Posts Tagged ‘EMC’

EMC World and IBM Edge 2013 Spotlight Mainframe Storage

May 6, 2013

Two major technology conferences this spring are converging on Las Vegas and each offers session tracks on mainframe storage. EMC World runs today through May 9, and IBM Edge 2013, June 10-14; each will bring enough expert material to divert mainframe storage managers from the gaming tables.

At neither show is the mainframe the primary focus, but considerable material still addresses mainframe storage. For example, EMC World, which opens today offers sessions like:

VMAX Performance: Mainframe Performance with Symmetrix VMAX & Enginuity 5876. Here’s how EMC describes it—Symmetrix VMAX 20K and VMAX 40K running Enginuity 5876 introduce several performance improvements and new features for the Mainframe, which can affect how customers deploy. DancingDinosaur reported on the introduction of the VMAX 40K here last year.

VMAX: What’s New for Mainframe Symmetrix Environments Plus an Update on the EMC & IBM Partnership.  Of particular interest to DancingDinosaur readers may be the details on how EMC develops IBM-compatible technology and EMC’s long-standing working relationship with IBM

DancingDinosaur will miss EMC World and be attending IBM Edge 2013 instead. Please join this blogger at Edge 2013; when not attending a session you can find me where bloggers congregate in the Social Media Lounge.

Here are some of the sessions that look particularly interesting:

IBM z/OS Storage Management Ecosystem Update—provides an overview of IBM’s strategy for managing the z/OS storage ecosystems.  Learn how the strategic z/OS storage management product, OMEGAMON XE for Storage, fits into the strategy and how the rest of the Tivoli z/OS Storage management portfolio works together to address common z/OS storage tasks and problem resolution. The session also promises to include a short review of Tivoli z/VM storage products.

IBM z/OS + DS8K Synergy—offers an overview of the IBM DS8000 architecture and its deep integration with IBM z/OS to deliver performance, high availability, optimization, and manageability. No other storage system has the unique integration with the IBM mainframe, according to IBM.  That becomes particularly apparent when you start looking at Flash storage.

Introduction to the TS7700 Virtualization Engine Grid for the Uninitiated or Those Needing a Refresher—intended to introduce attendees to the IBM TS7700 Virtualization Engine, a virtualized tape solution. This basic level discussion will start by explaining why tape virtualization came about, and then cover basic and advanced concepts, up through the latest enhancements.  If you are not already familiar with virtual tape you don’t want to miss this.

Retention management is an increasingly important and tricky topic these days, particularly as it ties in with compliance and even legal ediscovery. Edge 2013 offers two complementary sessions on retention management.

Untangling Retention Management under DFSMSrmm—DFSMS Removable Media Manager (DFSMSrmm) delivers a wide variety of retention controls for the z/OS tape resources it manages. Often the variety of options and the differences in how they behave can be confusing. The session promises to explain how and why DFSMSrmm does what it does so attendees can make the best decisions for their environment.

DFSMSrmm Best Practices, Features and New Stuff—DFSMS Removable Media Manager (DFSMSrmm) is one of the most regularly enhanced tape management systems in the market. Often, however, new features are overlooked. This session offers an overview of key product features that every DFSMSrmm data center should be taking full advantage of to properly safeguard their environments. In addition, it will detail several little-known product capabilities that can streamline administrator efficiency, allowing more time for other management activities.

Overall, IBM Edge 2013 will offer over 140 storage sessions, over 50 PureSystems sessions, more than 50 client case studies, and sessions on big data and analytics along with a full cloud track.

Full disclosure: this blogger’s trip to Edge 2013 and related DancingDinosaur posts are being underwritten by IBM.  However, the choice of content, ideas, and opinions …even the mention of EMC… are my own. Hope to see you at Edge 2013. Find me in  the Social Media Lounge.

EMC Introduces New Mainframe VTL

August 16, 2012

EMC introduced the high end DLm8000, the latest in its family of VTL products. This one is aimed for large enterprise mainframe environments and promises to ensure consistency of data at both production and recovery sites and provide the shortest possible RPO and RTO for critical recovery operations.

