This page describes the numerous analysis tables provided for each dataset. For illustrative purposes, we include the tables of the D04 [Backbone 1, 2002-08-14], bytes dataset on this page.

In the general design of the tables, a statistic is provided for all four possible combinations of link direction and source/destination endpoint (except for D08 [Backbone 1, 2003-05-07], which has only one direction). We use geographic orientation to label the direction of the backbone links rather than using the arbitrary (and not very informative) designations of 0 and 1. The northbound ("north") direction of both Backbone 1 and Backbone 2 travels from San Jose, CA to Seattle, WA. For the university link, we use inbound and outbound.

Object Diversity at Specific Traffic Percentiles

These tables show the percentage of objects that together contribute a given percentage of the total traffic. For example, we can see that 7.6% of the northbound source IP addresses contribute 99% of the total traffic. The values in the second column under each direction heading give the minimum volume of traffic (in either bytes or packets, depending on which set of tables is being viewed) contributed by each object. In the case of the previous example, each of the 7.6% of objects contribute at least 77k bytes.

See "Number of Objects Responsible for Specific Traffic Percentiles" for the object counts rather than object percentages. See "Traffic by IP/Prefix/Atom/AS" for the object diversity data grouped by object type rather than by traffic percentage.

north,src north,dst south,src south,dst IP 7.6% 77k 7.3% 112k 5.5% 426k 7.2% 53k Prefix 7.1% 7.5M 29.4% 14M 7.3% 60M 17.2% 7.4M Atom 6.4% 30M 28.7% 42M 6.3% 161M 17.1% 21M AS 5.2% 59M 29.6% 61M 6.0% 334M 16.3% 40M

Object Diversity of 99% of the Traffic

north,src north,dst south,src south,dst IP 1.0% 2.5M 3.2% 679k 1.4% 6.5M 2.9% 413k Prefix 1.6% 150M 15.6% 68M 2.6% 569M 7.4% 45M Atom 1.9% 416M 11.8% 228M 2.0% 1.7G 6.2% 171M AS 1.6% 800M 11.5% 362M 1.7% 3.5G 4.8% 341M

Object Diversity of 95% of the Traffic

north,src north,dst south,src south,dst IP 0.4% 10M 1.7% 1.7M 0.6% 22M 1.5% 985k Prefix 0.7% 474M 10.2% 161M 1.1% 1.4G 4.1% 116M Atom 1.0% 1.2G 6.2% 628M 1.1% 7.5G 3.2% 517M AS 0.7% 2.4G 5.6% 994M 1.0% 18G 2.3% 1.3G

Object Diversity of 90% of the Traffic

north,src north,dst south,src south,dst IP 0.0% 627M 0.1% 55M 0.0% 2.0G 0.1% 31M Prefix 0.0% 24G 1.4% 1.5G 0.1% 57G 0.3% 2.5G Atom 0.1% 37G 0.5% 18G 0.2% 74G 0.2% 16G AS 0.1% 69G 0.3% 78G 0.2% 96G 0.1% 40G

Object Diversity of 50% of the Traffic

Number of Objects Responsible for Specific Traffic Percentiles

These tables show the number of objects that together contribute a given percentage of the total traffic. For example, we can see that 21,816 of the northbound source IP addresses contribute 95% of the total traffic. See "Object Diversity at Specific Traffic Percentiles" for the object percentages rather than counts.

north,src north,dst south,src south,dst IP 21,816 129,244 15,742 369,433 Prefix 449 1,733 216 3,329 Atom 185 344 70 745 AS 82 211 35 298

Number of Objects Responsible for 95% of the Traffic

north,src north,dst south,src south,dst IP 291 3,390 168 8,900 Prefix 9 157 9 142 Atom 5 14 7 26 AS 4 5 5 8

Number of Objects Responsible for 50% of the Traffic

Number of Objects that Individually Contribute 1% of the Traffic

This table shows the number of objects that individually contribute at least 1% of the total traffic. Note that some of these objects contribute far more than 1% of the traffic, which is made clear by the earlier table titled "Number of Objects Responsible for 50% of the Traffic." For instance, in that table, only 4 ASes are responsible for 50% of the traffic in the (north, src) column. Hence, there must be a single AS that contributes at least 12.5% of the traffic.

