1 Traffic Engineering of High-Rate Large-sized Flows Acknowledgment: UVA work is supported by DOE ASCR grants DE-SC002350 and DE-SC0007341, and NSF grants,

Slides:



Advertisements
Similar presentations
Traffic Dynamics at a Commercial Backbone POP Nina Taft Sprint ATL Co-authors: Supratik Bhattacharyya, Jorjeta Jetcheva, Christophe Diot.
Advertisements

Storage System Integration with High Performance Networks Jon Bakken and Don Petravick FNAL.
Policy-based Congestion Management for an SMS Gateway Alberto Gonzalez (KTH) Roberto Cosenza (Infoflex) Rolf Stadler (KTH) June 8, 2004, Policy Workshop.
Detectability of Traffic Anomalies in Two Adjacent Networks Augustin Soule, Haakon Ringberg, Fernando Silveira, Jennifer Rexford, Christophe Diot.
FLAME: A Flow-level Anomaly Modeling Engine
S305 – Network Infrastructure Chapter 5 Network and Transport Layers Part 2.
Router Architecture : Building high-performance routers Ian Pratt
1 Chin Guok ESnet Network Engineer David Robertson DSD Computer Software Engineer Lawrence Berkeley National Laboratory.
Traffic Engineering With Traditional IP Routing Protocols
Traffic Engineering Jennifer Rexford Advanced Computer Networks Tuesdays/Thursdays 1:30pm-2:50pm.
Lan Nguyen Mounika Namburu 1.  DDoS Defense Research  A2D2 Design ◦ Subnet Flooding Detection using Snort ◦ Class -Based Queuing ◦ Multi-level Rate.
A Novel Approach for Transparent Bandwidth Conservation David Salyers, Aaron Striegel University of Notre Dame Department of Computer Science and Engineering.
1 End-to-End Detection of Shared Bottlenecks Sridhar Machiraju and Weidong Cui Sahara Winter Retreat 2003.
1 Emulating AQM from End Hosts Presenters: Syed Zaidi Ivor Rodrigues.
Chapter 2 Internet Protocol DoD Model Four layers: – Process/Application layer – Host-to-Host layer – Internet layer – Network Access layer.
Network Monitoring for Internet Traffic Engineering Jennifer Rexford AT&T Labs – Research Florham Park, NJ 07932
Reduced TCP Window Size for Legacy LAN QoS Niko Färber July 26, 2000.
1 Scheduling calls with known holding times Reinette Grobler * Prof. M. Veeraraghavan University of Pretoria Polytechnic University
CECS 474 Computer Network Interoperability Tracy Bradley Maples, Ph.D. Computer Engineering & Computer Science Cal ifornia State University, Long Beach.
Reading Report 14 Yin Chen 14 Apr 2004 Reference: Internet Service Performance: Data Analysis and Visualization, Cross-Industry Working Team, July, 2000.
A Virtual Circuit Multicast Transport Protocol (VCMTP) for Scientific Data Distribution Jie Li and Malathi Veeraraghavan University of Virginia Steve Emmerson.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2007 (TPDS 2007)
NetworkProtocols. Objectives Identify characteristics of TCP/IP, IPX/SPX, NetBIOS, and AppleTalk Understand position of network protocols in OSI Model.
Protocols and the TCP/IP Suite
Traffic Engineering for ISP Networks Jennifer Rexford Internet and Networking Systems AT&T Labs - Research; Florham Park, NJ
© 2006 Cisco Systems, Inc. All rights reserved.Cisco Public 1 Version 4.0 Identifying Application Impacts on Network Design Designing and Supporting Computer.
VoIP over Wireless LAN Brandon Wilson PI: Alexander L. Wijesinha.
POSTECH DP&NM Lab. Internet Traffic Monitoring and Analysis: Methods and Applications (1) 2. Network Monitoring Metrics.
Windows 7 Firewall.
Othman Othman M.M., Koji Okamura Kyushu University 1.
AIMS’99 Workshop Heidelberg, May 1999 Linking User Acceptance and Network Performance Miles Wilkins (BT) P807 (JUPITER2)
NetFlow: Digging Flows Out of the Traffic Evandro de Souza ESnet ESnet Site Coordinating Committee Meeting Columbus/OH – July/2004.
Computer networks Funded projects (GRA openings) NSF SDCI: 2 years left DOE HNTES: 4 years left (new grant awarded) NSF CC-NIE (new): 3 years NSF SCRP:
HOPI Update Rick Summerhill Director Network Research, Architecture, and Technologies Jerry Sobieski MAX GigaPoP and TSC Program Manager Mark Johnson MCNC.
UNM RESEARCH NETWORKS Steve Perry CCNP, CCDP, CCNP-V, CCNP-S, CCNP-SP, CCAI, CMNA, CNSS 4013 Director of Networks.
