I sense your holding something back, tell us what you really think... :)
On Wednesday 20 March 2002 05:45 pm, you wrote:
> for most of that. Maybe S/390 just sucks
--
Rich Smrcina
Sytek Services, Inc.
Milwaukee, WI
[EMAIL PROTECTED]
[EMAIL PROTECTED]
Catch the WAVV! Stay for Requirements and
> sendmail are set a little low, and S/390 processors are simply not as fast
> as Intel for certain tasks, so the load averages are probably going to be
> higher on S/390 than Intel. If you've got unused capacity, a load average
The load average includes disk wait blocking so in theory its accou
ng doesn't help,
even when experts are doing the guessing.) Bump up sendmail's queuing and
reject levels and give it another try.
Mark Post
-Original Message-
From: Moloko Monyepao [mailto:[EMAIL PROTECTED]]
Sent: Wednesday, March 20, 2002 4:13 AM
To: [EMAIL PROTECTED]
Subje
---
From: Rich Smrcina <[EMAIL PROTECTED]>
To: [EMAIL PROTECTED]
Subject: Re: Bogomips S390(IFL) / Intel
>It can be difficult to tell without some sort of
instrumentation or analysis
>of how Linux is performing. At the first hint of a
performance problem, the
>typical solution in
On Wed, Mar 20, 2002 at 07:05:41AM -0600, Rich Smrcina wrote:
> While you are testing sendmail, what does the HMC indicate about the CPU load
> if your IFL? Also, does the IFL use dedicated CHPIDs to the DASD? If so,
> what is their utilization? As mentioned earlier, try dedicating the IFL to
>
Thanks, Alan. All helpful info
On Wednesday 20 March 2002 07:50 am, you wrote:
> top will show you process data
> sard will show you disk statistics providing your vendor ships that feature
> (look in proc/partitions and you should see stuff like..
> 2264 80043264 hdd 23376 219526 1943
oloko Monyepao
Sent: Wednesday, March 20, 2002 12:19 AM
To: [EMAIL PROTECTED]
Subject: Re: Bogomips S390(IFL) / Intel
How can I find out what is causing my problem "Connection rejected" on my
sendmail. Could it be the disk delays or what? How can I sort out this
problem because wheth
> Running in an LPAR you are somewhat limited in that you can only use Linux
> tools and the HMC displays. I do not know what monitoring packages exist for
> Linux (besides top), that will give you the information that you (and we)
> need to work this out. Of course under VM there are a number o
It can be difficult to tell without some sort of instrumentation or analysis
of how Linux is performing. At the first hint of a performance problem, the
typical solution in the Intel world is to throw more or bigger boxes at
it. We don't always have that luxury in the 390 world. Therefore alot
ED]
> Subject: Re: Bogomips S390(IFL) / Intel
>
> Other people have pointed out the absolute uselessness of BogoMIPS for
> anything and how they are _not_ generic across platforms, so I won't dwell
> on that. What I don't understand is why you are doing anythin
is problem.
Please assist
Moloko
> -Original Message-
> From: Thomas David Rivers [SMTP:[EMAIL PROTECTED]]
> Sent: 19 March 2002 16:24
> To: [EMAIL PROTECTED]
> Subject: Re: Bogomips S390(IFL) / Intel
>
> Philipp Knirsch <[EMAIL PROTECTED]>
> >
will be able to
handle a real life load or not.
Mark Post
-Original Message-
From: Moloko Monyepao [mailto:[EMAIL PROTECTED]]
Sent: Tuesday, March 19, 2002 4:25 AM
To: [EMAIL PROTECTED]
Subject: Bogomips S390(IFL) / Intel
I RedHat 7.2 (Server Installation). I am currentely testing sendmai
> Don't rely on BogoMIPS for anything, especially predicting which system
> will do your work faster.
>
> Bogo is short for Bogus; that should tell you everything.
Its an inaccurate measure of the time to sit in a tight loop counting. Its
for delay loops, timer calibration and to provide a quick
Philipp Knirsch <[EMAIL PROTECTED]>
>
> Moloko Monyepao wrote:
> > I RedHat 7.2 (Server Installation). I am currentely testing sendmail (Comparing
>the load handling between Linux on Intel and Linux on S390. I am using an IBM z37
>machine with one IFL and I gave my Linux LPar 80Pwt (processor we
> > This is the BogoMips rating for the various machines:
> >
> > Mainframe: 326.04 BogoMIPS (Mainframe)
> > Maggie (mail-spool, 500Mhz): 996.14 (Intel) 500meg (processor)
> >
> > Higher is better, BogoMIPS should also be generic across platforms.
>
> BogoMIPS is a fairly useless speed rating for
> I RedHat 7.2 (Server Installation). I am currentely testing sendmail (Compari
> ng the load handling between Linux on Intel and Linux on S390. I am using an
> IBM z37 machine with one IFL and I gave my Linux LPar 80Pwt (processor weight
> ing on the IFL)
> When the sever gets too busy start reje
Moloko Monyepao wrote:
> I RedHat 7.2 (Server Installation). I am currentely testing sendmail (Comparing the
>load handling between Linux on Intel and Linux on S390. I am using an IBM z37 machine
>with one IFL and I gave my Linux LPar 80Pwt (processor weighting on the IFL)
> When the sever gets
: Dienstag, 19. März 2002 10:25
An: [EMAIL PROTECTED]
Betreff: Bogomips S390(IFL) / Intel
I RedHat 7.2 (Server Installation). I am currentely testing sendmail
(Comparing the load handling between Linux on Intel and Linux on S390. I am
using an IBM z37 machine with one IFL and I gave my Linux LPar 80Pwt
I RedHat 7.2 (Server Installation). I am currentely testing sendmail (Comparing the
load handling between Linux on Intel and Linux on S390. I am using an IBM z37 machine
with one IFL and I gave my Linux LPar 80Pwt (processor weighting on the IFL)
When the sever gets too busy start rejecting mess
19 matches
Mail list logo