IBM FlashSystem® V9000 is a comprehensive all-flash high-speed enterprise storage solution that delivers the full capabilities of IBM FlashCore™ technology (Thesecret sauce). It delivers microsecond response times plus a rich set of software-defined storage features including: IBM Real-time Compression™, dynamic tiering, thin provisioning, snapshots, cloning, replication, data copy services and high-availability configurations.
It introduces you to IBM FlashSystem V9000 and provides in-depth knowledge of the product architecture, software and hardware, its implementation, and hints and tips. It provides use cases that demonstrate real-world solutions, as well as examples of the benefits gained by integrating FlashSystem storage into business environments.
IBM FlashCore™ technology is built on hardware accelerated I/O, advanced flash management, and IBM MicroLatency® modules with IBM-enhanced Micron technology.
Also part of the sauce is the integrated management in a FlashSystem V9000 scalable environment of components using Fibre Channel connections: All manageable from one central V9000 GUI.
A FlashSystem V9000 fixed or scalable building block consists of:
Two FlashSystem V9000 Control Enclosures
One FlashSystem V9000 Storage Enclosure
The FlashSystem V9000 scalable solution provides scalable performance. You can scale-up and scale-out independently, up to 2.5 million IOPS and 19.2 GB/s bandwidth, with deterministic IBM MicroLatency, and Quality of Service.
The scalable building blocks also allow for for the addition of up to 4 individual FlashSystem Storage Enclosures to be added to the storage system. If 228 TB from 4 building blocks isn't enough capacity, up to 4 additional Storage Enclosures (SEs) can then be added.
In total, a FlashSystem V9000 Storage System can contain a maximum of 8 FlashSystem V9000 Storage Enclosures, offering a potential storage capacity of 456TB, and up to 2.2 PB effective capacity is available at 80% compression. Real-time Compression is available as a software feature that allows users to elect to deploy Real-time Compression where it is desired.
The following image illustrates the scalable capacity of FlashSystem V9000 . It also shows that additional SEs can be added to a single Building Block, as well as to 2, 3, or 4 Building Blocks.
Read IBM Redbooks publication; Introducing and Implementing IBM FlashSystem V9000 for how-to guidance and examples to effectively deploy and integrate IBM FlashSystem V9000 into your enterprise environment. Topics include Encryption, Concurrent Code Load and Concurrent Maintenance, Performance guidelines and more.
Secure your data with industry-standard data-at-rest encryption with no performance impact.
With the ever-growing landscape of national, state, and local regulations, industry requirements, and increased security threats, ensuring the protection of an organization’s information is a key part of operating a successful business.
Encrypting “data at rest” is a key element when addressing these concerns.
Here are a few key facts about XIV encryption:
While most storage products offer encryption at an additional cost, the XIV encryption feature is available at no charge.
An external key server , implemented by the IBM Security Key Lifecycle Manager (SKLM) is required (licensed product).
Encryption support is available with the XIV System Software Version 11.4 on XIV Gen 3 Model 214 systems, with 1 TB, 2 TB, 3 TB, and 4 TB drive capacities, as long as those drives are self-encrypting drives (SEDs).
Unique among IBM products, IBM XIV Storage System offers hot encryption. This means that when encryption is enabled on the XIV, all data that resides on the XIV is encrypted within minutes, with no performance impact.
The IBM XIV solution not only secures data at rest but also offers a simple, cost-effective solution for securely erasing (cryptographic erasure) any disk drive that is being retired or repurposed.
For details about the encryption planning, process and implementation in XIV, refer to the IBM Redpaper, IBM XIV Security with Data-at-Rest Encryption, REDP-5047
Everyday we hear about data security breaches regarding social media, companies, governments, organizations, private devices, and on and on. Having worked in the storage management business for most of my career my first thought is how did they leave themselves so exposed. After reading the details there are many that could have been avoided and some where the answer is not so clear. We also don't hear about the ones that successfully prevented unauthorized access to their data. I want my data to be in the last category - successful protection. Understanding your options is a great way to evaluate your data protection environment or help you plan for implementing a secure system for your data. We just published the IBM Redpaper IBM Spectrum Scale Security to describe the security possibilities for Spectrum Scale implementations. Here is an overview of the organization and scope of the Redpaper.
