Jonathan Morton <chromati...@gmail.com> writes: > On 21 Mar, 2011, at 12:47 am, Dave Täht wrote: > >>> The interesting outlier thus far is 8... I'm tempted to stop the test >>> now and recompile for testing 3 u/l 3 d/l first....
I found the cause of the outlier, the arm box had a hiccough on its hard disk controller for some reason around then. Or at least that appears to be the case, but judging from this: Scenario 16: 1 uploads, 31 downloads... 4401 KiB/s up, 4111 KiB/s down, 0.59 Hz smoothness Scenario 17: 16 uploads, 16 downloads... 6108 KiB/s up, 2103 KiB/s down, 0.00 Hz smoothness Maybe not. Me thinks we need 3 digits of precision here. -- Dave Taht http://nex-6.taht.net _______________________________________________ Bloat mailing list Bloat@lists.bufferbloat.net https://lists.bufferbloat.net/listinfo/bloat