Wrapping up my coverage of the annual [2010 System Storage Technical University], I attended what might be perhaps the best session of the conference. Jim Nolting, IBM Semiconductor Manufacturing Engineer, presented the new IBM zEnterprise mainframe, "A New Dimension in Computing", under the Federal track.
The zEnterprises debunks the "one processor fits all" myth. For some I/O-intensive workloads, the mainframe continues to be the most cost-effective platform. However, there are other workloads where a memory-rich Intel or AMD x86 instance might be the best fit, and yet other workloads where the high number of parallel threads of reduced instruction set computing [RISC] such as IBM's POWER7 processor is more cost-effective. The IBM zEnterprise combines all three processor types into a single system, so that you can now run each workload on the processor that is optimized for that workload.
- IBM zEnterprise z196 Central Processing Complex (CPC)
Let's start with the new mainframe z196 central processing complex (CPC). Many thought this would be called the z11, but that didn't happen. Basically, the z196 machine has a maximum 96 cores versus z10's 64 core maximum, and each core runs 5.2GHz instead of z10's cores running at 4.7GHz. It is available in air-cooled and water-cooled models. The primary operating system that runs on this is called "z/OS", which when used with its integrated UNIX System Services subsystem, is fully UNIX-certified. The z196 server can also run z/VM, z/VSE, z/TPF and Linux on z, which is just Linux recompiled for the z/Architecture chip set. In my June 2008 post [Yes, Jon, there is a mainframe that can help replace 1500 servers], I mentioned the z10 mainframe had a top speed of nearly 30,000 MIPS (Million Instructions per Second). The new z196 machine can do 50,000 MIPS, a 60 percent increase!
(Update: Back in 2007, IBM and Sun mutually supported [OpenSolaris on an IBM System z mainframe]. Unfortunately, after Oracle acquired Sun, the OpenSolaris Governing Board has [grown uneasy over Oracle's silence] about the future of OpenSolaris on any platform. The OpenSolaris [download site] identifies 2009.06 as the latest release, but only for x86 and SPARC chip sets. Apparently, the 2010.03 release expected five months ago in March has slipped. Now it looks official that [OpenSolaris is Dead].)
The z196 runs a hypervisor called PR/SM that allows the box to be divided into dozens of logical partitions (LPAR), and the z/VM operating system can also act as a hypervisor running hundreds or thousands of guest OS images. Each core can be assigned a specialty engine "personality": GP for general processor, IFL for z/VM and Linux, zAAP for Java and XML processing, and zIIP for database, communications and remote disk mirroring. Like the z9 and z10, the z196 can attach to external disk and tape storage via ESCON, FICON or FCP protocols, and through NFS via 1GbE and 10GbE Ethernet.
- IBM zEnterprise BladeCenter Extension (zBX)
There is a new frame called the zBX that basically holds two IBM BladeCenter chassis, each capable of 14 blades, so total of 28 blades per zBX frame. For now, only select blade servers are supported inside, but IBM plans to expand this to include more as testing continues. The POWER-based blades can run native AIX, IBM's other UNIX operating system, and the x86-based blades can run Linux-x86 workloads, for example. Each of these blade servers can run a single OS natively, or run a hypervisor to have multiple guest OS images. IBM plans to look into running other POWER and x86-based operating systems in the future.
If you are already familiar with IBM's BladeCenter, then you can skip this paragraph. Basically, you have a chassis that holds 14 blades connected to a "mid-plane". On the back of the chassis, you have hot-swappable modules that snap into the other side of the mid-plane. There are modules for FCP, FCoE and Ethernet connectivity, which allows blades to talk to each other, as well as external storage. BladeCenter Management modules serve as both the service processor as well as the keyboard, video and mouse Local Console Manager (LCM). All of the IBM storage options available to IBM BladeCenter apply to zBX as well.
Besides general purpose blades, IBM will offer "accelerator" blades that will offload work from the z196. For example, let's say an OLAP-style query is issued via SQL to DB2 on z/OS. In the process of parsing the complicated query, it creates a Materialized Query Table (MQT) to temporarily hold some data. This MQT contains just the columnar data required, which can then be transferred to a set of blade servers known as the Smart Analytics Optimizer (SAO), then processes the request and sends the results back. The Smart Analytics Optimizer comes in various sizes, from small (7 blades) to extra large (56 blades, 28 in each of two zBX frames). A 14-blade configuration can hold about 1TB of compressed DB2 data in memory for processing.
