perfSONAR User Q&A and Other Discussion

[Phil Reese <>]

    Ivan,
    
    Thanks for your thoughts on TWAMP.  After more review, I came to the
    same conclusion, for now.
    
    Putting the period at the end of the sentence, my mesh has been
    fully happy for the last few days.  I still think there must be a
    variable to tweak in there somewhere.
    
    I did do some quick math, a 17x17 Loss grid, uses 256 tests (16x16,
    not including the original agent), which can happen simultaneously,
    but running this many tests (plus the other standard tests) every
    300secs is a lot!  Still the hosts aren't showing big load nor high
    mem use.  I'll try to find and talk with Mark at SC.
    
    Sorry you won't be able to attend SC, this year.
    
    Phil

On 11/4/19 6:11 AM, Garnizov, Ivan wrote:

With regards the TWAMP measurements I do not have much experience, but I have a running example.

IMHO there’ll be no real benefit for you with a TWAMP mesh.