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

Re: motherlode & queue size



On Mon, 31 Jul 2000, Tom McDermott wrote:

> On Thu, 27 Jul 2000, Robb Kambic wrote:
> 
> > A new top-level source, designed as a replacement for thelma.ucar.edu,
> > is now available: "motherlode.ucar.edu".  thelma will still be
> > available for a while, but external sites currently using thelma as a
> > source of data should switch to using motherlode instead, at their
> > convenience.
> 
> Because our primary feed, Cornell, had a scheduled power outage over the
> weekend, Brockport failed over to SUNY Albany, which in turn failed over
> to the ldm server at Penn State, which is now connected to motherlode.

> Prior to this weekend our logical pqueue size was 200MB, of which approx.
> 150MB was being physically used on the disk.  Because my logs were filled
> with thousands of 'Deleting oldest' messages over the weekend, I remade
> the pq w/ a size of 300MB yesterday and today all of that space is
> physically being used on the disk (although no deleting oldest messages
> yet).  Do you have any idea of what accounts for this?  Is more total data
> being transmitted by motherlode or is it simply capable of transmitting
> data at a greater rate, i.e., more data/hour than thelma?



Tom,

I not exactly sure why you are/were receiving the extra products.  The
allow lines on motherlode are UNIDATA|FLS2 for all top tier sites
including PSU. Maybe SUNY was getting some extra products, ie radars that 
were being relayed down the pipe. I would change my request line to only
be UNIDATA|FSL2 and then see if that helps.   Also, if you run notifyme
maybe you can determine what the extra products are?  You are not seeing
NMC2 products?


> 
> BTW, our max. latencies for the times when the 12Z model runs were being
> transmitted were awesome today, <4 minutes, vs. the usual >30 minutes and
> possibly this may be related to the changeover, we'll have to see.
> 
That's great, thelma was slow because of the high disk I/O problem. You
could be correct that the data rate might of pushed more of the model data
into one hour but an 200MB queue should of been large enough.

Robb...




> Tom
> ------------------------------------------------------------------------------
> Tom McDermott                         Email: address@hidden
> System Administrator                  Phone: (716) 395-5718
> Earth Sciences Dept.                  Fax: (716) 395-2416
> SUNY College at Brockport
> 
> 
>  
> > The acquisition of motherlode was described in the Summer/Fall 1999
> > issue of the Unidata Newsletter.  It is the result of a joint project
> > between Unidata and NCAR's Scientific Computing Division (SCD) to
> > provide an archive of IDD products, convenient access to critical data
> > sets in SCD's Mass Storage System, a McIDAS ADDE server, a DODS
> > server, and other new ways to access remote data.  The motherlode
> > machine is a Sun E450, with 4 450 Mhz processors, 4 GB of memory,
> > redundant power supplies, and 500 GB of disk.  It sits on the network
> > directly connected to the vBNS by one router.  It's currently running
> > LDM version 5.1.2, a new version that will be available for general
> > use in about a month.
> > 
> > To check access permissions before switching from thelma to
> > motherlode, invoke
> > 
> >   notifyme -vl - -h motherlode.ucar.edu
> > 
> > and let us know of any problems.
> > 
> > Thanks,
> > Robb...
> > 
> > 
> > ===============================================================================
> > Robb Kambic                                Unidata Program Center
> > Software Engineer III                      Univ. Corp for Atmospheric
> > Research
> > address@hidden                   WWW:
> > http://www.unidata.ucar.edu/
> > ===============================================================================
> > 
> > 
> > 
> > 
> 

===============================================================================
Robb Kambic                                Unidata Program Center
Software Engineer III                      Univ. Corp for Atmospheric Research
address@hidden             WWW: http://www.unidata.ucar.edu/
===============================================================================