- IBM zEnterprise Unified Resource Manager
You can have up to eight z196 machines and up to four zBX frames connected together into a monstrously large system. There are two internal networks. The Inter-ensemble data network (IEDN) is a 10GbE that connects all the OS images together, and can be further subdivided into separate virtual LANs (VLAN). The Inter-node management network (INMN) is a 1000 Mbps Base-T Ethernet that connects all the host servers together to be managed under a single pane of glass known as the Unified Resource Manager. It is based on IBM Systems Director.
By integrating service management, the Unified Resource Manager can handle Operations, Energy Management, Hypervisor Management, Virtual Server Lifecycle Management, Platform Performance Management, and Network Management, all from one place.
- IBM Rational Developer for System z Unit Test (RDz)
But what about developers and testers, such as those Independent Software Vendors (ISV) that produce mainframe software. How can IBM make their lives easier?
Phil Smith on z/Journal provides a history of [IBM Mainframe Emulation]. Back in 2007, three emulation options were in use in various shops:
- Open Mainframe, from Platform Solutions, Inc. (PSI)
- FLEX-ES, from Fundamental Software, Inc.
- Hercules, which is an open source package
None of these are viable options today. Nobody wanted to pay IBM for its Intellectual Property on the z/Architecture or license the use of the z/OS operating system. To fill the void, IBM put out an officially-supported emulation environment called IBM System z Professional Development Tool (zPDT) available to IBM employees, IBM Business Partners and ISVs that register through IBM Partnerworld. To help out developers and testers who work at clients that run mainframes, IBM now offers IBM Rational Developer for System z Unit Test, which is a modified version of zPDT that can run on a x86-based laptop or shared IBM System x server. Based on the open source [Eclipse IDE], the RDz emulates GP, IFL, zAAP and zIIP engines on a Linux-x86 base. A four-core x86 server can emulate a 3-engine mainframe.
With RDz, a developer can write code, compile and unit test all without consuming any mainframe MIPS. The interface is similar to Rational Application Developer (RAD), and so similar skills, tools and interfaces used to write Java, C/C++ and Fortran code can also be used for JCL, CICS, IMS, COBOL and PL/I on the mainframe. An IBM study ["Benchmarking IDE Efficiency"] found that developers using RDz were 30 percent more productive than using native z/OS ISPF. (I mention the use of RAD in my post [Three Things to do on the IBM Cloud]).
What does this all mean for the IT industry? First, the zEnterprise is perfectly positioned for [three-tier architecture] applications. A typical example could be a client-facing web-server on x86, talking to business logic running on POWER7, which in turn talks to database on z/OS in the z196 mainframe. Second, the zEnterprise is well-positioned for government agencies looking to modernize their operations and significantly reduce costs, corporations looking to consolidate data centers, and service providers looking to deploy public cloud offerings. Third, IBM storage is a great fit for the zEnterprise, with the IBM DS8000 series, XIV, SONAS and Information Archive accessible from both z196 and zBX servers.
To learn more, see the [12-page brochure] or review the collection of [IBM Redbooks]. Check out the [IBM Conferences schedule] for an event near you. Next year, the IBM Storage University will be held July 18-22, 2011 in Orlando, Flordia.
technorati tags: IBM, Technical University, zEnterprise, x86, POWER7, RISC, z/OS, Linux, AIX, OpenSolaris, Oracle, FICON, NFS, z196, zBX, DB2, SAO, IEDN, INMN, RDz, ISV, Eclipse, Cloud Computing
Fellow master inventor and blogger Barry Whyte (IBM) recounts the past 20 years of history in IT storage from his perspective in a series of blog posts. They are certainly worth a read:
In his last post in this series, he mentions that the amazingly successful IBM SAN Volume Controller was part of a set of projects:
"IBM was looking for "new horizon" projects to fund at the time, and three such projects were proposed and created the "Storage Software Group". Those three projects became know externally as TPC, (TotalStorage Productivity Center), SanFS (SAN File System - oh how this was just 5 years too early) and SVC (SAN Volume Controller). The fact that two out of the three of them still exist today is actually pretty good. All of these products came out of research, and its a sad state of affairs when research teams are measured against the percentage of the projects they work on, versus those that turn into revenue generating streams."
But this raises the question: Was SAN File System just five years too early?
IBM classifies products into three "horizons"; Horizon-1 for well-established mature products, Horizon-2 was for recently launched products, and Horizon-3 was for emerging business opportunities (EBO). Since I had some involvement with these other projects, I thought I would help fill out some of this history from my perspective.
