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

20030702: LSU LDM/network stress Test



>From: Robert Leche <address@hidden>
>Organization: LSU
>Keywords: 200306161954.h5GJs2Ld016710 LDM-6 IDD

Hi Bob,

>Go ahead with the test, Terry has made the changes to the network. All 
>Port 388 traffic to/from SRCC LDM hosts have a dedicated  20 meg-bit 
>pipe. We are currently using less than 2 MB peak.

I started cranking up LDMs on various machines here at Unidata this morning.
Here is the list currently of UPC machines feeding from seistan:

Machine                        Feeds from seistan
------------------------------+---------------------------------------------
emo.unidata.ucar.edu           HDS
chevy.unidata.ucar.edu         HDS, IDS|DDPLUS, UNIWISC
newshemp.unidata.ucar.edu      HDS
zasu.unidata.ucar.edu          HDS, IDS|DDPLUS, UNIWISC
zero.unidata.ucar.edu          HDS, IDS|DDPLUS, UNIWISC

I am thinking about adding another machine to the list:

Machine                        Feeds from seistan
------------------------------+---------------------------------------------
imogene.unidata.ucar.edu      HDS

but I want to wait to see what the performance of seistan is with the
above feeds.

For the recond, ULM is also feeding the same set of data and more
from seistan:

Machine                        Feeds from seistan
------------------------------+---------------------------------------------
tornado.geos.ulm.edu           HDS, FSL2, IDS|DDPLUS, NNEXRAD, UNIWISC

During peak HDS hours, seistan should be feeding ~ 6 x 300 MB (~1.8 GB)
of data per hour (the peak data rate in HDS is ~300 MB/hour).

I just checked the HDS latencies for the various UPC machines feeding
from seistan, and they all look good so far.

Tom