Re: [conduit] Large CONDUIT latencies to UW-Madison idd.aos.wisc.edu starting the last day or two.

NSSL uses the Boulder TIC, so it may have been a Colorado problem.   Also, our problems actually started on Thursday -- (my memory is getting bad). 

I switched us over to a back up IRADS server for data, and the problem has not recurred.

The problem is, that the latencies were intermittent.  I at first thought it was just a few hours early Thursday morning (11Z-13Z), but then it happened again mid-day Thursday (17Z-19Z).   Which makes me wonder if it's model data or something saturating the network and throttling us.

I then made a switch to the OU IRADS backup server, and am not sure if I would have seen it again. 

This morning I started up one of my backup servers, and now I'm connected to both of OU's IRADS servers separately to see if either or both of them are still having the issue.  I plan to leave it running that way for most of the day today for testing. 

On Mon, Feb 22, 2016 at 8:49 AM, Carissa Klemmer - NOAA Federal <address@hidden> wrote:

Karen,

There was definitely something going on outside of NCEPs servers. We heard from a couple of folks from Colorado to Oregon having issues that moved their services to a new location and rates went back to normal. Since you are in Ok it may have been further reaching into the mid-west than we heard. Are you still having issues? We are trying to gauge from our users now to see if something is still lingering out there.

Carissa Klemmer
NCEP Central Operations
Dataflow Team Lead
301-683-3835

On Mon, Feb 22, 2016 at 8:52 AM, Patrick L. Francis <address@hidden> wrote:

 

All,

Something bigger than just CONDUIT users occurred on the 19th. We had numerous users of other servers complain of similar drops in transfer rates. A few of them were also able to move downloads to a new location where speeds were normal. We believe that this issue was outside of NCEP due to that reasoning. Having said that though, is anyone still seeing abnormal rates?

 

 

Hi Carissa J

 

From our Amazon location in VA, everything is fine as it was on Friday… From our colo facility, packet loss is still shown via 140.90.111.36, which is the hop from gigapop to ncep.. here is an MTR showing the packet loss:

 

http://drmalachi.org/files/ncep/he-ncep.2016.02.22.jpg

 

Notice that since our colo is directly on the Hurricane Electric backbone, there are only a few hops to get to the ncep server, and pings only jump once they reach gigapop.

 

Here is a screen cap of current download speeds for 0.25deg gfs from the ncep server to our colo:

 

http://drmalachi.org/files/ncep/he-ncep.wget.2016.02.22.jpg

 

In order to ensure proper delivery, we have setup a push / pull from our amazon box to the colo, but most people probably won’t have that flexibility.. The issue appears to potentially be related to packetfiltering and / or redirection / funneling via certain routes, but that’s just a guess J

 

Happy Monday J

 

Cheers,

 

--patrick

 

 

 

 

-------------------------------------------------------

Patrick L. Francis

Vice President of Research & Development

 

Aeris Weather

 

http://aerisweather.com/

http://modelweather.com/

 

http://facebook.com/wxprofessor/

 

--------------------------------------------------------

_______________________________________________
conduit mailing list
address@hidden
For list information or to unsubscribe, visit: http://www.unidata.ucar.edu/mailing_lists/

--

“The presence of those seeking the truth is infinitely to be preferred to the presence of those who think they’ve found it."

 -- Terry Prachett

-------------------------------------------
address@hidden

Phone#:  405-325-6456
Cell:   405-834-8559
National Severe Storms Laboratory

_______________________________________________
conduit mailing list
address@hidden
For list information or to unsubscribe, visit: 
http://www.unidata.ucar.edu/mailing_lists/