On Tue, 30 Sep 2008, Brian Oborn wrote:
It works well except that the fileserver gets hammered if there's a time when many nodes are turned on at once.
I don't know what you call "many"... When I boot 100+ nodes simultaneously, the avgload on the rsync server stays under 1; the server is a "normal" machine, with 2 SATA disks under RAID-1, so nothing spectacular. The key is to make sure that the size of the "image" served to the nodes fits in RAM, then it's only read from disk once and served from cache. If you have several "images" (I need to, because the nodes are not identical, f.e. 32bit vs. 64bit), then the same applies to the total size of "images". RAM is cheap these days and any "normal" machine of today is able to take 4GB or more which should be enough for any cluster node installation - so no big hurdles in trying it.
-- Bogdan Costescu IWR, University of Heidelberg, INF 368, D-69120 Heidelberg, Germany Phone: +49 6221 54 8869/8240, Fax: +49 6221 54 8868/8850 E-mail: [EMAIL PROTECTED] _______________________________________________ Beowulf mailing list, [email protected] To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
