FutureGrid Overview

(1)

FutureGrid Overview

Geoffrey Fox

SC09

(2)

FutureGrid

• _{The goal of FutureGrid is to}_{support the research}_{on the}

future of distributed, grid, and cloud computing.

• _{FutureGrid will build a robustly managed simulation}

environment or testbed to support the development and early use in science of new technologies at all levels of the software stack: from networking to middleware to scientific applications.

• _{The environment will mimic TeraGrid and/or general parallel}

and distributed systems – FutureGrid is part of TeraGrid and one of two experimental TeraGrid systems (other is GPU)

• _{This test-bed will succeed if it enables major advances in}

science and engineering through collaborative development of science applications and related software.

• _{FutureGrid is a (small 5600 core)}_{Science/Computer Science}

(3)

(4)

System type # CPUs # Cores TFLOPS Total RAM (GB) Secondary

Storage (TB) Site Status

Dynamically configurable systems

IBM iDataPlex 256 1024 11 3072 339* IU New System

Dell PowerEdge 192 1152 8 1152 15 TACC New System

IBM iDataPlex 168 672 7 2016 120 UC New System

IBM iDataPlex 168 672 7 2688 72 SDSC Existing System

Subtotal 784 3520 33 8928 546

Systems not dynamically configurable

Cray XT5m 168 672 6 1344 339* IU New System

Shared memory

system TBD 40 480 4 640 339* IU

New System 4Q2010

Cell BE Cluster 4 80 1 64 IU Existing System

IBM iDataPlex 64 256 2 768 1 UF New System

High Throughput

Cluster 192 384 4 192 PU Existing System

Subtotal 468 1872 17 3008 1

(5)

Storage Hardware

System Type Capacity (TB) File System Site Status

DDN 9550

(Data Capacitor)

339 Lustre IU Existing System

DDN 6620 120 GPFS UC New System

SunFire x4170 72 Lustre/PVFS SDSC New System

Dell MD3000 30 NFS TACC New System

• FutureGrid has dedicated network (except to TACC) and a network fault and delay generator

• Can isolate experiments on request; IU runs Network for NLR/Internet2

• _{Additional partner machines}_{could run FutureGrid software and be}

(6)

Network Impairments Device

Spirent XGEM Network Impairments Simulator

for jitter, errors, delay, etc

Full Bidirectional 10G w/64 byte packets

up to 15 seconds introduced delay (in 16ns

increments)

0-100% introduced packet loss in .0001%

increments

Packet manipulation in first 2000 bytes

up to 16k frame size

(7)

System Milestones

• _{New IBM Systems}

– _{Delivery: December 2009} – _{Acceptance: March 2010} – Available for Use: April 2010

• _{Dell System}

– Delivery: January 2010

– _{Acceptance: March 2010} – Available for Use: April 2010

• _{Existing IU iDataPlex}

– Move to SDSC: January 2010

– _{Available for Use: March 2010}

• _{Storage Systems (Sun & DDN)}

– _{Delivery: October 2009}

(8)

FutureGrid Partners

• _{Indiana University}_{(Architecture, core software, Support)} • _{Purdue University}_{(HTC Hardware)}

• _{San Diego Supercomputer Center}_{at University of California San} Diego (INCA, Monitoring)

• _{University of Chicago}_{/Argonne National Labs (Nimbus)} • _{University of Florida}_{(ViNE, Education and Outreach)}

• _{University of Southern California Information Sciences Institute}

(Pegasus to manage experiments)

• _{University of Tennessee Knoxville (Benchmarking)}

• _{University of Texas at Austin}_{/Texas Advanced Computing Center} (Portal)

• _{University of Virginia (OGF, Advisory Board and allocation)}

• _{Center for Information Services and GWT-TUD from Technische}

Universtität Dresden. (VAMPIR)

(9)

Other Important Collaborators

• _NSF

• _{Early users from an application and computer science}

perspective and from both research and education

• _{Grid5000/Aladdin and D-Grid in Europe} • _{Commercial partners such as}

– _{Eucalyptus ….}

– _{Microsoft (Dryad + Azure) – Note current Azure external to}

FutureGrid as are GPU systems

– _{Application partners}

• _TeraGrid

• _{Open Grid Forum}

• _Possibly_{Open Nebula, Open Cirrus Testbed, Open Cloud}

(10)

Future Grid Users

• _{Application/Scientific}

users

• _{System administrators}

• _{Software developers}

• _{Testbed users}

• _{Performance modelers}

• _Educators

• _Students

• _{Supported by}

• _FutureGrid

• _{Infrastructure}

&

Software

offerings

(11)

FutureGrid Usage Scenarios

• _{Developers of}_{end-user applications}_{who want to develop}

new applications in cloud or grid environments, including analogs of commercial cloud environments such as Amazon or Google.

