Skip to Content.
Sympa Menu

perfsonar-user - [perfsonar-user] Potential enhancement for perfsonar

Subject: perfSONAR User Q&A and Other Discussion

List archive

[perfsonar-user] Potential enhancement for perfsonar


Chronological Thread 
  • From: Brent Draney <>
  • To:
  • Subject: [perfsonar-user] Potential enhancement for perfsonar
  • Date: Fri, 23 Jun 2017 11:00:30 -0700
  • Ironport-phdr: 9a23:bdgLqROZhE0nRQ+zJOkl6mtUPXoX/o7sNwtQ0KIMzox0K/r+rarrMEGX3/hxlliBBdydsK0UzbeO+4nbGkU+or+5+EgYd5JNUxJXwe43pCcHRPC/NEvgMfTxZDY7FskRHHVs/nW8LFQHUJ2mPw6a8TWO6msKFw/xLg1zL/6wB5Xfley20fy/4Zvef18OiTagMp1oKxDjhx/csNVerZFrLKsggk/DuHdScuJb1EtuKEiIlFDz4dnmr80ryDhZp/90r50Iaq79ZaltFbE=

Hi All,
When performance tends to drop my best go-to tool is to take a tcpdump
capture and run it
through TCPtrace and generate a time sequence graph and plot it using xplot.
I was wondering
if others thought it would be a useful enhancement to perfsonar to be able to
request that the
perfsonar node automatically dump the first (1000?) packets and generate the
plot file and make
the dump available for download and generate a graphic of the plot file.

I’m sure that it would NOT be something that we would want for every test as
there is significant
overhead in just taking the dump but I suspect that it would significantly
cut down the time to
resolution for problems in the network.

Do others have thoughts on whether this is a good or bad idea (or a waste of
cycles)?

Thanks,
Brent
NERSC Networking




Archive powered by MHonArc 2.6.19.

Top of Page