TCLUG Archive
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [TCLUG:5285] NTS4 vs. Linux study from Mindcraft.



pani@frontiernet.net wrote:
> 
> Maybe the benchmark would make more sense if it was run on
> machines that an average user would buy for that kind of an
> application.  How many users really have these Xeon boxes being
> used for web/file serving or planning to invest in one for the
> same purpose anyway ?
> 

Umm, my company has quite a few of these (2-4 Xeon) for Lotus Notes
(blech!), and we are looking at getting a couple at 35-40K apiece
(depends on disk space -- can you say 18GB UW-SCSI drives ... mmmm).  We
would not run NT on them, but IntraNetware (NetWare 4.x).  I keep saying
Linux, but noone takes me seriously.  

Anyway, what about the next TCLUG meeting?  If we can get a high speed
connection, we could do a pseudo-real-world study of local SMB, proxy,
web, and email.  I have DSL at home, and I would be willing to set
something up here, or bring my box to the meeting.

-Chris

> If linux beats NT on cheaper hardware, which it most certainly
> does, which more people can afford to buy then who cares that
> NT runs faster if you add 4Gigs of RAM and 10 more processors ?
> 
> Aah well, I am just pissed off that I do not have one of those
> xeons, that is all *greeen*
> --
> sandipan
> 
> Scott Dier wrote:
> >
> > Heh, what about us pre-college but-going-to-be-CS-majors-next-fall? :)
> >
> > Anyways, I have peeked through the smart reseller stuff.  Pretty neato
> > benchmarks, but nothing like the data from the mindcraft survey.  Really,
> > it would be cool to set it up, hammer some machines and have a managed
> > port that we could hook MRTG to or something and make some graphs.
> > Problem is, where do we get these sweet-ass boxes? :)  I only know one
> > person with a dual-celeron 504.  And thats not even a xenon.  Oh well.
> > Even if we had a ppro system we could tell what it was like comparitevly.
> > (linux vs nt vs netware etc.)  I have access to NT Enterprise through a
> > MSDN Universal subscription. (yay!) Too bad we couldn't convince my school
> > district to let us conduct an experiment at school, Maple Grove Sr. High
> > ;( (500+ pentium win95 boxen.)   Anyways.  That sparked more of a
> > discussion than I expected.  And it was on-topic.  Sweet. :)  (just
> > digging the signal-to-noise ratio here.)
> >
> > Perhaps at the next meeting there should be a side-discussion
> > (after-major-stuff, i guess i dont know the format of the meetings (yet))
> > of interested parties to see if there is a real interest and avalibility
> > of hardware to do this.  Write it up as a report, and publish it to the
> > world at large.
> >
> > I guess this also means that I am going to start going to tclug meetings.
> > :)
> 
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: tclug-list-unsubscribe@listserv.real-time.com
> For additional commands, e-mail: tclug-list-help@listserv.real-time.com
> Try our website: http://tclug.real-time.com