Enable personal
supercomputing
Scale to divisional sized
clusters, enable new categories
of interactive HPC applications,
and interoperate with existing
IT infrastructure.
Integrate well with existing HPC
and IT infrastructure.
Highly performant and scalable
parallel applications.
Deploy, manage, and
troubleshoot clusters of up to
1000s of nodes.
Make Windows Server the mainstream way to solve scaled-out business, engineering and scientific
computational problems.
MONITORING: Ability to see at a glance current/recent changes to the system
across the whole stack( that affect my app)
Deployment Monitoring
Diagnostics Reporting
Provide reliable and consistent
system management and “excellent
manageability” at departmental and
divisional scale (1000s of nodes).
WS2K8WS2K8 R2WS2K8WS2K8 R2
WS2K8WS2K8 R2
V2
V2 V2
WS2K8
V2…
SQL
2008
V3
V3 V3 V3
V2 Head
node
V3 Head
node
+
- +.
.
.
.
: Se
ar
ch
:
s
Admin Workstation
•Node.xml
•Node Templates
•Images
Investments in higher
resilience and better
failure recovery.
Remote Database.
Move to asynchronous
communication model.
WS2K8WS2K8 R2WS2K8WS2K8 R2
WS2K8WS2K8 R2
SQL
Express
2005
V2
V2 V2
WS2K8
V2…
SQL
Express
2008
V3
V3 V3 V3
WS2K8WS2K8 R2WS2K8WS2K8 R2
WS2K8WS2K8 R2
V2
V2 V2
WS2K8
V2…
SQL
2008
V3
V3 V3 V3
Data Center
Use DHCP reservations to provide Storage Server information to the
diskless compute nodes.
Leverage Storage vendor provided differencing capacity to store
Differencing Disks per compute node.
• Manage and Monitor the cluster at scale.
• Manage all resources from a single console.
Starting
•Select nodes and tests
•Start test run
Running
•View Progress
•Cancel Test
Completed
• View test result history
• View detailed results
• Pivot to failed nodes
• View and clear alerts
• Export result to Excel
• Each step is defined by a command line.
– This allows test to be developed in any coding/scripting language.
 Node Availability Report
 Job Resource Usage Report
 Job Throughput Report
 Job Turnaround Report
Windows HPC Server Customer Data Analysis
Data Warehouse
Other Authoring
Tools
DATADATADATA
Data Sources Management Job Scheduler Performance Metrics Event Logs
Data Collection Data Collector
Data Store
Data Store
Data Presentation Historical
Reports
Monitoring
Charts
Scalability,Reliability
Heat Map
Reporting Data
Extensibility
• Node Attributes
• Node Event History
Node Data
• Job Configurations
• Job Task Summary
• Job State and
Statistics
• Job Allocation History
Job Data
• Performance Metrics
History
Performance
Metrics
Expand the capacity of HPC clusters while increasing the return on your existing technology investments by utilizing desktop
cycles as part of your over HPC infrastructure.
Requirements
– Windows 7 Professional or Enterprise, 32 or 64-bit (requires
Active Directory support)
– Desktops and cluster in same AD Domain
– Desktops, head nodes, compute nodes, and broker nodes need
to be on the same physical, public, network (topology 5)
Security policy prevents unintentional deployment of an OS to desktop nodes
Desktop Nodes
Windows 7
HPC Pack 2008 R2 Desktop
Compute Nodes
Windows HPC Server
Database Server
(Optional)
Windows Server 2008 R2
SQL Server
Head Node
Head node
Broker Nodes
Windows HPC Server
Windows HPC Server
Public Network
• Windows HPC Server 2008 R2 Technical Library -
http://go.microsoft.com/fwlink/?LinkId=168271
• Windows HPC Server 2008 R2 Beta site on Microsoft
Connect - http://go.microsoft.com/fwlink/?LinkId=169523
• Diagnostics Extensibility in Windows HPC Server 2008 R2
CTP2 Step-by-Step Guide -
http://go.microsoft.com/fwlink/?LinkId=177604
• Test Focus Guide for Windows HPC Server 2008 R2 Beta 2 -
http://technet.microsoft.com/en-
us/library/ee783563(WS.10).aspx
• Twitter - @windowshpc
www.microsoft.com/teched www.microsoft.com/learning
http://microsoft.com/technet http://microsoft.com/msdn
Sign up for Tech·Ed 2011 and save $500
starting June 8 – June 31st
http://northamerica.msteched.com/registration
You can also register at the
North America 2011 kiosk located at registration
Join us in Atlanta next year
Managing and Deploying High Performance Computing Clusters using Windows HPC Server 2008 R2
Managing and Deploying High Performance Computing Clusters using Windows HPC Server 2008 R2

Managing and Deploying High Performance Computing Clusters using Windows HPC Server 2008 R2

  • 3.
