Presentation is loading. Please wait.

Presentation is loading. Please wait.

1 (Brief) Introductory Remarks On Behalf of the U.S. Department of Energy ESnet Site Coordinating Committee (ESCC) W.Scott Bradley ESCC Chairman

Similar presentations


Presentation on theme: "1 (Brief) Introductory Remarks On Behalf of the U.S. Department of Energy ESnet Site Coordinating Committee (ESCC) W.Scott Bradley ESCC Chairman"— Presentation transcript:

1 1 (Brief) Introductory Remarks On Behalf of the U.S. Department of Energy ESnet Site Coordinating Committee (ESCC) W.Scott Bradley ESCC Chairman bradley@bnl.gov

2 2 Welcome!!! Much thanks to our UM Hosts, Internet2 Staff. Close collaboration between DOE and University Networking Communities has evolved past a “nice to have,” to a mutual operational necessity. While the demand placed on ESnet continues to accelerate at unprecedented scale, relatively little ESnet traffic remains within the DOE complex. -Onslaught of the LHC -Onslaught of Grid Computing

3 Traffic Volume of the Top 30 AS-AS Flows, June 2006 (AS-AS = mostly Lab to R&E site, a few Lab to R&E network, a few “other”) DOE Office of Science Program LHC / High Energy Physics - Tier 0-Tier1 LHC / HEP - T1-T2 HEP Nuclear Physics Lab - university LIGO (NSF) Lab - commodity Math. & Comp. (MICS) Terabytes FNAL -> CERN traffic is comparable to BNL -> CERN but on layer 2 flows that are not yet monitored for traffic – soon) Large-Scale Flow Trends, June 2006 Subtitle: “Onslaught of the LHC”)

4 4 The Onslaught of Grids Answer: Most large data transfers are now done by parallel / Grid data movers In June, 2006 72% of the hosts generating the 1000 work flows were involved in parallel data movers (Grid applications) This, combined with the dramatic increase in the proportion of traffic due to large-scale science (now 50% of all traffic) represents the most significant traffic pattern change in the history of ESnet This probably argues for a network architecture that favors path multiplicity and route diversity plateaus indicate the emergence of parallel transfer systems (a lot of systems transferring the same amount of data at the same time) Question: Why is peak flow bandwidth decreasing while total traffic is increasing?

5 5 We mutually face networking challenges far more complex than what throwing more bandwidth on-line can fix: Nature of data flows redefining the nature of networks themselves: -Long Term vs. Short Term Programmed Bulk Data Transfer -Chaotic, Short Term Preemptive Activity (e.g. ad-hoc jobs, control activity) Services in R&D only a few years ago are now standard fare (e.g. QoS, MPLS, Layer 2)

6 6 The Moral of the Story: The US cannot remain a world leader in scientific research without addressing these networking challenges And With That…

7 7 Let’s Get to Work!!!


Download ppt "1 (Brief) Introductory Remarks On Behalf of the U.S. Department of Energy ESnet Site Coordinating Committee (ESCC) W.Scott Bradley ESCC Chairman"

Similar presentations


Ads by Google