Effective Parameters on Response Time of Data Stream Management Systems

Size: px
Start display at page:

Download "Effective Parameters on Response Time of Data Stream Management Systems"

Transcription

1 Effective Parameters on Response Time of Data Stream Management Systems Shirin Mohammadi 1, Ali A. Safaei 1, Mostafa S. Hagjhoo 1 and Fatemeh Abdi 2 1 Department of Computer Engineering, Iran University of Science and Technology Tehran, Iran sh_mohammadi@comp.iust.ac.ir, safaeei@iust.ac.ir, haghjoom@iust.ac.ir 2 Department of Science, Babol-Branch, Islamic Azad University, Babol, Iran sulmaz_abdi@yahoo.com Abstract considering rapid and time variant (bursty) nature of data streams, data would rapidly lost its value while time is going on. So, the results with high response time are not reliable in Data Stream Management Systems (DSMSs). In other words, one of the most important factors in data stream management systems is the response time (i.e., the amount of time which a data stream tuple arrives into the system until it exits as the output while processed by a query). In this paper, the parameters which are more effective on DSMSs response time are considered, categorized and analyzed. Static and dynamic system properties, input and output data streams properties, and also properties of queries and query processing algorithms are factors which influence on DSMS s response time. Experimental results are shown to illustrate the impact of each parameter on the response time metric. Keywords: DSMS, Query processing, Response time, Effective parameters IKE'11-10th Int'l Conference on Information and Knowledge Engineering I. INTRODUCTION Traditional Database management systems as finite set of stored data are able to respond ad-hoc queries in best cases. But most of new applications need data stream processes which are infinite continuous streams of data [1, 2]. These applications need a new series of systems called as data stream management systems (DSMS). DSMSs provide requirements of mentions applications. Continuous data streams are infinite and rapid and varying time. DSMSs are able to discuss queries on data streams. These queries are executed in long time processes since being received continuously and are called as continuous queries [2]. Such queries with long lasting execution time need to be evaluated by the system until they finish [3]. One of the important factors of evaluating DSMSs is the response time of the system. Response time or tuple latency is defined as the average time which a tuple needs to be processed by a query. Of course, it includes all waiting times in buffers [3]. In other words, response time for an output tuple is the time period since providing all required information for concluding the output tuple until generation of the output tuple in real [4]. Generally, figure 1 represents DSMS architecture. Incoming data streams on the left produce data indefinitely and drive query processing. In many applications stream data also may be copied to an archive, for preservation and possible offline processing of expensive analysis or mining queries which we primarily concerned with the online processing of continuous queries. Finally, processing of such queries requires intermediate state, which denoted as Scratch Store in the figure and could be stored and accessed on disk or in memory. Applications or users register their Continuous Queries (CQ), which they remain active until explicit deregistration. Results are generally transmitted as output streams of data, although they could be relational results being updated over time [1]. Register Query Input Streams Scratch Store Streamed Result Data Stream Management System (DSMS) Stored Relation Figure 1- DSMS Architecture [1] Stored Result Archive The remained parts of this paper are structured as follows: related work is studied in section 2. Effective parameters on DSMS s response time are categorized and analyzed in section 3. In section 4, experimental results are shown to illustrate the impact of these parameters on the response time. Finally, we conclude the paper in section 5. II. RELATED WORKS Lots of researches on DSMSs are done [13]. Several primary samples of DSMSs like the STREAM [1,2], Aurora [5] and TelegraphCQ [14] are provided too. scheduling strategies of operators to process continuous queries on data streams varies from simple ones like the Round Robin [6], chain [15] and Greedy [6] to more complex ones [16,17]. Some of them are

2 provided for optimizing a performance factor [18, 19], while some others try to optimize multiple factors or a compound one [20, 21]. Totally most of these methods are provided to minimize tuple latency or the response time factor. Determination and analysis of effective parameters on response time of DSMSs are explicitly studied in few references which [22] is one of them. III. EFFECTIVE PARAMETERS ON RESPONSE TIME A. Categorizing the parameters based on DSMS architecture Response time of a query in a Data stream management system depends on several parameters, some with less influence and some with more importance. Considering the figure 2 effective parameters on response time of DSMSs are represented in total categories of: Data stream properties, Query properties, Query execution properties, Output properties, System properties (static conditions) and System condition (Dynamic). System properties (static Conditions) Data Stream(s) Queries execution Registered Queries Data Stream Management System (DSMS) System Conditions (dynamic) Output Figure 2 - categorizing the effective parameters on response time B. Data stream properties A data stream includes data elements generated in an infinite, continuous and rapid manner which varies in time. In other words Data stream of S is a set of s elements with time stamp of τ which the elements arrive to the system in time stamp order. The time stamp specifies the logical entrance time of a tuple into the data stream. By using discrete and regular domain of T a data stream can be defined as below [1]: S = { s, τ τ T} (1) 1) Type of elements in a data stream: Data stream S includes data elements s which are divided into three categories of well-structured data, semi-structured data and unstructured data [3]. 2) Domain of attributes: Domain or element type of tuples, belongs to attribute set of Att which its members are m types of a 1, a 2, a 3,, a m as: s = ( e1, e2,..., en ), ei Att, Att = { a1, a2,..., am} (2) 3) Number of attributes: each tuple s is represented by an ordered list of elements like (e 1,e 2,, e n ) which the n represents the number of attributes of a tuple. 4) Data stream distribution: The DSMSs usually don t have any control on order, rate and distribution of input streams [2]. Data stream distribution parameter represents the manner of distribution in stream arrival into the DSMS. Distribution of data arrival can be Uniform or bursty distribution such as the Pareto distribution. 5) Arrival rate into the system: A data stream includes an ordered set of tuples which arrives to the system continuously. Time rate of data which arrive to the system is called as arrival rate. Arrival information of a data stream usually could not be controlled or predicted. The produced tuples often has fluctuate and high arrival rate [3]. C. Query properties Continuous queries are those which have several processes on new data to generate new results. They are executed in a long lasting mode and generate the results continuously [3]. 1) Type of query: Registered queries of a DSMS can be categorized as below [2]: - One-time query which is evaluated in a specific moment of time. - Continuous query which is continuously evaluated until arriving tuples to the system. The output is generated continuously. It could be saved as a relation or updated by processing new tuples or the output could be sent as a data stream. 2) Number of operators in a query: Each query includes a set of operators. If Q represents a query andop represents the i i th operator, then n represents the number of operators in a query, as we have: Q = ( Op, 1 Op2,..., Op n ) (3) 3) Arrangement of operators in query plan: Arrangement of operators represents the query plan and its execution procedure. By changing the Arrangement and execution order of the operators, which occurs in query optimization they can lead to decrease cost of query execution and tuple latency. 4) Type of operators: A query includes a set of operators which is shown by symbolo. If we consider o j as the j th operator and m as number of operators in a system, then we have: Q = ( Op1, Op2,..., Opn ), Opi O, O = { o1, o2,..., om} (4) Each Op gets one or more streams as input and generates i an output. The output stream of each operator may provide the input for one or more other operators. D. Execution of Queries To execute multiple queries concurrently in a DSMS, first the query selection has to be executed. In second step the manner of accurate execution of queries has to be specified. The first and second steps are discussed as scheduling queries and scheduling query operators. 1) Scheduling queries: To schedule queries in noncontinuous systems algorithms like the FIFO can be used but they could not be applied in DSMSs considering the continuous nature of queries and streams. So we have to use scheduling algorithms with circular manner, like the RR and the WRR (weighted RR). The Quantum length in such scheduling algorithms is an important factor of response time

