- 28.1 INTRODUCTION. - In this chapter, we discuss the development, architecture, and functionality of the National Partnership for Advanced Computational Infrastructure NPACI Grid Portals project. - This is part of the unique role that portals play at the Grid middleware layer: portals drive the integration of. - The NPACI HotPage was developed to help facilitate and support usage of the NPACI resources. - However, the goals of the HotPage included not only the provision of information but also the capability to use all NPACI resources interactively via a single, integrated Web portal. - Grid computing tech- nologies, which were supported as part of the NPACI program, were utilized to provide these functionalities. - In 1999, a second version of the HotPage was developed that used the Globus Toolkit [9]. - This version of the HotPage has been further enhanced and is in production for NPACI and for the entire PACI program. - Versions of the HotPage are in use at many other universities and government laboratories around the world.. - The mission of the HotPage project has always been to provide a Web portal that would present an integrated appearance and set of services to NPACI users: a user por- tal. - It was apparent during the development of the HotPage that there was growing interest in developing higher-level application portals that launched specific applications on predetermined resources. - Much of the functionality required to build these higher-level application portals had already been developed for the HotPage. - The driving philosophy behind the design of the HotPage and GridPort is the convic- tion that many potential Grid users and developers will benefit from portals and portal technologies that provide universal, easy access to resource information and usage while requiring minimal work by Grid developers. - Developers of Grid portals can avoid many of the complexities of the APIs of Grid middleware by using GridPort and similar toolkits. - The GridPort project has met all of the goals listed above with the exception of the last one. - 28.1.3 Grid portal users and developers. - Therefore, this group will be easiest for transition to using Grids instead of individual resources, but most of the work falls on the Grid portal developers. - Many of the users in this group may never know (or care) anything about HPC or how parallel computers are running their code to accomplish their sci- ence. - For these users, a user portal like the HotPage cannot replace their use of the command line environment of each individual system during periods of code development and tuning, but it can augment their usage of the systems for production runs in support of their research.. - 28.2 THE GRID PORTAL TOOLKIT (GRIDPORT). - GridPort evolved out of the need to simplify the integration of these services and technologies for portal developers. - 28.2.1 GridPort architecture. - GridPort modularizes each of the steps required to translate the portal requests into Grid service function calls, for example, a GRAM submission. - In the context of the architecture of Foster et al. - Each layer represents a logical part of the system in which data and service requests flow back and forth and addresses some specific aspect or function of the GridPort portal system. - Figure 28.1 The diagram shows the layers used in the GridPort multilayered architecture. - Each layer represents a logical part of the portal in which data and service requests flow back and forth.. - GridPort modularizes each of the steps required to translate the portal requests into Grid service function calls, for example, a GRAM submission.. - We describe each of the layers and their functions below.. - Portals layer: The portals layer consists of the portal-specific code itself. - One instance of GridPort can support multiple concurrent application portals, but they must exist on the same Web server system in which they share the same instance of the GridPort libraries. - Resources running any of the above can be added to the set of Grid resources supported by GridPort by incorporating the data about the system into GridPort’s configuration files.. - 28.2.2 GridPort capabilities. - (Note that these accounts are not the same as the individual accounts a user needs on the resources.) The portal manages the user’s account and keeps track of sessions, user preferences, and portal file space.. - Once a user is logged in to a GridPort portal and has been authenticated, the user has access to any other GridPort-hosted portal that is part of the single-login environment. - 28.2.3 GridPort security. - Secure access at all layers is essential and is one of the more complex issues to address. - Alternatively, the proxy may be generated from a proxy retrieved on behalf of the user from a MyProxy server.. - Furthermore, none of the files in these directories are allowed to be executable, and the Web server daemon may not access files outside these directories. - Grid task execution is accomplished using the GSI model: when a portal uses GridPort to make a request on behalf of the user, GridPort presents the user’s credentials to the Grid resource, which decides, on the basis of the local security model, whether the request will be honored or denied. - Thus, the portal acts as a proxy for executing requests on behalf of the user (on resources that the user is authorized to access) on the basis of the credentials presented by the user who created the portal account. - 28.3 GRIDPORT PORTALS. - In this design, each portal has its own file space and shares the same instance of the GridPort modules as well as common portal account and authorization information. - In addition, there are a number of remote sites that have ported GridPort and installed local versions of the HotPage [22–25].. - These examples illustrate some of the features and capabilities of GridPort. - They also reveal some of the issues encountered in constructing Grid portals owing to limitations of GridPort and the Grid services employed by GridPort or to the fact. - Because they are Web-based, GridPort portals are accessible wherever there is a Web browser, regardless of the user’s location. - 28.3.1 HotPage user portal. - The layout of the HotPage allows a user to view information about these resources from either the Grid or the individual resource perspectives in order to quickly determine system-wide information such as operational status, computational load, and available computational resources (see Figure 28.3). - The interactive portion of the HotPage includes a file navigation interface and Unix shell- like tools for editing remote files, submitting jobs, archiving and retrieving files, and selecting multiple files for various common Unix operations. - With the introduction of personalization in a new beta version of the HotPage, users can now choose which systems they wish to have presented for both informational and interactive services.. - Published as part of the NPACI Portal GIS, much of this data is generated via special- ized custom scripts that are installed into the Globus Grid Resource Information Services (GRIS running on MDS 2.0 on each resource) and are also published via the HotPage.. - Figure 28.3 Screenshot of the NPACI HotPage, during an interactive session (user is logged in).. - Results of the job request will be displayed in a pop-up window.. - Each of the