APRICOT Latency Clustering
0 likes386 views
The document analyzes inter-country latency across Africa, highlighting variations in connectivity and end-to-end latencies among different countries and regions. It uses pings and traceroutes to identify key latency clusters and the impact of geographical and infrastructural factors. The findings emphasize the reliance on international transit providers and the sparse presence of local content in the African internet ecosystem.
APRICOT Latency Clustering
- 1. Insights into Africa’s country-level latencies 1 APRICOT 2018, Nepal Amreesh Phokeer AFRINIC
- 2. Circuitous routes and high end-to-end latencies across the continent 2
- 3. Which countries are better inter-connected, which ones are not? • Key clusters of connectivity in the region • How are inter-country latencies impacted by topology and interconnection strategies? 3 Source: AXIS Project
- 4. Vantage Points 4 850 software probes 319 Ases 52 countries 50% of the countries had at least 20% of their ASes probed.
- 6. • Ping from each probe: • select random African Speedtest server as target • launch 10 consecutive pings (one second apart) to their randomly chosen Speedtest server • return the minimum delay (RTT) observed at that time period • Traceroute from each probe: • launch a Traceroute to randomly selected Speedtest server • for each router hop • determine the ASN using the RIPE Routing Information Service • attach the geolocation using MaxMind GeoLite2-City 6
- 7. Data Collection 7 4 times a day Pings and traceroute 3 months 42 200 RTT samples 31 500 traces captured 319 ASNs
- 9. 9 Under 30ms • Mauritius • Reunion • Cote D’Ivoire Mean in-country Under 40ms • South Africa • Egypt • Benin
- 10. 10 Zambia <-> Malawi Zambia <-> Zimbabwe Mauritius <-> Reunion
- 14. Unusual Cases in Latency Clusters 14 • Senegal, Liberia and Benin on the West coast, in Northern cluster • Madagascar, Seychelles, islands of the Indian Ocean, clustered alongside countries in the North • Somalia, on the East coast, is clustered with countries on the West coast.
- 15. Unusual Cases in Latency Clusters 15 • Senegal, Liberia and Benin on the West coast, in Northern cluster • Madagascar, Seychelles, islands of the Indian Ocean, clustered alongside countries in the North • Somalia, on the East coast, is clustered with countries on the West coast.
- 16. 16 • Senegal, Liberia and Benin on the West coast, in Northern cluster • Madagascar, Seychelles, islands of the Indian Ocean, clustered alongside countries in the North • Somalia, on the East coast, is clustered with countries on the West coast.
- 17. Ethiopia Upstream 100% Overseas Angola Upstream 50% Overseas* *16% Southern -> Europe 17 EU 354ms 144ms N.America
- 18. inter-cluster median RTTs Southern and Eastern • Lowest inter-cluster delay ~ 92ms • Lowest intra-cluster RTTs individually 18 Inter-cluster delays are mostly exceeding 200ms Western cluster has the highest intra-cluster RTTs
- 20. Africa’s upstream providers 20 37.8% of traceroute paths transit (1st AS hop) outside of Africa 6.6% through SA and 4.5% through Mauritius (WIOCC)
- 21. Africa’s Top 10 Upstream Providers 21
- 22. Africa’s Top 10 upstream providers 22 France Telecom (Orange) accounts for 17% for French speaking countries in West Africa
- 24. Same cluster 203ms Other African Cluster 243ms Overseas 268ms Northern ⤇ North America: 71ms Southern ⤇ North America: 227ms 24CDF of RTTs grouped by location of upstream providers RTT to the first AS hop
- 25. 25 Below 40ms Benin Egypt Mauritius Ivory Coast Reunion South Africa Cluster w/ high delays (Western) Due to higher usage of international transit providers Africa’s Interdomain communications highly reliant on inter-continental transit
- 26. WHERE IS OUR LOCAL CONTENT? 26
- 27. Where is African local content? 27 1400+ News websites 36 countries
- 28. Africa’s upstream providers 28 37.8% of traceroute paths transit (1st AS hop) outside of Africa 6.6% through SA and 4.5% through Mauritius (WIOCC)
- 30. 30
- 32. 32 Median RTT
- 33. 33