3 of the system. 2) Scheduling query operators: A DSMS includes several query plans which are connected as a DAG of operators which are connected by connector queues and transforms the input stream into the output stream. Considering the high rate and the input variable of data stream, also the limitations on resources such as processor and memory, scheduling algorithms of operators are important factors on responding the queries [5]. Scheduling algorithms like Round-Robin, FIFO, Greedy, Chain and two-phase are proposed algorithms in scheduling the query operators [6, 7]. E. Output properties 1) Type of output: Four types of output are considered for a DSMS: output as a data stream (continuous), output as a relation, output as an announcement and output at once. 2) Number of outputs: number of outputs affects the DSMS s response time since for example, preparing a stream as the output result takes less time rather than preparing a relation in addition to the output stream. F. System properties (static conditions) Depending on total or the static conditions of the DSMS, even in case of number of queries, amount of available memory, number of processors and processing capacity of the them, effective parameters on response time in this category can be considered as below: 1) Number of registered queries: Continuous queries are stored in DSMS and are used permanently to process the queries. In a DSMS the achieved data of various query executions from resources is processed. 2) query registration time : Queries are separated into two categories of below about the time of registration as below: -Predefined queries: before starting to receive data stream(s) the query is registered. This kind of query is often a continuous type of queries. -Ad-hoc queries: after starting data streams arrival, it can be continuous or one time use and may need to process previous data. 3) Number of processes (logical machines): In parallel processing of a query, we have number of N same processes p (logical machines) which are associated. These machines can be physical machines (such as processes of a multi-processor system or nodes of a clustered computer) or virtual machines (such as threads which are executed on each cores of a multi core processor) [9]. If a proper architecture for parallel processing of queries in DSMSs is provided, an increase in number of processes can highly improve the response time. 4) Processing capacity of processor(s): Time of completing a job by the computer depends on several factors which first one is the processor speed. Obviously the processing capacity of processors has reverse relation on the response time. 5) System architecture: Several types of architectures exist for parallel machines. The leading ones are shared memory, shared disk, shared nothing and hierarchical [10]. 6) The amount of available memory: If arrival rate of the input stream is greater than the output rate of the output stream or the sliding windows are mostly used in operators of query, the amount of memory consumption will increase. If the amount of required memory is greater than the amount of available memory, the system will be forced to discard the overload or to use secondary memories. If discarding the overload is prevented, it will influence the factor of validity and if the method of buffering on secondary memories is used, in cause of I/O operations, response time will increase. G. System condition (Dynamic) Dynamic status of the system includes changes which may occur while systems execution, like the amount of assigned memory to execute a specified query when we have several processes in processing state or occurring a deadlock. 1) Allocated processing capacity of processor(s) for query execution: Considering that the assigned processor(s) to the DSMS are simultaneously assigned to execute other processes, then always a part of the processor is assigned to execute the query. 2) Memory usage: When memory consumption exceeds the available memory, then overload problem occurs and the system is forced to discard some parts of data. As been considered in static state of the system, this influences the quality of output. 3) Overload in DSMS: Overload situation occurs when requested system resources exceeds the available capacity [8,11]. In such a situation, most part of data are accumulated in systems queues which may cause to increase response time if required main memory is available and in cases of insufficient main memory and requirement to data transfer with the secondary memory, vast delay occurs in generating results of the query. 4) Occurring deadlock: If three conditions to occur a deadlock are established in the DSMS, then failure occurs and the response time will infinitely increase. IV. EVALUATION As the evaluation process we developed a prototype which been implemented in the Java language with JDK 6.0 on a machine which was equipped with a Core i Intel processor and 6GB of RAM in Linux environment. The Input data set includes data of monitoring IP packets which is located in Internet Traffic Archive (ITA) [12]. One of traces, specifically the DEC-PKT contains all wide-area traffic of an hour between Digital Equipment Corporation and the rest of the world. This real-world data set is used in our experiments. Two types of monitored packets, the TCP and the UDP packets, are selected as input streams. Each TCP packet contains five items of source address, destination address, source port, destination port, and length. UDP packets are the same as TCP missing the length of packets. So elements of the stream are in type of well-structures data (tuple). Registered queries are continuous and registration time of them in system is pre-defined. To schedule queries the RR algorithm and to schedule query operators the FIFO

4 algorithm are used. Also type of relations is assumed. The experiment is done through a milliseconds time period with 10 times of runs, considering average results of these runs as the final experimental results. Effect of parameters of input rate, processing capacity of the processor, number of query operators, type of operators, Quantum length of scheduling between queries, number of registered queries of a system, number of processes and size of buffer memory are evaluated. 1) Effects of parameter of Stream arrival rate to the system: Considering the definition if response time based on "the time period since arriving a tuple until it exits as an output tuple" and considering the figure 3, if stream arrival rate increases as much the value that the system is unable to execute desired queries on input tuples, soon buffers of system will be filled of tuples and waiting time for tuples in queues will increase, then these cause the response time to increase. Conversely, if arrival rate of tuples of data streams is less that the response time, then the response time will decrease. Consequently input rate of data stream has direct relation with the response time. Figure 5 response time vs type of operator 4) Effects of parameter of Quantum length in scheduling queries: Considering the continuous nature of queries and that the best scheduling is one such as the RR, the quantum length been used in algorithm is an important parameter of response time. As shown in figure 6, in short quantum samples the response time is high. Then in an optimized mode, by increasing the quantum length the response time increases too. Figure 6 response time vs quantum length of the RR algorithm Figure 3- response time vs input rate of data stream 2) Effects of parameter of number of query operators: As shown in figure 4, as much as registered query operators in a system we have, it causes an arrived tuple to get more time to be processed. It means that response time increases while the number of operators increases. So, number of operators has direct effect on the response time. 5) Effects of parameter of number of registered queries of a system: Number of queries which are executed on input tuples is competing to achieve system resources such as the processor and memory and when resources are allocated to a query which is under execution, on execution tuples of other queries will be kept on a waiting queue and the response time increases. As shown in figure 7, the number of queries has direct effect on the response time. Figure 4- response time vs number of query operators 3) Effects of parameter of type of operators: Type of operator has great influence on response time. For example an operator such as the Join is more time consuming than the Selection operator. So as much as the response time of an operator been used in query increases, response time of DSMS will increase too. In figure 5 response time of six operators of Selection, Count, Max, Min, Union and Join are evaluated. Figure 7- response time vs number of registered queries 6) Effects of parameter of processing capacity of the processor(s): In figure 8, effects of number of queries parameter on a Dual core and a Quad core processor is studied. It is obvious that processing capacity of the processors has reverse relation with the response time. As much as the capacity increases the response time of each operator and consequently the total response time of the system will decrease.

