NSF Unidata

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

[IDD #BKI-822215]: LDM feed sites

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 Note that the archive is no longer being updated. We provide the archive for reference; many of the answers presented here remain technically correct, even if somewhat outdated.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.



Hi Adam,

We are curious as to the size of your LDM queue on tornado.  We ask
because the volume of data you are receiving is high:

http://www.unidata.ucar.edu/cgi-bin/rtstats/rtstats_summary_volume?tornado.geos.ulm.edu

Data Volume Summary for tornado.geos.ulm.edu

Maximum hourly volume   9322.126 M bytes/hour
Average hourly volume   4661.935 M bytes/hour

Average products per hour     187700 prods/hour

Feed                           Average             Maximum     Products
                     (M byte/hour)            (M byte/hour)   number/hour
NEXRAD2                1609.383    [ 34.522%]     2206.471    55634.383
CONDUIT                1476.247    [ 31.666%]     4661.303    40444.170
NGRID                   612.111    [ 13.130%]     1402.037    14442.830
NEXRAD3                 297.440    [  6.380%]      370.064    29893.638
HDS                     208.653    [  4.476%]      436.922    17260.191
FNMOC                   173.058    [  3.712%]     1850.444     1801.617
NIMAGE                  158.075    [  3.391%]      279.354      191.596
FNEXRAD                  65.697    [  1.409%]       82.139       50.511
IDS|DDPLUS               29.993    [  0.643%]       50.081    27663.340
UNIWISC                  26.050    [  0.559%]       33.047       30.085
GEM                       3.763    [  0.081%]       29.473      258.000
FSL2                      1.345    [  0.029%]        1.604       20.000
LIGHTNING                 0.120    [  0.003%]        0.249        9.213

If your LDM queue is too small, or if tornado is not fast enough to
process data out of the queue, you would be seeing a situation where
data is being received, but some part of it is never seen on disk (i.e.,
products get overwritten in your LDM queue before the pqact invocation(s)
have had a chance to act on them).

Again, just a curiosity.  The size of the queue should have no effect
on the latencies you are seeing...

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: BKI-822215
Department: Support IDD
Priority: Normal
Status: Closed