1 / 6

Masaki Hirabaru <masaki@crl.go.jp> CRL, Japan

Common Performance Measurement Platform. APAN Engineering Team Meeting APAN 2003 in Busan, Korea August 27, 2003. Masaki Hirabaru <masaki@crl.go.jp> CRL, Japan. Motivations. MIT Haystack – CRL Kashima e-VLBI Experiment on August 27, 2003 to measure UT1-UTC in 24 hours

juro
Télécharger la présentation

Masaki Hirabaru <masaki@crl.go.jp> CRL, Japan

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Common Performance Measurement Platform APAN Engineering Team Meeting APAN 2003 in Busan, KoreaAugust 27, 2003 Masaki Hirabaru <masaki@crl.go.jp> CRL, Japan

  2. Motivations • MIT Haystack – CRL Kashima e-VLBI Experiment on August 27, 2003 to measure UT1-UTC in 24 hours • 41.54 GB CRL => MIT 107 Mbps (~50 mins) 41.54 GB MIT => CRL 44.6 Mbps (~120 mins) • RTT ~220 ms, UDP throughput 300-400 MbpsHowever TCP ~6-8 Mbps (per session, tuned) • BBFTP with 5 x 10 TCP sessions to gain performance • HUT – CRL Kashima Gigabit VLBI Experiment • - RTT ~325 ms, UDP throughput ~70 MbpsHowever TCP ~2 Mbps (as is), ~10 Mbps (tuned) • - Netants (5 TCP sessions with ftp stream restart extension) They need high-speed / real-time / reliable / long-haul high performance data transfer.

  3. Purpose • Ensure >1 Gbps end-to-end performance in high bandwidth-delay product networks • to support for networked science applications • to help operations in finding a bottleneck • to evaluate advanced transport protocols (e.g. Tsunami, SABUL, HSTCP, FAST, XCP, ikob)

  4. Seoul XP 10G Korea Kashima Daejon HUT KOREN 0.1G Taegu Tokyo XP 2.5G Helsinki Kwangju 0.1G? Busan Koganei Stockholm funet 1Gx2 2.4G 1G 250km Nordunet 2.4G 2.5G SONET TransPAC 0.6G GEANT APII/JGN 7,000km 2.5G + 1G x2 2.4G Kitakyushu 1,000km Cicago MIT Haystack 1Gx2 0.6G 10,000km Fukuoka Abilene 1G Genkai XP Fukuoka Japan 4,000km QGPOP Los Angeles New York 10G

  5. Proposal • Place a good PC box for performance measurement at each NOC / POP as well as experiment sites (hop-by-hop and end-to-end) • Advanced rate-based / window-based transports (kernel may be modified) • Common measurement method / tool (iperf?) • Monitor for TCP / UDP protocol behavior (tcpdump & tcptrace) • Combine with ping, traceroute, routing stats • Share the boxes and develop scheduler to avoid duplicate tests • Need a consensus to put a strong pressure on our networks (?)

  6. Questions? • See http://www2.crl.go.jp/ka/radioastro/index.htmlfor VLBI

More Related