iSGTW - International Science Grid This Week
iSGTW - International Science Grid This Week
Null

Home > iSGTW 01 August 2007 > iSGTW Technology - GridWay: interoperability without the headache

 

Technology - GridWay: interoperability without the headache


The GridWay metascheduler can schedule jobs across several grids, including Open Science Grid, EGEE and TeraGrid.
Image courtesy of GridWay

What looks and feels like your Local Resource Management system, but lets you submit jobs to multiple heterogeneous grids?

Sounds like the beginning of a bad joke or pipe dream? You might need to upgrade your metascheduler.

So says Tino Vazquez Blanco, a grid technology engineer working on the GridWay metascheduler project.

“GridWay allows you to do much more than your local LRM system. You can of course use GridWay to submit, monitor, and control your jobs; the added bonus is that you can do this across several different grids.”

GridWay is a scheduler for other schedulers, Blanco explains.

“It simulates a familiar environment, so it’s as if you’re working on a local cluster, but in fact you’re working across grids formed by heterogeneous clusters. You don’t need to worry about where the clusters are …it just finds the best resource for your jobs.”

Since its January 2005 release, GridWay has been downloaded more than 1000 times in 60 different countries.
Stock image from sxc.hu
Built with adapters that interface with different middlewares and different grids, GridWay allows you to “submit and forget,” regardless of which grid your job is ultimately completed on.

“GridWay can run single, array, or complex jobs on heterogeneous and dynamic grids,” says Blanco. “You have the ability to control, submit and monitor your jobs. You can see whose jobs are queued, how many jobs are queued, and where they have been sent.”

Controling an elaborate choreography of job statistics, execution times, available hosts and user-defined metrics, GridWay schedules jobs based on user preferences as well as the bigger picture: “Users prioritize their jobs, and then the system prioritizes users based on fixed and fair share priorities,” says Blanco.

And if your job is waiting too long?

“You can simply send it to another resource, by hand or GridWay can do it for you, based on metrics you provide. If there’s a problem with one host, it will salvage your job and send it elsewhere. If there’s a problem there too, it will keep trying new solutions until your job gets done.”

GridWay is being developed by the Distributed Systems Architecture Group from Universidad Complutense de Madrid.


- Cristy Burne, iSGTW

 

Tags:



Null
 iSGTW 22 December 2010

Feature – Army of Women allies with CaBIG for online longitudinal studies

Special Announcement - iSGTW on Holiday

Video of the Week - Learn about LiDAR

 Announcements

NeHC launches social media

PRACE announces third Tier-0 machine

iRODS 2011 User Group Meeting

Jobs in distributed computing

 Subscribe

Enter your email address to subscribe to iSGTW.

Unsubscribe

 iSGTW Blog Watch

Keep up with the grid’s blogosphere

 Mark your calendar

December 2010

13-18, AGU Fall Meeting

14-16, UCC 2010

17, ICETI 2011 and ICSIT 2011

24, Abstract Submission deadline, EGI User Forum

 

January 2011

11, HPCS 2011 Submission Deadline

11, SPCloud 2011

22, ALENEX11

30 Jan – 3 Feb, ESCC/Internet2

 

February 2011

1 - 4, GlobusWorld '11

2, Lift 11

15 - 16, Cloudscape III


More calendar items . . .

 

FooterINFSOMEuropean CommissionDepartment of EnergyNational¬†Science¬†Foundation RSSHeadlines | Site Map