IBM® Edge2013 - What’s new with the DS8000
-
Upload
glennboynton -
Category
Documents
-
view
231 -
download
4
description
Transcript of IBM® Edge2013 - What’s new with the DS8000
© 2013 IBM Corporation
Session 1312:
What’s new with the DS8000
Brian Sherman- Distinguished Engineer
10 June 2013
© 2013 IBM Corporation
DS8000 Unique Technology Advantages Provides Value to Clients
� IBM Servers + DS8000 are integrated by design– System z, Power i, p– Available years ahead of competitors
� OLTP and Batch Performance– High Performance FICON (zHPF)– Cache efficiency– Easy Tier– QoS - IO Priority Manager (IOPM)
� Availability– Built on Power technology– Highest levels of availability and data access protection
� Remote Copy– Lowest latency for Metro Mirror– Best RPO and lowest bandwidth requirements with Global Mirror– Superior management with GDPS / TPC for Replication (TPC-R)
� Ease of Use– Common GUI across the IBM platform– Simplified creation, assignment and management of volumes
� Encryption
2
Enterprise Storage for the World’’’’s Most Demanding Clients
© 2013 IBM Corporation
DS8870 R7.1 Announcement Content
� R7.1 announced June 4, 2013 (GA June 7, 2013) and provides the following:
� Introducing Easy Tier V
– Easy Tier Server provides deep Power AIX / DS8000 integration
– Easy Tier Application allows for pinning volumes to a given tier
– Heat map transfer enables the transfer Easy Tier optimization to remote mirror target
� VMware enhancements
– VAAI - Write Same
– SRM 5.0/5.1
– vCenter Plug-In
� Resiliency improvements
– Improved FlashCopy handling of volume reservations in Open Systems - SCSI reserves Detection and Removal
– z/OS Soft Fence
– Timestamp synchronization for Sysplex and DS8000
– New ICKDSF Verify Offline command
� Power i variable LUN sizes
� Support for Symantec space reclamation
� Field model conversion from DS8800 to DS8870
3
© 2013 IBM Corporation
DS8000 4Q2012 key dates
� DS8870 R7.0 (242x 961 / 96E)– Announcement date: October 3, 2012
– General availability date: October 19, 2012
� AIX PowerHA support for HyperSwap
– Announcement date: October 3, 2012
– General availability: November 9, 2012
4 4
© 2013 IBM Corporation
Easy Tier Evolution
� Easy Tier 1 (DS8700 R5.1)– Automated cross-tier performance management for SSD/HDD hybrid pools
– Manual mode management support for dynamic extent pool merge and dynamic volume relocation
� Easy Tier 2 (DS8700/DS8800 R6.1)– Automated cross-tier performance or storage economics management for
hybrid pools with any 2 tiers (SSD/ENT, SSD/NL or ENT/NL) – Automated intra-tier performance management (auto-rebalance)
in hybrid pools – Manual mode management support for rank depopulation and optimized volume restriping within non-managed pools
(manual volume rebalance)
� Easy Tier 3 (DS8700/DS8800 R6.2)– Automated cross-tier performance and storage economics management for hybrid pools with 3 tiers (SSD/ENT/NL) – Automated intra-tier performance management in both hybrid (multi-tier) as well as homogenous (single tier) pools (auto-
rebalance)
– Thin Provisioning support for Extent Space Efficient (ESE) Volumes
� Easy Tier 4 (DS8800 R6.3 / DS8870 R7.0)– Support for encryption capable environments
• DS8800 and DS8870 have FDE capable SSD and nearline drives
� Easy Tier 5 (DS8870 R7.1)– Server– Application– Heat map transfer
5
© 2013 IBM Corporation
DS8000 Easy Tier Automated TieringCombining the benefits across tiers and within a tier
� Full 3-tier technology support– Faster performance for hot data with SSDs– Cost savings (reduced footprint and $/GB)
for cold data– Sophisticated algorithms automatically
optimize each pool continuously
� Enhanced auto intra-tier re-balancing to support homogeneous (single-tier) pools
– Supports both mixed-tier pools and single-tier pools
� Easy Tier supports thick and thin provisioned volumes
6
Logical Volume
Easy Tier Managed Extent Pool
SSD Arrays
Nearline Arrays
Extent Virtualization Enterprise Arrays
6
© 2013 IBM Corporation
Easy Tier 5 - Easy Tier Server Overview
� IBM Power p / DS8000 integration
� Easy Tier Server is an architecture:
– A Host flash-cache based on IBM research technology using IBM flash hardware (Easy Tier Caching Client)
– Easy Tier based algorithms for automatic application aware system-wide optimization (Easy Tier / Easy Tier Caching Server)
