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

20020906: thelma looks good

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 Note that the archive is no longer being updated. We provide the archive for reference; many of the answers presented here remain technically correct, even if somewhat outdated.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: 20020906: thelma looks good
  • Date: Sat, 07 Sep 2002 09:19:51 -0600
>From:  anne <address@hidden>
>Organization:  UCAR/Unidata
>Keywords:  200209070020.g870Kbj28858

Anne,

>thelma's looking good - the load average is below 5 at the moment.

I must say that I am not suprised that the load average went down
after awhile given that CONDUIT data would lessen/cease and folks at
Penn State would eventually leave for the weekend.

>Is this a result of cutting off Penn State's NIMAGE from atm?

This is hard to say for sure.  I watched thelma's load average for about
10-15 minutes after I removed the allow for NIMAGE in atm's ldmd.conf
file, and there was no major change.  This may have been due to a backlog
of products working their way through the ingest phase on ldm.meteo, but
it also may have been caused by high traffic load on a Friday afternoon
at Penn State (although I shut them off at around 4:35, which would
make it 6:20 eastern time, so you might figure that the usage should
have been going down).

I think what we need to do the next time this happens (like Monday) is

1) verify that the big CPU users on thelma are Washington and Penn State
2) monitor traceroutes to each using mtr
3) figure out if there is another way we can assess the traffic that
   these sites are experiencing

I will send Art Person an email asking him to fill us in on his
perceived usage and whether or not he has upgraded to LDM 5.2 yet.
If he has, I will ask him to add in reporting of realtime stats.
If not, and I don't think he has since he was waiting for the patches
that are in 5.2.1, I will advise him that we are pursuing getting
5.2.1 ready so he can move to it (and then he can run rtstats).

Tom
--
+-----------------------------------------------------------------------------+
* Tom Yoksas                                             UCAR Unidata Program *
* (303) 497-8642 (last resort)                                  P.O. Box 3000 *
* address@hidden                                   Boulder, CO 80307 *
* Unidata WWW Service                             http://www.unidata.ucar.edu/*
+-----------------------------------------------------------------------------+