5 time w.r.t the values of effective parameters and also using proper mechanisms to estimate the response time in a DSMS can be followed. Figure8 response time vs processing capacity of processors 7) Effects of parameter of number of queries: As we can see in figure 9, if a proper architecture is used for parallel processing of queries in a DSMS, increasing the number of processes can great influence on improving the response time. So the parameter of number of processes or N has direct p effect on the response time. Figure 9 response time vs number of processes 8) Effects of parameter of memory buffer size: Considering the evaluation result of figure 10, as much as the buffer size increases, tuples in waiting queues will wait more and the response time of the system increases, on the other hand when the buffer size is small, the system is forced to discard some tuples, so accuracy of result decreases. Figure 10 response time vs memory buffer size V. CONCLUSION AND FUTURE WORKS Rapid and bursty arrival of input data streams raises this fact that, to be fast is a major challenge for a DSMS. We considered the time period from arriving a tuple to the DSMS, until it exits as an output tuple as the response time of the system. Many different factors affect on response time of the system. In this paper, these factors were studied in six categories: data stream properties, query properties, query execution properties, output properties, static properties and also dynamic status of the system. Experimental results are shown to illustrate the impact of each parameter on the response time. As the further works, dynamically setting of the changeable parameters based on the of machine learning techniques, determining and providing a function to compute the response REFERENCES [1] A. Arasu, et. al., STREAM: The Stanford Stream Data Manager. In: Proc. of ACM SIGMOD, USA, [2] B. Shivnath, "Adaptive Query Processing in Data Stream Management Systems", Ph.D. thesis, Department of Computer Science, Stanford University, USA, September [3] S. Chakravarthy, et. al., Stream data processing: a quality of service perspective: modeling, scheduling, load shedding, and complex event processing, book, springer, USA, [4] Y. Bai, et. al., Minimizing Latency and Memory in DSMS-a Unified Approach to Quasi-Optimal Scheduling, Proceedings of the 2nd international workshop on Scalable stream processing system, University of California, Los Angeles, [5] D. Abadi, et. al., Aurora: A New Model and Architecture for Data Stream Management, In VLDB Journal (12)2: , August [6] B. Babcock, et. al., Operator Scheduling in Data Stream Systems, VLDB Journal, 13(4): , [7] D. Carney, et al., Operator Scheduling in a Data Stream Manager, in Proceedings of the 29th international conference on Very large data bases, Germany, pp , [8] N. Tatbul, et. al., Load Shedding Techniques for Data Stream Management Systems", Ph.D. thesis, Brown University, May [9] A.A.Safaei, et. al., Parallel Processing of Continuous Queries over Data Streams, Distributed and Parallel Databases, Volume 28, Numbers 2-3, , [10] A Silberschatz, Database System Concepts, book, 5th edition, [11] F. Reiss, et. al., Data Triage: An Adaptive Architecture for Load Shedding in TelegraphCQ, U.C. Berkeley Department of Electrical Engineering and Computer Science, And Intel Research Berkeley, Conference paper, Proceedings of the 21st International Conference on Data Engineering, ICDE 2005, 5-8 April 2005, Tokyo, Japan, [12] Internet Traffic Archive, [13] B. Babcock, et. al., Models and Issues in Data Stream Systems, Invited paper in Proc. of PODS 2002, June [14] S. Chandrasekaran, et al., TelegraphCQ: Continuous Dataflow Processing, in ACM SIGMOD, [15] B Babcock, et al., Chain: Operator Scheduling for Memory Minimization in Data Stream Systems, Proceedings of the ACM SIGMOD International conference, [16] M. A. Sharaf, Preemptive Rate-Based Operator Scheduling in a Data Stream Management System, in IEEE/AICCSA, [17] M. S. Soliman, G. Tan, Operator-scheduling using dynamic chain for continuous-query processing, IEEE Int. Conference on Computer Science and Software Engineering, [18] S. Chakravarthy, et. al., Scheduling Strategies and Their Evaluation in a Data Stream Management System, Springer LNCS 4042, [19] M. A. Sharaf, et. al., Scheduling Continuous Queries in Data Stream Management Systems, in PVLDB, [20] B. Srivastava, et. al., Exploiting k-constraints to Reduce Memory Overhead in Continuous Queries over Data Streams, Technical Report, November [21] M. Ghalambor, et. al., DSMS scheduling regarding complex QoS metrics, IEEE/ACS International Conference on Computer Systems and Applications (AICCSA), May [22] S. Chakravarthy, et. al., Stream data processing: a quality of service perspective: modeling, scheduling, load shedding, and complex event processing, book, springer, USA, 2009.

ADAPTIVE DATA STREAM MANAGEMENT SYSTEM USING LEARNING AUTOMATA

ADAPTIVE DATA STREAM MANAGEMENT SYSTEM USING LEARNING AUTOMATA ADATIVE DATA STREAM MANAGEMENT SYSTEM USING LEARNING AUTOMATA Shirin Mohammadi 1, Ali A. Safaei 2, Fatemeh Abdi 3 and Mostafa S. Haghjoo 4 1 Department of Computer Engineering, Iran University of Science

More information

Preemptive Rate-based Operator Scheduling in a Data Stream Management System

Preemptive Rate-based Operator Scheduling in a Data Stream Management System Preemptive Rate-based Operator Scheduling in a Data Stream Management System Mohamed A. Sharaf, Panos K. Chrysanthis, Alexandros Labrinidis Department of Computer Science University of Pittsburgh Pittsburgh,

More information

Optimizing Timestamp Management in Data Stream Management Systems

Optimizing Timestamp Management in Data Stream Management Systems Optimizing Timestamp Management in Data Stream Management Systems Yijian Bai bai@cs.ucla.edu Hetal Thakkar hthakkar@cs.ucla.edu Haixun Wang IBM T. J. Watson haixun@us.ibm.com Carlo Zaniolo zaniolo@cs.ucla.edu

More information

Control-Based Load Shedding in Data Stream Management Systems

Control-Based Load Shedding in Data Stream Management Systems Control-Based Load Shedding in Data Stream Management Systems Yi-Cheng Tu and Sunil Prabhakar Department of Computer Sciences, Purdue University West Lafayette, IN 4797, USA Abstract Load shedding has

More information

Processing of Flow Accounting Data in Java: Framework Design and Performance Evaluation

Processing of Flow Accounting Data in Java: Framework Design and Performance Evaluation Processing of Flow Accounting Data in Java: Framework Design and Performance Evaluation Jochen Kögel and Sebastian Scholz Institute of Communication Networks and Computer Engineering (IKR) University of

More information

Load Distribution in Large Scale Network Monitoring Infrastructures

Load Distribution in Large Scale Network Monitoring Infrastructures Load Distribution in Large Scale Network Monitoring Infrastructures Josep Sanjuàs-Cuxart, Pere Barlet-Ros, Gianluca Iannaccone, and Josep Solé-Pareta Universitat Politècnica de Catalunya (UPC) {jsanjuas,pbarlet,pareta}@ac.upc.edu

More information

Task Scheduling in Data Stream Processing. Task Scheduling in Data Stream Processing