– A proprietary protocol provides in band (SAN) communication and coherency
� Hosts (Caching Clients)
– Work independently to cache their applications IO streams providing real-time performance enhancement
– Use the Cooperative Caching protocol to have cooperative system-aware caching that interfaces with IBM Storage running the Cooperative Caching Server
7
Host
Caching
Client
IBM Server IBM Server
Host
Caching
Client
Easy Tier
Caching Server
DS8870
Flash Cache
SAN
Flash Cache
SSD
HDD
© 2013 IBM Corporation
Easy Tier Caching Client and Easy Tier Server work together
8
EasyTier
Caching
Server
SSDHDD
IBM Storage
Global Heat
and Statistics
Data
Easy Tier Cache Server
� While the Client Host SCSI stack driver does its own caching, it also receives ‘advice’ through Easy Tier Server specific communication
� The ‘advice’ is based on a unified view of the SAN storage, hosts, and their access patterns. It is a priority sorted list of extents
� The Client combines this advice with its own population list, resulting in both short and longer term cache population, higher hit ratio, and better storage solution optimization, including application aware storage.
� SAN based multi-host applications are enabled through the Easy Tier Server SAN Storage coherency protocol
� With coherency managed, storage advanced replication functions such as FlashCopy and remote mirroring are transparently enabled
Caching
Statistics
Easy Tier Cache Client
� The driver in the Host SCSI stack determines what to cache based on access patterns
� The cache makes per-io decisions of what to keep in cache and what to evict
� Selection algorithms achieve high performance by remembering the latest evicted tracks when selecting what to promote into the cache
IBM ServerIBM Server
SAN StorageCoherency
Host Caching
Client
Flash Cache
Host Caching
Client
Flash Cache
© 2013 IBM Corporation
Easy Tier Server boosts transaction dramatically
Up to 5X performance increase for DB2 banking brokerage workload
Easy Tier caches hottest data to server
5.3Xperformance increase!
Base configuration is all-HDD with Easy Tier Server not activatedIBM Power 770 server running AIX with 1 Ultra SSD I/O DrawerDS8870 146GB 15K drives (RAID 5) with 2 1.3TB database volumes
© 2013 IBM Corporation
Easy Tier Server Requirements
Caching Server (storage device)
DS8000 Model/Code DS8870 Release 7.1
LIC Feature Key “Easy Tier Server” FC7084 new LIC Key
No charge
DS8870 drive types All types supported, with or without multiple tiers
DS8870 configuration All (1–4 frame, all cache sizes, etc)
Volume Types Open volumes only (no CKD)
Caching Client (the host)
Host Type Power AIX
Host Environment Native AIX, No VIOS
AIX 7.1 TL2, AIX 6.1 TL8
Hardware (initial / more to come)
P7+, P7, P6 –
Any supported direct attach flash such as EXP30 UltraSSD w/ GX++, EXP24S w/ SAS adapters, or TRES I/O expansion drawers
10
© 2013 IBM Corporation
© 2013 IBM Corporation
Easy Tier 5 – Easy Tier Application
Easy TierApplication
Data Placement
� Databases and ISV solutions will be able to provide performance tips to Easy Tier
– Will guide what, when, where and how data is placed across the server and storage systems dynamically
� Enables Administrators to direct data
placement based on business
knowledge and application knowledge– Provide volume level pin / unpin capability
– Tier placement
11
© 2013 IBM Corporation
Technology Prototype Demonstration: zEC12 + DB2 for z/OS + DS8000 Directive Data Placement
Use Case
DB2 for z/OS integration of Directive Data Placement capability in REORG� Demonstrate DB2 is able to control the data placement of a Shadow data set based on
the storage tier of a REORG Target data setCustomer Value: Performance Assurance On Demand
� Just-In-Time Data Placement– Based on unique knowledge about data processing task and data classification,
application can timely choose data placement decision – Easy Tier function continues to manage the rest of data placement decisions in a
coordinated fashion� Storage Performance Assurance
– Ensure a newly created Shadow dataset is placed at the same tier as the existing target dataset during a typical database operation such as REORG
– Assure new dataset is performance optimized immediately after the reorganization.
