Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Tracing Data Packet Paths over the Internet using Traceroute

Thomas Dreibholz, Somnath Mazumdar

TL;DR

This work tackles how data packets travel on the Internet from an end-user perspective, revealing that routing is dynamic and not guaranteed to follow geographic shortest paths. It employs a trace-driven methodology using Ping, Traceroute, and the HiPerConTracer toolkit across five years, six ISPs, and multiple countries to characterize end-to-end paths and RTTs. Key contributions include demonstrating non-deterministic routing, frequent detours through third-party countries, and IPv4/IPv6–dependent latency differences, all analyzed without ISP cooperation. The results have practical implications for traffic engineering and performance optimization, and the authors provide an open-source measurement framework to support reproducibility and further study. Future work points to integrating BGP data, improving geo-location, and analyzing higher-layer protocols to better understand the end-user experience under dynamic Internet routing.

Abstract

Network communication using the Internet Protocol (IP) is a pillar of modern Internet applications. IP allows data packets to travel the world through a complex set of interconnected computer networks managed by different operators. How IP-based data communication changes over time can be interesting from an end-system's perspective without relying on underlying network providers. This article presents an extensive, trace-driven analysis of user data traffic (covering five years of observations, six large Internet service providers (covering research, business and consumer category type), twenty autonomous systems, and fourteen countries. Our three primary findings are: i users data packet transmission paths are not deterministic and does not always select the geographically shortest path; ii) user packets take different routes that cover many countries and detour between two fixed points. Even after changing the types of Internet service provider type (e.g., from commercial to research), the routing can differ significantly between two locations. iii) Packet transmission delay can be influenced by changing the Internet service provider and IP protocol versions (i.e., from IPv4 to IPv6).

Tracing Data Packet Paths over the Internet using Traceroute

TL;DR

This work tackles how data packets travel on the Internet from an end-user perspective, revealing that routing is dynamic and not guaranteed to follow geographic shortest paths. It employs a trace-driven methodology using Ping, Traceroute, and the HiPerConTracer toolkit across five years, six ISPs, and multiple countries to characterize end-to-end paths and RTTs. Key contributions include demonstrating non-deterministic routing, frequent detours through third-party countries, and IPv4/IPv6–dependent latency differences, all analyzed without ISP cooperation. The results have practical implications for traffic engineering and performance optimization, and the authors provide an open-source measurement framework to support reproducibility and further study. Future work points to integrating BGP data, improving geo-location, and analyzing higher-layer protocols to better understand the end-user experience under dynamic Internet routing.

Abstract

Network communication using the Internet Protocol (IP) is a pillar of modern Internet applications. IP allows data packets to travel the world through a complex set of interconnected computer networks managed by different operators. How IP-based data communication changes over time can be interesting from an end-system's perspective without relying on underlying network providers. This article presents an extensive, trace-driven analysis of user data traffic (covering five years of observations, six large Internet service providers (covering research, business and consumer category type), twenty autonomous systems, and fourteen countries. Our three primary findings are: i users data packet transmission paths are not deterministic and does not always select the geographically shortest path; ii) user packets take different routes that cover many countries and detour between two fixed points. Even after changing the types of Internet service provider type (e.g., from commercial to research), the routing can differ significantly between two locations. iii) Packet transmission delay can be influenced by changing the Internet service provider and IP protocol versions (i.e., from IPv4 to IPv6).
Paper Structure (27 sections, 9 figures, 10 tables)

This paper contains 27 sections, 9 figures, 10 tables.

Table of Contents

  1. Introduction
  2. Research Context
  3. Research Findings
  4. Related Work
  5. Path Inflation and Routing Policies
  6. Path Tracing
  7. Methodology
  8. Tools: Ping, Traceroute and HiPerConTracer
  9. Ping
  10. Traceroute
  11. HiPerConTracer
  12. Measurement Infrastructure
  13. Data Set Description
  14. Trace Analysis
  15. Measurement Setup
  16. ...and 12 more sections

Figures (9)

  • Figure 1: RTT Time Series for Karlstad, SE to Trondheim, NO. Blue colour: high-speed fibre, green colour: ADSL connection.
  • Figure 2: RTT CDF for Karlstad, SE to Trondheim, NO.
  • Figure 3: RTT Time Series for Essen, DE to Trondheim, NO.
  • Figure 4: RTT CDF for Essen, DE to Trondheim, NO.
  • Figure 5: RTT Time Series for Haikou, CN to Trondheim, NO.
  • ...and 4 more figures