capabilities listed above is provided using Perl scripts that employ GridPort modules and can be extended by the portal application developer. - A key advance realized by the construction of the portal is that researchers can now run multiple tasks at the same time, whereas before they were limited to single job runs. - GridPort was chosen to build the LAPK portal based on developers’ ability to use GridPort to rapidly deploy a prototype portal demonstrating the viability of the portal concept. - Construction of the prototype portal took less than two weeks. - Figure 28.4 Screenshot of the LAPK Portal, in which users (medical researchers) utilize the portal without being exposed to the fact that HPC Grid and archival resources are being used. - Most of the work on the portal is done by student interns at SDSC, and thus it is a relatively inexpensive project. - The size of the portal software is relatively large, but not complex: there are approximately 50 cgi files, with an average size of about 200 lines each. - The LAPK portal system demonstrates one of the reasons GridPort has been successful: it is easy to program (the portal was developed by interns), easy to extend (the portal provides graphical images), and is extensible (LAPK has an additional authentication layer).. - 28.3.3 Telescience portal. - The basic architecture of the Telescience portal is shown in Figure 28.5: portal users have access to remote instrumentation (a microscope) via an Applet, an SRB collection for storage of raw results and analyzed data, portal tools for creating and managing projects, and remote visualization applications.. - A central component of the portal is a tool known as FastTomo, which enables microscopists to obtain near real-time feedback (in the range of 5 to 15 min) from the tomographic reconstruction process, on-line and without calibration, to aid in the selection of specific areas for tomographic reconstruction. - Figure 28.5 Basic architecture diagram of the Telescience portal, in which portal users will have access to remote instrumentation (microscope), automatic SRB collection access for storage of raw results and analyzed data, portal tools for creating and managing projects, and remote visualization applications.. - The ultimate purpose of the resource is to facilitate biomedical research by making advanced computational data and visualization capabilities as easy to access and use as the World Wide Web, freeing researchers to focus on biology. - While the original version of the GAMESS/QMView infrastructure provided a complete system for carrying out computational quantum chemistry on a vari- ety of platforms, the system was not accessible through a secure and robust Web interface.. - The CE Portal gives users on-line capabilities to upload input files to query the CE database, submit searches to the CE database, display a status of the database searches, and view results of the searches. - Anonymous login gives users general functionality such as starting a CE search and viewing results of the search. - By registering for a portal account, the portal user has additional benefits such as a personal and password-protected account to store queries and results, the ability to track the progress of searches after submission, and reduced restrictions on the usage of the HPC resources. - For example, the NPACI HotPage is one of the most-visited Web pages in the NPACI domain. - However, experience has demonstrated that traditional HPC users have not fully adopted Grid portals for interactive services for three main reasons: user portals do not possess the full capabilities of the command line or mature user-oriented interfaces for the commands they do present, portal-interactive capabilities are not responsive as command-line actions, and Grid portals interactive responses are slower than traditional Web portals (e.g. - The reasons are both obvious and understandable: the Grid is still new and evolving, and much of the basic framework and infrastructure is still being developed or even conceived. - the construction of Grid application portals and Grid applications that realize the benefits of the underlying network of Grid resources, and the toolkits being developed to simplify their construction, is difficult and in some cases impossible. - Portals must provide true connection to on-line knowledge centers, data repositories, and user data and make all data easy to incorporate into analytical processes, as well as enable enhanced usage of the available computational resources.. - Grid accounts and allocations: Accounts and access should be managed at the orga- nizational level instead of the machine level by allowing users to run on all systems under an umbrella account/allocation.. - Registration and management of the executable binaries for each Grid compute architecture is even more difficult and must be automated. - On the basis of the experiences discussed above and on the emergence of new portal and Web technologies, work has begun on a new version of GridPort that will have a. - 28.5.1 GridPort GCE architecture. - Application services layer (enhancement of the portal services layer – GridPort): GridPort components will be expanded to provide mediation services between Grid technologies and applications as well as portals. - Shaded boxes represent layers and types of services that will be implemented as part of the GridPort toolkit.. - 28.5.2 GridPort Grid Web services. - A major focus for all future work on GridPort will be on the development and use of Grid Web services to facilitate dynamic operation of the Grid portals and applications. - impact of the Web services architecture on the development of the Grid is demonstrated in Figure 28.8. - 28.5.3 Grid portals and applications. - These new features and capabilities will be implemented in the next version of GridPort, enabling users to build their own customized views of the HotPage and their own application portals and applications. - The set of choices is left to the needs and imagination of the developers and users.. - Proceedings of the Ninth IEEE International Symposium on High Performance Distributed Computing, August, 2000, Project Website last accessed on 7/1/02 at http://hotpage.npaci.edu.. - Proceedings of the Ninth IEEE International Symposium on High Performance Distributed Computing, August, 2000.. - Proceedings of the Tenth IEEE International Symposium on High Performance Distributed Computing, August, 2001, Project Website last accessed on 7/1/02 at http://gridport.npaci.edu.. - (2001) The anatomy of the grid: enabling scalable vir- tual organizations. - Proceedings of the Tenth International Symposium on High Performance Distributed Computing (HPDC-10), IEEE Press, August 2001.. - Project Website last accessed on 7/1/02 at. - Proceed- ings of the Eight IEEE International Symposium on High Performance Distributed Computing, August, 1999, Cactus problem solving environment project. - Website last accessed on 7/1/02 at http://www.cactuscode.org.. - The Physiology of the Grid: An Open Grid Services Architecture for Distributed Systems Integration . - Network Weather Service (NWS), Project Website last accessed on 7/1/02 at:. - Proceedings of the International Multiconfer- ence in Computer Science, July, 2002.. - Project website last accessed on 12/1/02 at:
Xem thử không khả dụng, vui lòng xem tại trang nguồn hoặc xem
Tóm tắt