Search For:

Displaying 1-38 out of 38 total
Orchestrating an Ensemble of MapReduce Jobs for Minimizing Their Makespan
Found in: IEEE Transactions on Dependable and Secure Computing
By Abhishek Verma,Ludmila Cherkasova,Roy H. Campbell
Issue Date:September 2013
pp. 314-327
Cloud computing offers an attractive option for businesses to rent a suitable size MapReduce cluster, consume resources as a service, and pay only for resources that were consumed. A key challenge in such environments is to increase the utilization of MapR...
 
Performance Modeling of MapReduce Jobs in Heterogeneous Cloud Environments
Found in: 2013 IEEE 6th International Conference on Cloud Computing (CLOUD)
By Zhuoyao Zhang,Ludmila Cherkasova,Boon Thau Loo
Issue Date:June 2013
pp. 839-846
Many companies start using Hadoop for advanced data analytics over large datasets. While a traditional Hadoop cluster deployment assumes a homogeneous cluster, many enterprise clusters are grown incrementally over time, and might have a variety of differen...
 
Dealing with Burstiness in Multi-Tier Applications: Models and Their Parameterization
Found in: IEEE Transactions on Software Engineering
By Giuliano Casale,Ningfang Mi,Ludmila Cherkasova,Evgenia Smirni
Issue Date:September 2012
pp. 1040-1053
Workloads and resource usage patterns in enterprise applications often show burstiness resulting in large degradation of the perceived user performance. In this paper, we propose a methodology for detecting burstiness symptoms in multi-tier applications bu...
 
Two Sides of a Coin: Optimizing the Schedule of MapReduce Jobs to Minimize Their Makespan and Improve Cluster Performance
Found in: 2012 IEEE 20th International Symposium on Modelling, Analysis & Simulation of Computer and Telecommunication Systems (MASCOTS)
By Abhishek Verma,Ludmila Cherkasova,Roy H. Campbell
Issue Date:August 2012
pp. 11-18
Large-scale MapReduce clusters that routinely process petabytes of unstructured and semi-structured data represent a new entity in the changing landscape of clouds. A key challenge is to increase the utilization of these MapReduce clusters. In this work, w...
 
Selling T-shirts and Time Shares in the Cloud
Found in: Cluster Computing and the Grid, IEEE International Symposium on
By Daniel Gmach,Jerry Rolia,Ludmila Cherkasova
Issue Date:May 2012
pp. 539-546
Cloud computing has emerged as a new and alternative approach for providing computing services. Customers acquire and release resources by requesting and returning virtual machines to the cloud. Different service models and pricing schemes are offered by c...
 
Optimizing Completion Time and Resource Provisioning of Pig Programs
Found in: Cluster Computing and the Grid, IEEE International Symposium on
By Zhuoyao Zhang,Ludmila Cherkasova,Abhishek Verma,Boon Thau Loo
Issue Date:May 2012
pp. 811-816
As cloud computing continues to mature, IT managers have started concentrating on the support of additional performance requirements: quality of service and tailored resource allocation for achieving service performance goals. In this paper, we consider th...
 
Play It Again, SimMR!
Found in: Cluster Computing, IEEE International Conference on
By Abhishek Verma,Ludmila Cherkasova,Roy H. Campbell
Issue Date:September 2011
pp. 253-261
A typical MapReduce cluster is shared among different users and multiple applications. A challenging problem in such shared environments is the ability to efficiently control resource allocations among the running and submitted jobs for achieving users' pe...
 
Resource and virtualization costs up in the cloud: Models and design choices
Found in: Dependable Systems and Networks, International Conference on
By Daniel Gmach,Jerry Rolia,Ludmila Cherkasova
Issue Date:June 2011
pp. 395-402
Virtualization offers the potential for cost-effective service provisioning. For service providers who make significant investments in new virtualized data centers in support of private or public clouds, one of the serious challenges is the problem of reco...
 
Workload Analysis and Demand Prediction of Enterprise Data Center Applications
Found in: IEEE Workload Characterization Symposium
By Daniel Gmach, Jerry Rolia, Ludmila Cherkasova, Alfons Kemper
Issue Date:September 2007
pp. 171-180
Advances in virtualization technology are enabling the creation of resource pools of servers that permit multiple application workloads to share each server in the pool. Understanding the nature of enterprise workloads is crucial to properly designing and ...
 
