revamping our beowulf
Many of your questions may have already been answered in earlier discussions or in the FAQ. The search results page will indicate current discussions as well as past list serves, articles, and papers.
Felix Rauch rauch at inf.ethz.chFri Sep 6 00:41:25 PDT 2002
- Previous message: revamping our beowulf
- Next message: revamping our beowulf
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
On Thu, 5 Sep 2002, Tintin J Marapao wrote: > I am actually more concerned about how I can go about cloning the nodes > efficiently...with the least amount of anxiety For cloning we use our own tool called "Dolly". It uses a virtual TCP chain to distribute large files or partitions from one node to all the other nodes in a cluster. It works very well if you have a switched network. For documentation, source codes and a list of publications, see [1] and search for "Dolly". If you want to try a more recent version of the source, write me personally (I did not yet have the time to update the webpage). We use Dolly to clone our 128 node cluster "xibalba" [2,3]. Cloning a 20 GB disk to all nodes takes less than 30 minutes (with two 100 MBit/s NICs per node). - Felix [1] http://www.cs.inf.ethz.ch/CoPs/patagonia/ [2] http://www.xibalba.inf.ethz.ch/ [3] http://www.inf.ethz.ch/research/next/infrastructure.html -- Felix Rauch | Email: rauch at inf.ethz.ch Institute for Computer Systems | Homepage: http://www.cs.inf.ethz.ch/~rauch/ ETH Zentrum / RZ H18 | Phone: +41 1 632 7489 CH - 8092 Zuerich / Switzerland | Fax: +41 1 632 1307
- Previous message: revamping our beowulf
- Next message: revamping our beowulf
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
