[K12OSN] Relative performance characteristics

Tue Jan 9 18:37:04 UTC 2007

On 1/9/07, Nadav Kavalerchik <nadavkav at gmail.com> wrote:
> KDE + Opera / Konqueror + OpenOffice (some times Firefox 2)
>  we have issues with Firefox rendering hebrew sites correctly :-(
>
> when KOffice supports the RTL languages better (hebrew) , i think we'll
> switch to that too.
> they all share the same QT libs, thus using less memory,in general.
>
> when measuring ram with the FL_TeacherTool ( which is not reflecting the
> memory use correctly)
> we get (per user) 100MB for plain KDE desktop + 30MB for Opera + 50MB Open
> Office (+60 Firefox 2)
> but actually the more users are logged in it uses less per user because the
> app's CODE is in memory and it only allocate DATA space (the TeacherTool
> reports all the memory owned by the user)

Yes this is correct. fl-tt reports RSS resident set size which
includes shared memory. So the actual usage per user is less. Look at
top to see RES and SHR. There is only one instance of the shared
memory allocation for all the users using firefox. So subtract SHR
from RES for the actual memory used by the user.

>
> ( and games, edu apps, drawing, java science... )
>
> + 500MB goes to squid (web proxy) which make a big difference !!!
>
> Nadav :-)
> (Bless Eric)
>
>
> On 1/9/07, "Terrell Prudé Jr." < microman at cmosnetworks.com> wrote:
> >
> >
> > With that amount of DRAM, I'd be interested to know which desktop you have
> your users on, and which apps they use.  Also, do they all use the same
> desktop?
> >
> > --TP
> >
> >
> > Nadav Kavalerchik wrote:
> >
> > we use (intel 830 model - pentium 4 ) 3.2 GHz with 2 GB RAM to serve 25
> clients
> >
> >
> >
> > On 1/8/07, "Terrell Prudé Jr." < microman at cmosnetworks.com> wrote:
> > >
> > > Sounds like your issue is DRAM.  Depending on the apps running (e. g.
> TuxType), it could also be server bandwidth, but from what you describe, it
> sounds like you're starting to swap to disk once you hit 60 clients.  That
> will definitely slow any kind of terminal server, including LTSP servers, to
> a crawl.  You might not have any DRAM hogs, but if you've got a bunch of
> instances of an app running, all using a certain amount of DRAM, that adds
> up.  For that reason, I normally didn't push my servers, which generally
> have 4GB DRAM, past 30 clients.  Since you're only at 65% CPU usage, it
> really doesn't sound like that's your problem.  Also, make sure that you are
> indeed checking that *all* of your server's CPUs are seeing only 65% usage.
> By default, top shows only an average between all of them.
> > >
> > > --TP
> > >
> > > _______________________________
> > > Do you GNU!?
> > > Microsoft Free since 2003--the ultimate antivirus protection!
> > >
> > >
> > >
> > > Immanuel Derks wrote:
> > > Hi all,
> > >
> > > Just wondering at the moment how people feel about the difference in
> > > performance characteristics between the latest Xeon core duo breed
> > > processors and the old fashioned dual Xeon server layouts for LTSP.
> > >
> > >
> > >
> > > We have multiple IBM X235/x236 with double Xeon 3GHz processors
> > > outfitted for a failover LTPS configuration at our school (80-100
> > > clients) and are wondering whether we can simplify the configuration by
> > >
> > > making use of a single server with double Xeon dual core processors (say
> > >
> > > an X3650 that comes with 2 dual-core Xeon 2.33/2.66 or 3.0GHz)
> > >
> > > Can anybody testify a configuration with similar loads who made such a
> > >
> > > swap? I know dual core processors don't have a similar performance as 2
> > >
> > > separate xeons at the same speed, but one might wonder with all the
> > > threaded apps en memory use in LTSP, that it could stack up to it...
> > >
> > >
> > > I must say I feel a bit skeptical sometimes at the performances quotas
> > >
> > > that I sometimes see here on the list, since we noticed (even on our
> > > glass backbone) that x236 servers with 3GHz processors and 8GB ram
> > >
> > > fitted are really dropping performance to a slow when 60 people login (2
> > >
> > > classes) and start working on office and firefox stuff at the same time.
> > > That's why we needed 2 similar servers and we are doing fine now.
> > >
> > > As soon as the CPU loads get over the 65% peak loads, we get a real drop
> > >
> > > in performance, but no iowait or memory hogs or anything....
> > > (we basically run standard RedHat 4 edu edition)
> > >
> > > Kind regards,
> > >
> > >
> > > Immanuel Derks
> > >
> > >
> > >
> > >
> >
> > _______________________________________________
> > K12OSN mailing list
> > K12OSN at redhat.com
> > https://www.redhat.com/mailman/listinfo/k12osn
> > For more info see <http://www.k12os.org>
> >
> >
>
>
> _______________________________________________
> K12OSN mailing list
> K12OSN at redhat.com
> https://www.redhat.com/mailman/listinfo/k12osn
> For more info see <http://www.k12os.org>
>
>

-- 
Robert Arkiletian
Eric Hamber Secondary, Vancouver, Canada
Fl_TeacherTool http://www3.telus.net/public/robark/Fl_TeacherTool/
C++ GUI tutorial http://www3.telus.net/public/robark/