It is built around EMC VMAX enterprise storage and its SRDF replication and relies on synchronous replication to ensure immediate data consistency between the primary and target storage by writing the data simultaneously at each. Synchronous replication addresses the potential problem latency mismatch that occurs with the usual asynchronous replication, where a lag between writes to the primary and to the backup target storage can result in inconsistent data.

Usually this mismatch exists for a brief period. EMC suggests the issue, especially for large banks and financial firms—its key set of mainframe target customers—is much more serious. Large financial organizations with high transaction volume, EMC notes, have historically faced recovery challenges because their mainframe tape and DASD data at production and secondary sites were never fully in synch.  As such, recovery procedures often slowed until the differences between the two data sets were resolved, which slowed the resulting failover.  This indeed may be a real issue but for only a small number of companies, specifically those that need an RTO and RPO of just about zero.

EMC used the introduction of the DLm8000 to beat up tape backup in general. Physical tape transportation by third party records management companies, EMC notes, hinders recovery efforts by reducing what it refers to as the granularity of RPOs while dramatically increasing the RTO.  In addition, periodic lack of tape drive availability for batch processing and for archive and backup applications can impair SLAs, further increasing the risks and business impact associated with unplanned service interruptions. That has been long recognized, but, remember EMC is a company that sells disk, not tape storage, and ran a Tape Sucks campaign after its purchase of Data Domain. What would you expect them to say? 

The DLm8000 delivers throughput of up to 2.7 GB/s, which it claims is 2.5x the performance of its nearest competitor. DancingDinosaur can’t validate that claim, but EMC does have a novel approach to generating the throughput. The DLm8000 is packed with eight Bus-Tech engines (acquired in its acquisition of Bus-Tech in Nov. 2010) and it assigns two FICON connections to each engine for a total of 16 FICON ports cranking up the throughput. No surprise they can aggregate that level of throughput.

EMC has not announced pricing for the DLm8000. The device, however, is the top of its VTL lineup and VMAX enterprise storage tops its storage line. With high throughput and synchronous replication, this product isn’t going to be cheap. However, if you need near zero RPO and RTO then you have only a few choices.

Foremost among those choices should be the IBM TS7700 family, particularly the 7740 and the 7720. Both of these systems provide VTL connectivity. The TS7700 avoids the latency mismatch issue by using a buffer to get the most optimal write performance and then periodically synch primary and target data. “Synchronous as EMC does it for VTL is overkill,” says an IBM tape manager. The EMC approach essentially ignores the way mainframe tape has been optimized.

Among the other choices are the Oracle Virtual Storage Manager and Virtual Library Extension. Oracle uses StorageTek tape systems. The Oracle approach promises to improve tape drive operating efficiencies and lower TCO by optimizing tape drive and library resources through a disk-based virtual tape architecture. HDS also has a mainframe tape backup and VTL product that uses Luminex technology.

EMC is a disk storage company and its DLm8000 demonstrates that. When it comes to backup, however, mainframe shops are not completely averse to tape. Disk-oriented VTL has some advantages but don’t expect mainframe shops to completely abandon tape.

In breaking storage news, IBM today announced acquiring Texas Memory Systems (TMS), a long established (1978) Texas company that provides solid state memory to deliver significantly faster storage throughput and data access while consuming less power. TMS offers its memory as solid state disk (SSD) through its RamSan family of shared rackmount systems and Peripheral Component Interconnect Express (PCIe) cards. SSD may be expensive on a cost per gigabyte basis but it blows away spinning hard disk on a cost per IOPS. Expect to see IBM to use TMS’s SSD across its storage products as one of its key future storage initiatives, as described by Jai Menon, CTO and VP, Technical Strategy for IBM Systems and Technology Group (STG), at last June’s Storage Edge 2012 conference. BottomlineIT, DancingDinosaur’s sister blog, covered it here back in June. BTW, Edge 2013 already is scheduled for June 10-14 in Las Vegas.


May 23, 2012

EMC introduced the latest addition to its top mainframe Symmetrix storage, the VMAX 40K, which can scale to 4PB and is intended for extreme scalable environments. EMC claims the new device will deliver up to 3X more performance and more than 2X more usable capacity than any other offering in the industry. By configuring it with 2.5″ SAS drives and MLC (eMLC) Flash drives the device can also deliver the most densely packed storage.

