Pulse 2011 virtualization and storwize v7000


Published on

An IBM Presentation on Storwize V7000 and SAN Volume Controller (SVC).

Published in: Technology, Business
1 Comment
  • Why is download disabled? Could i get a PDF copie of it?
    thank you
    Are you sure you want to  Yes  No
    Your message goes here
No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide
  • In July this year, an article appeared on Search Storage dot com dot au that promoted the benefits of Storage Virtualization. The benefit list could have been taken straight from an IBM SAN Volume Controller Redbook. And yet one gets the feeling that somehow Storage Virtualization is something new… something that only NOW should be considered. But is this true?
  • IBM has been doing Storage Virtualization since June of 2003. That’s over 8 years of commitment to Storage Virtualization. You can see the CNET news article that announced this function.
  • The software stack has grown considerably over 8 years with many new functions added such as RAID, Easy Tier, Thin provisioning and Volume Mirroring. All added without breaking the stack. The SCSI back end code has been enhanced every year as we add support for extra back end controllers. The SCSI front end code has been enhanced as well as well add code for extra host operating systems.
  • Dr Evil had nothing to do with the Storwize V7000, but he would have apprecaited what Project Quicksilver achived: 1 millions IOPS (not dollars). This got us thinking about SAS attached SSDs and the best way to use them.
  • In 2010 we combined our greatest strengths to enhance the SVC and bring a startling new product to the midrange storage space. We took our already mature, tried and tested and well loved SVC…. We took the RAID code out of the device adapters of the DS8000… we took the EasyTier code, developed by IBM in Almaden Resource Center and already field proven in the DS8000….. And then we created a new management GUI…. Inspired by the world leading GUI of the XIV…. We put it all into the SVC code, Creating a dramatic new release of that product. And then on top of that we created something new… exciting hardware!
  • So what are you looking at? At its simplest form… it’s a midrange storage controller… maybe ‘just’ a midrange product. But as with anything it’s the secret sauce that makes all the difference. Lets look at the building blocks.
  • Pulse 2011 virtualization and storwize v7000

    1. 1. Storage Virtualisation: Storwise V7000 and SVC<br />Anthony Vandewerdt<br />Storage Solutions Specialist<br />
    2. 2. Is this new?Six reasons to adopt storage virtualisation<br />Storage virtualisation reduces complexity<br />Storage virtualisation makes it easier to allocate storage<br />Better disaster recovery<br />Better tiered storage<br />Virtual storage improves server virtualisation<br />Virtual storage lets you take advantage of advanced virtualisation features<br /> June 2011: http://searchstorage.techtarget.com.au/feature/Six-reasons-to-adopt-storage-virtualisation<br />2<br />
    3. 3. 3<br />http://news.cnet.com/IBM-enhances-storage-virtualization/2100-1015_3-1012438.html?tag=mncol;txt<br />
    4. 4. The hardware is not exciting<br />
    5. 5. The software stack is far more exciting…<br />5<br />
