Hello, I am looking at mechanisms to save energy on ganglia clusters. I was wondering if there is any ongoing or previous work in this regard. The idea is essentially to put Idle machines to sleep and wake them up (perhaps using wake-on-lan) when there is a job to be run on the node (using Gexec). While GMond will make the decision as to whether (and when) to put the machine to sleep, Gexec will perform appropriate scheduling based on the power-performance tradeoff that the user provides.
Also, where can I find statistics about the largest Ganglia clusters? This is basically for knowing whether Ganglia production clusters are large enough so that we can add scheduling logic that appropriately turns off machines which are spatially together, so that the HVAC resources for the particular area can also be turned off (further saving energy). Thank you, -- Prashanth Mohan http://www.cs.berkeley.edu/~prmohan/ ------------------------------------------------------------------------------ Come build with us! The BlackBerry(R) Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9 - 12, 2009. Register now! http://p.sf.net/sfu/devconference _______________________________________________ Ganglia-developers mailing list Ganglia-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ganglia-developers