Demonstration Execution� Apply special DB2 utility, DFSMS, and storage prototype support in demonstration
environment� Perform DB2 for z/OS REORG � Confirm the storage tier assigned for a newly reorganized data matches original data
storage tier12
© 2013 IBM Corporation
Easy Tier 5 - Heat Map Transfer
WorkloadHotspotAnalysis
MM/GC/GM Replication
13
© 2013 IBM Corporation
Heat Map Transfer Learning� Primary site:
– Optimize the storage allocation according to the customer workload– Save the learning data– Transfer the learning data from the Primary site to the Secondary site
� Secondary site:
– Without learning, only optimize the storage allocation according to the Replication work load – With learning, Easy Tier can apply the checkpoint learning data from the primary site– Following Primary storage data placement to optimize for the customer workload
� Heat Map Transfer Utility
– Available on• Windows• SLES11+/RHEL4+
– Up to 30 systems supported– TPC-R also supported
• TPC 5.1.1
14
© 2013 IBM Corporation
DS8000 STAT – System Summary Updated
15
� System Summary– Pools/volumes monitored– How much hot capacity– Current configuration of the pools
• SSD, Enterprise, NL or any combination– Tier Status
• IOPS overloaded, BW overloaded – Data Management Status
© 2013 IBM Corporation
DS8000 STAT – New Intra-tier Rebalance
16
� Intra-tier Status– Ranks monitored for IOPS
• Current IOPS, utilization of the rank and projected
© 2013 IBM Corporation17
DS8000 STAT – Pool View Updated
© 2013 IBM Corporation
DS8000 STAT – New Workload Skew
18
� Workload Skew– Customer skew data by pool– Utilized by Disk Magic
© 2013 IBM Corporation19
DS8000 STAT – Volume Heat Distribution Updated
© 2013 IBM Corporation
Workload skew from different client environments
20
0
10
20
30
40
50
60
70
80
90
100
0 10 20 30 40 50 60 70 80 90 100
Percentage of extents
Co
mu
lati
ve P
erc
en
tag
e o
f A
cti
vit
y
Mainframe1 - Small IOs Mainframe1 - MB Mainframe2 - Small IOs Mainframe2 - MBMainframe 3 - Small IOs Mainframe3 - MB Open1 - Small IOs Open1 - MBOpen2 - Small IOs Open2 - MB Open3 - Small IOs Open3 - MB
Nearline
Enterprise
SSD
20
© 2013 IBM Corporation
Drive Selection in an Easy Tier Environment
� 3-5% SSD, 95-97% Enterprise – Provides improved performance compared to single tier
solution– Removes requirement for over provisioning for high
access density environments– All data guaranteed to have at least enterprise
performance
� 3-5% SSD, 25-53% Enterprise, 40-70% Nearline– Provides improved performance and density to a single
tier solution– Significant reduction in environmental costs
� 20-50% Enterprise, 50-80% Nearline– Provides reduced costs and comparable performance to
a single tier Enterprise solution
21
Nearline
Enterprise
SSD
FlashSystem family
© 2013 IBM Corporation
New upcoming GUI: https://<DS8000-IP>:8452/preview (Read-only)
22 © 2013 IBM Corporation
© 2013 IBM Corporation
Integration of Power and DS8000
23
� Pre-deposit write (Copy services one protocol exchange, keeps link full)� Cache Optimization Algorithms – AMP, ARC, WOW, 4K Cache Blocks
� Easy Tier – Easy Tier Server and Application
� DB2 End-to-End I/O Priorities and Cooperative Caching for Power AIX
� I/O Priority Manager
� Integrated performance monitoring tools between Power i and DS8000
� FlashSystem family
� HyperSwap (AIX)
� Power HA p, Power HA i
� Remote Pair FlashCopy and Enhancements
� FlashCopy and Functions like Fast Reverse Restore
� Full System FlashCopy (FSFC) Toolkit for Power i
� Heat map transfer
� Dynamic Volume Expansion
� Thin Provisioning
