|
|
Resource limiting and accounting facility for FreeBSD
Tomori, Rudolf ; Děcký, Martin (advisor) ; Bulej, Lubomír (referee)
This thesis analyses the implementation of the Linux cgroups subsystems responsible for limiting CPU time and disk I/O throughput. Apart from the Linux cgroups approach, an overview and short analysis of other possible approaches to the problem of limiting CPU time and disk I/O throughput is presented. Based on the analysis, the thesis proposes an extension to the resource limit- ing and accounting framework racct/rctl in the FreeBSD kernel. Our prototype implementation of this extension provides features that enable the administrators and privileged users to define disk I/O throughput limits and relative CPU time limits for a particular process, user or FreeBSD jail.
|
|
|
Integrated Network Traffic Processing Framework
Hrubý, Tomáš ; Tůma, Petr (advisor) ; Bulej, Lubomír (referee)
Knowledge of what data are carried by network links is crucial to be able to prevent attacks and to improve quality of services. Therefore it is important to develop network monitoring tools which can operate on speeds of new gigabit networks. This thesis discusses general principles of designing a highly flexible framework which is divided into several levels. These spread across various hardware and software environments. This allows us to keep up with a gigabit speed. We show details on an extension of the FFPF framework to run on top of an IXP based PCI board. In addition, we present an implementation of Ruler, a language for packet pattern matching and data anonymization, implemented for highspeed traffic monitoring using IXP network processor. This work also presents performance evaluation, discussion of bottle-necks, general problems and compares with other related projects.
|
|
|
Extending Java Performance Monitoring Framework with Support for Windows Performance Counters
Dráb, Martin ; Bulej, Lubomír (advisor) ; Kruliš, Martin (referee)
Java Performance Measurement Framework (JPMF) is a library that allows to collect performance data from underlying operating system. The main goal of the framework is to provide a way of performance data measurement regardless of the application under test. This goal sets the framework apart from many ad-hoc performance measurement solutions targeted at specific applications or middleware platforms. Such solutions collect certain performance data at fixed points of the execution of the application under test. The main goal of this thesis is to implement a library that allows to collect performance statistics of various kinds on machines running Microsoft Windows operating system. The library should be integrated into the framework, which extends its portability.
|
|
|
Reproducible Partial-Load Experiments in Workload Colocation Analysis
Podzimek, Andrej ; Bulej, Lubomír (advisor) ; Pena, Tomás Fernández (referee) ; van Hoorn, André (referee)
Hardware concurrency is common in all contemporary computer systems. Efficient use of hardware resources requires parallel processing and sharing of hardware by multiple workloads. Striking a balance between the conflicting goals of keeping servers highly utilized and maintaining a predictable performance level requires an informed choice of performance isolation techniques. Despite a broad choice of resource isolation mechanisms in operating systems, such as pinning of workloads to disjoint sets of processors, little is known about their effects on overall system performance and power consumption, especially under partial load conditions common in practice. Performance and performance interference under partial processor load is analyzed only after the fact, based on historical data, rather than proactively tested. This dissertation contributes a systematic approach to experimental analysis of application performance under partial processor load and in workload colocation scenarios. We first present a software tool set called Showstopper, capable of achieving and sustaining a variety of partial processor load conditions. Based on arbitrary pre-existing computationally intensive workloads, Showstopper replays processor load traces using feedback control mechanisms to maintain the desired load. As opposed to...
|
|
|
Universal Framework for Mngmt and Monitoring of Linux Traffic Control Facilities
Poduška, Jan ; Bulej, Lubomír (advisor) ; Peterka, Jiří (referee)
The terms "Traffic Control" and "Quality of Service" are used in the terminology of packet-switching based computer networks. They refer to control mechanisms, which can assign different priorities to different data flows or guarantee certain properties according to the requirements of an application (e.g. bandwidth, latency, accessibility). The properties guaranteed by the Quality of Service are especially important if the line capacity is limited, especially for applications that need to transmit data in real-time (IP telephony), since these types of applications usually require stable dataflow and are sensitive to delays. This thesis analyzes the current situation in Traffic Control configuration in Linux. The Linux kernel offers a variety of functions for the classification and scheduling of network traffic. However the configuration of traffic control is proving challenging, since the basic concept used is difficult to understand and the configuration language - "tc"- is very difficult to use. Based on the analysis of the current situation, a universal and extensible framework - the jpQOS - was designed and implemented. This allows easy to use and well arranged configuration and monitoring of the QoS using a unified graphical user interface.