Firewall Fingerprinting Amir R. Khakpour 1, Joshua W. Hulst 1, Zhihui Ge 2, Alex X. Liu 1, Dan Pei 2, Jia Wang 2 1 Michigan State University 2 AT&T Labs.
1 Hybrid network traffic engineering system (HNTES) Zhenzhen Yan, Chris Tracy, Malathi Veeraraghavan University of Virginia and ESnet April 23, 2012
High-speed TCP  FAST TCP: motivation, architecture, algorithms, performance (by Cheng Jin, David X. Wei and Steven H. Low)  Modifying TCP's Congestion.
1 BWdetail: A bandwidth tester with detailed reporting Masters of Engineering Project Presentation Mark McGinley April 19, 2007 Advisor: Malathi Veeraraghavan.
Agenda NSF SDCI Project Review, Oct. 29, 2012 –9:00-9:20: Overview, MV, UVA –9:20-9:50: Details, Zhenyang Liu, UVA –9:50-10:00: GUI, Tyler Clinch, UVA.
Scavenger performance Cern External Network Division - Caltech Datagrid WP January, 2002.
1 On Scalable Edge-based Flow Control Mechanism for VPN Tunnels --- Part 2: Scalability and Implementation Issues Hiroyuki Ohsaki Graduate School of Information.
Jennifer Rexford Princeton University MW 11:00am-12:20pm Measurement COS 597E: Software Defined Networking.
15744 Course Project1 Evaluation of Queue Management Algorithms Ningning Hu, Liu Ren, Jichuan Chang 30 April 2001.
1 Network Measurement Summary ESCC, Feb Joe Metzger ESnet Engineering Group Lawrence Berkeley National Laboratory.
April 4th, 2002George Wai Wong1 Deriving IP Traffic Demands for an ISP Backbone Network Prepared for EECE565 – Data Communications.
1 An update on HNTES Thanks to the US DOE ASCR for grants DE-SC and DE- SC (UVA), and for DE-AC02- 05CH11231 (ESnet) Thanks to Brian Tierney,
Analysis of QoS Arjuna Mithra Sreenivasan. Objectives Explain the different queuing techniques. Describe factors affecting network voice quality. Analyse.
QoS provisioning for large, high-rate file transfers Zhenzhen Yan, Malathi Veeraraghavan, Chris Tracy, and Chin Guok University of Virginia and ESnet Apr.
Trajectory Sampling for Direct Traffic Oberservation N.G. Duffield and Matthias Grossglauser IEEE/ACM Transactions on Networking, Vol. 9, No. 3 June 2001.
A User Driven Dynamic Circuit Network Implementation Evangelos Chaniotakis Network Engineering Group DANMS 2008 November Energy Sciences Network.
1 Hybrid network traffic engineering system (HNTES) Zhenzhen Yan, M. Veeraraghavan, Chris Tracy University of Virginia ESnet June 23, 2011 Please send.
ACCESS CONTROL LIST.
1 Hybrid network traffic engineering system (HNTES) Project 1 Zhenzhen Yan, Zhengyang Liu, Chris Tracy, Malathi Veeraraghavan University of Virginia and.
Planning and Analyzing Wireless LAN
1 Hybrid network traffic engineering system (HNTES) Zhenzhen Yan, Zhengyang Liu, Chris Tracy, Malathi Veeraraghavan University of Virginia and ESnet March.
Lambda scheduling algorithm for file transfers on high-speed optical circuits Hojun Lee Polytechnic Univ. Hua Li and Edwin Chong Colorado State Univ. Malathi.
1 Hybrid network traffic engineering system (HNTES) Zhenzhen Yan, Zhengyang Liu, Chris Tracy, Malathi Veeraraghavan University of Virginia and ESnet Jan.
SCIENCE_DMZ NETWORKS STEVE PERRY, DIRECTOR OF NETWORKS UNM PIYASAT NILKAEW, DIRECTOR OF NETWORKS NMSU.
Internet Traffic Engineering Motivation: –The Fish problem, congested links. –Two properties of IP routing Destination based Local optimization TE: optimizing.
1 Resource Optimization in Hybrid Core Networks with 100G Links Malathi Veeraraghavan University of Virginia [Collaboration with Admela Jukan] Date: Sep.
Supporting Advanced Scientific Computing Research Basic Energy Sciences Biological and Environmental Research Fusion Energy Sciences High Energy Physics.
1 Deploying Measurement Systems in ESnet Joint Techs, Feb Joseph Metzger ESnet Engineering Group Lawrence Berkeley National Laboratory.
UNM SCIENCE DMZ Sean Taylor Senior Network Engineer.
Past research work and research work in progress on elephant flows
Flow Collection and Analytics
Queue Dynamics with Window Flow Control
GREE-SC Project Flow Engineering: Using OpenFlow with QoS for Network Traffic Fatma Alali Sujoy Saha Mehdi Mohammadi Yimeng Zhao May 30, 2015.
COS 461: Computer Networks
Hybrid network traffic engineering system (HNTES)
Presentation transcript:

