1. FABIAN SCHNEIDER, SACHIN AGARWAL,TANSU ALPCAN, AND ANJA FELDMANN DEUTSCHE TELEKOM LABORATORIES/TECHNISCHE UNIVERSITAT BERLIN 10587 BERLIN, GERMANY ΣΗΜΑΝΤΗΡΑΚΗ ΟΛΥΜΠΙΑ Α.Μ 2225 The New Web: Characterizing AJAX Tra ffi c 1

2. AJAX vs. normal Web browsing 2

3. Motivation Network tra ffi c generation has to be realistic for networking experiments Real-world tra ffi c characteristics change with the applications used Need to check if tra ffi c models are still applicable, on a regular basis ⇒ Do new Web applications change the characteristics? We picked four popular representative of AJAX apps and studied their tra ffi c: Google Maps Google Mail gmx.de (popular German webmailer) lokalisten.de (popular German social network) 3

4. Outline 4 1. How AJAX applications work 2. Analysis approach 3. Measurement results 4. Conclusions

5. Google Maps internals 5 Google Maps... Is an AJAX application Pre-fetches tiles Opens multiple TCP connections to various di ff erent servers Uses Cookies to identify users Transfers data via persistent and pipelined HTTP

6. Difficulties of identifying Google Maps related tra ffi c 6 Identifying Google Maps related tra ffi c by: Server IP’s: not precise enough Server name: very costly URL prefix: good enough We found similar methodologies for the other three AJAX applications.

7. Trace based analysis 7  Three HTTP (Port 80) full packet traces :  Two environments: Large scientific user populations, including student housing High bandwidth internet access  Analysis Procedure: Bro for TCP stream reassembly and HTTP protocol analysis Extract one-line summaries per HTTP request/reply pair

8. Selecting AJAX traffic 8 Identifying the complete AJAX-based tra ffi c is not possible by looking at the request/response stream only Need to choose Web applications that are AJAX-enabled We choose the 4 most popular AJAX applications that we found in our traces: Google Maps Google Mail gmx.de (popular German webmailer) lokalisten.de (popular German social network) Compare AJAX vs. All-HTTP tra ffi c

9. Results 9 Parameters studied:  Number of bytes transfered (HTTP payload)  Number of HTTP requests  Inter-request-times Reported results are consistent over all data sets Results presented as CCDF and PDF Colors used: red/pink All-HTTP green Google Maps

10. Bytes per connection (HTTP payload) 10

11. Session Tracking 11 Session: set of connections related to a user browsing on a webpage AJAX tra ffi c: Track the cookie of connections to the entry pages Connections with the same user identification cookie are grouped into a session All-HTTP tra ffi c: All connections where the 3-tuple (server IP, server Port, client IP) is identical are group into a session For both All-HTTP and AJAX sessions, an inactivity timeout of 10 minutes was applied

12. Bytes per session (HTTP payload) 12

13. Requests per session 13

14. Inter-Request-Times 14

15. Summary 15 On average AJAX apps transfer more bytes per connection/session The number of requests per session is higher for AJAX apps Significantly shorter inter-request-times ⇒ Larger sessions and burstier tra ffi c is upcoming with AJAX applications

16. 16 ΕΥΧΑΡΙΣΤΩ ΠΟΛΥ !!