|
|
|
Support for development of enterprise applications in Java
Krůček, Jiří ; Hnětynka, Petr (advisor) ; Bulej, Lubomír (referee)
The master thesis provides a comparative analysis of two broadly-used technologies for building Java-based enterprise applications, the Spring Framework 2.5 and Enterprise JavaBeans (EJB) 3.0. Its main goal is to serve as a valuable source of information about their key features, thus helping developers with the decision which technology to use according to given requirements on the application to be developed. First, an overview of Spring and EJB's basic ideas and core design concepts is given. Further, a detailed examination of their capabilities is carried out in three main areas of comparison: the thesis focuses on how they (1) address management of application business objects, (2) analyses a basic set of provided middleware services, and also (3) concerns with more practical issues related to various application development efforts, such as architecture, testing, and configuration of applications being developed by using these technologies. Each area of comparison is divided into several tightly-focused sections thoroughly discussing Spring and EJB's capabilities relevant to a particular subject, their strengths and weaknesses. At the end, their key features are summarized, evaluated, and some recommendations are given.
|
|
|
Extending Java Performance Monitoring Framework with Support for Linux Performance Data Sources
Júnoš, Peter ; Bulej, Lubomír (advisor) ; Babka, Vlastimil (referee)
Title: Extending Java Performance Monitoring Framework with Support for Linux Performance Data Sources Author: Peter Júnoš Department: Department of Distributed and Dependable Systems Supervisor: Ing. Lubomír Bulej, Ph.D Abstract: Java Perfomance Measurement Framework (JPMF) is a library, that is able to hook into program and gain performance information in given watchpoints. Notable drawback of currect implementation are missing sen- sors, that would be able to measure performance statistics related to stor- age, CPU, memory and network interfaces under Linux. Linux does not provide unified way of accessing such performance statis- tics. They can be accessed using virtual file systems, syscalls and netlink interface. The goal of this work is extending JPMF, so that it will provide measurement of mentioned performance statistics in a Linux-specific way. Keywords: performance measurement, JPMF, Linux, netlink stats, procfs stats 1
|
|
|
Intelligent proxy for mobile user interfaces to electronic health record
Mišúr, Juraj ; Bulej, Lubomír (advisor) ; Král, Jaroslav (referee)
In the present work we study possibilities of using the electronic healthcare record, created and implemented by Josef Špidlen, on thin user clients as web browser on PC, PDA or mobile phone. The task of this work is to present patient's medical informations to the users (physicians, nurses, emergency staff) in the fastest, well arranged and user-friendly form. The main benefit of this project is integration of patient's data from several sources (databases of electronic healthcare record MUDR), which every of them has only the fragment of knowledge about patient, as in real life separate physicians or hospitals. Proxy keeps the patient's data from all available sources and presents them as complete and compact image of the patient. This kind of global EHR data integration is a major help for every interaction with the patient with respect to his/her health condition.
|
|
|
Flexible Event Processing Subsystem for the Java Performance Monitoring Framework
Júnoš, Peter ; Bulej, Lubomír (advisor) ; Hnětynka, Petr (referee)
Java Performance Measurement Framework (JPMF) is a framework dedicated to description of points, where the performance is measured. This description is used to gather performance data in these running points. Data are gathered and written without any processing. The handling increases bandwidth and puts high load on the storage. JPMF does not provide any possibility for user to reduce this data. This thesis aims to solve the described problem by introduction of filtering and aggregation, that should reduce the bandwidth. Additionally, performance bottlenecks in various parts of JPMF are investigated and removed. Powered by TCPDF (www.tcpdf.org)
|
|
|
Uncertainty-Aware Self-Adaptive Cyber-Physical Systems
Al Ali, Rima ; Bulej, Lubomír (advisor) ; Pelliccione, Patrizio (referee) ; Bühnová, Barbora (referee)
Cyber-physical systems (CPS) need to be designed to deal with various forms of uncertainty associated with data contributing to the system's knowledge of the environment. Dealing with uncertainty requires adopting an appropriate model, which then allows making the right decisions and carrying out the right actions (possibly affecting the environment) based on imperfect information. However, choosing and incorporating a suitable model into CPS design is difficult, because it requires identifying the kind of uncertainty at hand as well as knowledge of suitable models and their application to dealing with the uncertainty. While inspiration can be found in other CPS designs, the details of dealing with uncertainty in another CPS can be confounded by domain-specific terminology, context, and requirements. To make this aspect of CPS design less daunting, we aim at providing an overview of approaches dealing with uncertainty in the design of CPS targeting collective behavior. To this end, we present a systematic review of relevant scientific projects with industrial leadership and synthesis of relations between system features, the kinds of uncertainty, and methods used to deal with it. The results provide an overview of uncertainty across different domains and challenges and reason about a guide for...
|
guest ::