A Regression-Based Analytic Model for Dynamic Resource Provisioning of Multi-Tier Applications
Found in: Autonomic Computing, International Conference on
By Qi Zhang, Ludmila Cherkasova, Evgenia Smirni
Issue Date:June 2007
pp. 27
The multi-tier implementation has become the industry standard for developing scalable client-server enterprise applications. Since these applications are performance sensitive, effective models for dynamic resource provisioning and for delivering quality ...
 
R-Opus: A Composite Framework for Application Performability and QoS in Shared Resource Pools
Found in: Dependable Systems and Networks, International Conference on
By Ludmila Cherkasova, Jerome Rolia
Issue Date:June 2006
pp. 526-535
We consider shared resource pool management taking into account per-application quality of service (QoS) requirements and server failures. Application QoS requirements are defined by complementary specifications for acceptable and time-limited degraded per...
 
Optimizing the Reliable Distribution of Large Files within CDNs
Found in: Computers and Communications, IEEE Symposium on
By Ludmila Cherkasova
Issue Date:June 2005
pp. 692-697
Content Delivery Networks (CDNs) provide an efficient support for serving http and streaming media content while minimizing the network impact of content delivery as well as overcoming the server over-load problem. For serving the large documents and media...
 
An SLA-Oriented Capacity Planning Tool for Streaming Media Services
Found in: Dependable Systems and Networks, International Conference on
By Ludmila Cherkasova, Wenting Tang, Sharad Singhal
Issue Date:July 2004
pp. 743
This paper addresses the problem of mapping the requirements of a known media service workload into the corresponding system resource requirements and accurately sizing a media server cluster to handle the workload. In this paper, we propose a new capacity...
 
Session-Based Admission Control: A Mechanism for Peak Load Management of Commercial Web Sites
Found in: IEEE Transactions on Computers
By Ludmila Cherkasova, Peter Phaal
Issue Date:June 2002
pp. 669-685
<p><b>Abstract</b>—In this paper, we consider a new, session-based workload for measuring web server performance. We define a session as a sequence of client's individual requests. Using a simulation model, we show that an overloaded web ...
 
Dynamics and Evolution of Web Sites: Analysis, Metrics and Design Issues
Found in: Computers and Communications, IEEE Symposium on
By Ludmila Cherkasova, Magnus Karlsson
Issue Date:July 2001
pp. 0064
Abstract: Our goal is to develop a web server log analysis tool that produces a web site profile and its system resource usage in a way useful to service providers. Understanding the nature of traffic to the web site is crucial in properly designing site s...
 
Scalable Web Server Cluster Design with Workload-Aware Request Distribution Strategy WARD
Found in: Advanced Issues of E-Commerce and Web-Based Information Systems, International Workshop on
By Ludmila Cherkasova, Magnus Karlsson
Issue Date:June 2001
pp. 0212
Abstract: In this work, we consider a web cluster in which the content-aware distribution is performed by each of the node in a web cluster. Each server in the cluster may forward a request to another node based on the requested content. We propose a new W...
 
Customized Library of Modules for STREAMS-Based TCP/IP Implementation to Support Content-Aware Request Processing for Web Applications
Found in: Advanced Issues of E-Commerce and Web-Based Information Systems, International Workshop on
By Wenting Tang, Ludmila Cherkasova, Lance Russell, Matt W. Mutka
Issue Date:June 2001
pp. 0202
Abstract: Content-aware request processing enables the intelligent routing and request processing inside the cluster to provide the quality of service requirements for different types of content and to improve overall cluster performance. STREAMS-based TCP...
 
Predictive Admission Control Strategy for Overloaded Commercial Web Server
Found in: Modeling, Analysis, and Simulation of Computer Systems, International Symposium on
By Ludmila Cherkasova, Peter Phaal
Issue Date:September 2000
pp. 500
We use a session-based workload to measure a web server's performance. An over loaded web server can experience a severe loss of throughput when measured as the number of completed sessions. Moreover, the overloaded web server discriminates against longer ...
 
Optimizing a 'Content-Aware' Load Balancing Strategy for Shared Web Hosting Service
Found in: Modeling, Analysis, and Simulation of Computer Systems, International Symposium on
By Ludmila Cherkasova, Shankar R. Ponnekanti
Issue Date:September 2000
pp. 492
FLEX is a new scalable “locality aware” solution for achieving both load balancing and efficient memory usage on a cluster of machines hosting several web sites [1, 2]. FLEX allocates the sites to different machines in the cluster based on their traffic ch...
 