� Space Efficient FlashCopy
� Disk Encryption
� TPC for Replication
Performance
Availability
Management/Growth
© 2013 IBM Corporation
Active-Query or Asymmetric Workload
Active-Active for Symmetric Workload
Primary Site(Production)
Secondary Site(Warm Standby)
Primary Site(Production)
Secondary Site(Query Workload)
Production Site 1 Production Site 2
Infrastructure Base Solution
• AIX HyperSwap
Virtualized Storage Solution
• SVC Stretched Cluster VDM
Software Base Solution
• DB2 HA-DR / Replication
• PowerHA GLVM
Infrastructure Base Solution
• AIX HyperSwap + FlashCopy
Virtualized Storage Solution
• SVC Stretched Cluster VDM
Software Base Solution
• DB2 HA-DR / Replication
• PowerHA GLVM
Infrastructure Base Solution
• AIX HyperSwap + Parallel DB
Virtualized Storage Solution
• SVC Stretched Cluster VDM + Parallel DB
Software Base Solution
• DB2 Geographically Dispersed PureScale Clusters (GDPC)
• Geographically Dispersed GPFS Cluster + Parallel DB
• PowerHA-AIX LVM Mirroring
Active-Standby for Fast Takeover
2424
IBM Power Active-Active Solution Portfolio
© 2013 IBM Corporation
Power HyperSwap Technology
25
Synchronous
Mirroring
Application
HyperSwap
Cluster
Primary DS8000
Site 1
Secondary DS8000
Site 2
Legend:
Active Path
Passive Path
HA/DR
Customer Benefits
Oct 3 PowerHA HyperSwap Announcement
� HyperSwap non-disruptively substitutes secondary for primary devices for planned and unplanned events through in-band commands
– Transparent to applications - continue to use same the same device
� Customer Benefits– Unplanned HyperSwap
• Continuous availability against storage failures
– Planned HyperSwap
• Storage migrations without downtime
• Storage maintenance without downtime
� Requirements– AIX 6.1 TL8 with SP1 or AIX 7.1 TL2 with SP1– PowerHA 7.1.2 SP1 with APAR IV2758
• Available November 9, 2012– DS8800 R6.3 SP2, DS8870 R7.1
Brings together AIX, PowerHA and DS8000 to provide a comprehensive application and data availability solution
© 2013 IBM Corporation
HyperSwap Multi Site Deployments: Oracle RAC
� Active-Active Sites (coming soon) – Active-Active workload across sites– Continuous availability of site compute
infrastructure and storage outages– Oracle RAC long distance deployment
� Compute Node outages: – Active-Active workload provides continuous availability
� Storage outages:– HyperSwap provides continuous availability
Fig 1: Active-Passive HyperSwap
Oracle RACSite 1
N1-1 N1-2
S1
(Active) (Active)
N2-1 N2-2
S2
(Passive) (Passive)
< 100 KM
Site 2
PowerHA Cluster
SYNC
Fig 2: Active-Active HyperSwap
Oracle RACSite 1
N1-1 N1-2
S1
(Active) (Active)
N2-1 N2-2
S2
(Active) (Active)
< 100 KM
Site 2
SYNC
� Active-Passive Sites– Active-Active workload within a site– Active-Passive across sites– Continuous availability for site storage outages
26
© 2013 IBM Corporation
PowerHA HyperSwap Client Test Results
27
Client ApplicationConnection Maintains
Unplanned HyperSwap Completed in 17 sec
Planned HyperSwap Completed in <1 sec
© 2013 IBM Corporation
Integration of z/OS and DS8000
28
� zHPF Enhancements (now includes all z/OS DB2 I/O, BxAM/QSAM)
� Extended Distance FICON
� Caching Algorithms – AMP, ARC, WOW, 4K Cache Blocking
� DFSMS Recognition of SSDs and Storage Tiering
� Easy Tier – Easy Tier Server and Application
� z/OS GM Multiple Reader Support
� SSDs + DFSMS + zHPF + HyperPAV + DB2
� zWLM + DS8K I/O Priority Manager
� HyperPAV
� GDPS and GDOC Automation
� GDPS/Active/Standby
� HyperSwap Technology Improvements
� Remote Pair FlashCopy and Enhancements
� zCDP for DB2, zCDP for IMS – Eliminating Backup windows
