Diskless Image Management (DIM) for Cluster Administration
dc.altmetrics.display | true | en |
dc.contributor.author | Morjan, Peter | en |
dc.contributor.author | Rodgers, Greg | en |
dc.contributor.author | Aiken, Ross | en |
dc.contributor.author | Turner, George | en |
dc.contributor.author | Hancock, David Y. | en |
dc.contributor.author | Feinswog, Laurie | en |
dc.date.accessioned | 2006-11-03T15:38:11Z | en |
dc.date.available | 2006-11-03T15:38:11Z | en |
dc.date.issued | 2006-09 | en |
dc.description.abstract | Large computing systems have large administration needs. But just as technologies have evolved to take advantage of certain parallelisms of large scale computing, administrating these technologies must evolve to take advantage of the associated operational efficiencies. Using a straightforward push technology, and scalable to thousands of blades, Diskless Image Management (DIM) allows system administrators to boot, patch, or modify one, several or all distributed images in minutes from a single management console. DIM was prototyped on the MareNostrum cluster with 2406 blades, but is scalable to 7000 blades. Using IBM JS20 blade technology MareNostrum consists of 172 BladeCenters. | en |
dc.format.extent | 1224083 bytes | en |
dc.format.mimetype | application/pdf | en |
dc.identifier.uri | https://hdl.handle.net/2022/424 | en |
dc.language.iso | en_US | en |
dc.publisher | IBM, Inc. and Indiana University | en |
dc.subject | technology | en |
dc.subject | Image Management | en |
dc.subject | Clusters | en |
dc.subject | Cluster Administration | en |
dc.title | Diskless Image Management (DIM) for Cluster Administration | en |
dc.type | Technical Report | en |
Files
Original bundle
1 - 1 of 1
Collections
Can’t use the file because of accessibility barriers? Contact us with the title of the item, permanent link, and specifics of your accommodation need.