Security for storage systems can be classified as follows:
Data storage (data at rest, which includes data durability and immutability)
Access to data
Movement of data (data in flight)
Management of data
IBM® Spectrum Scale is a software-defined storage system for high performance, large-scale workloads on-premises or in the cloud. IBM Spectrum™ Scale addresses all four aspects of security by securing data at rest (protecting data at rest with snapshots, and backups and immutability features) and securing data in flight (providing secure management of data, and secure access to data by using authentication and authorization across multiple supported access protocols). These protocols include POSIX, NFS, SMB, Hadoop, and Object (REST). For automated data management, it is equipped with powerful information lifecycle management (ILM) tools that can help administer unstructured data by providing the correct security for the correct data. The various aspects of security in IBM Spectrum Scale™, include the following items:
Security of data in transit
Security of data at rest
Security for transparent cloud tiering (TCT)
Security for OpenStack drivers
For example, Chapter 9 describes Security for transparent cloud tiering (TCT). It starts with a high level figure shown here.
Figure 1. Transparent cloud tiering configuration
The Chapter drills down to the following detailed items:
Securing data in flight and at rest
Securing the keys that are used to protect the data
Configuring transparent cloud tiering with an external key manager: IBM Security Key Lifecycle Manager
TCT daemon communications
Security of TCT commands
Data integrity protection
Security considerations while configuring a cloud object storage
Data Security is a never ending process of planning, implementation, and validation.
In a recent posting , we introduced the upcoming support for VMware Virtual Volumes (VVOL) with the IBM XIV Storage System. With the announcement of vSphere 6.0, VMware also officially released support for the vSphere Virtual Volumes (VVOL) architecture
Since March 12 , 2015 , the VVOL and XIV integration is effectively supported through IBM Spectrum Control Base, and based on the VMware API for Storage Awareness (VASA). IBM Spectrum Control Base is a follow on to the IBM Storage Integration Server.
Virtualization technology is transforming businesses and organizations. Current storage capacity, performance, and Independent Software Vendor (ISV) integration requirements are growing faster than ever before while the infrastructure budget is shrinking in the same proportion.
IBM Redpaper REDP-5148 Deploying IBM FlashSystem V840 in a VMware Environment describes and demonstrates how to address IBM FlashSystem V840 business performance and capacity requirements by creating a Software Defined Storage (SDS) Control Plane to more efficiently integrate with VMware and Independent Software Vendor (ISV).
The IBM developed solution, IBM Storage Integration Server, addresses this requirement bringing automation, elasticity, Storage as a service capabilities and operations management for Storage management.
IBM Storage Integration Server provides the ability for IBM disk arrays and IBM FlashSystem V840 flash arrays to be automatically orchestrated and monitored in a cloud environment.
The IBM Storage Integration Server is a centralized server system that consolidates a range of IBM storage provisioning, virtualization, cloud, automation, and monitoring solutions through a unified server platform.
The IBM Storage Integration Server facilitates the integration of IBM Storage System resources by using options (user credential, storage system, and storage pool management) with supported independent software vendor (ISV) platforms and frameworks. It provides a foundation for integration with IBM systems and ISV solutions, and can be downloaded at no extra cost!
You can download the latest version at any time from the IBM Fix Central Website:
IBM Storage Integrated Server provides a single server back-end location and enables centralized management of IBM storage resources for different virtualization and cloud platforms, including:
VMware vCenter Server
VMware vSphere Web Client
VMware vSphere APIs for Storage Awareness (VASA)
As shown below, IBM Storage Integration Server works as an abstraction layer between the VMware environment and the FlashSystem V840, thereby consolidating and reducing the VMware components generated requests against the storage system:
In IBM Spectrum Scale v4.2.2 and later, Spectrum Scale supports a REST API for file system management. The IBM Spectrum Scale REST API is an HTTP programming interface for performing IBM Spectrum Scale management tasks. With the REST API, you can automate storage management operations and integrate IBM Spectrum Scale capabilities into your applications. The API can be installed on one or more cluster nodes and requires the Apache HTTP server to be installed on the same node. Clients communicate using HTTPS protocol and JSON syntax is used to frame data inside HTTP requests and responses. In this release the API supports operations on filesets, snapshots, and quotas and retrieving information about CES objects, file systems, and nodes. Here's a figure to give the high level architecture view.