The VMAX 40K, according to EMC, can store 60% more data than the Hitachi Virtual Storage Platform and 74% more than the IBM System Storage DS8000. The DS8000 today has a maximum capacity of 2.3PB. The Hitachi VSP tops out at 2.5PB.

If sheer capacity is the only issue, last summer word got out that IBM’s Almaden Lab delivered a 120PB array consisting of 200,000 SAS disk drives (rather than SATA) to ensure better performance for an unnamed client. Reports at that time also suggested the giant array was using IBM’s new General Parallel File System (GPFS), capable of indexing 10 billion files in just 43 minutes. The client and the use case have not been identified but the specs clearly suggest an extreme Big Data analytics situation.

For general enterprise computing as done by mainframe shops there is more to storage than just sheer capacity.  For zEnterprise shops, the issue is how well optimized the EMC storage is for other parts of the System z.  The zEnterprise already is highly optimized across its memory, processors, firmware, and networks as well as DS8000 storage.

As of the first quarter of this year IBM reports that the DS8000 supported the following capabilities that the EMC Symmetrix does not:

  • Dynamic Volume Expansion
  • Basic Hyper Swap
  • zHPF—QSAM, BSAM, BPAM, format writes, DB2 list prefetch cache optimization
  • Sub-volume tiering for CKD volumes
  • zDAC performance optimization
  • IMS WADS enhanced performance
  • Workload Manager I/O performance support
  • Metro Mirror suspension –message aggregation

If these capabilities are used in your data center, then the new EMC storage won’t work without extra effort on your part no matter how much capacity it delivers.

The VMAX 40K, however, does offer some nifty features, such as new Federated Tiered Storage (FTS) for VMAX through which external arrays can be used either as capacity pools for FAST VP (Fully Automated Storage Tiering for Virtual Pools) or managed as pass-through devices. FAST VP also now supports the System z and IBM i servers. Of course, IBM already delivers such storage tiering through EasyTier.

It is hard to assess how the VMAX 40K will work in the mainframe environment based on the spec sheet.  And without pricing and workload benchmark data it is not possible to make an accurate assessment.

Still EMC rivals are decidedly cool. To HP, for instance, the VMAX 40K looks like a typical EMC midlife kicker; nothing surprising here, said an HP manager. He added that this does not change the fact that the EMC architecture is aging, and it doesn’t fundamentally change the economics of VMAX. HP, he notes, is beating VMAX head to head more and more with 3PAR based on its architectural advantage and newer technology. The HP mainframe storage is a Hitachi box, the P9500 XP Disk Array.

An IBMer, similarly, described the VMAX 40K as a business-as-usual, next-generation disk system announcement with new hardware and a few new functions.  It still doesn’t appear to address the unsupported z capabilities noted above. The new EMC storage doesn’t do enough to offset advantages DS8000 offers mainframe shops today.

The introduction of the VMAX 40K, however, raises a larger question.  In an increasingly scale-out world (as opposed to scale-up), do enterprises really need to load multi-petabytes of storage into a single frame?  IBM recently boosted its SmartCloud offerings for enterprise computing.  Will IBM put the zEnterprise and DS8000 storage up there too?

Virtualized Storage Comes to the zEnterprise/zBX

March 27, 2012

Huh? Mainframe storage has been virtualized for decades. In a presentation at the latest SHARE gathering, however, Dave Lytle from Brocade and Bill Smith from Hitachi Data Systems gave a joint presentation about bringing virtual storage to the z.

In the presentation they explained how the Brocade DCX 8510 Backbone switch combined with the Hitachi Virtual Storage Platform (VSP) provide an alternative for mainframe-attached storage environments.  They aren’t suggesting you replace the workhorse DS8000 mainframe storage but, rather, augment it.

They call for an open virtualized storage infrastructure that makes it possible to deploy lower cost storage devices in conjunction with automated data tiering to lower the overall total cost of storage.  The cost savings result from shifting more of the storage to slower but less expensive open systems storage through the Hitachi Virtual Storage Platform (VSP).  When a piece of data needs the faster, more costly primary z storage, the automation brings it back. Without the automation, this would be a slow, error-prone operation that almost nobody would bother with.