Note that the counts in a particular column may decrease in the progression from IP addresses to prefixes to atoms to ASes. For example, in the first column (north, src), the prefix count is 15 while the AS count is 14. This can happen when two prefixes, each contributing at least 1% of the traffic, belong to the same AS. The atom count can be higher than the AS count for a similar reason; in this case, two prefixes belonging to the same AS are put into two different atoms (it is not abnormal for the prefixes belonging to a single AS to be assigned to different atoms).

north,src north,dst south,src south,dst IP 3 0 7 0 Prefix 15 8 21 12 Atom 14 20 23 16 AS 14 19 16 16

Number of Objects that Individually Contribute 1% of the Traffic

Traffic by IP/Prefix/Atom/AS

These tables show the object diversity at specific traffic percentiles in the same manner as "Object Diversity at Specific Traffic Percentiles", except with the tables grouped by object type rather than by traffic percentage.

north,src north,dst south,src south,dst 99% 7.6% 77k 7.3% 112k 5.5% 426k 7.2% 53k 95% 1.0% 2.5M 3.2% 679k 1.4% 6.5M 2.9% 413k 90% 0.4% 10M 1.7% 1.7M 0.6% 22M 1.5% 985k 50% 0.0% 627M 0.1% 55M 0.0% 2.0G 0.1% 31M

Traffic by IP

north,src north,dst south,src south,dst 99% 7.1% 7.5M 29.4% 14M 7.3% 60M 17.2% 7.4M 95% 1.6% 150M 15.6% 68M 2.6% 569M 7.4% 45M 90% 0.7% 474M 10.2% 161M 1.1% 1.4G 4.1% 116M 50% 0.0% 24G 1.4% 1.5G 0.1% 57G 0.3% 2.5G

Traffic by Prefix

north,src north,dst south,src south,dst 99% 6.4% 30M 28.7% 42M 6.3% 161M 17.1% 21M 95% 1.9% 416M 11.8% 228M 2.0% 1.7G 6.2% 171M 90% 1.0% 1.2G 6.2% 628M 1.1% 7.5G 3.2% 517M 50% 0.1% 37G 0.5% 18G 0.2% 74G 0.2% 16G

Traffic by Atom

north,src north,dst south,src south,dst 99% 5.2% 59M 29.6% 61M 6.0% 334M 16.3% 40M 95% 1.6% 800M 11.5% 362M 1.7% 3.5G 4.8% 341M 90% 0.7% 2.4G 5.6% 994M 1.0% 18G 2.3% 1.3G 50% 0.1% 69G 0.3% 78G 0.2% 96G 0.1% 40G

Traffic by AS

Crossover

These tables describe several properties of the crossovers present in the datasets. By definition, the crossover split (100 - C)%/C% occurs when C% of the largest objects (by traffic volume) contribute (100 - C)% of the total traffic. For example, a split of 90%/10% would mean just 10% of the objects contribute 90% of the traffic. Although the crossover must exist, it rarely happens that C% of objects contribute exactly (100 - C)% of the traffic. Because object counts are discrete values with a limited range, it is more typical for C% of objects to contribute (100 - C + delta)%, for some small delta. In our tables, we list the C% that produces the smallest absolute delta. For all our datasets, the sum of the chosen object percentage (C%) and the traffic volume percentage [approx. (100 - C)%] is within 1% of 100%.

For the crossover split (100 - C)%/C%, the C% of largest objects (by traffic volume) are the elephants, and the remaining (100 - C)% are the mice. The traffic cutoff at the crossover is the minimum volume of traffic (in either bytes or packets) contributed by each of the elephants. In the tables showing the aggregate traffic volume of elephants and mice, percentages are with respect to the total traffic volume.

north,src north,dst south,src south,dst IP 97.5/2.5% 96.2/3.8% 97.4/2.6% 96.4/3.6% Prefix 97.2/2.8% 89.9/10.1% 96.6/3.4% 93.7/6.3% Atom 97.1/2.9% 92.1/7.9% 97.0/3.0% 94.4/5.6% AS 97.4/2.6% 92.3/7.7% 97.0/2.9% 95.1/4.9%