Task Scheduling in Data Stream Processing. Task Scheduling in Data Stream Processing Task Scheduling in Data Stream Processing Task Scheduling in Data Stream Processing Zbyněk Falt and Jakub Yaghob Zbyněk Falt and Jakub Yaghob Department of Software Engineering, Charles University, Department

More information

Process Scheduling CS 241. February 24, 2012. Copyright University of Illinois CS 241 Staff

Process Scheduling CS 241. February 24, 2012. Copyright University of Illinois CS 241 Staff Process Scheduling CS 241 February 24, 2012 Copyright University of Illinois CS 241 Staff 1 Announcements Mid-semester feedback survey (linked off web page) MP4 due Friday (not Tuesday) Midterm Next Tuesday,

More information

A Group based Time Quantum Round Robin Algorithm using Min-Max Spread Measure

A Group based Time Quantum Round Robin Algorithm using Min-Max Spread Measure A Group based Quantum Round Robin Algorithm using Min-Max Spread Measure Sanjaya Kumar Panda Department of CSE NIT, Rourkela Debasis Dash Department of CSE NIT, Rourkela Jitendra Kumar Rout Department

More information

Introduction. Application Performance in the QLinux Multimedia Operating System. Solution: QLinux. Introduction. Outline. QLinux Design Principles

Introduction. Application Performance in the QLinux Multimedia Operating System. Solution: QLinux. Introduction. Outline. QLinux Design Principles Application Performance in the QLinux Multimedia Operating System Sundaram, A. Chandra, P. Goyal, P. Shenoy, J. Sahni and H. Vin Umass Amherst, U of Texas Austin ACM Multimedia, 2000 Introduction General

More information

Performance Evaluation of VMXNET3 Virtual Network Device VMware vsphere 4 build 164009

Performance Evaluation of VMXNET3 Virtual Network Device VMware vsphere 4 build 164009 Performance Study Performance Evaluation of VMXNET3 Virtual Network Device VMware vsphere 4 build 164009 Introduction With more and more mission critical networking intensive workloads being virtualized

More information

A New Hybrid Load Balancing Algorithm in Grid Computing Systems

A New Hybrid Load Balancing Algorithm in Grid Computing Systems A New Hybrid Load Balancing Algorithm in Grid Computing Systems Leyli Mohammad Khanli 1, Behnaz Didevar 2 1 University of Tabriz, Department of Computer Science, 2 Department of Technical and Engineering,

More information

Using Fuzzy Logic Control to Provide Intelligent Traffic Management Service for High-Speed Networks ABSTRACT:

Using Fuzzy Logic Control to Provide Intelligent Traffic Management Service for High-Speed Networks ABSTRACT: Using Fuzzy Logic Control to Provide Intelligent Traffic Management Service for High-Speed Networks ABSTRACT: In view of the fast-growing Internet traffic, this paper propose a distributed traffic management

More information

ICS 143 - Principles of Operating Systems

ICS 143 - Principles of Operating Systems ICS 143 - Principles of Operating Systems Lecture 5 - CPU Scheduling Prof. Nalini Venkatasubramanian nalini@ics.uci.edu Note that some slides are adapted from course text slides 2008 Silberschatz. Some

More information

Real Time Network Server Monitoring using Smartphone with Dynamic Load Balancing

Real Time Network Server Monitoring using Smartphone with Dynamic Load Balancing www.ijcsi.org 227 Real Time Network Server Monitoring using Smartphone with Dynamic Load Balancing Dhuha Basheer Abdullah 1, Zeena Abdulgafar Thanoon 2, 1 Computer Science Department, Mosul University,

More information

Self-Compressive Approach for Distributed System Monitoring

Self-Compressive Approach for Distributed System Monitoring Self-Compressive Approach for Distributed System Monitoring Akshada T Bhondave Dr D.Y Patil COE Computer Department, Pune University, India Santoshkumar Biradar Assistant Prof. Dr D.Y Patil COE, Computer

More information

CPU Scheduling. Basic Concepts. Basic Concepts (2) Basic Concepts Scheduling Criteria Scheduling Algorithms Batch systems Interactive systems

CPU Scheduling. Basic Concepts. Basic Concepts (2) Basic Concepts Scheduling Criteria Scheduling Algorithms Batch systems Interactive systems Basic Concepts Scheduling Criteria Scheduling Algorithms Batch systems Interactive systems Based on original slides by Silberschatz, Galvin and Gagne 1 Basic Concepts CPU I/O Burst Cycle Process execution

More information

Quantifying the Performance Degradation of IPv6 for TCP in Windows and Linux Networking

Quantifying the Performance Degradation of IPv6 for TCP in Windows and Linux Networking Quantifying the Performance Degradation of IPv6 for TCP in Windows and Linux Networking Burjiz Soorty School of Computing and Mathematical Sciences Auckland University of Technology Auckland, New Zealand

More information

Design Issues in a Bare PC Web Server

Design Issues in a Bare PC Web Server Design Issues in a Bare PC Web Server Long He, Ramesh K. Karne, Alexander L. Wijesinha, Sandeep Girumala, and Gholam H. Khaksari Department of Computer & Information Sciences, Towson University, 78 York

More information

A Flexible Network Monitoring Tool Based on a Data Stream Management System

A Flexible Network Monitoring Tool Based on a Data Stream Management System A Flexible Network Monitoring Tool Based on a Data Stream Management System Natascha Petry Ligocki, Carmem S. Hara Departamento de Informática Universidade Federal do Paraná Curitiba-PR, Brazil {ligocki,carmem}@inf.ufpr.br

More information

Comp 204: Computer Systems and Their Implementation. Lecture 12: Scheduling Algorithms cont d

Comp 204: Computer Systems and Their Implementation. Lecture 12: Scheduling Algorithms cont d Comp 204: Computer Systems and Their Implementation Lecture 12: Scheduling Algorithms cont d 1 Today Scheduling continued Multilevel queues Examples Thread scheduling 2 Question A starvation-free job-scheduling

More information

Performance Modeling and Analysis of a Database Server with Write-Heavy Workload

Performance Modeling and Analysis of a Database Server with Write-Heavy Workload Performance Modeling and Analysis of a Database Server with Write-Heavy Workload Manfred Dellkrantz, Maria Kihl 2, and Anders Robertsson Department of Automatic Control, Lund University 2 Department of

More information

A Framework For Supporting Load Shedding in Data Stream Management Systems

A Framework For Supporting Load Shedding in Data Stream Management Systems Department of Computer Science and Engineering University of Texas at Arlington Arlington, TX 76019 A Framework For Supporting Load Shedding in Data Stream Management Systems Qingchun Jiang and Sharma

More information

Objectives. Chapter 5: Process Scheduling. Chapter 5: Process Scheduling. 5.1 Basic Concepts. To introduce CPU scheduling

Objectives. Chapter 5: Process Scheduling. Chapter 5: Process Scheduling. 5.1 Basic Concepts. To introduce CPU scheduling Objectives To introduce CPU scheduling To describe various CPU-scheduling algorithms Chapter 5: Process Scheduling To discuss evaluation criteria for selecting the CPUscheduling algorithm for a particular

More information

A Review on Load Balancing In Cloud Computing 1

A Review on Load Balancing In Cloud Computing 1 www.ijecs.in International Journal Of Engineering And Computer Science ISSN:2319-7242 Volume 4 Issue 6 June 2015, Page No. 12333-12339 A Review on Load Balancing In Cloud Computing 1 Peenaz Pathak, 2 Er.Kamna

