SlideShare a Scribd company logo
SGI Customers Using
Green Storage
Peter Bright
SGI Technical Services Manager
©2011 SGI 2
MAID Customers
Government Federal Bureau of
Investigation
Federal Bureau of
Investigation
Education
Financial
Healthcare
Media and
Entertainment
Manufacturing
©2011 SGI
Customer Challenges-1
• Financial Sector Legislative obligations
– Prove customer’s data is secure
– Demonstrate ability to recover
• Increasing storage growth
• Reducing backup window
• Control Power costs
– Dual site, one being Co-Lo
– Real floorspace costs
– Finite power available, cannot scale
©2011 SGI
Customer Challenges-1
• Previous environment unsatisfactory
– Backup jobs failing
• media related problems
– Backup jobs taking too long
– Current disk and tape solution has limitations
• Disk has high reliability and cost but limited scale
• Tape has a lower cost but lower availability and performance
– High-Touch storage administrator efforts
– High risk of missing obligations
• Solution does not scale
©2011 SGI
• Significant savings in power and cooling
– All disks can be powered off when not in use
– Cap 25% or 50% of the disks can be powered on
– All can be powered off
– Reduced heat generation allows high density
• Reduced floor space
– Up to 896 SATA / SAS disks in a single rack (2.6PB)
• Extends disk life
– DiskAerobics software
• Data integrity verification, Proactive sparing
– Disk power down reduces wear and tear
• MTBF 6x drive manufacturer specification
MAID - VTL
©2011 SGI
Solution Benefits
• More reliable backups
– Near zero failure rate
– Reduced backup window
• Reduced Storage Administrator efforts
– Almost no problem-solving required
– Failures now unrelated to ‘backup system’ issues
– No media related failures
• Stage to tape
– Outside of backup window
©2011 SGI
Solution Benefits
• Legislation
– Prove reliability of backups
– Quickly demonstrate restores and recalls
• Achieved with minimal floorspace
• Significant power & cooling savings
©2011 SGI
Power consumption
©2011 SGI
Power consumption
©2011 SGI
Power consumption
©2011 SGI
Power consumption
©2011 SGI
Customer Challenges-2
• Research organisation with huge data ingest
• Rapid data growth / Big Data
• HPC processing
• Increasing reference data on Tier 1 disk
• Stale data with high € / GB overhead
• Backup duration limits amount of Tier 1 growth
• No D-R copies
©2011 SGI
Solution Benefits
• Dedicated scratch space
– HPC ingest and processing
• Minimal Tier 1 deployment
– High performance, Tier 1 cost
• Intermediate Tier 2 ‘cache’
– Reduce recall delays from tape
• Archive Tier 3 Tape Library
– Low cost, highly scalable capacity
• Software Automation
– Users ‘see’ entire estate as single mount point
©2011 SGI
SGI Tiered Storage example
By replacing a Tape Library with an SGI COPAN System, you can significantly decrease access times of
even the oldest data in your DMF environment while maintaining cost optimization
©2011 SGI
CXFS Client
Tier 2 Storage
COPAN 400T
896TB Raw
Central London Greater London
Compute Environment
Tier 0 Storage
Tier 1
IS5000
50 TB Storage
Tier 3 Storage
330TB Raw
SpectraLogic
T950 Tape
Library
Tier 1
IS5000
50 TB Storage
Compute Environment
Tier 0 Storage
CXFS Client
NFS Server
12km WAN
CXFS Client
NFS Server
CXFS Client
NFS Server
CXFS Client
NFS Server
Tier 3 Storage
330TB Raw
SpectraLogic
T950 Tape
Library
CXFS Client
LiveArc
Server
LiveArc
Server
CXFS Client
Parallel
Data Mover
FC FC
CXFS Server
DMF
CXFS Server
DMF
CXFS Client
Parallel
Data Mover
15
High Level Tiered Storage Design: Dual Site Integrated Compute & Storage
©2011 SGI 16
Example: NBA Digital Archives
 Up to 38 TB per day
ingested from new and legacy
content.
 Half-way through digitizing
450k tapes with content
going back to 1946.
 Restore 3TB per day, ~2000
clips from archive each day
for production use.
©2011 SGI
SGI MAID is Simple, Cost Effective and Eco-Friendly
• Solves challenges associated with data
protection
• Information integrity
– Automated disk management and monitoring
• Eco-friendly solution
– Up to 100% power and cooling reduction*
– Extends disk MTBF and disk life 6x
– Save 12,000 pounds of CO2 per year per kilowatt hour
saved**
• High disk density per square metre
*At the disk level
**US DOE statistics for emissions per KwH
©2011 SGI 18

