Pulse2010 :Data Reduction
- 1. Reduce Your Data Footprint Manage More Data with Less Infrastructure Vishal Maheshwari Sales Leader – Tivoli Storage ISA
- 2. Session abstract One of the primary IT-related solutions that companies are investing in today is any technology that will help them survive the tidal wave of data growth, especially those solutions that help reduce the overall data storage footprint. IBM is uniquely positioned to help our customers meet this challenge with a holistic approach to data reduction that addresses the major cause of data proliferation, as well as providing meaningful solutions that optimize storage. These solutions help to reduce capital and administrative costs, while improving service levels. This session will review an effective, four-step process to reduce your data storage footprint, and will cover techniques such as incremental backup, data categorization, space management, compression and data deduplication. 2
- 3. got too much data? And not enough ( blank ) to manage it all? Time Money People Floor Space Electricity Air Conditioning 3
- 4. Agenda • Are you drowning in a tidal wave of data? • Five approaches reducing your data footprint • Why IBM? • Next steps • More information 4
- 5. The tidal wave continues … • The amount of digital information continues to grow exponentially … • And we need to keep more of it, longer … • And the costs of losing data are increasingly unacceptable – Lost revenues – Lost customer confidence – Embarrassment in the market – Fines from contracts, government agencies – CEO and CFO could go to jail 2005 2006 2007 2008 2009 2010 We Need to do More with Less, Data created and copied is expected to grow at 48% CAGR and we need to do it smarter through 2010 Source: Various external consultant reports 5
- 6. The pressures on administrators are growing The consequences of data growth: More new data coming Backup takes longer Growth Backup Manage Recover Can’t buy more storage Recovery takes longer 6
- 7. Surviving the tidal wave Reducing your data storage footprint will: • Reduce your costs – Less storage = less capital expenditures – Less data = simplified management and administration • Improve service levels – Less downtime = higher application availability – Meet SLAs and customer expectations • Mitigate risks IBM can help you build a – Eliminate consequences of data loss dynamic storage infrastructure that will – Respond faster to events and intelligently improve service legal/government inquiries levels, reduce costs and manage risks 7
- 8. Surviving the tidal wave Choices for reducing your data storage footprint: • Discover & categorize your data • Automate data lifecycle management • Avoid data duplication • Compress and deduplicate • Maximize storage utilization 8
- 10. Determine what you have before you try to fix it • Systems are bursting w/ data that is old and rarely used • Is some of your data a liability? – Think e-discovery: do you know what was saved 5 years ago? • Categorize & then migrate or archive this data from production systems to: – Reduce capacity requirements and lower CAPEX and OPEX – Improve backup and restore performance – Help meet data retention and expiration mandates 10
- 11. Data discovery and categorization IBM Tivoli Storage Productivity Center for Data Identifies data eligible for migration, archiving and deletion: Provides: • Date saved or last accessed • Location and owner • File type and size • Duplicate files 11
- 13. Data lifecycle management using tiered storage Start with 1PB, add 100TB new data per quarter (40% CAGR) • Storage growth w/o tiered storage: 100 TB 100 TB Add new primary 100 TB 100 TB capacity each qtr. 1 PB NEW data grows into new capacity At $50,000 per TB, new storage costs $20 million* Storage growth with tiered storage: 100 TB 100 TB 100 TB Add new secondary 100 TB capacity each qtr. 1 PB OLD data migrates into new capacity At $15,000 per TB, new storage costs $6 million* * fully-burdened cost 13
- 14. Data lifecycle management Disk pools Optical pools App Prod. Data TSM Server Tape pools Servers • Regularly scrub production systems of old/stale data – Automated processes based on business-driven policies • Reduce the growth of primary storage – reduce CAPEX – Faster backup / restore • Migration / Hierarchical Storage Management (HSM): – Leaves a pointer; enables transparent access to migrated data • Archive – Completely removes files from production systems – Supports data retention and version control policies 14
- 15. Automating data migration IBM Tivoli Storage Manager for Space Management IBM Tivoli Storage Manager HSM for Windows • Get control of and efficiently manage data growth and its associated storage costs • Storage pool “virtualization” • Optimized restore management – Based on location of data in hierarchy • Transparent to the users and applications – Simple pointer (stub file) replaces data in original location – Fast, direct restore from disk to client • Migrations – Scheduled, automated, outside the backup window 15
- 16. Archive Features • Long-term storage on cost-effective media • Point in time copy; revision history and auditability • Retention period and ‘retention hold’ enforcement • Fast expiration processing Benefits Speed file-server recovery times – recover only active data Reduce backup times and resource usage Move archived files to a hierarchy of lower-cost storage Archived files are indexed with descriptive metadata to aid in locating historical information 16
- 17. IBM Smart Archiving solutions Arc ive hiv Arch e or App Servers App Servers Ret riev ieve Retr e Disk pools TSM Server Optical pools IBM Information Tape pools Archive Tivoli Storage Manager 6 IBM Information Archive • Integrated Backup, HSM Dedicated, scalable archive and Archive solution appliance • Leverage the same Supported by more than 40 hierarchy of storage Apps 17