To learn more about using Spectrum Scale's REST API support take a look at:
Announced on April 27, 2016 IBM FlashSystem A9000 and IBM FlashSystem A9000R
deliver the microsecond latency and high availability of IBM FlashCore™ technology with grid architecture, simple scalability, and industry-leading IBM software, designed to drive your business into the cognitive era.
Comprehensive data reduction capabilities, including inline deduplication and compression, help lower total cost of ownership,
while a new, highly intuitive user interface simplifies management.
IBM FlashSystem A9000 and IBM FlashSystem A9000R transform technology infrastructure into business innovation.
From a functional standpoint IBM FlashSystem A9000 and IBM FlashSystem A9000R leverage most of the software-defined storage features offered by the IBM Spectrum™ Accelerate software, including multi-tenancy and business continuity functions.
For a quick tour of the systems, refer to the following IBM Redbooks Product guides:
Announced on October 6 ( 2014), the DS8870 Release 7.4 (Licensed Machine Code 7.7.40.xx.xxx) brings enhanced replication options, improved synergy with System z, additional flash optimization, and new capacity options as well as an improved DS GUI.
The planned availability date is December 5, 2014.
New replication options:
Mutli Target Peer-to-Peer Remote Copy: provides two independent mirror target sites (secondary sites) , so High Availability and Disaster Recovery capabilities are unaffected if one target site fails. Other benefits include : simplified recovery after site failure , storage migration capability without compromising the High Availability of the solution, possible Incremental Resync between the two secondary sites.
Multiple Incremental FlashCopy : provides for up to 12 incremental FlashCopies for any volume, allowing more efficient and frequent backups for better continuous data protection and disk space saving.
System z Synergy:
z/OS Global Mirror (XRC) Workload based Write Pacing with HyperPAV is a Software Defined Storage enhancement to control XRC write pacing and can , for instance, prevent low priority work to negatively impact the Recovery Point Objective of business critical applications.
Easy Tier Application integration with System z thru a new Software Defined Storage API , allowing application to hint Easy Tier about data usage, such that Easy Tier will move the data to the appropriate storage tier.
zHyperwrite , allowing DB2 to perform dual, parallel log writes with DS8870 Metro Mirror, thus reducing DB2 log latency while HyperSwap remains enabled. This new technology can help reduce up to 43 percent of the DB2 log write time
Support for an additional 4 High Performance Flash Enclosures (HPFE) in the first Expansion Frame , doubling the HPFE capacity to 96 TB and improving overall system performance by up to 35%.
600 GB 15K rpm SAS FDE drive
1.6TB 2.5-inch FDE Flash drive (SSD) for up to 2.55PB of Flash capacity!
Improved User Interface
The improved DS8000 Storage Management GUI simplifies storage management, monitors system health in real time, and enables faster configuration
You will be able to read ample details about those new features and enhancements in updated DS8870RedBooks publications. Availability and other details will be announced on this blog.
Recently announced for the DS8870 , the high-performance flash enclosure (HPFE) is a RAID storage enclosure that can support up to thirty 400 GB encryption capable flash cards (1.8-inch, 46 mm form factor) in a 1U rack space. It is installed in the DS8870 base frame.
The high-performance flash enclosure comes with various capabilities and performance characteristics, as summarized here:
The high-performance flash enclosure delivers up to 250,000 IOPS and up to 3.4 GBps bandwidth in just one EIA (1U) of rack space.
Using high-performance flash enclosures can accelerate database performance by up to four times while still guaranteeing the industry-leading DS8870 availability.