More Related Content

PDF
10 Reasons to Choose NetApp for EUC/VDI
PDF
4 Ways FlexPod Forms the Foundation for Cisco and NetApp Success
PDF
RESUME_20160125
PPTX
Dave Wright, SolidFire - SDDC Symposium 2014
PPTX
The move from Siloed to Shared Infrastructure – and the future of the Data Ce...
PDF
Better Business in a Flash
PDF
10 Good Reasons: NetApp for Finance
PDF
L'Iperconvergenza 2.0: NetApp HCI in Action
10 Reasons to Choose NetApp for EUC/VDI
4 Ways FlexPod Forms the Foundation for Cisco and NetApp Success
RESUME_20160125
Dave Wright, SolidFire - SDDC Symposium 2014
The move from Siloed to Shared Infrastructure – and the future of the Data Ce...
Better Business in a Flash
10 Good Reasons: NetApp for Finance
L'Iperconvergenza 2.0: NetApp HCI in Action

What's hot (20)

PDF
Postgres Vision 2018: How to Consume your Database Platform On-premises
 
PDF
OpenStack at the speed of business with SolidFire & Red Hat
PDF
Converged Everything, Converged Infrastructure delivering business value and ...
PPTX
Nam Khong - SAP on Cloud for Your Intelligent Enterprise
PDF
Redefining HCI: How to Go from Hyper Converged to Hybrid Cloud Infrastructure
PDF
Downsizing Data Centers by NetApp IT
PDF
Cloud for the Hybrid Data Center
PPTX
Sap Seminar Leveraging Cloud Infrastructure
PPTX
Why build sap on cloud
PPTX
Keith Inight, CTO at Atos - Software Defined Everything
PDF
Postgres Vision 2018: AI Needs IA
 
PPTX
Huawei FusionCube for SAP HANA
PDF
Appplications – Driving Expansion In The Cloud
PDF
EMEA TechTalk – The NetApp Flash Optimized Portfolio
PDF
10 Good Reasons: NetApp AltaVault
PDF
Webinar: NetApp SaaS Backup
PDF
Postgres Vision 2018: Making Modern an Old Legacy System
 
PDF
Pivotal Digital Transformation Forum: Data Science Technical Overview
PDF
Introducing elastic.io iPaaS: Best-of-Breed Integrations - New in 2017
PPTX
Diigital transformation
Postgres Vision 2018: How to Consume your Database Platform On-premises
 
OpenStack at the speed of business with SolidFire & Red Hat
Converged Everything, Converged Infrastructure delivering business value and ...
Nam Khong - SAP on Cloud for Your Intelligent Enterprise
Redefining HCI: How to Go from Hyper Converged to Hybrid Cloud Infrastructure
Downsizing Data Centers by NetApp IT
Cloud for the Hybrid Data Center
Sap Seminar Leveraging Cloud Infrastructure
Why build sap on cloud
Keith Inight, CTO at Atos - Software Defined Everything
Postgres Vision 2018: AI Needs IA
 
Huawei FusionCube for SAP HANA
Appplications – Driving Expansion In The Cloud
EMEA TechTalk – The NetApp Flash Optimized Portfolio
10 Good Reasons: NetApp AltaVault
Webinar: NetApp SaaS Backup
Postgres Vision 2018: Making Modern an Old Legacy System
 
Pivotal Digital Transformation Forum: Data Science Technical Overview
Introducing elastic.io iPaaS: Best-of-Breed Integrations - New in 2017
Diigital transformation
Ad

Similar to Peter Bright (Silicon Graphics), Ing. Johann Schiessel (Schiessel EDV) (20)

PDF
Introducing StorNext5 and Lattus
PDF
Presentation expect more from your storage
PDF
The benefits of IBM FlashSystems
PDF
Building Scalable Applications using Pivotal Gemfire/Apache Geode
PPTX
Scale Out Database Solution
PDF
Implementing AI: High Performance Architectures: Solving Core Recommendation ...
 
