1 / 1

GENI Science Shakedown Experiments Paul Ruth, Anirban Mandal , Brian Blanton, Jeffery Tilson

GENI Science Shakedown Experiments Paul Ruth, Anirban Mandal , Brian Blanton, Jeffery Tilson. ExoGENI Custom Images. Images On Each Testbed. New script to snapshot ExoGENI VMs Images defined by XML metadata file Image (AMI) Kernel (AKI) Ramdisk (ARI ) Hosted on HTTP server

lot
Download Presentation

GENI Science Shakedown Experiments Paul Ruth, Anirban Mandal , Brian Blanton, Jeffery Tilson

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. GENI Science Shakedown ExperimentsPaul Ruth, AnirbanMandal, Brian Blanton, Jeffery Tilson ExoGENI Custom Images Images On Each Testbed • New script to snapshot ExoGENI VMs • Images defined by XML metadata file • Image (AMI) • Kernel (AKI) • Ramdisk (ARI) • Hosted on HTTP server • Snapshot script creates: image, kernel, ramdisk, metadata from running VM • High level steps • Create/modify a VM • Run the script • Copy the new image files to an http server • Insert metadata URL and hash into a request Shakedown Applications MotifnetworkScaled Porting Images Between Testbeds ADCIRC Initial Performance Results • Scaling of ADCIRC MPI application, 4-16 VMs • With 100 Mb/s, performance is better, but no scaling; placement issues? • Poor Scaling • ADCIRC (Storm surge model) • Tightly coupled MPI application • Current running on ExoGENI and InstaGENI • MotifNetwork (Computational Genomics) • Running on ExoGENI • Scaling to 100+ cores • Storage Limitations on InstaGENI • Remaining Challenges • Obtaining larger amount of storage on InstaGENI (~50 GB required for Motifnetwork) • Starting significant numbers of VMs on InstaGENI (limit ~16) • Future GECs • Performance evaluations • Scaling of ADCIRC MPI application, 4-16 VMs, for InstaGENI vs. ExoGENI for medium bandwidth case (500 Mb/s) • Performance on ExoGENI is 35–48% better • With larger scale performance difference is greater The 20th GENI Engineering Conference June 21-24, 2014 University of California Davis, Davis, CA • Porting images EG to IG • Successfully ported images from EG to IG • Too challenging to be recommended to most users • Porting IG to EG • Should be possible with ExoGENI snapshot script

More Related