    Enable personal supercomputing Scale todivisional sized clusters, enable new categories of interactive HPC applications, and interoperate with existing IT infrastructure. Integrate well with existing HPC and IT infrastructure. Highly performant and scalable parallel applications. Deploy, manage, and troubleshoot clusters of up to 1000s of nodes. Make Windows Server the mainstream way to solve scaled-out business, engineering and scientific computational problems.
  • 4.
    MONITORING: Ability tosee at a glance current/recent changes to the system across the whole stack( that affect my app) Deployment Monitoring Diagnostics Reporting Provide reliable and consistent system management and “excellent manageability” at departmental and divisional scale (1000s of nodes).
  • 5.
    WS2K8WS2K8 R2WS2K8WS2K8 R2 WS2K8WS2K8R2 V2 V2 V2 WS2K8 V2… SQL 2008 V3 V3 V3 V3
  • 6.
    V2 Head node V3 Head node + -+. . . . : Se ar ch : s Admin Workstation •Node.xml •Node Templates •Images
  • 10.
    Investments in higher resilienceand better failure recovery. Remote Database. Move to asynchronous communication model.
  • 11.
    WS2K8WS2K8 R2WS2K8WS2K8 R2 WS2K8WS2K8R2 SQL Express 2005 V2 V2 V2 WS2K8 V2… SQL Express 2008 V3 V3 V3 V3
  • 12.
    WS2K8WS2K8 R2WS2K8WS2K8 R2 WS2K8WS2K8R2 V2 V2 V2 WS2K8 V2… SQL 2008 V3 V3 V3 V3 Data Center
  • 14.
    Use DHCP reservationsto provide Storage Server information to the diskless compute nodes. Leverage Storage vendor provided differencing capacity to store Differencing Disks per compute node.
  • 16.
    • Manage andMonitor the cluster at scale. • Manage all resources from a single console.
  • 17.
    Starting •Select nodes andtests •Start test run Running •View Progress •Cancel Test Completed • View test result history • View detailed results • Pivot to failed nodes • View and clear alerts • Export result to Excel
  • 19.
    • Each stepis defined by a command line. – This allows test to be developed in any coding/scripting language.
  • 20.
     Node AvailabilityReport  Job Resource Usage Report  Job Throughput Report  Job Turnaround Report
  • 21.
    Windows HPC ServerCustomer Data Analysis Data Warehouse Other Authoring Tools DATADATADATA
  • 22.
    Data Sources ManagementJob Scheduler Performance Metrics Event Logs Data Collection Data Collector Data Store Data Store Data Presentation Historical Reports Monitoring Charts Scalability,Reliability Heat Map Reporting Data Extensibility
  • 23.
    • Node Attributes •Node Event History Node Data • Job Configurations • Job Task Summary • Job State and Statistics • Job Allocation History Job Data • Performance Metrics History Performance Metrics
  • 24.
    Expand the capacityof HPC clusters while increasing the return on your existing technology investments by utilizing desktop cycles as part of your over HPC infrastructure. Requirements – Windows 7 Professional or Enterprise, 32 or 64-bit (requires Active Directory support) – Desktops and cluster in same AD Domain – Desktops, head nodes, compute nodes, and broker nodes need to be on the same physical, public, network (topology 5) Security policy prevents unintentional deployment of an OS to desktop nodes
  • 25.
    Desktop Nodes Windows 7 HPCPack 2008 R2 Desktop Compute Nodes Windows HPC Server Database Server (Optional) Windows Server 2008 R2 SQL Server Head Node Head node Broker Nodes Windows HPC Server Windows HPC Server Public Network
  • 26.
    • Windows HPCServer 2008 R2 Technical Library - http://go.microsoft.com/fwlink/?LinkId=168271 • Windows HPC Server 2008 R2 Beta site on Microsoft Connect - http://go.microsoft.com/fwlink/?LinkId=169523 • Diagnostics Extensibility in Windows HPC Server 2008 R2 CTP2 Step-by-Step Guide - http://go.microsoft.com/fwlink/?LinkId=177604 • Test Focus Guide for Windows HPC Server 2008 R2 Beta 2 - http://technet.microsoft.com/en- us/library/ee783563(WS.10).aspx • Twitter - @windowshpc
  • 27.
  • 29.
    Sign up forTech·Ed 2011 and save $500 starting June 8 – June 31st http://northamerica.msteched.com/registration You can also register at the North America 2011 kiosk located at registration Join us in Atlanta next year