- 19. Avoiding data duplication • Performing periodic full backups is typically the largest contributor to data growth in a data center • As much as 95% of your data doesn’t change from week- to-week • Are you making another copy of that data every weekend? • Data deduplication solutions were created to address this problem – They claim 95% reduction ratios, this is the data they’re talking about Never perform a full backup again • Tivoli Storage Manager – ‘progressive-incremental’ and sub-file backup • Tivoli Storage Manager FastBack – block level incremental • Tivoli Storage Manager FastBack for Workstations • Tivoli Continuous Data Protection for Files 19
- 20. Data reduction: progressive-incremental backup Features • ONLY new or changed files are backed up • Synthetic FULL created in the background • Restores don’t require the same file to be restored multiple times • Supports multiple versions of files • Accurate point-in-time restores Benefits Requires less storage space, less network bandwidth and less time Shorter backup windows Fast accurate restores 20
- 21. Benefits of progressive-incremental backup Never perform a full backup again Capacity Requirements Comparison 2500 2000 Backup Capacity Gigabytes 1500 Needed for 1 Month: 1000 Vendor A: 26TB Vendor B: 14TB 500 IBM TSM: 7TB 0 Mon Tue Wed Thu Fri Wkend Mon Tue Wed Thu Fri WkEnd Week 1 Week 2 Vendor A: Full+Differential Vendor B: Full+Incremental TSM Progressive Incremental Assumes: Full backup completed, 2TB data to start, 26% annual growth rate, 10% new/changed data per day 21
- 23. Data compression in Tivoli Storage Manager • Selectable option – on average, yields 2:1 • Sub-file backup when only parts of a file change – Byte-Level: for smaller files – Block-Level: for larger files – File-Level: if more than 60% of the file has changed, TSM backs up the whole file • Tape Reclamation – increase tape utilization “Tivoli Storage Manager has been long recognized as having the best tape management capabilities on the market. These features are fully integrated into the product at no additional charge.” – Dave Russell, Gartner Inc. 23
- 24. Tape reclamation + = 100% 25 % 70 % 95 % full + full = full • Better utilizes tapes, thus, When free space reaches a set saving money threshold: • Tape utilization constantly – Tape is mounted monitored – Valid data is moved to • User-defined reclamation another tape threshold – Original tape is returned to • Can be scheduled to occur at the scratch pool specified times 24
- 25. Basics of data deduplication • A ‘hot’ data reduction technology • Eliminates redundant subfiles – Known as chunks, blocks, or extents • Only one instance is stored for each common chunk • Duplicate instances of the chunk point to the stored chunk 25
- 26. Where can data deduplication occur? Applications like email and content management are Some backup building in Single Instance applications can perform Store and deduplication client or remote office server deduplication WAN devices perform deduplication Backup Remote Client Office Server Source Side Target Side NAS LAN Storage Some deduplication vendors are promoting their FC appliances for live data as Storage well as a backup target Backup SAN Server Some NAS devices perform Single Instance Store or fixed block deduplication on live data or can serve as a target VTLs serve as a target for for backup applications backup applications and VTL have added in-line and post Backup applications like process deduplication TSM are including server deduplication 26
- 27. Deduplication in Tivoli Storage Manager v6.2 • Tivoli Storage Manager v6.1 and TSM FastBack v6.1 include target-side data deduplication, at no extra charge – Improves recovery times and/or reduces capacity requirements – Uses data from any source including: API, backup, HSM, archive – Operates as a post-process; automatic space reclamation – Builds on automatic data compression & progressive-incremental • New in TSM v6.2: client-side data deduplication – Reduces network traffic by determining if a chunk has already been backed up (maybe from a different client system) “The combination of TSM progressive incremental backups and target-side data deduplication reduced disk capacity by a factor of 19:1 after just 10 backups” – Tony Palmer, ESG Lab Validation Report, April 2009 27
- 29. Gain visibility and control of storage resources Tivoli Storage Productivity Center – Standard Edition • Enable end-to-end storage management – A holistic topology view of entire storage infrastructure – Centralized management of heterogeneous storage • Improve storage utilization, performance and service levels – Analytics, trending, change configuration, best practices guidance – Green features – High availability; transparency for Cloud deployments • Reduce storage complexity – Built-in, customizable operational control and automation – Deep-dive reporting across host file systems, databases and virtualized storage environments 29
- 30. Maximize utilization and simplify management IBM System Storage SAN Volume Controller (SVC) • Virtualization of total storage capacity across vendors – Eliminates storage silos • Thin provisioning - auto-assigns Virtual Disk Virtual Disk Virtual Disk Virtual Disk capacity SAN • Non-disruptive data migration & SAN Volume Controller data movement Advanced Copy Services • Greater efficiency and productivity Storage Pool • Industry-leading virtualization NetApp HDS IBM EMC HP software – Scales with your growth and minimizes costs 30
- 31. Why IBM