� Heat map transfer
� 1 TB EAVs
� Quick Init for CKD Volumes
� Dynamic Volume Expansion
� Space Efficient FlashCopy
� z/OS Distributed Data Backup
� System z Discovery and Automatic Configuration (zDAC)
� Alt Subchannel Exploitation
� Disk Encryption
� TPC for Replication, GDPS
Performance
Availability
Management/Growth
© 2013 IBM Corporation
System z and DS8870 Integration – New ICKDSF Function
� New ICKDSF parm – VerifyOffline
– INIT and REFORMAT commands will instruct the DS8870 to reject the I/O if the volume is
online to any other system
– Only the DS8870 has the information about every system (including different Sysplexes,
Vm, Linux,...) that has a path to this volume
� If the INIT/REFORMAT is rejected because it is online to some remote
system, client can issue Query Host Access from ICKDSF or DEVSERV
� Output listing indicates which host(s) have the volume online
29
© 2013 IBM Corporation
New ICKDSF INIT/REFORMAT parameter with DS8870 R7.1
� Why does this matter?
� Issue 1 - Prevent accidental loss of data when initializing a volume with z/OS ICKDSF
– Even though it’s documented the volume must be offline to all other systems, mistakes can happen
• Prior to this enhancement, ICKDSF has no means to know if a volume is being used from other systems
• This function protects accidental destroying a volume that is online to other systems
– Example:
• Use ICKDSF to initialize a volume. Incorrect volume serial provided and specifies a volume that is online to another system
� Issue 2 - Volume Integrity– There are scenarios when an operation is performed to a volume and the volume is
required to be offline to all other systems, to protect the integrity of the volume
– Example:
• Volume restored using DSS full-volume restore on system A while it is also online to system B
• System B may not be aware of any changes that were made to the volume such as the Volume serial, VTOC location, Index location or changes to the VVDS (Catalog)
30
© 2013 IBM Corporation
EC12 - New Channel Path Selection Algorithm with DS8870
� New channel path selection algorithm provides improved throughput and I/O service times when abnormal conditions occur:
– Abnormal conditions include the following:• Multi-system work load spikes
• Multi-system resource contention in the SAN or at the CU ports
• SAN congestion
• Destination port congestion
• Firmware failures in the SAN, channel extenders, WDMs, control units
• Hardware failures (link speeds did not initialize correctly)
• Miss-configuration
• Cabling Errors
• Dynamic changes in fabric routes (possible multi-hop cascading)
� When conditions occur that cause an imbalance in performance (I/O latency/throughput) across a set of channel paths to control unit
– Channel subsystem will bias the path selection away from poorer performing paths toward the well performing paths
• Accomplished by exploiting in-band I/O instrumentation and metrics of System z FICON and zHPF protocols and new intelligent algorithms in the channel subsystem to exploit this information
� Results show 50-100% throughput improvements with CU HBA/port congestion
– Complements DS8870 as premier storage consolidation platform
31
© 2013 IBM Corporation32
HyperSwap / DS8000 Synergy - z/OS Soft Fence
� After a GDPS/PPRC HyperSwap or an unplanned site switch, potential exposures exist to systems using the old Metro Mirror (MM) primaries
– Reading down-level data from the old MM primaries
– Updates the old MM primaries would be lost when the MM pairs are re-established in the reverse direction
