As often happens, my last summary garnered more good info than my original query. The last summary is below. Additional emails have been exchanged with: Dave Landsiedel dave_landsiedel@bobcat.com Larry McCann lmccann@hill.ucs.ualberta.ca Mark E. Drummond mark.drummond@sun.com One other who requested anonymity and especially with: Christophe Dupre [duprec@scorec.rpi.edu] I have now received much better info giving me a 90% probability that (many) E250s do indeed interleave memory. The only reason it's not 100% is because Larry McCann's system does not seem to have the relevant "memory-interleave" nvram variable. His firmware is way out of date though, and even though the patch for that says nothing about memory interleaving, he plans to try upgrading it anyway. > I asked: > > I know the E-450 uses two-way and four-way interleaving. I am > > looking at configuring an E-250, but can find no mention of this > > in its manuals. Should I spread 1GB across all 16 slots, or use > > larger DIMMs in only 8 slots? > > I received a few answers from: > > Mike's List [mikelist@sky.net] > Christophe Dupre [duprec@scorec.rpi.edu] > Ben Tierney [ben@securitycomputer.com] > > Mike says "yes I think so". > Christophe says "yes if all slots have the same size DIMMs". > Ben thinks "no". > > Only Ben supports his opinion with any references, saying that the > engineer handbook does not mention it. > > In fact, I've read every doc I can find (including those mentioned by > Mike) and have found no mention of it. The E450 docs mention it > prominently. Therefor I strongly suspect that the E250 does *not* > do memory interleaving. I await proof, however. [demime 0.99c.1 removed an attachment of type application/x-pkcs7-signature which had a name of smime.p7s] _______________________________________________ sunmanagers mailing list sunmanagers@sunmanagers.org http://www.sunmanagers.org/mailman/listinfo/sunmanagersReceived on Fri Feb 8 10:45:25 2002
This archive was generated by hypermail 2.1.8 : Thu Mar 03 2016 - 06:42:33 EST