By using high-performance flash enclosures, batch times shrink by up to 10%, therefore reducing impact on production applications.
High-performance flash enclosures can carry up to 12 TB of raw capacity per enclosure.
Flash cards in the high-performance flash enclosure support full drive encryption.
The high-performance flash enclosure is available in the following configurations:
DS8870 Model 961 Enterprise Class or Business Class configuration:
In the Enterprise or Business Class configuration, you can have up to four HPFEs installed vertically in the base frame. The base frame can still accommodate up to 10 standard drive enclosures, populated with either flash drives (SSDs) or spinning drives.
DS8870 Model 961 High Performance All Flash configuration
In the High Performance All Flash configuration, up to 8 HPFEs (four horizontally and four vertically) can be installed in the base frame. A High Performance All Flash configuration has four I/O enclosure pairs installed expanding the number of hosts and maximizing the bandwidth with up to 16 four or eight port Fibre Channel/IBM FICON® host adapters, offering maximum performance and connectivity in a single frame footprint.
Starting with IBM Storwize Family Software V7.2, including IBM SAN Volume Controller, we introduced native replication over IP networks. As this IBM Redpaper describes, you will see that it is easy to configure in an existing IP infrastructure. This is a lower-cost alternative to the Fibre Channel-based and FCoE-based replication, and by having it within the software itself, it can eliminate the need for FCIP routers and dark fibre.
This native IP replication addition allows us to:
Accelerate the flow of data
Maximize the capacity of the pipe
Optimize multiple connections with Artificial Intelligence
By placing the IP replication function in the Storwize Family Software, server CPU and management overhead is freed up, and a single point of replication control is available for all server types.
Native IP replication uses the Ethernet ports introduced in V7.2.
In this paper we show how to configure the IP partnership, create remote copy relationships and consistency groups, and easily move between the three flavors of replication: synchronous, asynchronous and asynchronous using change volumes.
We cover configuration guidelines, restrictions, and best practices as well as some basics of what the integrated SANSlide function provides.
I was flying above the clouds headed for Tokyo after working on our Redbooks Publication IBM SmartCloud Storage Access V1.2 Implementation Guide in Shanghai. It was a very uneventful flight and then I saw something looming in the distance rising up through the clouds. Although I tried to tie the object up ahead to an analogy of my storage cloud work I quickly figured out that we were doing an amazing fly by of Mt. Fuji from 20K+ ft.
Recently, I published a draft of a new Redpaper, IBM Private, Public, and Hybrid Cloud Storage Solutions, that describes storage cloud and the functions needed for a smart storage cloud. It also highlights the IBM System Storage solutions and how they are making it easier for clients to use in the cloud by supporting OpenStack®. OpenStack and offerings like it, provide a means for traditional IT to quickly adopt newer cloud computing workflows and best practices. The image of Mt. Fuji rising above the clouds came to mind but still no direct correlation to our storage cloud Redbooks and Redpapers. I don't think we want a volcano tied to what is inside a storage cloud.
Snow capped Mt. Fuji from 20K+ ft.
Back to the new Redpaper. The IBM Storage Driver for OpenStack is a software component that integrates with the OpenStack cloud environment and enables the usage of storage resources that are provided by the following IBM storage systems:
IBM Storwize® Family
Here is an example shown in the Redpaper of how IBM has contributed to support the DS8870 in an OpenStack cloud environment.
IBM contributes DS8870 support to OpenStack Cinder
I mentioned at the beginning of the blog the recently published draft of IBM SmartCloud Storage Access V1.2 Implementation Guide. SCSA is included in the Redpaper in the Automated Provisioning section and here is a diagram that shows how it can help cloud administrators and users easily manage both block and file data.
SCSA deployment architecture
To complete the picture of IBM storage in the cloud we discuss the major offerings which now includes SoftLayer (An IBM Company) and IBM Cloud Managed Services (formerly SCE+). The figure below shows the breadth of IBM Cloud Managed Services and SoftLayer together in offering complete cloud solutions.
