Search

By virtue of the recent technological developments in cloud computing, more applications are deployed in the cloud. Among these modern cloud-based applications, many societal applications require bounded and predictable low-latency responses. However, the current cloud infrastructure is unsuitable for these applications since it cannot satisfy these requirements due to many limitations in both hardware and software. This doctoral dissertation describes our attempts to reduce the latency of Internet services by carefully studying the multi-hundred-gigabit-per-second commodity hardware, optimizing it, and improving its performance. The main focus is to improve the performance of packet processing done by the network functions deployed on commodity hardware, known as network functions virtualization (NFV), which is one of the significant sources of latency for Internet services. The first contribution of this dissertation takes a step toward optimizing the cache performance of time-critical NFV service chains. By doing so, we reduce the tail latencies of such systems running at 100 Gbps. This is an important achievement as it increases the probability of realizing bounded and predictable latency for Internet services. The second contribution of this dissertation performs whole-stack optimizations on software-based network functions deployed on top of modular packet processing frameworks to further enhance the effectiveness of cache memories. We build a system to efficiently handle metadata and produce a customized binary of NFVservice chains. Our system improves both throughput & latency of per-core hundred-gigabit-per-second packet processing on commodity hardware. The third contribution of this dissertation studies the efficiency of I/O security solutions provided by commodity hardware at multi-hundred-gigabit-per-second rates. We characterize the performance of IOMMU & IOTLB (i.e., I/O virtual address translation cache) at 200 Gbps and explore the possible opportunities to mitigate its performance overheads in the Linux kernel. Tack vare den senaste tekniska utvecklingen inom molntjänster används allt fler tillämpningar i molnet. Bland dessa moderna molnbaserade tillämpningar kräver många samhällsorienterade tillämpningar svarstider med låg latens, som är förutsägbara och ligger inom givna gränser. Den nuvarande molninfrastrukturen är dock otillräcklig för sådana tillämpningar eftersom den inte kan uppfylla dessa krav på grund av olika begränsningar i både hårdvara och mjukvara. I denna doktorsavhandling beskrivs våra försök att minska latenstiden för Internettjänster genom att noggrant studera tillänglig hårdvara med stöd för flera hundra gigabit per sekund, optimera denna och förbättra dess prestanda. Huvudfokus ligger på att förbättra prestandan för den paketbearbetning som utförs av nätverksfunktioner som installeras på allmänt tillgänglig hårdvara, så kallad nätverksfunktionsvirtualisering (NFV), som är en av de betydande källorna till latens för Internettjänster. Det första bidraget i den här avhandlingen tar ett steg mot att optimera cache-prestanda för tidskritiska kedjor av NFV-tjänster. Genom att göra detta minskar vi de långa latenstiderna för sådana system som körs vid 100 Gbps. Detta är ett viktigt resultat eftersom det ökar sannolikheten för att uppnå en begränsad och förutsägbar fördröjning hos internettjänster. Det andra bidraget i den här avhandlingen är optimeringar av hela stacken av mjukvarubaserade nätverksfunktioner som används ovanpå modulära ramverk för paketbearbetning för att ytterligare förbättra effektiviteten hos cacheminnen. Vi bygger ett system för att effektivt hantera metadata och producera anpassade binärversioner av NFV-tjänstekedjor. Vårt system förbättrar både genomströmning och latens för tillgänglig hårdvara där varje CPU-kärna har kapacitet för paketbearbetning i storleksordningen 100 Gbps. . I det tredje bidraget i denna avhandling studeras effektiviteten hos I/O-säkerhetslösningar som tillhandahålls av allmänt tillgänglig hårdvara i hastigheter på flera hundra gigabit per sekund. Vi karakteriserar prestandan hos IOMMU and IOTLB (dvs. “I/O memory management unit” och “I/O virtual address translation cache”) vid 200 Gbps och undersöker möjligheterna att minska dess prestanda-overhead i kärnan av operativsystemet Linux. QC 20230206 Time-Critical Clouds (TCC) ULTRA

With the recent performance improvements in commodity hardware, low-cost commodity server-based storage has become a practical alternative to dedicated-storage appliances. Because of the high failure rate of commodity servers, data redundancy across multiple servers is required in a server-based storage system. However, the extra storage capacity for this redundancy significantly increases the system cost. Although erasure coding (EC) is a promising method to reduce the amount of redundant data, it requires distributing and encoding data among servers. There remains a need to reduce the performance impact of these processes involving much network traffic and processing overhead. Especially, the performance impact becomes significant for random-intensive applications. In this article, we propose a new lightweight redundancy control for server-based storage. Our proposed method uses a new local filesystem-based approach that avoids distributing data by adding data redundancy to locally stored user data. Our method switches the redundancy method of user data between replication and EC according to workloads to improve capacity efficiency while achieving higher performance. Our experiments show up to 230% better online-transaction-processing performance for our method compared with CephFS, a widely used alternative system. We also confirmed that our proposed method prevents unexpected performance degradation while achieving better capacity efficiency.

