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

[IDD #GEY-291391]: Latency blips when using primary/alternate configuration

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 Note that the archive is no longer being updated. We provide the archive for reference; many of the answers presented here remain technically correct, even if somewhat outdated.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: [IDD #GEY-291391]: Latency blips when using primary/alternate configuration
  • Date: Fri, 10 Jul 2009 16:03:12 -0600
Hi Art,

re:
> In a temporary configuration of our LDM relay, I'm feeding CONDUIT data to
> iddrs1.meteo.psu.edu from idd-ingest.meteo.psu.edu exclusively, but
> feeding CONDUIT to iddrs3.meteo.psu.edu from idd-ingest.meteo.psu.edu and
> idd.cise-nsf.gov in a primary/secondary configuration.
> idd-ingest.meteo.psu.edu is getting its CONDUIT data exclusively from
> idd.cise-nsf.gov.  Looking at the Unidata latency graphs, iddrs1 and
> idd-ingest look similar and low, and idd.cise-nsf.gov looks low, but
> iddrs3 has huge blips in it.  These blips, we've noticed, seem to show up
> when a primary/alternate configuration is used.

OK, I understand.

> My question:  are these
> blips some computational figment of the flip/flopping between
> primary/alternate data sources, or is there some real problem being
> detected?

I don't think so.

Question:

- is the LDM queue on iddrs3 the same as the one on iddrs1?

My first hunch is that the sporadic high latencies seen on products
being received from idd.cise-nsf.gov are ones that are not being
rejected as duplicates on iddrs3.  This could happen if the LDM
queue on iddrs3 is not large enough to still be holding "second trip"
products from an upstream.

Second question:

- if the LDM product queues are the same size on iddrs3 and idddrs1,
  is the set of data being sent to them the same?

> Reference URL's for comparisons:
> 
> www.unidata.ucar.edu/cgi-bin/rtstats/iddstats_nc?CONDUIT+iddrs1.meteo.psu.edu
> www.unidata.ucar.edu/cgi-bin/rtstats/iddstats_nc?CONDUIT+idd-ingest.meteo.psu.edu
> www.unidata.ucar.edu/cgi-bin/rtstats/iddstats_nc?CONDUIT+iddrs3.meteo.psu.edu
> www.unidata.ucar.edu/cgi-bin/rtstats/iddstats_nc?CONDUIT+idd.cise-nsf.gov

Cheers,

Tom
--
****************************************************************************
Unidata User Support                                    UCAR Unidata Program
(303) 497-8642                                                 P.O. Box 3000
address@hidden                                   Boulder, CO 80307
----------------------------------------------------------------------------
Unidata HomePage                       http://www.unidata.ucar.edu
****************************************************************************


Ticket Details
===================
Ticket ID: GEY-291391
Department: Support IDD
Priority: Normal
Status: Closed