Rasit Eskicioglu

Systems Administration

As industry-standard computing platforms such as workstations and small-scale symmetric multiprocessor servers continue to show better and better price performance, more and more significant clustering projects are developing internationally. What separates these systems is how usable they are in terms of actually producing computations of value to their users and at what “comfort level” for their users. Manageability of a system can be the single most important factor in its practical usability. This is complicated by the current fact that many clusters are in all or in part themselves experimental computing systems for computer science studies of architecture and/or software while attempting to offer research and/or production platforms for their user base. Even for a single system, the emphasis can vary over time to satisfy sponsor requirements and evolving research ideas, whereas a production-oriented user base typically is most interested in application results, system availability, and stability. The goals of various clustering projects are quite diverse, with extremes evident. First, there is the dedicated cluster for computer science research. The goal of this type of system is typically to undertake performance testing, benchmarking, and software tuning. This work is often done at the networking, application, and operating systems levels. These clusters are not typically used for computational science and quite often are in a state of flux. The opposite extreme is the production-computing environment. The tacit goal of these systems is to provide reliable computing cycles with dependable networking, application software, and operating systems. As noted above, systems may attempt both extremes, either by spatial division of the resources among emphases or by reallocation policies over time. Realistically, the entire range of work being done on clusters and the quality of the results generated on them are driven strongly by the tools available to the systems administrators. In this article, we describe some of the critical issues that arise when planning a cluster-computing installation and its ongoing support and maintenance. No matter what the goals of a particular cluster-computing project may be, good systems manageability will directly equate to better results. Systems such as the IBM SP have been successful in providing these types of utilities in the past. However, similar and in many cases superior tools are being developed for clusters out of necessity. Even if the users are just experimenting with a small test cluster, the ability to verify and ensure consistency in hardware, application software, and system settings across the cluster’s resources from a single console will

A practical fast method for medical imaging transmission based on the DICOM protocol

The standard format for medical imaging storage and transmission is Digital Imaging and Communications in Medicine (DICOM). Nowadays, and specifically with large amounts of medical images acquired by modern modalities, the need for fast data transmission between DICOM application entities is evident. In some applications, particularly those aiming to provide real-time services, this demand is critical. This paper introduces a method which provides a fast and simple way of image transmission by utilizing the DICOM protocol. The current implementations of DICOM protocol usually care more about connecting DICOM application entities. In the process of connecting two DICOM application entities, the format of the transmission (Transfer Syntax) is agreed upon. In this crucial step, the two entities choose an encoding that is supported by both and if one entity does not support compression the other one cannot use that option. In the proposed method, we use a pair of interfaces to deal with this issue and provide a fast method for medical data transmission between any two DICOM application entities. These interfaces use both compression and multi-threading techniques to transfer the images. The interfaces can be used without any change to the current DICOM application entities. In fact, the interfaces listen to the incoming messages from the DICOM application entities, intercept the messages, and carry out the data transmission. The experimental results show about 22% speed-up in Local Area Networks (LANs) and about 13-14 times speed-up in Wide Area Networks (WANs).

Adaptive Replica Placement in Hierarchical Data Grids

Data grids support distributed data-intensive applications that need to access massive (multi-terabyte or larger) datasets stored around the world. Ensuring efficient and fast access to such widely distributed datasets is hindered by the high latencies of wide-area networks. To speed up access, data files can be replicated so users can access nearby copies. Replication also provides high data availability, decreased bandwidth consumption, increased fault tolerance, and improved scalability. Since a grid environment is highly dynamic, resource availability, network latency, and users requests may change frequently. To address these issues a dynamic replica placement strategy that adapts to dynamic behavior in data grids is needed. In this paper, we extend our earlier work on popularity-based replica placement proposing a new adaptive algorithm for use in large-scale hierarchical data grids. Our algorithm dynamically adapts the frequency and degree of replication based on data access arrival rate and available storage capacities. We evaluate our algorithm using OptorSim. Our results show that our algorithm can shorten job execution time greatly and reduce bandwidth consumption compared to its non-adaptive counterpart which outperforms other existing replica placement methods.

A remote real-time PACS-based platform for medical imaging telemedicine

This paper describes a remote real-time PACS-based telemedicine platform for clinical and diagnostic services delivered at different care settings where the physicians, specialists and scientists may attend. In fact, the platform aims to provide a PACS-based telemedicine framework for different medical image services such as segmentation, registration and specifically high-quality 3D visualization. The proposed approach offers services which are not only widely accessible and real-time, but are also secure and cost-effective. In addition, the proposed platform has the ability to bring in a realtime, ubiquitous, collaborative, interactive meeting environment supporting 3D visualization for consultations, which has not been well addressed with the current PACS-based applications. Using this ability, physicians and specialists can consult with each other at separate places and it is especially helpful for settings, where there is no specialist or the number of specialists is not enough to handle all the available cases. Furthermore, the proposed platform can be used as a rich resource for clinical research studies as well as for academic purposes.