ReSS: Resource Selection Service for National and Campus Grid Infrastructure Page: 3 of 8
This article is part of the collection entitled: Office of Scientific & Technical Information Technical Reports and was provided to UNT Digital Library by the UNT Libraries Government Documents Department.
Extracted Text
The following text was automatically extracted from the image on this page using optical character recognition software:
In the GLUE Schema, a computational resource is described by a "Cluster", which is part of a
computing center or "Site". A Cluster is composed of one or more groups ("Subclusters") of
homogeneous computing nodes ("Hosts"). Hosts are characterized by the processor type, memory,
operating system, etc. Access to the Cluster can be achieved by one or more gateways or queues
("Computing Elements" or CE). CE is described by informational parameters, such as the gateway
address, state parameters, such as the number of running or idle jobs, policy parameters, such as the
maximum wall clock time allowed by the local scheduler, etc. In addition to total values for these
parameters, like the total number of running jobs at the CE, the model also allows for VO-specific
values ("VOView"), like the number of running jobs for a specific VO.
Recent, the focus of the work has been to advertise the Storage information in OSG via ReSS. A
Storage Element (SE) is described in the GLUE Schema by the "StorageElement". Each SE can access
multiple "Storage Areas" (SA). SA is described by informational parameters, such as the path to the
SA, total size ("TotalOnlineSize"), used size ("UsedOnlineSize"), free size ("FreeOnlineSize"), etc. In
addition, the model also allows for VO-specific ("VOInfo") values for these attributes which are
specific to a given VO.
Figure 2 shows a schematic UML representation of a site. In order to use readily available match-
making services for resource selection, ReSS describes resources in old classad format, an
unstructured list of [attribute, value] pairs.
For CE, the mapping [7] from the GLUE Schema to a set of old classads is built considering all
possible combinations of inter-related CE, cluster, and subcluster entities. In addition, if VO-specific
parameters are available to characterize CE (VOView); these are used instead of the general CE
attributes. Thus each resulting classad is a virtual homogeneous cluster with one access gateway,
described from the point of view of the VO. Thus the number of classads considering the information
related to CEs is -
NCE-classads - Nciuster x Nsubcluster x NCE x Nvo
For OSG resources, Nciusteris always 1.
For the SE, the mapping from the GLUE Schema to a set of old classads is built considering all
possible combinations of SEs, SAs and VOs supported by each SA. Thus the number of classads
considering the information related to SEs is -
NSE-classads = NSE x NSA x Nvo
The VO acts as a common link in binding together the classad information contributed by CEs and
SEs. In other words, the information for CE and SE is joined together for a given VO to form a single
classad. Thus in the system, total number of classads from a given site is
NTotal-classads = NCE-classads + NSE-classads
Being combinatorial, this algorithm produces a very large number of classads for each site. In
OSG, this results in a simple site producing as few as 1 classad while the most complex site produces
over 1000 classads.
Upcoming Pages
Here’s what’s next.
Search Inside
This article can be searched. Note: Results may vary based on the legibility of text within the document.
Tools / Downloads
Get a copy of this page or view the extracted text.
Citing and Sharing
Basic information for referencing this web page. We also provide extended guidance on usage rights, references, copying or embedding.
Reference the current page of this Article.
Mhashilkar, Parag; Garzoglio, Gabriele; Levshina, Tanya & Timm, Steve. ReSS: Resource Selection Service for National and Campus Grid Infrastructure, article, May 1, 2009; Batavia, Illinois. (https://digital.library.unt.edu/ark:/67531/metadc931893/m1/3/: accessed April 25, 2024), University of North Texas Libraries, UNT Digital Library, https://digital.library.unt.edu; crediting UNT Libraries Government Documents Department.