FLEX: Load Balancing and Management Strategy for Scalable Web Hosting Service
Found in: Computers and Communications, IEEE Symposium on
By Ludmila Cherkasova
Issue Date:July 2000
pp. 8
FLEX is a new scalable “locality aware” solution for achieving both load balancing and efficient memory usage on a cluster of machines hosting several web sites. FLEX allocates the sites to different machines in the cluster based on their traffic character...
 
Detecting Timed-Out Client Requests for Avoiding Livelock and Improving Web Server Performance
Found in: Computers and Communications, IEEE Symposium on
By Richard Carter, Ludmila Cherkasova
Issue Date:July 2000
pp. 2
A Web server's listen queue capacity is often set to a large value to accommodate bursts of traffic and to accept as many client requests as possible. We show that, under certain overload conditions, this results in a significant loss of server performance...
 
The Impact of Message Scheduling on a Packet Switching Interconnect Fabric
Found in: Hawaii International Conference on System Sciences
By Ludmila Cherkasova, Vadim Kotov, Tomas Rokicki
Issue Date:January 1996
pp. 668
The impact of different message scheduling strategies on the performance of a packet-switched network is explored. We present a new scheduling technique, called Alpha scheduling, that can combine the bandwidth-fairness of round robin scheduling with nearly...
   
Fibre Channel Fabrics: Evaluation and Design
Found in: Hawaii International Conference on System Sciences
By Ludmila Cherkasova, Vadim Kotov, Tomas Rokicki
Issue Date:January 1996
pp. 53
We consider how Fibre Channel switches can be cascaded to form a Fibre Channel fabric. We begin with an analytical model of topology performance that provides a theoretical upper bound on fabric performance and a method for the practical evaluation of fabr...
   
Building a Performance Model of Streaming Media Applications in Utility Data Center Environment
Found in: Cluster Computing and the Grid, IEEE International Symposium on
By Ludmila Cherkasova, Loren Staley
Issue Date:May 2003
pp. 52
Utility Data Center (UDC) provides a flexible, cost-effective infrastructure to support the hosting of applications for Internet services. In order to enable the design of a
 
Exploiting cloud heterogeneity for optimized cost/performance MapReduce processing
Found in: Proceedings of the Fourth International Workshop on Cloud Data and Platforms (CloudDP '14)
By Boon Thau Loo, Ludmila Cherkasova, Zhuoyao Zhang
Issue Date:April 2014
pp. 1-6
Cloud computing enables a user to quickly provision any size Hadoop cluster, execute a given MapReduce workload, and then pay for the time the resources were used. Typically, there is a choice of different types of VM instances in the Cloud (e.g., small, m...
     
Performance Modeling and Optimization of Deadline-Driven Pig Programs
Found in: ACM Transactions on Autonomous and Adaptive Systems (TAAS)
By Abhishek Verma, Boon Thau Loo, Ludmila Cherkasova, Zhuoyao Zhang
Issue Date:September 2013
pp. 1-28
Many applications associated with live business intelligence are written as complex data analysis programs defined by directed acyclic graphs of MapReduce jobs, for example, using Pig, Hive, or Scope frameworks. An increasing number of these applications h...
     
Meeting service level objectives of Pig programs
Found in: Proceedings of the 2nd International Workshop on Cloud Computing Platforms (CloudCP '12)
By Ludmila Cherkasova, Abhishek Verma, Boon Thau Loo, Zhuoyao Zhang
Issue Date:April 2012
pp. 1-6
Cloud computing offers a compelling platform to access a large amount of computing and storage resources on demand. As the technology matures, service providers have started shifting their focus to support additional user requirements such as QoS guarantee...
     
Lightning: self-adaptive, energy-conserving, multi-zoned, commodity green cloud storage system
Found in: Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing (HPDC '10)
By Klara Nahrstedt, Ludmila Cherkasova, Rini T. Kaushik, Roy Campbell
Issue Date:June 2010
pp. 332-335
The objective of this research is to present an energy-conserving, self-adaptive Commodity Green Cloud Storage, called Lightning. Lightning's File System dynamically configures the servers in the Cloud Storage into logical Hot and Cold Zones. Lightning use...
     
Automated anomaly detection and performance modeling of enterprise applications
Found in: ACM Transactions on Computer Systems (TOCS)
By Evgenia Smirni, Julie Symons, Kivanc Ozonat, Ludmila Cherkasova, Ningfang Mi
Issue Date:November 2009
pp. 1-32
Automated tools for understanding application behavior and its changes during the application lifecycle are essential for many performance analysis and debugging tasks. Application performance issues have an immediate impact on customer experience and sati...
     
