This archive contains answers to questions sent to Unidata support through mid-2025. Note that the archive is no longer being updated. We provide the archive for reference; many of the answers presented here remain technically correct, even if somewhat outdated. For the most up-to-date information on the use of NSF Unidata software and data services, please consult the Software Documentation first.
Hi Pete, re: > Here's a question that I just thought of. For CPUs on a relay box, is > the performance going to be better with more physical CPUs with fewer > cores each, or with fewer CPUs with more cores each. For example, do you > think performance would be better with two quad-core opteron CPUs or a > single 8 core? I don't think that we know the answer to this. Quite frankly, the limiting factors on machines used for IDD relay are memory and I/O. The CPU(s) has almost never been the bottleneck. re: > I always assumed that the 2x4 would be better than 1x8, but since all of > the cores would presumably be operating on roughly the same stream of > data, or data from a similiar region of the queue, perhaps the cache > would get a lot of hits and you might actually see better performance > from the single 8 core CPU? This is unknown. re: > Any ideas or thoughts on this? I will discuss it with our system administrator Mike Schmidt to see if he has any guidance for us. I have a feeling, however, that his comments will be that the CPU configuration is a toss-up. re: > Thanks again, No worries. Cheers, Tom -- **************************************************************************** Unidata User Support UCAR Unidata Program (303) 497-8642 P.O. Box 3000 address@hidden Boulder, CO 80307 ---------------------------------------------------------------------------- Unidata HomePage http://www.unidata.ucar.edu **************************************************************************** Ticket Details =================== Ticket ID: DYP-533202 Department: Support Platforms Priority: Normal Status: Closed