IBM SmartCloud Offerings
Keeping the size of the Redpaper to around 100 pages when describing the storage cloud possibilities is like trying to get your arms around Mt. Fuji.
As you know, the install of Tivoli Storage Productivity Center has improved with each release. So for this book the team did not feel it was necessary to provide detailed installation information. While installation hints and tips are included, things that we found during the install that we thought were important to pass along, we did not document step-by-step instructions. This allowed for more time to focus on the release features and functions.
Tivoli Storage Productivity Center V5.2 includes the Tivoli® Storage Productivity Center VASA provider which enables the Tivoli Storage Productivity Center administrator to bring visibility of Tivoli Storage Productivity Center managed storage resources to a vCenter server administrator. You will notice that this version of the book does not include information on the VASA provider. The chapter detailing the VASA provider and its use is under review. As soon as I can I will be updating the draft with this information. Check back to this blog for updates.
Before you install Tivoli Storage Productivity Center V5.2, check the 5.2 Limitations and known issues for Tivoli Storage Productivity Center and Tivoli Storage Productivity Center for Replication document at:
This document provides information about limitations and known issues that you might encounter when you use IBM® Tivoli® Storage Productivity Center Version 5.2 and Tivoli Storage Productivity Center for Replication Version 5.2.
We recently released the new IBM Redbooks draft: Harnessing the Power of ProtecTIER and Tivoli Storage Manager. This book helps you plan, install, tailor, configure, and monitor ProtecTIER products with Tivoli Storage Manager. We provide you step-by-step guidance and tips to harness the performance and the power of the two products working together as a data protection and deduplication solution.
This book also explains the concepts and differences between ProtecTIER and Tivoli Storage Manager deduplication, as well as how to implement data replication from a ProtecTIER and Tivoli Storage Manager perspective.
Tivoli Storage Manager and ProtecTIER products are the highest scaling data protection and deduplication solutions in the industry and they work well together:
ProtecTIER incorporates special Tivoli Storage Manager parsing for more efficient deduplication of Tivoli Storage Manager data.
Tivoli Storage Manager capacity pricing now gives credit for ProtecTIER deduplication, via the Tivoli Storage Manager Suite for Unified Recovery ProtecTIER option.
As of Tivoli Storage Manager 6.3, an option has been included, Virtual Tape Library (VTL) awareness that significantly increases mount performance and number of virtual drives.
You can use both Tivoli Storage Manager and ProtecTIER deduplication in the same backup environment, but typically not with the same data.
Figure 1 shows the various aspects of data reduction using both ProtecTIER and Tivoli Storage Manager technologies.
Figure 1. Data reduction with ProtecTIER and Tivoli Storage Manager.
Setup and configuration involves three main components:
The Tivoli Storage Manager server and its operating system
The ProtecTIER device, as a storage component
The infrastructure that connects the Tivoli Storage Manager to the ProtecTIER; Network (LAN), or Storage Area Network (SAN). The ProtecTIER File System Interface (FSI) uses LAN, the ProtecTIER VTL uses SAN.
The most complex environments may have several instances of Tivoli Storage Manager servers each managing several library client and storage agents. This environment has both ProtecTIER VTL devices and ProtecTIER FSI shares, each being fully replicated in a many-to-many relationship between multiple cities or locations.
The simplest configuration can consist of only a Tivoli Storage Manager server, direct attached via a Fibre Channel cable to an IBM TS7620 ProtecTIER Deduplication Appliance Express (TS7620). The TS7620 is a self-contained virtualization solution that includes an embedded pre-configured disk storage repository and fast, reliable, and easy to deploy backup and recovery for mid-sized environments.
Figure 2 shows a fairly simple configuration with a few Tivoli Storage Manager backup servers and two node IBM System Storage TS7650G ProtecTIER Deduplication Gateway (TS7650G) VTL cluster, attached via SAN fabric. The ProtecTIER VTL is built in the the disk storage systems that are attached as back-end storage. Tivoli Storage Manager uses ProtecTIER devices to store and manage data from backup clients.
Figure 2. Tivoli Storage Manager environment with two node ProtecTIER TS7650G Gateway