We define:
ping success = 1 - # 100 data byte ping packets lost / total number of 100 data byte ping packets
ping data rate = 2000 bytes / (average response time of 10 consecutive 1000 data byte ping packets)
Then for a set of pings (e.g. all the pings to a given host in one day) we calculate:
s = average(ping success) / max(ping success)
and
r = average(ping data rate) / max(ping data rate)
We scatterplot the daily average/max ratio of packet success(s) versus average/max ratio of data rate(r) for each host.
The results are shown below for 1996 for ESnet nodes, International Nodes, and other North Anerica nodes. In these scatter plots, points towards the top right indicate high predictability. It can be seen that service predictability as seen from SLAC is much higher for ESnet than other nodes.
ESnet | jan96 feb96 mar96 apr96 may96 jun96 jul96 aug96 sep96 oct96 nov96 dec96 jan97 |
International: | jan96 feb96 mar96 apr96 may96 jun96 jul96 aug96 sep96 oct96 nov96 dec96 jan97 |
ISP_Local: | jan96 feb96 mar96 apr96 may96 jun96 jul96 aug96 sep96 oct96 nov96 dec96 jan97 |
North_America_East: | jan96 feb96 mar96 apr96 may96 jun96 jul96 aug96 sep96 oct96 nov96 dec96 jan97 |
North_America_West: | jan96 feb96 mar96 apr96 may96 jun96 jul96 aug96 sep96 oct96 nov96 dec96 jan97 |
North America: | jan96 feb96 mar96 apr96 may96 jun96 jul96 aug96 sep96 oct96 nov96 dec96 jan97 |
All: | jan96 feb96 mar96 apr96 may96 jun96 jul96 aug96 sep96 oct96 nov96 dec96 jan97 |