More information

COMPARATIVE ANALYSIS OF DIFFERENT QUEUING MECHANISMS IN HETROGENEOUS NETWORKS

COMPARATIVE ANALYSIS OF DIFFERENT QUEUING MECHANISMS IN HETROGENEOUS NETWORKS COMPARATIVE ANALYSIS OF DIFFERENT QUEUING MECHANISMS IN HETROGENEOUS NETWORKS Shubhangi Rastogi 1, Samir Srivastava 2 M.Tech Student, Computer Science and Engineering, KNIT, Sultanpur, India 1 Associate

More information

PART III. OPS-based wide area networks

PART III. OPS-based wide area networks PART III OPS-based wide area networks Chapter 7 Introduction to the OPS-based wide area network 7.1 State-of-the-art In this thesis, we consider the general switch architecture with full connectivity

More information

DSEC: A Data Stream Engine Based Clinical Information System *

DSEC: A Data Stream Engine Based Clinical Information System * DSEC: A Data Stream Engine Based Clinical Information System * Yu Fan, Hongyan Li **, Zijing Hu, Jianlong Gao, Haibin Liu, Shiwei Tang, and Xinbiao Zhou National Laboratory on Machine Perception, School

More information

Transport Layer Protocols

Transport Layer Protocols Transport Layer Protocols Version. Transport layer performs two main tasks for the application layer by using the network layer. It provides end to end communication between two applications, and implements

More information

RTSTREAM: Real-Time Query Processing for Data Streams

RTSTREAM: Real-Time Query Processing for Data Streams RTSTREAM: Real-Time Query Processing for Data Streams Yuan Wei Sang H Son John A Stankovic Department of Computer Science University of Virginia Charlottesville, Virginia, 2294-474 E-mail: {yw3f, son,

More information

5 Performance Management for Web Services. Rolf Stadler School of Electrical Engineering KTH Royal Institute of Technology. stadler@ee.kth.

5 Performance Management for Web Services. Rolf Stadler School of Electrical Engineering KTH Royal Institute of Technology. stadler@ee.kth. 5 Performance Management for Web Services Rolf Stadler School of Electrical Engineering KTH Royal Institute of Technology stadler@ee.kth.se April 2008 Overview Service Management Performance Mgt QoS Mgt

More information

Flexible Data Streaming In Stream Cloud

Flexible Data Streaming In Stream Cloud Flexible Data Streaming In Stream Cloud J.Rethna Virgil Jeny 1, Chetan Anil Joshi 2 Associate Professor, Dept. of IT, AVCOE, Sangamner,University of Pune, Maharashtra, India 1 Student of M.E.(IT), AVCOE,

More information

COMPUTING SCIENCE. Scalable and Responsive Event Processing in the Cloud. Visalakshmi Suresh, Paul Ezhilchelvan and Paul Watson

COMPUTING SCIENCE. Scalable and Responsive Event Processing in the Cloud. Visalakshmi Suresh, Paul Ezhilchelvan and Paul Watson COMPUTING SCIENCE Scalable and Responsive Event Processing in the Cloud Visalakshmi Suresh, Paul Ezhilchelvan and Paul Watson TECHNICAL REPORT SERIES No CS-TR-1251 June 2011 TECHNICAL REPORT SERIES No

More information

W4118 Operating Systems. Instructor: Junfeng Yang

W4118 Operating Systems. Instructor: Junfeng Yang W4118 Operating Systems Instructor: Junfeng Yang Outline Introduction to scheduling Scheduling algorithms 1 Direction within course Until now: interrupts, processes, threads, synchronization Mostly mechanisms

More information

Content-Aware Load Balancing using Direct Routing for VOD Streaming Service

Content-Aware Load Balancing using Direct Routing for VOD Streaming Service Content-Aware Load Balancing using Direct Routing for VOD Streaming Service Young-Hwan Woo, Jin-Wook Chung, Seok-soo Kim Dept. of Computer & Information System, Geo-chang Provincial College, Korea School

More information

Network congestion control using NetFlow

Network congestion control using NetFlow Network congestion control using NetFlow Maxim A. Kolosovskiy Elena N. Kryuchkova Altai State Technical University, Russia Abstract The goal of congestion control is to avoid congestion in network elements.

More information

A Comparison Study of Qos Using Different Routing Algorithms In Mobile Ad Hoc Networks

A Comparison Study of Qos Using Different Routing Algorithms In Mobile Ad Hoc Networks A Comparison Study of Qos Using Different Routing Algorithms In Mobile Ad Hoc Networks T.Chandrasekhar 1, J.S.Chakravarthi 2, K.Sravya 3 Professor, Dept. of Electronics and Communication Engg., GIET Engg.

More information

Policy Distribution Methods for Function Parallel Firewalls

Policy Distribution Methods for Function Parallel Firewalls Policy Distribution Methods for Function Parallel Firewalls Michael R. Horvath GreatWall Systems Winston-Salem, NC 27101, USA Errin W. Fulp Department of Computer Science Wake Forest University Winston-Salem,

More information

Objectives. Chapter 5: CPU Scheduling. CPU Scheduler. Non-preemptive and preemptive. Dispatcher. Alternating Sequence of CPU And I/O Bursts

Objectives. Chapter 5: CPU Scheduling. CPU Scheduler. Non-preemptive and preemptive. Dispatcher. Alternating Sequence of CPU And I/O Bursts Objectives Chapter 5: CPU Scheduling Introduce CPU scheduling, which is the basis for multiprogrammed operating systems Describe various CPU-scheduling algorithms Discuss evaluation criteria for selecting

More information

FileNet System Manager Dashboard Help

FileNet System Manager Dashboard Help FileNet System Manager Dashboard Help Release 3.5.0 June 2005 FileNet is a registered trademark of FileNet Corporation. All other products and brand names are trademarks or registered trademarks of their

More information

Shareability and Locality Aware Scheduling Algorithm in Hadoop for Mobile Cloud Computing

Shareability and Locality Aware Scheduling Algorithm in Hadoop for Mobile Cloud Computing Shareability and Locality Aware Scheduling Algorithm in Hadoop for Mobile Cloud Computing Hsin-Wen Wei 1,2, Che-Wei Hsu 2, Tin-Yu Wu 3, Wei-Tsong Lee 1 1 Department of Electrical Engineering, Tamkang University

More information

Deciding which process to run. (Deciding which thread to run) Deciding how long the chosen process can run

Deciding which process to run. (Deciding which thread to run) Deciding how long the chosen process can run SFWR ENG 3BB4 Software Design 3 Concurrent System Design 2 SFWR ENG 3BB4 Software Design 3 Concurrent System Design 11.8 10 CPU Scheduling Chapter 11 CPU Scheduling Policies Deciding which process to run

More information

1. The subnet must prevent additional packets from entering the congested region until those already present can be processed.