� Example scenarios
– GDPS/PPRC provides IPL protection
• However, if GDPS isn’t used to IPL a system image, the IPL could be done against the former MM primaries
– Systems outside of the Sysplex will continue to access (and perhaps update) the old MM primary volumes following an unplanned HyperSwap
� Soft Fence (SF) will allow a host system to put a volume into a "soft fenced" state and also take it out of the “soft fenced” state. When a volume is in the soft fence state the disk subsystem will prevent all reads and writes to the volume from any host system
© 2013 IBM Corporation33
System z / DS8000 Integration - Timestamp Synchronization
� Future release of GDPS/Active-Active (A/A) is planned to integrate Global Mirror (GM) disk replication into the A/A environment
– Software replication will be mirroring the A/A workload data
– GM will be mirroring all data
• Both the A/A workload data and the non A/A workload data
� When a disaster occurs, A/A will need to understand the point of consistency for both software replication and GM in order to reconcile the two copies of the A/A workload data
– Consistency time stamps from software replication are relative to the Sysplex clock and the GM consistency time stamps are relative to the DS8870 clock
• The two clocks are not synchronized and time stamps cannot be validly compared to each other
� Solution is Host Timestamp is sent to the DS8000 for Read and Write I/O– GM Master Control Unit retrieves the Sysplex time from the I/Os issued from the
systems within the Sysplex and uses it when Consistency Groups are formed
© 2013 IBM Corporation
VMware Support on the DS8870
DS8870 supports vStorage API for Array Integration (VAAI):– Integration with vStorage API’s to improve performance
• R7.0 provided� Full copy (aka XCOPY) primitive offloads work from production virtual servers to storage which improves
application performance and reduces host and SAN resource utilization� Hardware-assisted locking (via Atomic Test & Set) primitive enables a finer grained level of locking
(block-level instead of LUN-level) on VMFS metadata which is more efficient and also scales better in larger VMware clusters
• R7.1 provides� Write Same (zero blocks) primitive, the process of zeroing the VMDK is off-loaded to the storage
subsystem
– Example tasks that can benefit from improved performance :• VM creation/cloning/snapshots/deletion• vMotion and storage vMotion• Extending a VMFS Volume• Extending the size of a VMDK file
VMware Storage Stack
VMFS NFS
VMware LVM
Data Mover
NFSClient
NetworkStack
vStorage APIfor Multi-Pathing
NFS
HBA Drivers NIC
vStorage APIs
Provisioning / Cloning
34
DS8870 also now supports– vCenter plugin– SRM v5.0/5.1
© 2013 IBM Corporation
DS8000 integration of EXP30 UltraSSD flash storage
� 1U drawer
– Up to 30 encryption capable eMLC SSD drives• With 387 GB drives = up to 11.6 TB (raw)
– Each drawer is independently installable; up to 4 per rack
� Two 6 Gb SAS adapters especially designed for SSD
– Directly connected to DS8000 internal PCIe fabric via currently open slots
� Great performance
– Up to 400,000 IOPS (100% read), up to 340,000 IOPS (60% read/40% write) and up to 270,000 IOPS (100% write)
– Up to 4.5 GB/s bandwidth
� Enterprise class RAS
– RAID protected with spares
– Dual power supplies, sensors, adapters and fans• Concurrently replaceable components
� Easy Tier enabled
35
June 4, 2012 SOD
35
Statements on IBMs future plans and directions are for informational purposes only. Future plans and directions are subject to change without notice.
