices the unbiased estimative method is preferred. Product Normal kernel density estimates are used to give a kernel estimator of true log-odds. The effect of correlation in the variables with product kernels is considered. With equal covariance matrices the kernel and parametric estimators are compared by simulation. For moderately correlated variables and large dimension sizes the product kernel method is a good estimator of true log-odds.

Spectrotemporal CT data acquisition and reconstruction at low dose.

PURPOSE: X-ray computed tomography (CT) is widely used, both clinically and preclinically, for fast, high-resolution anatomic imaging; however, compelling opportunities exist to expand its use in functional imaging applications. For instance, spectral information combined with nanoparticle contrast agents enables quantification of tissue perfusion levels, while temporal information details cardiac and respiratory dynamics. The authors propose and demonstrate a projection acquisition and reconstruction strategy for 5D CT (3D+dual energy+time) which recovers spectral and temporal information without substantially increasing radiation dose or sampling time relative to anatomic imaging protocols. METHODS: The authors approach the 5D reconstruction problem within the framework of low-rank and sparse matrix decomposition. Unlike previous work on rank-sparsity constrained CT reconstruction, the authors establish an explicit rank-sparse signal model to describe the spectral and temporal dimensions. The spectral dimension is represented as a well-sampled time and energy averaged image plus regularly undersampled principal components describing the spectral contrast. The temporal dimension is represented as the same time and energy averaged reconstruction plus contiguous, spatially sparse, and irregularly sampled temporal contrast images. Using a nonlinear, image domain filtration approach, the authors refer to as rank-sparse kernel regression, the authors transfer image structure from the well-sampled time and energy averaged reconstruction to the spectral and temporal contrast images. This regularization strategy strictly constrains the reconstruction problem while approximately separating the temporal and spectral dimensions. Separability results in a highly compressed representation for the 5D data in which projections are shared between the temporal and spectral reconstruction subproblems, enabling substantial undersampling. The authors solved the 5D reconstruction problem using the split Bregman method and GPU-based implementations of backprojection, reprojection, and kernel regression. Using a preclinical mouse model, the authors apply the proposed algorithm to study myocardial injury following radiation treatment of breast cancer. RESULTS: Quantitative 5D simulations are performed using the MOBY mouse phantom. Twenty data sets (ten cardiac phases, two energies) are reconstructed with 88 μm, isotropic voxels from 450 total projections acquired over a single 360° rotation. In vivo 5D myocardial injury data sets acquired in two mice injected with gold and iodine nanoparticles are also reconstructed with 20 data sets per mouse using the same acquisition parameters (dose: ∼60 mGy). For both the simulations and the in vivo data, the reconstruction quality is sufficient to perform material decomposition into gold and iodine maps to localize the extent of myocardial injury (gold accumulation) and to measure cardiac functional metrics (vascular iodine). Their 5D CT imaging protocol represents a 95% reduction in radiation dose per cardiac phase and energy and a 40-fold decrease in projection sampling time relative to their standard imaging protocol. CONCLUSIONS: Their 5D CT data acquisition and reconstruction protocol efficiently exploits the rank-sparse nature of spectral and temporal CT data to provide high-fidelity reconstruction results without increased radiation dose or sampling time.