This archive is retained to ensure existing URLs remain functional. It will not contain any emails sent to this mailing list after July 1, 2024. For all messages, including those sent before and after this date, please visit the new location of the archive at https://mailman.ripe.net/archives/list/ripe-atlas@ripe.net/
[atlas] Number of probes
- Previous message (by thread): [atlas] Number of probes
- Next message (by thread): [atlas] [dagstuhl seminar]: global measurements: practice and experience
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Wenqin Shao
wenqin.shao at telecom-paristech.fr
Wed May 11 18:03:45 CEST 2016
Hello Marc, It depends what you are looking for. Though the same AS path is measured between two ASes, the IP level paths could be different, which leads to different RTT behaviour. I analysed the RTT over 12h between 100 probes in AS3215 and m-root. The resulted times series demonstrate different level of variation. Further, it turned out that most variation in end2end RTT measurements takes place in access network, with the help of traceroute. So if you are looking to quantify the performance of AS level path, choose the ping trace with the least variation. For more detail, W. Shao, J.-L. Rougier, F. Devienne, and M. Viste, “Improve Round-Trip Time Measurement Quality via Clustering in Inter-Domain Traffic Engineering,” no. AnNet, pp. 1105–1108, 2016. My two cents, wenqin ----- Mail original ----- De: "Marc Sanchez" <marc.sanchez at csuc.cat> À: ripe-atlas at ripe.net Envoyé: Mercredi 11 Mai 2016 17:52:06 Objet: [atlas] Number of probes I'm new in RIPE and I don't know it enough deeper. I need to check the state of several networks and I'm wondering how many probes should I need to measure a ping between two ASN. Could be enough using just one probe for each measurement? Sorry for the inconvenience. Sent via RIPE Forum -- https://www.ripe.net/participate/mail/forum
- Previous message (by thread): [atlas] Number of probes
- Next message (by thread): [atlas] [dagstuhl seminar]: global measurements: practice and experience
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]