The promise, say Lytle and Smith, is faster deployment of new applications and non-disruptive re-deployment of storage assets between mainframe and open system environments. This kind of dynamic tiering already has gained traction in the open systems world.  Even the big mainframe storage players, IBM and EMC, have products there. IBM has the automated System Storage Easy Tier offering and EMC brings its Fully Automated Storage Tiering (FAST) product.

In addition to the HDS VSP offering the approach described by Lytle and Smith is built around a new 16 Gbps Fibre Channel Brocade DCX 8510 Backbones switching infrastructure. According to Brocade, they match the industry’s fastest and most scalable System z mainframes with the highest-performing and most reliable FICON infrastructure to maximize consolidation and virtualization of traditional mainframe and emerging Linux and Windows workloads. All the while they simplifying fabric management for FICON and Fibre Channel intermix environments. The Brocade DCX 8510 directors have been qualified for mainframe environments, allowing enterprises to fully exploit the capabilities of the IBM zEnterprise FICON infrastructure.

The reference to traditional mainframe and emerging Linux and Windows workloads sounds like the zEnterprise/zBX combination. Basically, you should be able to connect your lower cost, lower performing open system storage for use with your zBX Windows blades and manage it all through the z.  DancingDinosaur sees some definite cost, efficiency, and convenience advantages in that alone while providing one more reason for organizations to consider the zBX with Windows blades.

The Brocade and HDS products do boast some impressive capabilities.  The Brocade FICON product offers a simultaneous send-and-receive 16Gbps line rate on all chassis ports concurrently (no blocking), five-nines (99.999%) availability, and 4x improvement in energy efficiency over competitive switches.

The HDS VSP is fully mainframe compatible. It provides frontend and backend directors, cache, and processors to handle time-sensitive processing tasks and supports multiple types of disk drive (SSD, SAS and SATA) to meet a variety of performance and cost requirements. The virtual storage directors and cache combine to deliver performance throughput of over 1 million IOP/s with full FICON support.

The issue of connecting zEnterprise and open systems storage for the purposes of tiering is just ramping up.  Lytle and Smith report plans already underway for the next SHARE gathering (Aug. 5-10, 2012) in Anaheim, CA.  The MVS group at SHARE apparently is preparing to bring IBM, EMC, and HDS together to talk about tiering on the mainframe.

Hot Summer for System z Storage

September 5, 2011

Storage will become increasingly important in mainframe shops, especially as they carve out a role in virtualized, private clouds, and August will go down as a hot month for mainframe storage.  EMC kicked off August by announcing a new virtual tape library for IBM z/OS environments followed a few days later by announcing new virtual storage capabilities for its Symmetrix VMAX for z/VM environments.

IBM jumped in just this past week by revealing various storage-related research initiatives for archiving, scale out file systems, storage clouds, SSD-based systems, and more. The company, however, has been introducing new storage, much of it applicable to the mainframe, all year.

EMC clearly plans to target IBM in the mainframe storage market. Early in August it introduced a new mainframe disk library it described as the first integrated solution for all tape use cases. The new disk library takes advantage of features in Data Domain, EMC’s deduplication line, and EMC VNX (unified storage for block, file, and object-based data).

The disk library, the DLm6000, enables mainframe users to minimize their storage and replication costs and dramatically improve their disaster recovery capabilities. EMC says it will address the full range of mainframe tape workloads with a single, consolidated all-disk system. By matching different workloads to the most appropriate storage, the DLm6000 also promises to maximize system performance and accelerate data retrievals and backup and recovery times.

EMC also announced new software for its Symmetrix VMAX family of storage systems, which will enhance virtual data center and cloud storage capabilities. Of particular interest is the new version of EMC AutoSwap software, which now supports z/VM environments, effectively expanding Symmetrix VMAX-based solutions for all of the major virtual machine operating systems. The new EMC GDDR (Geographically Dispersed Disaster Restart) for z/VM allows continuous availability and improved protection for virtualized mainframe environments.