1. The subnet must prevent additional packets from entering the congested region until those already present can be processed. Congestion Control When one part of the subnet (e.g. one or more routers in an area) becomes overloaded, congestion results. Because routers are receiving packets faster than they can forward them, one

More information

Fast Prototyping Network Data Mining Applications. Gianluca Iannaccone Intel Research Berkeley

Fast Prototyping Network Data Mining Applications. Gianluca Iannaccone Intel Research Berkeley Fast Prototyping Network Data Mining Applications Gianluca Iannaccone Intel Research Berkeley Motivation Developing new network monitoring apps is unnecessarily time-consuming Familiar development steps

More information

Operating System Tutorial

Operating System Tutorial Operating System Tutorial OPERATING SYSTEM TUTORIAL Simply Easy Learning by tutorialspoint.com tutorialspoint.com i ABOUT THE TUTORIAL Operating System Tutorial An operating system (OS) is a collection

More information

Data Stream Management

Data Stream Management Data Stream Management Synthesis Lectures on Data Management Editor M. Tamer Özsu, University of Waterloo Synthesis Lectures on Data Management is edited by Tamer Özsu of the University of Waterloo. The

More information

STUDY AND SIMULATION OF A DISTRIBUTED REAL-TIME FAULT-TOLERANCE WEB MONITORING SYSTEM

STUDY AND SIMULATION OF A DISTRIBUTED REAL-TIME FAULT-TOLERANCE WEB MONITORING SYSTEM STUDY AND SIMULATION OF A DISTRIBUTED REAL-TIME FAULT-TOLERANCE WEB MONITORING SYSTEM Albert M. K. Cheng, Shaohong Fang Department of Computer Science University of Houston Houston, TX, 77204, USA http://www.cs.uh.edu

More information

A Practical Evaluation of Load Shedding in Data Stream Management Systems for Network Monitoring

A Practical Evaluation of Load Shedding in Data Stream Management Systems for Network Monitoring A Practical Evaluation of Load Shedding in Data Stream Management Systems for Network Monitoring Jarle Søberg, Kjetil H. Hernes, Matti Siekkinen, Vera Goebel, and Thomas Plagemann University of Oslo, Department

More information

Data Stream Management System

Data Stream Management System Case Study of CSG712 Data Stream Management System Jian Wen Spring 2008 Northeastern University Outline Traditional DBMS v.s. Data Stream Management System First-generation: Aurora Run-time architecture

More information

Research of Railway Wagon Flow Forecast System Based on Hadoop-Hazelcast

Research of Railway Wagon Flow Forecast System Based on Hadoop-Hazelcast International Conference on Civil, Transportation and Environment (ICCTE 2016) Research of Railway Wagon Flow Forecast System Based on Hadoop-Hazelcast Xiaodong Zhang1, a, Baotian Dong1, b, Weijia Zhang2,

More information

OpenFlow Based Load Balancing

OpenFlow Based Load Balancing OpenFlow Based Load Balancing Hardeep Uppal and Dane Brandon University of Washington CSE561: Networking Project Report Abstract: In today s high-traffic internet, it is often desirable to have multiple

More information

Data Management in the Cloud

Data Management in the Cloud Data Management in the Cloud Ryan Stern stern@cs.colostate.edu : Advanced Topics in Distributed Systems Department of Computer Science Colorado State University Outline Today Microsoft Cloud SQL Server

More information

FP-Hadoop: Efficient Execution of Parallel Jobs Over Skewed Data

FP-Hadoop: Efficient Execution of Parallel Jobs Over Skewed Data FP-Hadoop: Efficient Execution of Parallel Jobs Over Skewed Data Miguel Liroz-Gistau, Reza Akbarinia, Patrick Valduriez To cite this version: Miguel Liroz-Gistau, Reza Akbarinia, Patrick Valduriez. FP-Hadoop:

More information

Where IT perceptions are reality. Test Report. OCe14000 Performance. Featuring Emulex OCe14102 Network Adapters Emulex XE100 Offload Engine

Where IT perceptions are reality. Test Report. OCe14000 Performance. Featuring Emulex OCe14102 Network Adapters Emulex XE100 Offload Engine Where IT perceptions are reality Test Report OCe14000 Performance Featuring Emulex OCe14102 Network Adapters Emulex XE100 Offload Engine Document # TEST2014001 v9, October 2014 Copyright 2014 IT Brand

More information

Dynamic Adaptive Feedback of Load Balancing Strategy

Dynamic Adaptive Feedback of Load Balancing Strategy Journal of Information & Computational Science 8: 10 (2011) 1901 1908 Available at http://www.joics.com Dynamic Adaptive Feedback of Load Balancing Strategy Hongbin Wang a,b, Zhiyi Fang a,, Shuang Cui

More information

Announcements. Basic Concepts. Histogram of Typical CPU- Burst Times. Dispatcher. CPU Scheduler. Burst Cycle. Reading

Announcements. Basic Concepts. Histogram of Typical CPU- Burst Times. Dispatcher. CPU Scheduler. Burst Cycle. Reading Announcements Reading Chapter 5 Chapter 7 (Monday or Wednesday) Basic Concepts CPU I/O burst cycle Process execution consists of a cycle of CPU execution and I/O wait. CPU burst distribution What are the

More information

Load balancing model for Cloud Data Center ABSTRACT:

Load balancing model for Cloud Data Center ABSTRACT: Load balancing model for Cloud Data Center ABSTRACT: Cloud data center management is a key problem due to the numerous and heterogeneous strategies that can be applied, ranging from the VM placement to

More information

ZEN LOAD BALANCER EE v3.04 DATASHEET The Load Balancing made easy

ZEN LOAD BALANCER EE v3.04 DATASHEET The Load Balancing made easy ZEN LOAD BALANCER EE v3.04 DATASHEET The Load Balancing made easy OVERVIEW The global communication and the continuous growth of services provided through the Internet or local infrastructure require to

More information

Improving Distributed Workload Performance by Sharing Both CPU and Memory Resources

Improving Distributed Workload Performance by Sharing Both CPU and Memory Resources Improving Distributed Workload Performance by Sharing Both CPU and Memory Resources Xiaodong Zhang Yanxia Qu Li Xiao Department of Computer Science College of William and Mary Williamsburg, VA 387-8795

More information

Web Server Software Architectures

Web Server Software Architectures Web Server Software Architectures Author: Daniel A. Menascé Presenter: Noshaba Bakht Web Site performance and scalability 1.workload characteristics. 2.security mechanisms. 3. Web cluster architectures.