    6. 6. SVC release history is a continuous evolution<br />2008<br />Thin Provisioning<br />VDisk Mirroring<br />SVC EE<br />2004<br />2145-8F2<br />VSS<br />GDS<br />2006<br />Global Mirror<br />Multi Target FC<br />2010<br />Storwize V7000<br />New GUI<br />Easy Tier<br />2003<br />2145-4F2<br />4 node<br />6.2<br />1.1<br />1.2<br />2.1<br />3.1<br />4.1<br />4.2<br />4.3<br />5.1<br />6.1<br />2011<br />2145-CG8<br />VAAI<br />>2 TB MDisk<br />Performance Monitor<br />Flash Copy Enhancements<br />2004<br />8 nodes<br />2005<br />2145-8F4<br />2007<br />2145-8G4<br />Flash Copy Enhancements<br />2009<br />2145-CF8<br />SSD support<br />3 site Mirror<br /> > 2TB VDisk<br />Split Cluster<br />iSCSI<br />Zero Detect<br />
    7. 7. What was Project Quicksilver?<br />7<br />
    8. 8. What do you get when you add these together?<br />8<br />
    9. 9. A New Era in Midrange Disk Systems! <br />9<br />
    10. 10. We start with a Storage Bridge Bay enclosure<br />10<br />
    11. 11. We create a Control Enclosure<br />11<br />Top node canister<br />Power Supply with Battery Unit<br />Power Supply with Battery Unit<br />Bottom node canister<br />
    12. 12. The Node Canisteris an SVC Node <br />12<br />
    13. 13. Each Control Enclosure Power Supply has a Battery<br />13<br />
    14. 14. Then we add some disks <br />14<br />
    15. 15. 15<br />No restrictions on mixing sizes or quantities in an enclosure<br />What are our disk choices?<br />
    16. 16. Why SAS Version 2.0?<br />16<br />
    17. 17. SAS CablingFor EasyExpansion<br />17<br />ControlEnclosure<br />Note: Up to 9 expansion drawers from code level and above<br />
    18. 18. Configuration Concepts<br />18<br />
    19. 19. RAID arrays<br />19<br />
    20. 20. LAN<br />20<br />SAN<br />Vol4<br />Vol5<br />Vol6<br />Vol7<br />Vol3<br />Vol1<br />Vol2<br />Storwize<br />V7000<br />Virtualisation Concepts & Limits<br />Hosts<br /><ul><li>Up to 256 Hosts per cluster
    21. 21. Up to 512 FC ports per cluster & Host
    22. 22. Up to 256 iSCSI ports per cluster & Host</li></ul>Single Multipath driver(SDD, MPIO)<br />iSCSI or FCP<br />Host Mapping<br />Volumes<br /><ul><li>Up to 2,048 Volumes per cluster
    23. 23. Max. Volume size of 256TiB
    24. 24. Image Mode = Native Mode
    25. 25. Managed Mode = Virtualized Mode</li></ul>SAS<br />SSD<br />NL-SAS<br />Pool 3<br />Pool 4<br />Pool 5<br />Pool 1<br />Pool 2<br />Storage Pools<br /><ul><li>Up to 128 MDisks per Storage Pool
    26. 26. Up to 128 storage pools per cluster</li></ul>Internal Storage<br />External Storage<br />Internal Storage<br />1 to 8/16 drives (HDD) to form an Array<br />1 Array  Managed Disk (MD)<br />External Storage<br />Multiple Storage Subsystems<br />1 LUN  Managed Disk (MDdisks)<br />Up to 4,096 MDisks per cluster<br />Max. External MDisk<br />Size of 1 PB<br />with approved controllers<br />
    27. 27. Navigation, user indicator<br />Quick navigation<br />Action menus<br />Main display area withembedded help<br />Functionicons<br />Status details<br />Status indicators<br />New GUI<br />Icons with hover textActions or help on click<br />
    28. 28. Grouped Tasks<br />
    29. 29. Status pods<br />Click, move<br />Hover<br />Hover<br />
    30. 30. Persistent grids<br />Name filter<br />Drag-and-dropreorders columns<br />Type filter<br />Context menu offersadditional columns<br />Multi-select<br />
    31. 31. Presets reduce complexity<br />
    32. 32. 26<br />Create MDisks<br />© Copyright IBM Corporation 2011<br />