Crossover Split (volume%/object%)

north,src north,dst south,src south,dst IP 443k 486k 2.3M 263k Prefix 47M 164M 364M 60M Atom 184M 460M 820M 201M AS 353M 626M 1.3G 336M

Traffic Cutoff at the Crossover (i.e., Minimum Size of Elephants)

north,src north,dst south,src south,dst IP 52,549 2.5% 155,413 3.8% 28,835 2.6% 458,511 3.6% Prefix 780 2.8% 1,128 10.1% 287 3.4% 2,806 6.3% Atom 279 2.9% 230 7.9% 105 3.0% 676 5.6% AS 136 2.6% 141 7.7% 59 2.9% 303 4.9%

Number of Elephants

north,src north,dst south,src south,dst IP 1.2T 97.5% 1.2T 96.2% 2.1T 97.4% 2.1T 96.4% Prefix 1.2T 97.2% 1.1T 89.9% 2.1T 96.6% 2.0T 93.7% Atom 1.2T 97.1% 1.2T 92.1% 2.1T 97.0% 2.0T 94.4% AS 1.2T 97.4% 1.2T 92.3% 2.1T 97.0% 2.0T 95.1%

Total Traffic Volume of Elephants

north,src north,dst south,src south,dst IP 31G 2.5% 48G 3.8% 55G 2.6% 78G 3.6% Prefix 35G 2.8% 128G 10.1% 73G 3.4% 134G 6.3% Atom 37G 2.9% 100G 7.9% 65G 3.0% 118G 5.6% AS 33G 2.6% 98G 7.7% 63G 3.0% 105G 4.9%

Total Traffic Volume of Mice (computed from volume of elephants, and thus may be slightly imprecise)

Geographic Distribution of Traffic

These tables show the breakdown of the traffic by continent. The percentages add up to 100% in each column. The actual volume of traffic (in bytes or packets) appears in the second column below each direction heading.

Traffic is aggregated by continent with the following procedure:

1. Match a source or destination IP address to an address block issued by the Regional Internet Registeries (namely, ARIN, RIPE, APNIC, and LACNIC).
2. Extract the country recorded in the registration record of the address block.
3. Map the country to continent.
4. Add up all traffic volumes by continent.

The above procedure has known limitations. The most important being that the registration record merely provides the contact address of the organization that has obtained an address block. This contact address could simply be the headquarters of a multi-national organization (e.g., a Tier-1 ISP) while the actual hosts are spread worldwide, leading to improper placement of hosts. Registration records are also sometimes out-of-date.

Registry data collected on the 1st and 26th of June, 2003, are used to compute the geographic breakdown for all datasets, including those from 2002. For the country-to-continent mapping, we use data from NetGeo along with a few manual additions.

north,src north,dst south,src south,dst North America 77.6% 984G 88.8% 1.1T 91.4% 2.0T 65.5% 1.4T Asia 22.3% 283G 10.3% 131G 7.4% 159G 29.5% 631G Europe 0.0% 194M 0.1% 1.8G 0.1% 1.2G 3.9% 83G Oceania 0.1% 941M 0.2% 2.7G 1.2% 25G 0.3% 7.0G South America 0.0% 149M 0.5% 6.3G 0.0% 1.0M 0.6% 13G Africa 0.0% 34M 0.0% 136k 0.0% 320k 0.2% 3.8G unknown 0.0% 370M 0.0% 100M 0.0% 148M 0.0% 173M

Geographic Distribution of Traffic

north,src north,dst south,src south,dst North America 77.6% 984G 88.8% 1.1T 91.4% 2.0T 65.5% 1.4T Asia 22.3% 283G 10.3% 131G 7.4% 159G 29.5% 631G Europe 0.0% 194M 0.1% 1.8G 0.1% 1.2G 3.9% 83G other 0.1% 1.5G 0.7% 9.1G 1.2% 25G 1.1% 24G

Geographic Distribution of Traffic (brief)

north,src north,dst south,src south,dst North America 77.6% 984G 88.8% 1.1T 91.4% 2.0T 65.5% 1.4T Asia 22.3% 283G 10.3% 131G 7.4% 159G 29.5% 631G other 0.1% 1.7G 0.9% 11G 1.2% 26G 5.0% 107G

Geographic Distribution of Traffic (briefer)