PPTX
Cloudian Webinar - 7 Key Reasons why Object Storage lowers Storage TCO
PDF
NVMe and Flash – Make Your Storage Great Again!
PPTX
Denver Big Data Analytics Day
PDF
Greenplum: A Pivotal Moment on Wall Street - Greenplum Summit 2018
PPTX
Open Sourcing GemFire - Apache Geode
PPTX
An Introduction to Apache Geode (incubating)
PPT
Linux world consolidation of storage infrastructures 2006
PDF
Strongbox Data Storage Podcast
PPTX
The future of tape april 16
PPTX
Transforming your Business with Scale-Out Flash: How MongoDB & Flash Accelera...
PPTX
Introducing IBM Spectrum Scale 4.2 and Elastic Storage Server 3.5
PDF
HPC DAY 2017 | HPE Storage and Data Management for Big Data
PPT
Big data and ibm flashsystems
PPTX
IBM Spectrum Scale Overview november 2015
Introducing StorNext5 and Lattus
Presentation expect more from your storage
The benefits of IBM FlashSystems
Building Scalable Applications using Pivotal Gemfire/Apache Geode
Scale Out Database Solution
Implementing AI: High Performance Architectures: Solving Core Recommendation ...
 
Cloudian Webinar - 7 Key Reasons why Object Storage lowers Storage TCO
NVMe and Flash – Make Your Storage Great Again!
Denver Big Data Analytics Day
Greenplum: A Pivotal Moment on Wall Street - Greenplum Summit 2018
Open Sourcing GemFire - Apache Geode
An Introduction to Apache Geode (incubating)
Linux world consolidation of storage infrastructures 2006
Strongbox Data Storage Podcast
The future of tape april 16
Transforming your Business with Scale-Out Flash: How MongoDB & Flash Accelera...
Introducing IBM Spectrum Scale 4.2 and Elastic Storage Server 3.5
HPC DAY 2017 | HPE Storage and Data Management for Big Data
Big data and ibm flashsystems
IBM Spectrum Scale Overview november 2015
Ad

More from Praxistage (20)

PDF
Einladung zu den Praxistagen 2024 im virtuellen Landhaus
PPTX
Michael Jäger, MBA, Dipl. Wirtschaftsinformatiker (FH) Christian Kohler (Mait...
PPTX
Fr. RA Mag. Birgit Noha, LL.M. (Laws.at)
PPTX
Mag.a Mary-Ann Hayes (Unicredit Bank Austria AG)
PPTX
OR Dipl.-Ing. Bettina Gastecker, Bakk (Bundesministerium für Finanzen)
PPTX
Dipl.-Ing. (FH) Bernd Stockinger (Citycom Telekommunikation GmbH)
PPTX
Dipl.-Verww. (FH) Christian Zierau (Stadtrat für Finanzen, Personal, Ordnung ...
PPTX
Bernd Schellnast (Sphinx IT Consulting GmbH)
PPTX
Werner Panhauser (Helvetia Versicherungen AG)
PPTX
Michael Weilguny, Christian Schön (IVM Technical Consultants Wien Ges.m.b.H.)
PPTX
Dipl.-Ing. Werner Plessl (Hewlett Packard Enterprise)
PPTX
Dipl.-Ing. Marc Haarmeier (Prime Force Group Int. AG)
PPTX
Mag.a Verena Becker, BSc. (Wirtschaftskammer Österreich/BSIC)
PPTX
Doris Ingerisch (Axians ICT Austria GmbH)
PPTX
Josef Weissinger (Soroban IT-Beratung GmbH)
PPTX
Fr. Vanessa Kluge, BA (Kontron AIS GmbH)
PPTX
Ing. Boris Werner (Breitbandbüro des Bundesministeriums für Finanzen)
PPTX
Praxistage 2024 im virtuellen Landhaus, St. Pölten
PPTX
Hr. David Simon (Juniper Networks, Inc.)
PPTX
Mag. Michael Salat (Cisco Systems Austria GmbH)
Einladung zu den Praxistagen 2024 im virtuellen Landhaus
Michael Jäger, MBA, Dipl. Wirtschaftsinformatiker (FH) Christian Kohler (Mait...
Fr. RA Mag. Birgit Noha, LL.M. (Laws.at)
Mag.a Mary-Ann Hayes (Unicredit Bank Austria AG)
OR Dipl.-Ing. Bettina Gastecker, Bakk (Bundesministerium für Finanzen)
Dipl.-Ing. (FH) Bernd Stockinger (Citycom Telekommunikation GmbH)
Dipl.-Verww. (FH) Christian Zierau (Stadtrat für Finanzen, Personal, Ordnung ...
Bernd Schellnast (Sphinx IT Consulting GmbH)
Werner Panhauser (Helvetia Versicherungen AG)
Michael Weilguny, Christian Schön (IVM Technical Consultants Wien Ges.m.b.H.)
Dipl.-Ing. Werner Plessl (Hewlett Packard Enterprise)
Dipl.-Ing. Marc Haarmeier (Prime Force Group Int. AG)
Mag.a Verena Becker, BSc. (Wirtschaftskammer Österreich/BSIC)
Doris Ingerisch (Axians ICT Austria GmbH)
Josef Weissinger (Soroban IT-Beratung GmbH)
Fr. Vanessa Kluge, BA (Kontron AIS GmbH)
Ing. Boris Werner (Breitbandbüro des Bundesministeriums für Finanzen)
Praxistage 2024 im virtuellen Landhaus, St. Pölten
Hr. David Simon (Juniper Networks, Inc.)
Mag. Michael Salat (Cisco Systems Austria GmbH)