Editor’s notes: This article presents a technique to create robust DRAM PUFs with commodity hardware, and demonstrates its use on a Linux-based off-the-shelf device. —Rosario Cammarota, Intel Labs —Francesco Regazzoni, University of Amsterdam and Universita della Svizzera Italiana.

Network stacks currently implemented in operating systems can no longer cope with the packet rates offered by 10 Gbit Ethernet. Thus, frameworks were developed claiming to offer a faster alternative for this demand. These frameworks enable arbitrary packet processing systems to be built from commodity hardware handling a traffic rate of several 10 Gbit interfaces, entering a domain previously only available to custom-built hardware. In this paper, we survey various frameworks for high-performance packet IO and their interaction with a modular frameworks and specialized virtual network functions software for high-speed packet processing. We introduce a model to estimate and assess the performance of these packet processing frameworks. Moreover, we analyze the performance of the most prominent frameworks based on representative measurements in packet capturing scenarios. Therefore, we provide a comparison between them and select the area of applicability.

Observation of films of biological liquids allows finding markers of diseases such as diabetes or pneumonia. This may allow switching to more cost-effective diagnostic methods based on the use of relatively cheap commodity hardware required for optical microscopy. For this propose cuneiform dehydration of biological fluids is a promising method of medical diagnosis based on the study of structures in blood serum films. Currently, these structures are investigated at a qualitative level. It is known, that the geometric parameters of structures in blood serum films may be caused by some pathologies. In this paper the problems of image segmentation considered to create an image processing algorithm. Additionally, the images processing algorithm of blood serum films is described and experimental results are presented.

Driving a vehicle is an indispensable part of their everyday life for many people. However, sometimes this everyday life does not go as expected, as a lot of accidents happen on the public roads, and most of these accidents are due to inattentive driver behavior. Modern driver monitoring systems evaluate driver behavior by means of distinctive sensor technology and, if necessary, indicate undesirable driving behavior. However, many roadworthy vehicles do not have the possibility to implement such systems. Therefore, it seems to be interesting to investigate the implementation of such systems based on commodity hardware, e.g., smartphones, because nowadays almost every driver has a powerful smartphone equipped with many sensors at hand in the vehicle. Furthermore, recent advances in Machine Learning (ML) made it possible to analyze large amounts of data and to generate new outcomes. In this work we discuss how ML can be used for driver behavior recognition by improving an already existing threshold-based driver monitoring system with different ML-based techniques, Neural Networks and Random Forests, and evaluate their performance. We propose to use Microsoft Azure platform to analyze data generated by a Driver Monitoring System (DMS). Our results indicate ML as a useful technique for learning and adapting threshold-based reasoning about individual drivers’ states.

Deployment of 100Gigabit Ethernet (GbE) links challenges the packet processing limits of commodity hardware used for Network Functions Virtualization (NFV). Moreover, realizing chained network functions (i.e., service chains) necessitates the use of multiple CPU cores, or even multiple servers, to process packets from such high speed links. Our system Metron jointly exploits the underlying network and commodity servers’ resources: ( i ) to offload part of the packet processing logic to the network, ( ii ) by using smart tagging to setup and exploit the affinity of traffic classes, and ( iii ) by using tag-based hardware dispatching to carry out the remaining packet processing at the speed of the servers’ cores, with zero inter-core communication. Moreover, Metron transparently integrates, manages, and load balances proprietary “blackboxes” together with Metron service chains. Metron realizes stateful network functions at the speed of 100GbE network cards on a single server, while elastically and rapidly adapting to changing workload volumes. Our experiments demonstrate that Metron service chains can coexist with heterogeneous blackboxes, while still leveraging Metron’s accurate dispatching and load balancing. In summary, Metron has ( i ) 2.75–8× better efficiency, up to ( ii ) 4.7× lower latency, and ( iii ) 7.8× higher throughput than OpenBox, a state-of-the-art NFV system.

Timely detection of an individual’s stress level has the potential to improve stress management, thereby reducing the risk of adverse health consequences that may arise due to mismanagement of stress. Recent advances in wearable sensing have resulted in multiple approaches to detect and monitor stress with varying levels of accuracy. The most accurate methods, however, rely on clinical-grade sensors to measure physiological signals; they are often bulky, custom made, and expensive, hence limiting their adoption by researchers and the general public. In this article, we explore the viability of commercially available off-the-shelf sensors for stress monitoring. The idea is to be able to use cheap, nonclinical sensors to capture physiological signals and make inferences about the wearer’s stress level based on that data. We describe a system involving a popular off-the-shelf heart rate monitor, the Polar H7; we evaluated our system with 26 participants in both a controlled lab setting with three well-validated stress-inducing stimuli and in free-living field conditions. Our analysis shows that using the off-the-shelf sensor alone, we were able to detect stressful events with an F 1-score of up to 0.87 in the lab and 0.66 in the field, on par with clinical-grade sensors.