1 Traffic Engineering of High-Rate Large-sized Flows Acknowledgment: UVA work is supported by DOE ASCR grants DE-SC and DE-SC , and NSF grants, OCI , OCI , and CNS , and ESnet work is supported by DOE grant DE-AC02-05CH11231 Tian Jin, Chris Tracy, Malathi Veeraraghavan, Zhenzhen Yan University of Virginia and ESnet July 8-11, 2013

Outline Problem statement & Motivation –Example of ESnet measured load –Adverse effects of “alpha flows” Hybrid Network Traffic Engineering System (HNTES) HNTES evaluation –NetFlow data collection –Effectiveness –Afflicted-flow packet percentage 2

Problem statement Flows generated by high-rate large-sized file transfers are called alpha flows –thresholds used in this paper: 1 GB in  1 min Previous work shows that alpha flows –are the cause of burstiness of IP traffic Experiment shows adverse effects of alpha flows on real-time A/V flows Problem: How can a provider identify such alpha flows within their network and direct them to separate QoS-controlled VCs? 3

Motivation: ESnet4 Core network for US Dept. of Energy Labs StarLight MAN LAN (32 A of A) PNNL FNL ORNL LLNL GA BNL LANL IP router Lab Optical node SDN router Lab Link MAN NLR 10G 30/40/50G SDN IP Steve Cotter, Chin Guok, Joe Metzger, Bill Johnston Brookhaven National Laboratory

Traffic surges on ESnet interface 5 Link rate: 10 Gbps Outgoing traffic Incoming traffic 9 Gbps Jan. 12, 2013

Motivation: Adverse effects of alpha flows Used DOE 100G testbed Hosts: high-performance diskpts 6 BNL NEWY ping flow (delay-sensitive) TCP (alpha) flow UDP flow (background) buffer buildups

Impact of alpha flows on real-time flows 7 Impact on ping flow delay –significant in 1-queue configuration –negligible in 2-queue configuration Need separate virtual queue for alpha flow packets Pings: 1 per sec Delay: 60 ms in 1-queue case Delay: 2.1 ms in 2-queue case UDP flow TCP flow 3 Gbps 6 Gbps