© 2013 IBM Corporation
Flash Exploitation
Enterprise-class DS8000 flash evolution
All-flash
< 1 millisecond
Re
sp
on
se
Tim
e
Hybrid with Easy Tier
~ 1 millisecond
5-15 milliseconds
All-HDD
Combining flash optimization plus high-end capabilities
© 2013 IBM Corporation
The economics of all-flash enterprise systems
Performance-Cost benefits of flash will replace enterprise spinning drives over time
37
Performance-Cost curve
146GB 15k-RAID10
146GB 15k-RAID5
300GB 15k-RAID10
300GB 15k-RAID5
Larger capacity 10k-RAID5
TODAY
Time
© 2013 IBM Corporation
Performance with Flash is only one benefit
$7.2M
$4.9M
$3.1M
Traditional Disk All-Flash All-Flash (Atomic)
Source: Wikibon March 2013
38% Lower SoftwareLicense Costs– Fewer cores, Lower maintenance – Database, infrastructure SW…
Much HigherStorage Utilization– As much as 50%– Lower maintenance – Simplified management
17% Fewer Servers– Fewer cores– Fewer network connections– Lower maintenance
74% LowerEnvironmental Costs– Power / cooling, floor space
35% Lower OperationalSupport Costs– Server / Storage Administration
All Flash…
30+%Less Expensive
Businesses are 20% More Efficient…38
38
© 2013 IBM Corporation
DS8000 Functional Summary by Release
2004
•255 LCUs Supported
•RAID5/RAID10
•RMC/zGM/PTC/PAV
•64K Logical Volumes
•2GB FCP/FICON
•73/146/300GB DDs
10-2006
•HyperPAV
•HMC CIM Agent
•Enterprise Choice (extended) warranty
2-2008
•DS8000 M/T intermix
•Extended Distance FICON
10-2008
•zHPF
•zMGM Incremental Resync 7-2009
•Thin Provisioning
•Quick init
•zHPF Multi-track support
4-2010
•Easy Tier
•Thin Provisioning
•Quick Init
•2TB nearline SATA
•Multiple GM sessions
2006
•Turbo Models with Power5+
•500GB FATA nearline
•4GB FCP/FICON
•Flexible Warranties (242x)
•zOS Synergy Items
2007
•SSPC Support (new)
•Storage Pool Striping
•Space Efficient FlashCopy
•Dynamic Volume Expansion
•3rd & 4th expansion frames
5-2008
•Extended Address Volumes
•Variable LPAR
•IPv6
2-2009
•Solid State Drives
•1 TB SATA
•Intelligent Write Cache
•Full Disk Encryption (FDE)
•Remote pair FlashCopy
10-2009
•DS8700 with Power6 controller
•PCI-E internal fabric
•Increased Cache/NVS
10-2010
•DS8800
•Power6+
•All 2.5” SAS-2 drives
•8GB HA and DA
1.0
5-2011
•Easy Tier2
•IO Priority Manager (open)
•Resource Groups
•New GUI
•16TB LUN
•New Business Class option
DS8700 / DS8800 include all functional enhancements up to R6.3
DS8100 / DS8300 includes all functional enhancements up to R4.3
2.0 2.4 3.0 3.1 4.0 4.1 4.2 4.3 5.0 5.1 6.0 6.1
11-2011
•3TB nearline SAS
•Add’l expansion frame and 1,536 drives
•Easy Tier3
•I/O Priority Manager (CKD)
•zHPF QSAM BSAM BPAM
•1 TB EAV
•DB2 list pre-fetch optimizer
6.2
4-2012
•Encryption for SSD and NL-SAS on
DS8800
•Easy Tier4
•400GB SSD
•Thin Provisioning for all copy services
Note: not all enhancements are included
6.3
11-2012
•DS8870 with Power 7 controller
•Increased Cache / NVS
•All FDE drives
•RoHS 2013
•Energy savings
39
7.17.0
6-2013
•Easy Tier V
•Server, App, Heat Map Transfer
•VMware
•VAAI, vSphere, SRM
•zSynergy
© 2013 IBM Corporation
DS8000 is Smarter Storage for Smarter Computing
Increase information access