    33. 33. Create Pools & Volumes<br />Create Storage Pool (auto-config )<br />Create Volumes<br />
    34. 34. Create Hosts and Map Volumes<br />Create Host<br />Map Volumes to Host<br />
    35. 35. 29<br />Easy Tier<br />SSDs (Solid State Drives) are still expensive<br />Putting entire volumes on an SSD is wasteful<br />
    36. 36. 30<br />Data Migration by Volume and Sub-Volume <br />HDD Storage Pool<br />SSD Storage Pool<br />Change Disk Class<br />Change RAID Type<br />Change RPM<br />Change striping<br />Hybrid Storage Pool (SSD & HDD)<br />Existing Volume Based <br />Data Migration<br />Easy Tier<br />Enabled in Hybrid Pool<br />Easy Tier Automated Data Migration<br />
    37. 37. Domino<br />DB2<br />Exchange<br />Easy Tier Process<br />SVC/Storwize V7000 Node<br />Volume<br />Easy Tier Code<br />DPA<br />IOM<br />DMP<br />DM<br />31<br />Magnetic Disk<br />SSD<br />
    38. 38. 32<br />Easy Tier – Automated Data Relocation<br />Hybrid Storage Pool<br />Host Volume<br />Extent <br />Virtualization<br />MDisk from SSD Array<br />Hot Extents <br />Migrate Up<br />Cold Extents <br />Migrate Down<br />MDisks from HDD Arrays<br />
    39. 39. Easy Tier – Summary Report<br />33<br />
    40. 40. Easy Tier - Heat Distribution Report<br />34<br />
    41. 41. Easy Tier Application Transaction Improvement<br />PRELIMINARY<br />240% from<br />Original<br />brokerage<br /> transaction<br />Easy Tier<br />Learning<br />Easy Tier<br />In Action<br />
    42. 42. Easy Tier Application Transaction Improvement<br />PRELIMINARY<br />Easy Tier<br />Learning<br />Easy Tier<br />In Action<br />
    43. 43. Enhancements v6.2 <br />37<br />
    44. 44. 38<br />Real-time Performance Statistics<br />
    45. 45. VAAI: A tale of three primitives<br />39<br />Block zeroFull CopySmarter locking<br />
    46. 46. Storage VMotion done right<br />Before VAAI<br />After VAAI<br />
    47. 47. 41<br />Selected system<br />Selected system’s pools<br />Selected system’s details<br />Storwize V7000 Plug-In for VMware vCenter<br />
    48. 48. Base Storwize V7000<br />Maximums<br />Hosts (FC): 512 FC ports: 16x8Gb<br />Hosts (iSCSI) 128 Ethernet ports: 8x1Gb <br />Capacity: 48TB (optional) 8x10Gb <br />Cache: 32GB Volumes: 4096<br />Drives: 24LFF or 48 SFF or mix<br />Disk types: SAS, NL-SAS, SSD<br />Maximums<br />Hosts (FC): 256 FC ports: 8x8Gb<br />Hosts (iSCSI) 64 Ethernet ports: 4x1Gb <br />Capacity: 24TB (optional) 4x10Gb <br />Cache: 16GB Volumes: 2048<br />Drives: 12 LFF or 24 SFF<br />Disk types: SAS, NL-SAS, SSD<br />Clustered Storwize V7000 Control Enclosures<br />Cluster<br />Expand<br />Expand<br />+ External Virtualization for more capacity<br />Maximums<br />Hosts (FC): 512 FC ports: 16x8Gb<br />Hosts (iSCSI) 128 Ethernet ports: 8x1Gb <br />Capacity: 480TB (optional) 8x10Gb <br />Cache: 32GB Volumes: 4096<br />Drives: 240 LFF or 480 SFF or mix<br />Disk types: SAS, NL-SAS, SSD<br />Maximums<br />Hosts (FC): 256 FC ports: 8x8Gb<br />Hosts (iSCSI) 64 Ethernet ports: 4x1Gb <br />Capacity: 240TB (optional) 4x10Gb <br />Cache: 16GB Volumes: 2048<br />Drives: 120 LFF or 240 SFF or mix<br />Disk types: SAS, NL-SAS, SSD<br />Cluster<br />42<br />
    49. 49. History of SVC Node Development<br />43<br />
    50. 50. 10 Gbps iSCSI Option<br />10Gbps iSCSI<br />8Gbps FC<br />1Gbps iSCSI<br />New Node CG8 with optional 10 Gbps iSCSI<br />