– _{Is a Science Cloud for me? Is my application secure?}

• _{Developers of end-user applications who want to experiment}

with multiple hardware environments.

• _Grid/Cloud_{middleware developers}_{who want to evaluate}

new versions of middleware or new systems.

• _{Networking researchers}_{who want to test and compare}

different networking solutions in support of grid and cloud applications and middleware. (Some types of networking research will likely best be done via through the GENI

program.)

• _Education_{as well as research}

(12)

Selected FutureGrid Timeline

• _{October 1 2009}

_{Project Starts}

• _{November 16-19}

_{SC09 Demo/F2F Committee}

Meetings/Chat up collaborators

• _{January 2010}

_{– Significant Hardware available}

• _{March 2010}

_{FutureGrid network complete}

• _{March 2010}

_{FutureGrid Annual Meeting}

• _{September 2010}

_{All hardware (except Track IIC}

lookalike) accepted

• _{October 1 2011}

_{FutureGrid allocatable via}

(13)

FutureGrid Architecture

(14)

FutureGrid Architecture

• _{Open Architecture allows to configure resources based}

on images

• _{Managed images allows to create similar experiment}

environments

• _{Experiment management allows}

_reproducible

activities

• _{Through our modular design we allow}

_{different clouds}

and images

to be “rained” upon hardware.

• _{Note will be}

_{supported 24x7}

_{at “TeraGrid Production}

Quality”

• _{Will support deployment of}

_{“important” middleware}

(15)

Software Goals

• _{Open-source, integrated suite of software to}

–

_{instantiate and execute grid and cloud}

experiments.

–

_{perform an experiment}

–

_{collect the results}

–

_{tools for instantiating a test environment,}

• _{Torque, MOAB, xCAT, bcfg, and Pegasus, Inca, ViNE, a}

number of other tools from our partners and the open source community

• Portal to interact

–

_Benchmarking

(16)

(17)

Command line

• _{fg-deploy-image}

– _{host name} – _{image name} – _{start time} – _{end time} – _{label name}

• _fg-add

– label name

– _{framework hadoop} – _{version 1.0}

• _{Deploys an image on a}

host

• _{Adds a feature to a}

deployed image

(18)

FG Stratosphere

• _Objective

– _{Higher than a particular}

cloud

– Provides all mechanisms to provision a cloud on a

given FG hardware

– Allows the management of reproducible experiments

– Allows monitoring of the environment and the results

• _Risks

– _{Lots of software}

– Possible multiple path to do the same thing

• Good news

– _{We worked in a team,}

know about different solutions and have

identified a very good plan

– We can componentize Stratosphere

(19)

RAIN: Dynamic Provisioning



Change underlying system to support current

user demands



Linux, Windows, Xen, Nimbus, Eucalyptus



Stateless images



Shorter boot times



Easier to maintain



Stateful installs



Windows



Use moab to trigger changes and xCAT to

manage installs

(20)

xCAT and Moab



xCAT



uses installation infrastructure to perform installs



creates stateless Linux images



changes the boot configuration of the nodes



remote power control and console (IPMI)



Moab



meta-schedules over resource managers

 _{TORQUE and Windows HPC}



control nodes through xCAT

 _{changing the OS}

 _{remote power control}

(21)

SALSA

Dynamic Virtual Cluster Hosting

iDataplex Bare-metal Nodes (32 nodes) iDataplex Bare-metal Nodes (32 nodes)

XCAT Infrastructure XCAT Infrastructure Linux Bare-system Linux Bare-system Linux on Xen Linux on Xen Windows Server 2008 Bare-system Windows Server 2008 Bare-system

Cluster Switching from Linux Bare-system to Xen VMs to Windows 2008

HPC

Cluster Switching from Linux Bare-system to Xen VMs to Windows 2008

HPC SW-G Using

Hadoop SW-G Using

Hadoop

SW-G : Smith Waterman Gotoh Dissimilarity Computation – A typical MapReduce style application

(22)

SALSA

Pub/Sub Broker Network

Summarizer Summarizer

Switcher Switcher

Monitoring Interface

iDataplex Bare-metal Nodes (32 nodes)

(23)

(24)

Experiment Manager

• _Objective

– _{Manage the provisioning}

for reproducible experiments

– _{Coordinate workflow of}

experiments

– _{Share workflow and}

experiment images

– _{Minimize space through}

reuse

• _Risk

– _{Images are large}

– _{Users have different}

requirements and need different images

(25)

Core Use IU and TeraGrid

(26)

Science Merit v TeraGrid Allocation

(27)