Cluster Monitoring software?
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.eduThu Oct 26 10:01:51 PDT 2000
- Previous message: Cluster Monitoring software?
- Next message: Who has experience with wulfkit?
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
On Thu, 26 Oct 2000, Jeff Davis (Work) wrote: > where could one find this web interface you mentioned? > > Jeff Davis > http://www.jrdavis.net/ > jdavis at hess.com To see a working one online: <a href="http://www.ee.duke.edu/~jpormann/cluster.html">Duke EE Department Beowulf Cluster</a> (John Pormann in the Duke EE program wrote the actual web interface). The web application/CGI stuff is NOT in the RPM -- too hard to generically RPMify a web app. The web stuff should be in the currently distributed tarball, together with instructions.) rgb P.S. -- I'm forwarding this response to the whole list and not just you, since the I should probably have pointed out this URL in the first place. I should also note that although John doesn't monitor network load and uses a fairly long sampling granularity, procstatd supports network load on up to four interfaces (and SMP CPU load on up to four CPUs) and one can query at much shorter intervals at a slightly increased cost in terms of the load imposed by procstatd itself. I personally use it with about a 10 second time granularity. If/when I or somebody else (volunteers welcome!) write a scrolling stripchart display that can talk to the daemon, an adjustable granularity of 5-60 seconds would probably be about right. P.P.S. -- This is a GPL tool, so hack away to meet your needs or contribute revisions/additions back to the project if you so desire. Well, actually it is GPL version 2"b" (for beverage) -- my own beer-in-cheek contribution to the concept of open source. Still, if you contribute I'll certainly share the beer with you or buy you one myself...;-) So far I haven't quite received one beer on the basis of the license, although I came close once. The bar was closed. -- 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: Cluster Monitoring software?
- Next message: Who has experience with wulfkit?
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