    51. 51. SANVolume Controller<br />SANVolume Controller<br />Fujitsu<br />Eternus<br />DX60, DX80, DX90, DX410<br />DX8100, DX8300, DX9700<br />8000 Models 2000 & 1200<br />4000 models 600 & 400, 3000<br />HitachiVirtual Storage<br />Platform (VSP)<br />Lightning<br />Thunder<br />TagmaStore<br />AMS 2100, 2300, 2500<br />WMS, USP, USP-V<br />Sun<br />StorageTek<br />HPStorageWorks<br /> P9500,<br />MA, EMA<br />MSA 2000, XP <br />EVA 6400, 8400<br />EMC<br />VNX<br />VMAX<br />CLARiiON<br />CX4-960<br />Symmetrix<br />IBM DS<br />DS3400, DS3500<br />DS4000<br />DS5020, DS3950<br />DS6000<br />DS8000, DS8800<br />IBM<br />Storwize V7000<br />IBMN series<br />NEC<br />iStorage<br />Bull<br />Storeway<br />Pillar<br />Axiom<br />IBMXIV<br />DCS9550DCS9900<br />TMS<br />RamSan-<br />620<br />Compellent<br />Series 20<br />NetApp<br />FAS<br />v6.2 Supported Environments*<br />Linux(Intel/Power/zLinux)<br />RHEL<br />SUSE 11<br />Citrix Xen Server<br />IBMBladeCenter<br />IBM Power7<br />IBM AIX<br />IBM i 6.1 (VIOS)<br />HP-UX 11i<br />Tru64<br />OpenVMS<br />MicrosoftWindows<br />Hyper-V<br />IBM TS7650G<br />1024<br />Hosts<br />SunSolaris<br />VMware<br />vSphere 4.1<br />IBM<br />z/VSE<br />Novell<br />NetWare<br />AppleMac OS<br />SGI IRIX<br />VAAI<br />Native iSCSI*<br /> 1 or 10 Gigabit<br />Point-in-time Copy<br />Full volume, Copy on write256 targets, Incremental, Cascaded, Reverse,<br />Space-Efficient, FlashCopy Mgr<br />8Gbps SAN fabric<br />SAN<br />Continuous Copy<br />Metro/Global Mirror<br />Multiple Cluster Mirror<br />Easy Tier<br />SSD<br />Space-Efficient Virtual Disks<br />New<br />New<br />New<br />New<br />Virtual Disk Mirroring<br />45<br />
    52. 52. What about software integration?<br />IBM Tivoli FlashCopy Manager (FCM)<br />IBM Tivoli Storage Productivity Center (TPC)<br />IBM TPC for Replication (TPC-R)<br />BM Tivoli Storage Manager FastBack<br />IBM Systems Director<br />Microsoft Operations Manager (SCOM)<br />Microsoft VSS <br />VMWare vCenterPlugin<br />46<br />
    53. 53. So what does the future hold?<br />47<br />
    54. 54. Thank you! <br />Email:<br />anthonyv@au.ibm.com<br />Twitter: <br />http://twitter.com/#!/aussiestorblog<br />Blog: <br />https://aussiestorageblog.wordpress.com/<br />
    55. 55. Trademarks and disclaimers<br />© Copyright IBM Australia Limited 2011 ABN 79 000 024 733 © Copyright IBM Corporation 2011 All Rights Reserved. TRADEMARKS: IBM, the IBM logos, ibm.com, Smarter Planet and the planet icon are trademarks of IBM Corp registered in many jurisdictions worldwide. Other company, product and services marks may be trademarks or services marks of others. A current list of IBM trademarks is available on the Web at "Copyright and trademark information" at www.ibm.com/legal/copytrade.shtml<br />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.<br />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 pricesand 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.<br />All statements regarding IBM future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only.<br />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.<br />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.<br />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.<br />Photographs shown may be engineering prototypes. Changes may be incorporated in production models.<br />49<br />