| < Previous by Date | Date Index | Next by Date > |
| < Previous in Thread | Thread Index | Next in Thread > |
On Jul 11, 2008, at 21:52 , Adam Roach wrote:
So.... for <10k transactions, we would run *faster* with the firewall turned on some non-trivial fraction of the time? This is getting more bizarre...
I'm not so sure that's valid. I mean the variability under 10K transactions (total) is so large that I think we have to assume that we lose the precision in the range... PS: it took me a minute longer than expected to disable the AFW, therefore the ~72K and ~97K points that are green and clearly in the w AFW range are really with the firewall enabled.
Here's the plots with a moving average. Initial average is inital point, so it's an approximation (from awk: awk 'BEGIN { sum=0;} {if (sum==0) sum=$4; sum=(9*sum+$4)/10 ; print $0" "sum;}' sorted.dat > ma.dat
)
Attachment:
20080711-resip-perf-ma.pdf
Description: Adobe PDF document