As Video Streaming and Analytics (VSA) systems become increasingly popular, serious privacy concerns have risen on exposing too much unnecessary private information to the VSA providers. Yet, it is challenging to protect privacy while still preserving desired VSA features, i.e., effective analytics, forensic support, resource efficiency, and real-time execution. In this paper, we present a VSA privacy enhancement system (PECAM), which addresses the above challenge with no change in the VSA back-end. PECAM leverages a novel Generative Adversarial Network to perform the privacy-enhanced securely-reversible video transformation. PECAM also incorporates a couple of system optimizations into its VSA workflow to reduce network bandwidth usage and enable real-time processing on cameras. We implement our PECAM prototype on commodity hardware and evaluate its performance via both security study and extensive experiments. Results demonstrate that PECAM can effectively enhance the visual privacy of VSA in the presence of an adversary, and its transformed videos, when taken as input for various VSA back-end tasks, maintain a 96% accuracy of corresponding original videos. Additionally, it performs 12.3× and 1.8× better than baseline methods in terms of the computing cost and network bandwidth usage, respectively.

Due to the advent of new technologies, devices, and communication tools such as social networking sites, the amount of data produced by mankind is growing rapidly every year. Big data is a collection of large datasets that cannot be processed using traditional computing techniques. MapReduce has been introduced to solve large-data computational problems. It is specifically designed to run on commodity hardware, and it depends on dividing and conquering principles. Nowadays, the focus of researchers has shifted towards Hadoop MapReduce. One of the most outstanding characteristics of MapReduce is data locality-aware scheduling. Data locality-aware scheduler is a further efficient solution to optimize one or a set of performance metrics such as data locality, energy consumption and job completion time. Similar to all situations, time and scheduling are the most important aspects of the MapReduce framework. Therefore, many scheduling algorithms have been proposed in the past decades. The main ideas of these algorithms are increasing data locality rate and decreasing the response and completion time. In this paper, a new hybrid scheduling algorithm has been proposed, which uses dynamic priority and localization ID techniques and focuses on increasing data locality rate and decreasing completion time. The proposed algorithm was evaluated and compared with Hadoop default schedulers (FIFO, Fair), by running concurrent workloads consisting of Wordcount and Terasort benchmarks. The experimental results show that the proposed algorithm is faster than FIFO and Fair scheduling, achieves higher data locality rate and avoids wasting resources.

The spatial join is a popular operation in spatial database systems and its evaluation is a well-studied problem. This paper reviews research and recent trends on spatial join evaluation. The complexity of different data types, the consideration of different join predicates, the use of modern commodity hardware, and support for parallel processing open the road to a number of interesting directions for future research, some of which we outline in the paper.

The reemergence of virtual reality (VR) in the past few years has led to affordable, high-quality commodityhardware that can offer new ways to teach, communicate, and engage with complex concepts. In a higher-education context,these immersive technologies make it possible to teach complex molecular topics in a way that may aid or even supersedetraditional approaches such as molecular models, textbook images, and traditional screen-based computational environments. Inthis work we describe a study involving 22 third-year UK undergraduate chemistry students who undertook a traditionalcomputational chemistry class complemented by an additional component which we designed to utilize real-time interactivemolecular dynamics simulations in VR (iMD-VR). Exploiting the flexibility of an open-source iMD-VR framework which werecently described, the students were given three short tasks to complete in iMD-VR: (1) interactive rearrangement of thechorismate molecule to prephenate using forces obtained from density functional theory calculations; (2) unbinding ofchorismate from the active site chorismate mutase enzyme using molecular mechanics forces calculated in real-time; and (3)docking of chorismate with chorismate mutase using real-time molecular mechanics forces. A student survey indicated that moststudents found the iMD-VR component more engaging than the traditional approach, and also that it improved their perceivededucational outcomes and their interest in continuing on in the field of computational sciences.

Hadoop Distributed File System (HDFS) is developed to efficiently store and handle the vast quantity of files in a distributed environment over a cluster of computers. Various commodity hardware forms the Hadoop cluster, which is inexpensive and easily available. The large number of small files stored in HDFS consumed more memory which lags the performance because small files consumed heavy load on NameNode. Thus, the efficiency of indexing and accessing the small files on HDFS is improved by several techniques, such as archive files, New Hadoop Archive (New HAR), CombineFileInputFormat (CFIF), and Sequence file generation. The archive file combines the small files into single blocks. The new HAR file combines the smaller files into a single large file. The CFIF module merges the multiple files into a single split using NameNode, and the sequence file combines all the small files into a single sequence. The indexing and accessing of a small file in HDFS are evaluated using performance metrics, such as processing time and memory usage. The experiment shows that the sequence file generation approach is efficient when compared to other approaches concerning file access time is 1.5[Formula: see text]s, memory usage is 20 KB in multi-node, and the processing time is 0.1[Formula: see text]s.

Real time facial animation for virtual 3D characters has important applications such as AR/VR, interactive 3D entertainment, pre-visualization and video conferencing. Yet despite important research breakthroughs in facial tracking and performance capture, there are very few commercial examples of real-time facial animation applications in the consumer market. Mass adoption requires realtime performance on commodity hardware and visually pleasing animation that is robust to real world conditions, without requiring manual calibration. We present an end-to-end deep learning framework for regressing facial animation weights from video that addresses most of these challenges. Our formulation is fast (3.2 ms), utilizes images of real human faces along with millions of synthetic rendered frames to train the network on real-world scenarios, and produces jitter-free visually pleasing animations.