SC12 Home > SC12 Schedule > SC12 Presentation - OpenFlow Enabled Hadoop over Local and Wide Area Clusters

SCHEDULE: NOV 10-16, 2012

When viewing the Technical Program schedule, on the far righthand side is a column labeled "PLANNER." Use this planner to build your own schedule. Once you select an event and want to add it to your personal schedule, just click on the calendar icon of your choice (outlook calendar, ical calendar or google calendar) and that event will be stored there. As you select events in this manner, you will have your own schedule to guide you through the week.

OpenFlow Enabled Hadoop over Local and Wide Area Clusters

SESSION: SCinet Research Sandbox Presentations continued

EVENT TYPE: SCinet Research Sandboxes

TIME: 10:50AM - 11:10AM

SESSION CHAIR: Andrew Lee

Presenter(s):Stuart Bailey, Anand Daga, Matthew Greenway, Robert Grossman, Sandhya Narayan

ROOM:155-F2

ABSTRACT:
In the recent years, data intensive programming using Hadoop and MapReduce has become increasing important. As normally deployed, Hadoops implementation of MapReduce in a multi-rack cluster is dependent upon the top of the rack switches and of the aggregator switches connecting multiple racks. We are currently developing Hadoop-OpenFlow Enabled or Hadoop-OFE. The basic idea is to combine OpenFlow (OF) enabled switches and a modified Hadoop JobTracker that is OpenFlow aware in order to improve the performance of Hadoop. Over time our hope is that Hadoop-OFE over standard Ethernet can provide superior performance to Hadoop over specialized interconnects, such as InfiniBand. We quantify the performance improvement of a Hadoop application called Matsu that is used for processing satellite image data when using Hadoop-OFE versus standard Hadoop. In our Open Cloud Consortium (OCC) SC 12 Research Booth, we will also quantify the performance of Hadoop-OFE running on a wide area network between an OCC Cluster at the University of Chicago and an OCC Cluster at the AMPATH facility in Miami.

Chair/Presenter Details:

Andrew Lee (Chair) - Indiana University

Stuart Bailey - Infoblox

Anand Daga - University of Houston

Matthew Greenway - University of Chicago

Robert Grossman - University of Chicago

Sandhya Narayan - Infoblox

Add to iCal  Click here to download .ics calendar file

Add to Outlook  Click here to download .vcs calendar file

Add to Google Calendarss  Click here to add event to your Google Calendar

OpenFlow Enabled Hadoop over Local and Wide Area Clusters

SESSION: SCinet Research Sandbox Presentations continued

EVENT TYPE:

TIME: 10:50AM - 11:10AM

SESSION CHAIR: Andrew Lee

Presenter(s):Stuart Bailey, Anand Daga, Matthew Greenway, Robert Grossman, Sandhya Narayan

ROOM:155-F2

ABSTRACT:
In the recent years, data intensive programming using Hadoop and MapReduce has become increasing important. As normally deployed, Hadoops implementation of MapReduce in a multi-rack cluster is dependent upon the top of the rack switches and of the aggregator switches connecting multiple racks. We are currently developing Hadoop-OpenFlow Enabled or Hadoop-OFE. The basic idea is to combine OpenFlow (OF) enabled switches and a modified Hadoop JobTracker that is OpenFlow aware in order to improve the performance of Hadoop. Over time our hope is that Hadoop-OFE over standard Ethernet can provide superior performance to Hadoop over specialized interconnects, such as InfiniBand. We quantify the performance improvement of a Hadoop application called Matsu that is used for processing satellite image data when using Hadoop-OFE versus standard Hadoop. In our Open Cloud Consortium (OCC) SC 12 Research Booth, we will also quantify the performance of Hadoop-OFE running on a wide area network between an OCC Cluster at the University of Chicago and an OCC Cluster at the AMPATH facility in Miami.

Chair/Presenter Details:

Andrew Lee (Chair) - Indiana University

Stuart Bailey - Infoblox

Anand Daga - University of Houston

Matthew Greenway - University of Chicago

Robert Grossman - University of Chicago

Sandhya Narayan - Infoblox

Add to iCal  Click here to download .ics calendar file

Add to Outlook  Click here to download .vcs calendar file

Add to Google Calendarss  Click here to add event to your Google Calendar