Fan noise
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.
Robert G. Brown rgb at phy.duke.eduMon Jul 8 11:39:04 PDT 2002
- Previous message: Fan noise
- Next message: Fan noise
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
On Mon, 8 Jul 2002, Pengcheng Zhang wrote: > Is there a way to reduce the noise of fans? Our 8-node cluster > makes me feel like working in an airplane. They are running Our cluster room is more like working right behind a jet, but more than half the noise is the air conditioner. So you wear headphones and listen to music while you work (which also keeps your ears warm, since it is between 55F and 65F depending on where you sit;-) > Redhat 7.3. The same problem happens on a PC. When it's under > WindowsXP, it's really quite; but under Linux it's noisy. Curious. We actually plug our fans directly into the power supply so they run all the time when the system is up instead letting them be regulated by the OS or BIOS at all -- a cool system is a happy system, and when one is cranking away on a computation, the system generates a lot of heat and the fans SHOULD be running all the time anyway. On my laptop, OTOH, the fan only kicks on and runs when it heats up under linux or anything else. Now, when I run linux and do some sort of computation, it does generate heat and the fan eventually kicks on. When I used to run Windoze, I of course couldn't do any real work without spending a fortune on compilers and so forth so the system spent all of its time twiddling its silicon thumbs, and the fan never kicked on. Could this be the problem? Are you actually using your cluster under linux so that it generates enough heat for the fans to kick on while under windows your most common instruction is a noop? Remember, the fans are your friends. If you are working on the cluster and the fans DON'T kick on, your system could be expensive yard art a few minutes later... rgb > > Thanks. > _______________________________________________ > Beowulf mailing list, Beowulf at beowulf.org > To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf > -- Robert G. Brown http://www.phy.duke.edu/~rgb/ Duke University Dept. of Physics, Box 90305 Durham, N.C. 27708-0305 Phone: 1-919-660-2567 Fax: 919-660-2525 email:rgb at phy.duke.edu
- Previous message: Fan noise
- Next message: Fan noise
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
