Application models for utility computing

Ulrich (Uli) HomannChief Architect, WW Enterprise ServicesMicrosoft Corp.Session Code: ARC307

Session Objectives And Takeaways

Highlight the looming energy crisis in the data centerUnderstand the application designers role in reducing energy consumptionUnderstand how virtualization can support you in going Green

Will your Data Centers be Rated by the Government?Congress Passed Public Law 109-431 Dec 2006EPA to study and promote IT EfficiencyEPA provided response August 2007

http://www.energystar.gov/ia/partners/prod_development/downloads/EPA_Datacenter_Report_Congress_Final1.pdf

Outcome: EPA Energy Star Program•Energy Star for Servers May 2009 release•Energy Star for DCs Jan 2010 release

http://www.energystar.gov/index.cfm?c=prod_development.server_efficiency

4

Why the Government Cares?

In the US:

Capacity Growth = 0.8%/yr

Usage Growth = 1.1%/yrDC Growth = 15%/yr

US Projections:2020 10%

2030 30-40%

5

Today in US1.8 to 2.0%

All of this Drives Costs - Data Center Economics have Changed!

Belady, C., “In the Data Center, Power and Cooling Costs More than IT Equipment it Supports” Electronics Cooling Magazine (Feb 2007)

Microsoft‘s Annualized Costs

IT

Ops

DC

Energy

6

Source: EYP Mission Critical Facilities Inc., New York

Microsoft is focusing on all the pieces of the pie

Utility LoadPUE = ------------------ = 2

IT Load

Where Data Center Power Goes

7

“Sins” of our fathersFrom an application development perspective

Synchronicty is Dead

“Success” - a design tenet

SOYP – capacity planning methodology

Application architects – Belts-and-suspenders people?

Solution approaches

Constraint based planningSe

rvic

e U

nits

Ava

ilabl

e

#’s of DC’s

You can:• Increase DC count• Hold # DC• Decrease # DC

•With a corresponding• Increase Capacity• Hold capacity steady• Decrease Capacity

Key lesson: Servers use vital resources whether on or off

DataCenter Se

rvic

e U

nits

Con

sum

ed

Energy Spend

You can:• Increase DC size• Hold DC Size• Decrease DC size

•With a corresponding• Increase power $$• No change• Increase flexibility at a

cost of faster to full

Trends in DC designConfiguration & Construction

Modularize the Data CenterUse the same kit of parts in pre-manufactured modulesSolution to accept racks, skids or containersRedundancy & Reliability customized to each DC ClassFacility to accommodate Variable Power Density

CostReduce capital cost/MW by ClassLeverage industry to drive down initial & operating costsTime To Market - Move to lowest $ Cost DC investmentData Center Facility delivered with the servers>ROIC – return on invested capital

SustainabilityLowest yearly average PUE in the Industry

2008 < 1.5, 2010 < 1.25, 2012 < 1.125Calculate TCOE not just operational efficiencyInitiative to reduce building, copper, waterDrive to Chiller-less data centers and aggressive outside economization

Pre-assembled containers (PAC)

Pre-manufactured buildings (PMB)

ModularScalablePlug-and-play infrastructureFactory pre-assembled PACs & PMBsRapid deploymentDemountable"Fail Small“Reduce TTMReduced constructionSustainable measures

Next Gen DC - Key Characteristics

A Responsible Dynamic Topology?

SQL IIS IIS ASPASP

IIS ASPIIS

IIS

ASP

ASP

Key transformation elements

Approach:• Modular• As-needed reliability• As-needed maintainability• Manufacturing-oriented• Services-based

‘Traditional’ New

Space Watts

Per layer thinking Integrated systems

Monolithic Modular

Network-centric

Custom Standard

‘Free-form’ variability

Managed variability (product line approach)

Services-based approach

•Deployed software operates as service

•Applications run on standardized ‘hosts’ – SharePoint, etc

SaaS•Standa

rdized platform services

•Windows Azure Services platform as possible template

PaaS

•Resource-pool based model for physical resource (compute, storage, network)

•Virtualized environment (goal: 100%)