- 32. IBM’s unique position in the industry • IBM is the only vendor with a comprehensive set of data reduction technologies • IBM does not force any particular approach – Our broad portfolio gives us the freedom to solve customer issues with the most effective and appropriate technology • IBM’s high quality global support services will ensure your investment in data reduction will meet your needs • IBM is continuing to invest in research to deliver the advanced data reduction features our customers are requesting 32
- 33. IBM’s comprehensive data reduction portfolio Remote Office(s) Data Center Tiered Storage FastBack FastBack TSM B/A ProtecTIER Clients Clients Clients Applications Applications File Servers File Servers VMware Servers VMware Servers FastBack for Tiers of Workstations Storage WAN FastBack Information FastBack Server TSM Servers Archive Server Plus: Incremental-only backup • TPC for Data categorization/deletion Data compression and tape management • TPC-SE for storage resource management • SVC for storage virtualization Data deduplication • Optim for database archiving • … and many others Space management and archive 33
- 34. IBM’s comprehensive data reduction portfolio Remote Office(s) Data Center Tiered Storage FastBack FastBack TSM B/A ProtecTIER Clients Clients Clients Applications Applications File Servers File Servers VMware Servers VMware Servers FastBack for Tiers of Workstations Storage WAN FastBack Information FastBack Server TSM Servers Archive Server Incremental-only backup Data compression and tape management “IBM delivers data reduction in more Data deduplication places than any other vendor”, analyst Space management and archive Mike Karp with Ptak, Noel & Associates, 02/10 34
- 35. Next steps
- 36. Next steps • IBM Global Technology Services and IBM Business Partners stand ready to help you assess your current situation and recommend next steps. • We can help you determine which data reduction techniques will have the most cost-effective impact on your operations. • Ask for a comprehensive ROI analysis using IBM’s comprehensive Business Value Analyst (BVA) tool. 36
- 37. THANK YOU
- 38. Trademarks and disclaimers Intel, Intel logo, Intel Inside, Intel Inside logo, Intel Centrino, Intel Centrino logo, Celeron, Intel Xeon, Intel SpeedStep, Itanium, and Pentium are trademarks or registered trademarks of Intel Corporation or its subsidiaries in the United States and other countries./ Linux is a registered trademark of Linus Torvalds in the United States, other countries, or both. Microsoft, Windows, Windows NT, and the Windows logo are trademarks of Microsoft Corporation in the United States, other countries, or both. IT Infrastructure Library is a registered trademark of the Central Computer and Telecommunications Agency which is now part of the Office of Government Commerce. ITIL is a registered trademark, and a registered community trademark of the Office of Government Commerce, and is registered in the U.S. Patent and Trademark Office. UNIX is a registered trademark of The Open Group in the United States and other countries. Java and all Java-based trademarks are trademarks of Sun Microsystems, Inc. in the United States, other countries, or both. Other company, product, or service names may be trademarks or service marks of others. Information is provided "AS IS" without warranty of any kind. The customer examples described are presented as illustrations of how those customers have used IBM products and the results they may have achieved. Actual environmental costs and performance characteristics may vary by customer. Information concerning non-IBM products was obtained from a supplier of these products, published announcement material, or other publicly available sources and does not constitute an endorsement of such products by IBM. Sources for non-IBM list prices and performance numbers are taken from publicly available information, including vendor announcements and vendor worldwide homepages. IBM has not tested these products and cannot confirm the accuracy of performance, capability, or any other claims related to non- IBM products. Questions on the capability of non-IBM products should be addressed to the supplier of those products. All statements regarding IBM future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only. Some information addresses anticipated future capabilities. Such information is not intended as a definitive statement of a commitment to specific levels of performance, function or delivery schedules with respect to any future products. Such commitments are only made in IBM product announcements. The information is presented here to communicate IBM's current investment and development activities as a good faith effort to help with our customers' future planning. Performance is based on measurements and projections using standard IBM benchmarks in a controlled environment. The actual throughput or performance that any user will experience will vary depending upon considerations such as the amount of multiprogramming in the user's job stream, the I/O configuration, the storage configuration, and the workload processed. Therefore, no assurance can be given that an individual user will achieve throughput or performance improvements equivalent to the ratios stated here. Prices are suggested U.S. list prices and are subject to change without notice. Starting price may not include a hard drive, operating system or other features. Contact your IBM representative or Business Partner for the most current pricing in your geography. Photographs shown may be engineering prototypes. Changes may be incorporated in production models. © IBM Corporation 1994-2010. All rights reserved. References in this document to IBM products or services do not imply that IBM intends to make them available in every country. Trademarks of International Business Machines Corporation in the United States, other countries, or both can be found on the World Wide Web at http://www.ibm.com/legal/copytrade.shtml. 38