[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

20030327: pqact causes unusually high CPU usage on LDM 6/Soalris Intel

This archive contains answers to questions sent to Unidata support through mid-2025. Note that the archive is no longer being updated. We provide the archive for reference; many of the answers presented here remain technically correct, even if somewhat outdated. For the most up-to-date information on the use of NSF Unidata software and data services, please consult the Software Documentation first.

  • Subject: 20030327: pqact causes unusually high CPU usage on LDM 6/Soalris Intel
  • Date: Fri, 28 Mar 2003 07:39:42 -0700
>From: Robert Mullenax <address@hidden>
>Organization: NMSU/NSBF
>Keywords: 200303250413.h2P4D9B2010509 LDM-6 pqact

Robert,

>This really weird.  I did confirm that switching back to LDM 5.2
>makes everything fine..2-5% CPU usage (the queue was fine I checked that).

>Here's the weird thing..when I switched back the LDM 6.02, pqact went
>up to 10-30% CPU usage, but I also noticed that EVERY decoder, GEMPAK or
>McIDAS was also using about twice the amount of CPU they normally do.

This _is_ weird.  Not only that, it is actually a contrary observation
to what others are seeing.  One user even said:

"The load average on my machine is considerably lower, yet data is coming 
in fine. What's up with that?"

I can add that the machine in question is running RedHat 8.0 Linux,
not Solaris x86, but I can further add that our experience on our
x86 machine matched the above.

>I switched
>back to LDM 5.2 and everything is fine again.  I didn't try splitting
>the pqact's up yet.  I am just back on 5.2 until I hear from yiu again.
>This is very odd.

This is very, very strange.  Can I get onto this machine to take
a firsthand look?

>BTW I am running Solaris 8..the box was patched about 2 months
>ago.

OK.  Our x86 box is up to date with regard to patches, but I
don't expect that this will be the problem.

Again, letting us on would help us find out what is so different
on your machine.

Tom