Recently uploaded (20)

PPTX
KOM of Painting work and Equipment Insulation REV00 update 25-dec.pptx
PPT
Teaching material agriculture food technology
PPTX
Machine Learning_overview_presentation.pptx
PDF
Spectral efficient network and resource selection model in 5G networks
PPTX
Group 1 Presentation -Planning and Decision Making .pptx
PDF
Advanced methodologies resolving dimensionality complications for autism neur...
PDF
Building Integrated photovoltaic BIPV_UPV.pdf
PPTX
Tartificialntelligence_presentation.pptx
PDF
Encapsulation_ Review paper, used for researhc scholars
PDF
TokAI - TikTok AI Agent : The First AI Application That Analyzes 10,000+ Vira...
PDF
Mobile App Security Testing_ A Comprehensive Guide.pdf
PDF
Reach Out and Touch Someone: Haptics and Empathic Computing
PPTX
Programs and apps: productivity, graphics, security and other tools
PDF
Video forgery: An extensive analysis of inter-and intra-frame manipulation al...
PPT
“AI and Expert System Decision Support & Business Intelligence Systems”
PPTX
MYSQL Presentation for SQL database connectivity
PDF
Optimiser vos workloads AI/ML sur Amazon EC2 et AWS Graviton
PDF
Encapsulation theory and applications.pdf
PDF
Profit Center Accounting in SAP S/4HANA, S4F28 Col11
PDF
Diabetes mellitus diagnosis method based random forest with bat algorithm
KOM of Painting work and Equipment Insulation REV00 update 25-dec.pptx
Teaching material agriculture food technology
Machine Learning_overview_presentation.pptx
Spectral efficient network and resource selection model in 5G networks
Group 1 Presentation -Planning and Decision Making .pptx
Advanced methodologies resolving dimensionality complications for autism neur...
Building Integrated photovoltaic BIPV_UPV.pdf
Tartificialntelligence_presentation.pptx
Encapsulation_ Review paper, used for researhc scholars
TokAI - TikTok AI Agent : The First AI Application That Analyzes 10,000+ Vira...
Mobile App Security Testing_ A Comprehensive Guide.pdf
Reach Out and Touch Someone: Haptics and Empathic Computing
Programs and apps: productivity, graphics, security and other tools
Video forgery: An extensive analysis of inter-and intra-frame manipulation al...
“AI and Expert System Decision Support & Business Intelligence Systems”
MYSQL Presentation for SQL database connectivity
Optimiser vos workloads AI/ML sur Amazon EC2 et AWS Graviton
Encapsulation theory and applications.pdf
Profit Center Accounting in SAP S/4HANA, S4F28 Col11
Diabetes mellitus diagnosis method based random forest with bat algorithm

Peter Bright (Silicon Graphics), Ing. Johann Schiessel (Schiessel EDV)