IaaS

•Modular dc build out strategy

•Possible OpEx model with partners

DCaaS

Windows packaging taxonomyComponent

Feature

Workload

Solution

Product

Component Component

Feature

Role

Component

Feature

Role Role

Workload

-Reusable, self-describing unit of testing, distribution and servicing

Product building block which, in combination with other features or components, delivers a set of functionality

Composition of features that forms the unit of management (deployment, update, etc)

Composition of often related roles that run together on a server or set of servers

–A set of integrated workloads that together address a specific problem for a targeted customer segment

–A SKU or solution packaged as a product

Segment your solution

<ITService>

<Server Group>

<Server>

<ServerRole>

Service Model

<Site>

Simple topology view

Server (workload) segmentation

Server Groups manage like servers (workloads);Today Server Groups are static – numbers of instances are effectively fixed;Enable your solutions and deployment to allow the infrastructure to reduce and increase the numbers of servers in any given server group at any given time;

The term “server” doesn’t mean what it used to anymore!

Server Role segmentation

Introduce Server Roles as part of your solutionGoing from component to Services is not granular enough

Group related functionality in Server RolesE.g. Payrolls, general ledger

Plan your Services deployment with Server Role isolation in mindAllow the infrastructure to dynamically start and stop server roles (deployed as VM’s)

Start slow and grow in ‘scale units’

Initial Size

• 2 SharePoint App Servers

• 1 SQL Server

Growth Unit ACapacity Driver: # of users

• +1 SharePoint Application Server

Growth Unit BCapacity driver: content db size

• +1 SQL Server

Max Growth

•4 SharePoint App Servers

•2 SQL Server

Pete’s SharePoint order (representing max growth):- 50,000 users- 20,000 team sites- 150MB/site- Responses per second: 100

Farm configuration

RPS

2 by 1 99

Farm configuration

RPS

4 by 2 120

Farm configuration

RPS

3 by 1 115

Monitoring counters in the operational configuration and monitoring environment (SC OM 2007) trigger growth (or shrink) provisioning once the specific capacity driver hits 80% of specified value:- Growth based upon RPS (growth type A): initial size – 99 RPS; counter is set to 80 RPS- Growth based upon content db size (growth type B): initial size – 0.8 TB; counter is set to 0.7 TB

Projected Load Profile

Jan

Mar

May Ju

lSe

pNov Ja

nMar

May Ju

lSe

pNov

Load by Time of Day

0 2 4 6 8 10 12 14 16 18 20 22 24

Enable Virtualization and "Run Full"Decompose application into work loads (servers) that can be dynamically scheduledBreak dependencies between your product’s services

Allow customers to pick time of day, day of week, etc, and allocate capacity of individual parts dynamicallyIf one server role is “out” right now, application should not break

Define scale units for your server roles so that they can be reduced in size to a minimal level and grown in chunksApplication server roles should not break if resources get allocated by quota by application role

(20% CPU for you, 60% for you)Monitoring can no longer assume all parts are “on” at all times.

Server roles become dependency bound for scheduling of parts that need to run together.If inseparable parts, put in same server role, deploy in same image

Break up the work types that your application does so they can operate out of band over units of timeSynchronicity (scale out) is not by server. It is by virtual server image.

Parts communicate across images

question & answer

www.microsoft.com/teched

Sessions On-Demand & Community

http://microsoft.com/technet

Resources for IT Professionals

http://microsoft.com/msdn

Resources for Developers

www.microsoft.com/learning

Microsoft Certification & Training Resources

Resources

Complete an evaluation on CommNet and enter to win an Xbox 360 Elite!

© 2009 Microsoft Corporation. All rights reserved. Microsoft, Windows, Windows Vista and other product names are or may be registered trademarks and/or trademarks in the U.S. and/or other countries.The information herein is for informational purposes only and represents the current view of Microsoft Corporation as of the date of this presentation. Because Microsoft must respond to changing market conditions, it should not be interpreted to be a commitment on the part of Microsoft, and Microsoft cannot guarantee the accuracy of any information provided after the date of this presentation. MICROSOFT MAKES NO WARRANTIES, EXPRESS,

IMPLIED OR STATUTORY, AS TO THE INFORMATION IN THIS PRESENTATION.