PPT-Congestion-Aware Load Balancing at the Virtual Edge

Aran Bergman Technion VMware Naga Katta Aditi Ghag Mukesh Hira Changhoon Kim Isaac Keslassy Jennifer Rexford CLOVE 1 Data center load balancing today E qual C ost . as well as the server?. Nikhil Handigol. Stanford University. Joint work with Nick . McKeown. and . Ramesh. . Johari. Datacenter. Wide-area. Enterprise. Can’t choose path :’(. LOAD-BALANCER. Client. Haidong. . Xue. Part One: Knowledge in Textbook. Motivation, Models, Concepts, Algorithms. Part Two: Recent Work. Use the Mobile Agent and Include I/O. Duplex Loading Balancing Strategy. Stability Analysis Based. Sig Freund. Outline. Introduction. Distributed vs. Traditional . scheduling. Process Interaction models. Distributed . Systems. Research Studies. Guess about the Future?. Questions. Introduction. Load Sharing. Balancing (GSLB). Global server load balancing is used to manage traffic flow to a web site hosted on . two separate . server farms that ideally are in different geographic locations. . For . example. Abhinav Bhatele, Laxmikant V. Kale. University of Illinois at Urbana-Champaign. Sameer Kumar. IBM T. J. Watson Research Center. Motivation: Contention Experiments. May 29th, 2009. 2. Abhinav Bhatele @ LSPP 2009. Julia Chuzhoy. Toyota Technological Institute at Chicago. Routing Problems. Input. : Graph G, source-sink pairs (s. 1. ,t. 1. ),…,(. s. k. ,t. k. ).. Goal. : Route as many pairs as possible; minimize edge congestion.. Tensor Contractions. David . Ozog. *, Jeff R. Hammond. †. , James . Dinan. †. , . Pavan. . Balaji. †. , Sameer . Shende. *, Allen . Malony. * . *University of Oregon . †. Argonne National Laboratory. Keqiang He. , Eric . Rozner. , . Kanak. . Agarwal. , Wes . Felter. , John Carter, . Aditya. . Akella. 1. Background. Datacenter . n. etworks support a wide variety of traffic. Elephants: throughput sensitive. Angen Zheng. Static. Load . Balancing. Distribute the load evenly across processing unit.. Is this good enough? . It depends!. No data dependency!. Load distribution remain unchanged!. Initial Balanced Load Distribution. as well as the server?. Nikhil Handigol. Stanford University. Joint work with Nick . McKeown. and . Ramesh. . Johari. Datacenter. Wide-area. Enterprise. Can’t choose path :’(. LOAD-BALANCER. Client. Hong Zhang. 1. . Junxue. Zhang. 1. , . Wei Bai. 1. , Kai Chen. 1. , . Mosharaf. Chowdhury. 2. Datacenter networks --- multi-rooted trees (e.g., Fat-tree, Leaf-spine). Multiple-paths between each end host pair. Sig Freund. Outline. Introduction. Distributed vs. Traditional . scheduling. Process Interaction models. Distributed . Systems. Research Studies. Guess about the Future?. Questions. Introduction. Load Sharing. Vlad. . Nae. , . Radu. . Prodan. , Thomas . Fahringer. Institute of Computer Science. University of Innsbruck. 10/25/2010. MMOG Subscriptions (last 10 years). 1. Introduction. 24 million subscribers. Gengbin. . Zheng. , Esteban . Meneses. , . Abhinav. . Bhatele. and . Laxmikant. V. Kale. Parallel Programming Lab. University of Illinois at Urbana Champaign. Motivations. Load balancing is key to scalability on very large supercomputers.