More information

Grid Computing Approach for Dynamic Load Balancing

Grid Computing Approach for Dynamic Load Balancing International Journal of Computer Sciences and Engineering Open Access Review Paper Volume-4, Issue-1 E-ISSN: 2347-2693 Grid Computing Approach for Dynamic Load Balancing Kapil B. Morey 1*, Sachin B. Jadhav

More information

Attack graph analysis using parallel algorithm

Attack graph analysis using parallel algorithm Attack graph analysis using parallel algorithm Dr. Jamali Mohammad (m.jamali@yahoo.com) Ashraf Vahid, MA student of computer software, Shabestar Azad University (vahid.ashraf@yahoo.com) Ashraf Vida, MA

More information

Stream Processing on GPUs Using Distributed Multimedia Middleware

Stream Processing on GPUs Using Distributed Multimedia Middleware Stream Processing on GPUs Using Distributed Multimedia Middleware Michael Repplinger 1,2, and Philipp Slusallek 1,2 1 Computer Graphics Lab, Saarland University, Saarbrücken, Germany 2 German Research

More information

Implementing New Approach for Enhancing Performance and Throughput in a Distributed Database

Implementing New Approach for Enhancing Performance and Throughput in a Distributed Database 290 The International Arab Journal of Information Technology, Vol. 10, No. 3, May 2013 Implementing New Approach for Enhancing Performance and in a Distributed Database Khaled Maabreh 1 and Alaa Al-Hamami

More information

Research on Errors of Utilized Bandwidth Measured by NetFlow

Research on Errors of Utilized Bandwidth Measured by NetFlow Research on s of Utilized Bandwidth Measured by NetFlow Haiting Zhu 1, Xiaoguo Zhang 1,2, Wei Ding 1 1 School of Computer Science and Engineering, Southeast University, Nanjing 211189, China 2 Electronic

More information

NetFlow Collection and Processing Cartridge Pack User Guide Release 6.0

NetFlow Collection and Processing Cartridge Pack User Guide Release 6.0 [1]Oracle Communications Offline Mediation Controller NetFlow Collection and Processing Cartridge Pack User Guide Release 6.0 E39478-01 June 2015 Oracle Communications Offline Mediation Controller NetFlow

More information

The Three-level Approaches for Differentiated Service in Clustering Web Server

The Three-level Approaches for Differentiated Service in Clustering Web Server The Three-level Approaches for Differentiated Service in Clustering Web Server Myung-Sub Lee and Chang-Hyeon Park School of Computer Science and Electrical Engineering, Yeungnam University Kyungsan, Kyungbuk

More information

Network Performance Monitoring at Small Time Scales

Network Performance Monitoring at Small Time Scales Network Performance Monitoring at Small Time Scales Konstantina Papagiannaki, Rene Cruz, Christophe Diot Sprint ATL Burlingame, CA dina@sprintlabs.com Electrical and Computer Engineering Department University

More information

QoS & Traffic Management

QoS & Traffic Management QoS & Traffic Management Advanced Features for Managing Application Performance and Achieving End-to-End Quality of Service in Data Center and Cloud Computing Environments using Chelsio T4 Adapters Chelsio

More information

MEASURING WORKLOAD PERFORMANCE IS THE INFRASTRUCTURE A PROBLEM?

MEASURING WORKLOAD PERFORMANCE IS THE INFRASTRUCTURE A PROBLEM? MEASURING WORKLOAD PERFORMANCE IS THE INFRASTRUCTURE A PROBLEM? Ashutosh Shinde Performance Architect ashutosh_shinde@hotmail.com Validating if the workload generated by the load generating tools is applied

More information

REAL TIME OPERATING SYSTEMS. Lesson-18:

REAL TIME OPERATING SYSTEMS. Lesson-18: REAL TIME OPERATING SYSTEMS Lesson-18: Round Robin Time Slicing of tasks of equal priorities 1 1. Common scheduling models 2 Common scheduling models Cooperative Scheduling of ready tasks in a circular

More information

Implementation of a Hardware Architecture to Support High-speed Database Insertion on the Internet

Implementation of a Hardware Architecture to Support High-speed Database Insertion on the Internet Implementation of a Hardware Architecture to Support High-speed Database Insertion on the Internet Yusuke Nishida 1 and Hiroaki Nishi 1 1 A Department of Science and Technology, Keio University, Yokohama,

More information

Operating Systems Lecture #6: Process Management

Operating Systems Lecture #6: Process Management Lecture #6: Process Written by based on the lecture series of Dr. Dayou Li and the book Understanding 4th ed. by I.M.Flynn and A.McIver McHoes (2006) Department of Computer Science and Technology,., 2013

More information

An XML Framework for Integrating Continuous Queries, Composite Event Detection, and Database Condition Monitoring for Multiple Data Streams

An XML Framework for Integrating Continuous Queries, Composite Event Detection, and Database Condition Monitoring for Multiple Data Streams An XML Framework for Integrating Continuous Queries, Composite Event Detection, and Database Condition Monitoring for Multiple Data Streams Susan D. Urban 1, Suzanne W. Dietrich 1, 2, and Yi Chen 1 Arizona

More information

How To Monitor And Test An Ethernet Network On A Computer Or Network Card

How To Monitor And Test An Ethernet Network On A Computer Or Network Card 3. MONITORING AND TESTING THE ETHERNET NETWORK 3.1 Introduction The following parameters are covered by the Ethernet performance metrics: Latency (delay) the amount of time required for a frame to travel

More information

A Framework for Performance Analysis and Tuning in Hadoop Based Clusters

A Framework for Performance Analysis and Tuning in Hadoop Based Clusters A Framework for Performance Analysis and Tuning in Hadoop Based Clusters Garvit Bansal Anshul Gupta Utkarsh Pyne LNMIIT, Jaipur, India Email: [garvit.bansal anshul.gupta utkarsh.pyne] @lnmiit.ac.in Manish

More information

Lecture 16: Quality of Service. CSE 123: Computer Networks Stefan Savage

Lecture 16: Quality of Service. CSE 123: Computer Networks Stefan Savage Lecture 16: Quality of Service CSE 123: Computer Networks Stefan Savage Final Next week (trust Blink wrt time/location) Will cover entire class Style similar to midterm I ll post a sample (i.e. old) final

More information

Multiprocessor Scheduling and Scheduling in Linux Kernel 2.6

Multiprocessor Scheduling and Scheduling in Linux Kernel 2.6 Multiprocessor Scheduling and Scheduling in Linux Kernel 2.6 Winter Term 2008 / 2009 Jun.-Prof. Dr. André Brinkmann Andre.Brinkmann@uni-paderborn.de Universität Paderborn PC² Agenda Multiprocessor and

More information

The Load Balancing System Design of Service Based on IXP2400 Yi Shijun 1, a, Jing Xiaoping 1,b

The Load Balancing System Design of Service Based on IXP2400 Yi Shijun 1, a, Jing Xiaoping 1,b Advanced Engineering Forum Vol. 1 (2011) pp 42-46 Online: 2011-09-09 (2011) Trans Tech Publications, Switzerland doi:10.4028/www.scientific.net/aef.1.42 The Load Balancing System Design of Service Based

More information

Scaling Analysis Services in the Cloud

Scaling Analysis Services in the Cloud Our Sponsors Scaling Analysis Services in the Cloud by Gerhard Brückl gerhard@gbrueckl.at blog.gbrueckl.at About me Gerhard Brückl Working with Microsoft BI since 2006 Windows Azure / Cloud since 2013

More information

Control-Based Quality Adaptation in Data Stream Management Systems

Control-Based Quality Adaptation in Data Stream Management Systems Control-Based Quality Adaptation in Data Stream Management Systems Yi-Cheng Tu 1, Mohamed Hefeeda 2, Yuni Xia 1, Sunil Prabhakar 1, and Song Liu 1 1 Purdue University, West Lafayette, IN 47906, U.S.A.