IBM hasn’t exactly been twiddling its thumbs when it comes to enterprise storage. It enhanced DS8700 and DS8800 storage systems as well as SAN Volume Controller (SVC). At a recent storage research briefing IBM identified initiatives in both bit and logical data preservation and other enhancements to archiving. Other initiatives are looking at data density and data retention. A 50-year retention period is the latest goal; 100 years shouldn’t be far off. Similarly, IBM is aiming to pack 1 petabyte (PB) of data into a 1u slot; guess how much fits in a standard 40u rack. Behind much of IBM’s latest storage initiatives is its General Parallel File System (GPFS)

Maybe the most interesting IBM storage announcement this summer was XIV Gen 3. XIV focuses on storage for distributed systems but connects to the System z through z/VM via FC switches or SVC. XIV storage also can be accessed by z/VM guests through guest-attached FCP subchannels provided the applicable FCP multi-path driver is available. XIV should be of most interest with a heterogeneous Linux environment including Linux on z.

XIV may be IBM’s most innovative storage. It’s fully autonomic, meaning it can pretty much run itself. It is based on a grid design that connects a set of modules, each containing a powerful processor, memory, and storage. Multiple modules connect to create a seamless scalable storage grid. This design delivers predictable, sustained high performance storage with little or no intervention on the part the staff. Plus, it brings a slew of high reliability and availability capabilities. It also scales in near linear fashion: adding an XIV module increases storage capacity along with more CPU and RAM. Automatic rebalancing ensures load balance is maintained regardless of adding, deleting, or resizing volumes after new disk/module additions and even after a system component failure or during rebuild.

Watch DancingDinosaur for more enterprise storage info in the coming months.

Brick and mortar IBM commitment to System z

May 17, 2010

Do you worry about the future of the System z and mainframes in general? I did until I saw an IBM press release in April about opening a new 56,000 sq. ft., $30 million manufacturing facility in Poughkeepsie to produce the next generation of System z mainframes and high-end Power Systems servers. By the time that facility is obsolete and ready to be shuttered, I should be long gone.

With IBM making that kind of investment in bricks and mortar on behalf of the System z, the company clearly expects the z to hang around for many more years. I don’t know what the depreciation schedule is on a new high tech manufacturing facility, but it must be longer than the usual 3-5 years for IT investments, lots longer.

Yet, there has been surprisingly little comment in the press about the announcement. Instead, there continues the stream of mainframe-is-dead pieces. The most recent, reported by Joe Clabby for Pund-IT, recounted Gartner’s advice to abandon the z in favor of x86-based servers. But as Joe pointed out, Gartner had some conflicts of interest, leaving them as anything but an unbiased advisor when it comes to mainframe computing.

The latest generation of Intel and AMD multi-core x86-based processors has generated a flood of articles predicting that the x86 architecture will dominate enterprise computing going forward. Last week at EMC World, EMC CEO Joe Tucci repeatedly declared the x86 architecture the wave of the future and would be the processor EMC would base all its products on now and in the future. The x86 processor was the future not only for EMC but everyone, everywhere.

Tucci obviously hadn’t noticed what Apple is doing. In January Apple brought out its own CPU, from a chip manufacturer it had previously acquired, to power the iPOD and iPAD. Sorry Joe, given the number of those devices Apple is selling there will be a considerable chunk of the world that does sophisticated computing and communications (and video and audio…) without an x86 processor.

The x86 architecture clearly isn’t the only game in town. In addition to Apple’s A4, IBM revved its POWER chip architecture and introduced systems based on the new POWER7 chip. These AIX and Linux machines are putting up impressive benchmarks. Even Sun/Oracle may be bringing out a new SPARC chip. Although the company appears to be somewhat vague about that if it wants to stay in the large enterprise computing game it will have to come up with a new SPARC chip or IBM and HP will continue to pick off its customers and VARs.

And then there is the next generation System z, dubbed the Hybrid z in briefings earlier this year. It apparently will be based on a highly optimized POWER7 multi-core architecture too. The mainframe is not likely to cede any performance to the new x86 processors, whether from Intel or AMD.

As IBM stated in its new factory announcement, “The facility is designed to handle the next generation of systems and [deliver] the capacity and flexibility to manufacture future products. The first products for customers are expected to roll off the assembly line later this year.” Just in time for the hybrid System z.


Get every new post delivered to your Inbox.

Join 735 other followers

%d bloggers like this: