[Halld-online] [New Logentry] DAQ Network seems OK

[davidl at jlab.org]

Logentry Text:
--
I checked the infiniband switch and the ports for gluonraid1 (5) and gluon100 (33) seem to be functioning OK (gluonraid2(port 12) is throwing lots of errors which may account for it's sluggishness earlier today, but does not explain why things are slow with gluonraid1).

I also confirmed that gluon100 and gluonraid1 are communicating through the infiniband network and not one of the slower networks.

Looking at the traffic on the ib interface on gluonraid1 there were 2 connections using lots of bandwidth. One was for writing to disk and the other was for transporting data to gluon47 for the online monitoring system. I confirmed that turning on and off the monitoring system affected the data rate and live time. See images below showing a clear dip in both when the monitoring system was restarted. The monitoring system is reading at about 300MB/s

---

This is a plain text email for clients that cannot display HTML.  The full logentry can be found online at https://logbooks.jlab.org/entry/3389637
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.jlab.org/pipermail/halld-online/attachments/20160309/555b2806/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Screen Shot 2016-03-09 at 12.21.26 AM.png
Type: image/png
Size: 411813 bytes
Desc: not available
URL: <https://mailman.jlab.org/pipermail/halld-online/attachments/20160309/555b2806/attachment-0002.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Screen Shot 2016-03-09 at 12.21.35 AM.png
Type: image/png
Size: 409023 bytes
Desc: not available
URL: <https://mailman.jlab.org/pipermail/halld-online/attachments/20160309/555b2806/attachment-0003.png>