More information

Devices and Device Controllers

Devices and Device Controllers I/O 1 Devices and Device Controllers network interface graphics adapter secondary storage (disks, tape) and storage controllers serial (e.g., mouse, keyboard) sound co-processors... I/O 2 Bus Architecture

More information

A Novel Load Balancing Optimization Algorithm Based on Peer-to-Peer

A Novel Load Balancing Optimization Algorithm Based on Peer-to-Peer A Novel Load Balancing Optimization Algorithm Based on Peer-to-Peer Technology in Streaming Media College of Computer Science, South-Central University for Nationalities, Wuhan 430074, China shuwanneng@yahoo.com.cn

More information

Los Angeles, CA, USA 90089-2561 [kunfu, rzimmerm]@usc.edu

Los Angeles, CA, USA 90089-2561 [kunfu, rzimmerm]@usc.edu !"$#% &' ($)+*,#% *.- Kun Fu a and Roger Zimmermann a a Integrated Media Systems Center, University of Southern California Los Angeles, CA, USA 90089-56 [kunfu, rzimmerm]@usc.edu ABSTRACT Presently, IP-networked

More information

SWISSBOX REVISITING THE DATA PROCESSING SOFTWARE STACK

SWISSBOX REVISITING THE DATA PROCESSING SOFTWARE STACK 3/2/2011 SWISSBOX REVISITING THE DATA PROCESSING SOFTWARE STACK Systems Group Dept. of Computer Science ETH Zürich, Switzerland SwissBox Humboldt University Dec. 2010 Systems Group = www.systems.ethz.ch

More information

Operating Systems. III. Scheduling. http://soc.eurecom.fr/os/

Operating Systems. III. Scheduling. http://soc.eurecom.fr/os/ Operating Systems Institut Mines-Telecom III. Scheduling Ludovic Apvrille ludovic.apvrille@telecom-paristech.fr Eurecom, office 470 http://soc.eurecom.fr/os/ Outline Basics of Scheduling Definitions Switching

More information

High Performance Cluster Support for NLB on Window

High Performance Cluster Support for NLB on Window High Performance Cluster Support for NLB on Window [1]Arvind Rathi, [2] Kirti, [3] Neelam [1]M.Tech Student, Department of CSE, GITM, Gurgaon Haryana (India) arvindrathi88@gmail.com [2]Asst. Professor,

More information

Multi Stage Filtering

Multi Stage Filtering Multi Stage Filtering Technical Brief With the increasing traffic volume in modern data centers, largely driven by e-business and mobile devices, network and application performance monitoring has become

More information

Main Points. Scheduling policy: what to do next, when there are multiple threads ready to run. Definitions. Uniprocessor policies

Main Points. Scheduling policy: what to do next, when there are multiple threads ready to run. Definitions. Uniprocessor policies Scheduling Main Points Scheduling policy: what to do next, when there are multiple threads ready to run Or multiple packets to send, or web requests to serve, or Definitions response time, throughput,

More information

Understanding Slow Start

Understanding Slow Start Chapter 1 Load Balancing 57 Understanding Slow Start When you configure a NetScaler to use a metric-based LB method such as Least Connections, Least Response Time, Least Bandwidth, Least Packets, or Custom

More information

Networking Virtualization Using FPGAs

Networking Virtualization Using FPGAs Networking Virtualization Using FPGAs Russell Tessier, Deepak Unnikrishnan, Dong Yin, and Lixin Gao Reconfigurable Computing Group Department of Electrical and Computer Engineering University of Massachusetts,

More information

Technical Properties. Mobile Operating Systems. Overview Concepts of Mobile. Functions Processes. Lecture 11. Memory Management.

Technical Properties. Mobile Operating Systems. Overview Concepts of Mobile. Functions Processes. Lecture 11. Memory Management. Overview Concepts of Mobile Operating Systems Lecture 11 Concepts of Mobile Operating Systems Mobile Business I (WS 2007/08) Prof Dr Kai Rannenberg Chair of Mobile Business and Multilateral Security Johann

More information

Benchmark Study on Distributed XML Filtering Using Hadoop Distribution Environment. Sanjay Kulhari, Jian Wen UC Riverside

Benchmark Study on Distributed XML Filtering Using Hadoop Distribution Environment. Sanjay Kulhari, Jian Wen UC Riverside Benchmark Study on Distributed XML Filtering Using Hadoop Distribution Environment Sanjay Kulhari, Jian Wen UC Riverside Team Sanjay Kulhari M.S. student, CS U C Riverside Jian Wen Ph.D. student, CS U

More information

Comparison of Request Admission Based Performance Isolation Approaches in Multi-tenant SaaS Applications

Comparison of Request Admission Based Performance Isolation Approaches in Multi-tenant SaaS Applications Comparison of Request Admission Based Performance Isolation Approaches in Multi-tenant SaaS Applications Rouven Kreb 1 and Manuel Loesch 2 1 SAP AG, Walldorf, Germany 2 FZI Research Center for Information

More information

Introduction to LAN/WAN. Network Layer

Introduction to LAN/WAN. Network Layer Introduction to LAN/WAN Network Layer Topics Introduction (5-5.1) Routing (5.2) (The core) Internetworking (5.5) Congestion Control (5.3) Network Layer Design Isues Store-and-Forward Packet Switching Services

More information

Implementing Parameterized Dynamic Load Balancing Algorithm Using CPU and Memory

Implementing Parameterized Dynamic Load Balancing Algorithm Using CPU and Memory Implementing Parameterized Dynamic Balancing Algorithm Using CPU and Memory Pradip Wawge 1, Pritish Tijare 2 Master of Engineering, Information Technology, Sipna college of Engineering, Amravati, Maharashtra,

More information

Load Balancing Scheduling with Shortest Load First

Load Balancing Scheduling with Shortest Load First , pp. 171-178 http://dx.doi.org/10.14257/ijgdc.2015.8.4.17 Load Balancing Scheduling with Shortest Load First Ranjan Kumar Mondal 1, Enakshmi Nandi 2 and Debabrata Sarddar 3 1 Department of Computer Science

More information

Proposal of Dynamic Load Balancing Algorithm in Grid System

Proposal of Dynamic Load Balancing Algorithm in Grid System www.ijcsi.org 186 Proposal of Dynamic Load Balancing Algorithm in Grid System Sherihan Abu Elenin Faculty of Computers and Information Mansoura University, Egypt Abstract This paper proposed dynamic load

More information

Load Balance Strategies for DEVS Approximated Parallel and Distributed Discrete-Event Simulations

Load Balance Strategies for DEVS Approximated Parallel and Distributed Discrete-Event Simulations Load Balance Strategies for DEVS Approximated Parallel and Distributed Discrete-Event Simulations Alonso Inostrosa-Psijas, Roberto Solar, Verónica Gil-Costa and Mauricio Marín Universidad de Santiago,

More information

Scheduling. Yücel Saygın. These slides are based on your text book and on the slides prepared by Andrew S. Tanenbaum

Scheduling. Yücel Saygın. These slides are based on your text book and on the slides prepared by Andrew S. Tanenbaum Scheduling Yücel Saygın These slides are based on your text book and on the slides prepared by Andrew S. Tanenbaum 1 Scheduling Introduction to Scheduling (1) Bursts of CPU usage alternate with periods

More information