  • 1. SGI Customers Using Green Storage Peter Bright SGI Technical Services Manager
  • 2. ©2011 SGI 2 MAID Customers Government Federal Bureau of Investigation Federal Bureau of Investigation Education Financial Healthcare Media and Entertainment Manufacturing
  • 3. ©2011 SGI Customer Challenges-1 • Financial Sector Legislative obligations – Prove customer’s data is secure – Demonstrate ability to recover • Increasing storage growth • Reducing backup window • Control Power costs – Dual site, one being Co-Lo – Real floorspace costs – Finite power available, cannot scale
  • 4. ©2011 SGI Customer Challenges-1 • Previous environment unsatisfactory – Backup jobs failing • media related problems – Backup jobs taking too long – Current disk and tape solution has limitations • Disk has high reliability and cost but limited scale • Tape has a lower cost but lower availability and performance – High-Touch storage administrator efforts – High risk of missing obligations • Solution does not scale
  • 5. ©2011 SGI • Significant savings in power and cooling – All disks can be powered off when not in use – Cap 25% or 50% of the disks can be powered on – All can be powered off – Reduced heat generation allows high density • Reduced floor space – Up to 896 SATA / SAS disks in a single rack (2.6PB) • Extends disk life – DiskAerobics software • Data integrity verification, Proactive sparing – Disk power down reduces wear and tear • MTBF 6x drive manufacturer specification MAID - VTL
  • 6. ©2011 SGI Solution Benefits • More reliable backups – Near zero failure rate – Reduced backup window • Reduced Storage Administrator efforts – Almost no problem-solving required – Failures now unrelated to ‘backup system’ issues – No media related failures • Stage to tape – Outside of backup window
  • 7. ©2011 SGI Solution Benefits • Legislation – Prove reliability of backups – Quickly demonstrate restores and recalls • Achieved with minimal floorspace • Significant power & cooling savings
  • 12. ©2011 SGI Customer Challenges-2 • Research organisation with huge data ingest • Rapid data growth / Big Data • HPC processing • Increasing reference data on Tier 1 disk • Stale data with high € / GB overhead • Backup duration limits amount of Tier 1 growth • No D-R copies
  • 13. ©2011 SGI Solution Benefits • Dedicated scratch space – HPC ingest and processing • Minimal Tier 1 deployment – High performance, Tier 1 cost • Intermediate Tier 2 ‘cache’ – Reduce recall delays from tape • Archive Tier 3 Tape Library – Low cost, highly scalable capacity • Software Automation – Users ‘see’ entire estate as single mount point
  • 14. ©2011 SGI SGI Tiered Storage example By replacing a Tape Library with an SGI COPAN System, you can significantly decrease access times of even the oldest data in your DMF environment while maintaining cost optimization
  • 15. ©2011 SGI CXFS Client Tier 2 Storage COPAN 400T 896TB Raw Central London Greater London Compute Environment Tier 0 Storage Tier 1 IS5000 50 TB Storage Tier 3 Storage 330TB Raw SpectraLogic T950 Tape Library Tier 1 IS5000 50 TB Storage Compute Environment Tier 0 Storage CXFS Client NFS Server 12km WAN CXFS Client NFS Server CXFS Client NFS Server CXFS Client NFS Server Tier 3 Storage 330TB Raw SpectraLogic T950 Tape Library CXFS Client LiveArc Server LiveArc Server CXFS Client Parallel Data Mover FC FC CXFS Server DMF CXFS Server DMF CXFS Client Parallel Data Mover 15 High Level Tiered Storage Design: Dual Site Integrated Compute & Storage
  • 16. ©2011 SGI 16 Example: NBA Digital Archives  Up to 38 TB per day ingested from new and legacy content.  Half-way through digitizing 450k tapes with content going back to 1946.  Restore 3TB per day, ~2000 clips from archive each day for production use.
  • 17. ©2011 SGI SGI MAID is Simple, Cost Effective and Eco-Friendly • Solves challenges associated with data protection • Information integrity – Automated disk management and monitoring • Eco-friendly solution – Up to 100% power and cooling reduction* – Extends disk MTBF and disk life 6x – Save 12,000 pounds of CO2 per year per kilowatt hour saved** • High disk density per square metre *At the disk level **US DOE statistics for emissions per KwH