and improve ROI
Manage cost and capacity growth
Improve performance and
productivity
• Built for Performance
• Simplified Storage Management
• Reduced Environmentals
• Encryption without compromise
• Easy Tier
• Server / Storage integration
• Replication: Metro and Global Mirror
• Ease of volume management
• IO Priority Manager (QoS)
• Multi-tenancy / Resource Groups
40
© 2013 IBM Corporation
DS8000 Family Additional Resources
� DS8870 enterprise storage video
� DS8870 performance whitepaper
� DS8870 SPC-1 and SPC-2 benchmarks
� Analyst whitepaper: IBM Easy Tier Automated Storage Tiering, Silverton Consulting
� Analyst whitepaper: When Infrastructure Really Matters, DS8870, The Clipper Group
� Analyst whitepaper: Developing An Enterprise Flash Strategy with IBM, Storage Switzerland
� DS8000 storage efficiency and optimization solution brief
� DS8870 3D product tour (posted on DS8000 home page)
� DS8870 Installation and Planning Guide
� Redbook : IBM System Storage DS8870 : Architecture Implementation and Usage
� Redpaper : IBM System Storage DS8870 : VMware vStorage APIs for Array Integration (VAAI) support
4141
© 2013 IBM Corporation
Additional R7.1 Enhancements
42
© 2013 IBM Corporation43
Improved FlashCopy handling of reserves in FB environments -SCSI reserves Detection and Removal
� SCSI reserve could be left on devices when a server has been shut down
– User error
– Desire to shutdown quickly
– Various other reasons
� Problem for FlashCopy target devices that are used for testing
– Subsequent FlashCopy will fail and no easy way to either detect or correct
� Changes in DSCLI to allow:
– Detection of whether a SCSI reserve exists for devices in an environment and identify the server that holds the reserve
– Reset of the reserve when performing a FlashCopy Establish after it has been identified that it is not a valid reserve for a running server
© 2013 IBM Corporation
Power i Variable Size LUNS
� New volume type for Power i
– Unprotected Variable Capacity LUN – 2107 Model 050
– Protected Variable Capacity LUN – 2107 Model 099
� Volume characteristics:
– Format is 520 byte sector
– Size in multiples of 1 Gigabyte
– Maximum Size is 282 Gigabyte
– Volume types supported: Standard, Track Space Efficient (TSE), and Extent Space Efficient (ESE)
– Change from Protected to Unprotected and vice versa
– Volume resize is available for these models
� Existing Models:
– A01, A81, A02, A82, A04, A84, A05, A85, A06, A86, A07, A87
� New Models:
– 050, 099
� DSCLI supported with R7.1:
– Updated mkfbvol, chfbvol, lsfbvol
44
© 2013 IBM Corporation
Thank You
45
© 2013 IBM Corporation
IBM Corporation 1994-2013 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.
Intel, Intel logo, Intel Inside, Intel Inside logo, Intel Centrino, Intel Centrino logo, Celeron, Intel Xeon, Intel SpeedStep, Itanium, and Pentium are trademarks or registeredtrademarks 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.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.
Photographs shown may be engineering prototypes. Changes may be incorporated in production models.
Trademarks and Disclaimers
4646