TTM Documentation / FAQ
| q: How is the data generated? |
| At each location (GlobalSwitch, Telecity II, SARA, NIKHEF) a RIPE TTM testbox is installed by the AMS-IX. These testboxes are continuously testing against eachother. The RIPE testboxes are connected to an edge switch through 100baseTX ports. |
| q: Why are there large shifts in the delay plots? |
| It is possible there are one or more large shifts in the delay plots. This is caused by VSRP failovers at the AMS-IX switch platform. The change to the backup core switch causes a shift in delay, corresponding to the distance of the fiber path between colocation sites. This is expected behaviour. |
| q: [realtime stats] What is the error estimate in the real-time statistics? |
| One way measurements involve sending a time-stamped message from one machine to another. The second machine compares its arrival time with its local clock and determines the transfer delays from that. This requires that the local clocks are synchronized and provide the time with a high enough accuracy. The synchronization is the difference between the clock on this machine and an absolute time standard. The accuracy is the error in the time measurement. The errors in synchronization and accuracy determine the overall error in the delay measurement. The error estimate is the grean area in the graphs. Most delay spikes are caused by the error estimate being high, this does not indicate any problem at the AMS-IX platform. |
| q: [realtime stats] Why do I see packetloss in the months before februari? |
| There was a problem in the process of copying data to a real time stream in the RIPE boxes. This resulted in an inaccurate representation of the test data (only for this stream). Our real-time statistics are based on this stream. The measurement results and statistics at the RIPE website are not affected by this. RIPE implemented a solution for this problem on 19 January. |