Applying syntactic similarity algorithms for enterprise information management
Found in: Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining (KDD '09)
By Alistair Veitch, Charles B. Morrey, Joseph Tucek, Kave Eshghi, Ludmila Cherkasova
Issue Date:June 2009
pp. 1-24
For implementing content management solutions and enabling new applications associated with data retention, regulatory compliance, and litigation issues, enterprises need to develop advanced analytics to uncover relationships among the documents, e.g., con...
     
Performance engineering for EA systems in next generation data centresPerformance engineering for EA systems in next generation data centres
Found in: Proceedings of the 6th international workshop on Software and performance (WOSP '07)
By Jerome Rolia, Ludmila Cherkasova, Richard Friedrich
Issue Date:February 2007
pp. 50-53
Software Performance Engineering (SPE) methods have been in use for over two decades as an approach to manage the risks of developing systems that fail to satisfy their performance requirements. In general, SPE advocates the use of performance oriented des...
     
Supporting application quality of service in shared resource pools
Found in: Communications of the ACM
By Jerry Rolia, Ludmila Cherkasova, Martin Arlitt, Vijay Machiraju
Issue Date:March 2006
pp. 55-60
Dividing an application's workload demands to better manage resource capacity.
     
A capacity management service for resource pools
Found in: Proceedings of the 5th international workshop on Software and performance (WOSP '05)
By Artur Andrzejak, Jerry Rolia, Ludmila Cherkasova, Martin Arlitt
Issue Date:July 2005
pp. 229-237
Resource pools are computing environments that offer virtualized access to shared resources. When used effectively they can align the use of capacity with business needs (flexibility), lower infrastructure costs (via resource sharing), and lower operating ...
     
MediSyn: a synthetic streaming media service workload generator
Found in: Proceedings of the 13th international workshop on Network and operating systems support for digital audio and video (NOSSDAV '03)
By Amin Vahdat, Ludmila Cherkasova, Wenting Tang, Yun Fu
Issue Date:June 2003
pp. 12-21
Currently, Internet hosting centers and content distribution networks leverage statistical multiplexing to meet the performance requirements of a number of competing hosted network services. Developing efficient resource allocation mechanisms for such serv...
     
Measuring the capacity of a streaming media server in a Utility Data Center environment
Found in: Proceedings of the tenth ACM international conference on Multimedia (MULTIMEDIA '02)
By Loren Staley, Ludmila Cherkasova
Issue Date:December 2002
pp. 299-302
Abstract In order to design a "utility-aware" streaming media service which automatically requests the necessary resources from Utility Data Center infrastructure, several classic performance questions should be answered: how to measure the basic capacity ...
     
Characterizing locality, evolution, and life span of accesses in enterprise media server workloads
Found in: Proceedings of the 12th international workshop on Network and operating systems support for digital audio and video (NOSSDAV '02)
By Ludmila Cherkasova, Minaxi Gupta
Issue Date:May 2002
pp. 33-42
The main issue we address in this paper is the workload analysis of today's enterprise media servers. This analysis aims to establish a set of properties specific for enterprise media server workloads and to compare them with well known related observation...
     
Components of congestion control
Found in: Proceedings of the eighth annual ACM symposium on Parallel algorithms and architectures (SPAA '96)
By Al Davis, Ian Robinson, Ludmila Cherkasova, Robin Hodgson, Tomas Rokicki, Vadim Kotov
Issue Date:June 1996
pp. 208-210
We consider the problem of sorting a file of N records on theD-disk model of parallel I/0 [VS94] in which there are two sourcesof parallehsm. Records are transferred to and from diskconcurrently in blocks of B con-tiguous records. In each I/Ooperation, up ...
     
Modeling a fibre channel switch with stochastic Petri nets
Found in: Proceedings of the 1995 ACM SIGMETRICS joint international conference on Measurement and modeling of computer systems (SIGMETRICS '95/PERFORMANCE '95)
By Gianfranco Ciardo, Ludmila Cherkasova, Tomas Rokicki, Vadim Kotov
Issue Date:May 1995
pp. 261-269
We explore processor-cache affinity scheduling of parallel network protocol processing in a setting in which protocol processing executes on a shared-memory multiprocessor concurrently with a general workload of non-protocol activity. We find that affinity...
     
 1