Outline Problem statement & Motivation  Hybrid Network Traffic Engineering System (HNTES) HNTES evaluation –NetFlow data collection –Effectiveness –Afflicted-flow packet percentage 8

Hybrid network traffic engineering system (HNTES) - Intradomain identification/redirection of alpha flows 9 Three steps –Analysis of NetFlow reports from ingress routers to identify address prefixes of completed alpha flows –IDC creates L3 circuits between ingress-egress router pairs and configures QoS –IDC sets firewall filters to direct future alpha flows with matching address prefixes to L3 circuits Aging parameter (A): age out rules corresponding to prefixes for which no alpha flows have been observed

Outline Problem statement & Motivation Hybrid Network Traffic Engineering System (HNTES) HNTES evaluation –NetFlow data collection –Effectiveness –Afflicted-flow packet percentage 10

Data collection for HNTES evaluation: NetFlow data from 4 routers were collected for 7 months (214 days) 11 router-1 & router-2: provider-edge (PE) routers router-3: core router (REN peering) router-4: core router (commercial peering) OP: observation point

Effectiveness Analysis Two types of effectiveness –Cumulative effectiveness (C i ): percent of alpha bytes (bytes reported in alpha NetFlow reports) that would have been redirected in period (1,i) –Daily effectiveness (E i ): percent of alpha bytes that would have been redirected on day i Choose aging parameter for: –High effectiveness –Stability in firewall-filter size 12

Aging parameter: tradeoff effectiveness with size of firewall filter graphs for router 1 (similar for other routers) 30 days is good compromise for aging parameter 13 Firewall filter size stable with aging parameter 30 Cumulative effectiveness > 90%

Cumulative effectiveness (/24) 14 Provider edge routers (single customers) Peering routers (router-3: REN; router-4: commercial) Why is cumulative effectivness lower for peering routers, esp. router-4? Boxplots for 214 values each router-1 omitted as it is similar to router-2 Cumulative effectiveness

Effectiveness comparisons 15 Obs. 1: higher effectiveness for /24 than for /32 Obs. 2: higher effectiveness for router-1 and router-2 than for router-3 and router-4 Obs. 3: fewer alpha prefix IDs for router-3 and router-4

Explanations 16 Obs. 1 : data-transfer node clusters are typically located in the same /24 subnet; thus, repetition is greater with /24 than /32 Obs. 2 and obs. 3: Higher effectiveness for routers 1 & 2: downloads from supercomputing facilities are repetitive (a scientist accesses the same data transfer nodes) Lower effectiveness for routers 3 & 4: fewer uploads to DoE labs than downloads from DOE labs expect few, if any, scientific data transfers from commerical peers (router-4)

Outline Problem statement & Motivation Hybrid Network Traffic Engineering System (HNTES) HNTES evaluation –NetFlow data collection –Effectiveness –Afflicted-flow packet percentage 17

Afflicted-flow packets B: set of non-alpha NetFlow reports for flows that share alpha prefix IDs Divide B into four subsets in sequence –C: non-alpha reports of alpha flows –D  B-C: data-transfer reports (heuristic) –W  B-C-D: well-known ports –L: leftover = B-C-D-W Afflicted flows: W+L 18

Afflicted-flow packets Tradeoff: /24 vs /32 –/32 has lower effectiveness: large % of afflicted-flow packets will be impacted when an alpha flow is not redirected –/24 has higher afflicted-flow packet percentage: small % of afflicted-flow packets are adversely impacted Recommend /24 address prefixes for firewall filters 19 Percentage of afflicted-flow packets in samples of beta-flow (non- alpha flow) packets; across the 214-day period

Conclusions Hypothesis: Most high-speed data transfer nodes have static IP addresses, and alpha flows are created repeatedly between the same source-destination subnets –Validated for flows generated by dataset downloads as observed at edge routers HNTES solution of determining src-dest address prefixes of completed alpha flows & using these prefixes to set firewall filters for future alpha-flow redirection is effective for downloads from DOE labs Less effective for uploads esp. from commercial peering links – But alpha-flow causing uploads are fewer 20