I am currently building a 4 processor xeon system, each processor
containing 2 megs of L2 cache. I am going to use this for pseudo
realtime image processing. I spent a lot of money for the 2 meg caches
in the hopes that it would keep the main memory from becoming the system
bottleneck.
If the processes are allowed to rotate, I anticipate that each cache
will have to be refreshed. 2 megabytes of data swapped 4 times seems
like a lot of overhead to me. What am I missing?
I hope to have the machine up in a week. If anybody wants to perform
affinity experiments I would be happy to make them an account. Currently
I am still waiting for my heatsinks and memory:-(
thanks
don
-- ------------------------------------------------------------------- | Don Fisher dfisher@as.arizona.edu | | MMT Observatory VOICE: (520)621-7647 | | University of Arizona FAX: (520)670-5740 | | Tucson, AZ 85721 | -------------------------------------------------------------------- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/