It may not be a direct buffer bloat problem, but the berkeley tool to identify buffer bloat gives a lot of useful info, maybe helpful to you in your troubleshooting if you have not yet used it (or something similar):
http://netalyzr.icsi.berkeley.edu/index.html cheers! Kress On Wed, Jun 6, 2012 at 8:53 PM, Daniel Hagerty <[email protected]> wrote: > Daniel Feenberg <[email protected]> writes: > > > I have difficulty reconciling these facts. If pings are fast and packets > > are not dropped, why do users see problems? I can confirm things seem > > slow. Is this the dreaded "buffer bloat" problem so recently hyped? Is > > there anything I can do here to aleviate it while waiting for more > > bandwidth? > > I agree, it doesn't quite add up. Bufferbloat would show up with > slow ping, or other slow real time apps. Try interactive ssh over the > suspect link and see what your fingers tell you about round trip times. > > It's possible that the link has a really snazzy queueing setup with > buffering issues within it. The theory here would be that the ping > you're running is hitting a small queue, but the traffic your users > actually care about are all hitting an overfull one. > > I've solved problems like this in the past with clever queueing, but > it's not clear that this is your problem. > > _______________________________________________ > bblisa mailing list > [email protected] > http://www.bblisa.org/mailman/listinfo/bblisa >
_______________________________________________ bblisa mailing list [email protected] http://www.bblisa.org/mailman/listinfo/bblisa