Back in 2000, IBM executive [Linda Sanford] was in charge of IBM storage business and presented that IBM Research was working on the concept of "Storage Tank" which would hold Petabytes of data accessible to mainframes and distributed servers.
In 2001, I was the lead architect of DFSMS for the IBM z/OS operating system for mainframes, and was asked to be lead architect for the new "Horizon 3" project to be called IBM TotalStorage Productivity Center (TPC), which has since been renamed to IBM Tivoli Storage Productivity Center.
In 2002, I was asked to lead a team to port the "SANfs client" for SAN File System from Linux-x86 over to Linux on System z. How easy or difficult to port any code depends on how well it was written with the intent to be ported, and porting the "proof-of-concept" level code proved a bit too challenging for my team of relative new-hires. Once code written by research scientists is sufficiently complete to demonstrate proof of concept, it should be entirely discarded and written from scratch by professional software engineers that follow proper development and documentation procedures. We reminded management of this, and they decided not to make the necessary investment to add Linux on System z as a supported operating system for SAN file system.
In 2003, IBM launched Productivity Center, SAN File System and SAN Volume Controller. These would be lumped together with Horizon-1 product IBM Tivoli Storage Manager and the four products were promoted together as the inappropriately-named [TotalStorage Open Software Family]. We actually had long meetings debating whether SAN Volume Controller was hardware or software. While it is true that most of the features and functions of SAN Volume Controller is driven by its software, it was never packaged as a software-only offering.
The SAN File System was the productized version of the "Storage Tank" research project. While the SAN Volume Controller used industry standard Fibre Channel Protocol (FCP) to allow support of a variety of operating system clients, the SAN File System required an installed "client" that was only available initially on AIX and Linux-x86. In keeping with the "open" concept, an "open source reference client" was made available so that the folks at Hewlett-Packard, Sun Microsystems and Microsoft could port this over to their respective HP-UX, Solaris and Windows operating systems. Not surprisingly, none were willing to voluntarily add yet another file system to their testing efforts.
Barry argues that SANfs was five years ahead of its time. SAN File System tried to bring policy-based management for information, which has been part of DFSMS for z/OS since the 1980s, over to distributed operating systems. The problem is that mainframe people who understand and appreciate the benefits of policy-based management already had it, and non-mainframe couldn't understand the benefits of something they have managed to survive without.
(Every time I see VMware presented as a new or clever idea, I have to remind people that this x86-based hypervisor basically implements the mainframe concept of server virtualization introduced by IBM in the 1970s. IBM is the leading reseller of VMware, and supports other server virtualization solutions including Linux KVM, Xen, Hyper-V and PowerVM.)
To address the various concerns about SAN File System, the proof-of-concept code from IBM Research was withdrawn from marketing, and new fresh code implementing these concepts were integrated into IBM's existing General Parallel File System (GPFS). This software would then be packaged with a server hardware cluster, exporting global file spaces with broad operating system reach. Initially offered as IBM Scale-out File Services (SoFS) service offering, this was later re-packaged as an appliance, the IBM Scale-Out Network Attached Storage (SONAS) product, and as IBM Smart Business Storage Cloud (SBSC) cloud storage offering. These now offer clustered NAS storage using the industry standard NFS and CIFS clients that nearly all operating systems already have.
Today, these former Horizon-1 products are now Horizon-2 and Horizon-3. They have evolved. Tivoli Storage Productivity Center, GPFS and SAN Volume Controller are all market leaders in their respective areas.
technorati tags: IBM, Barry Whyte, TPC, SANfs, SVC, EBO, Storage Tank, SoFS, SONAS, SBSC, cloud storage, NAS, storage, NFS, CIFS, HTTP
Am I dreaming? On his Storagezilla blog, fellow blogger Mark Twomey (EMC) brags about EMC's standard benchmark results, in his post titled [Love Life. Love CIFS.]. Here is my take:
- A Full 180 degree reversal
For the past several years, EMC bloggers have argued, both in comments on this blog, and on their own blogs, that standard benchmarks are useless and should not be used to influence purchase decisions. While we all agree that "your mileage may vary", I find standard benchmarks are useful as part of an overall approach in comparing and selecting which vendors to work with, and which architectures or solution approaches to adopt, and which products or services to deploy. I am glad to see that EMC has finally joined the rest of the planet on this. I find it funny this reversal sounds a lot like their reversal from "Tape is Dead" to "What? We never said tape was dead!"
- Impressive CIFS Results
The Standard Performance Evaluation Corporation (SPEC) has developed a series of NFS benchmarks, the latest, [SPECsfs2008] added support for CIFS. So, on the CIFS side, EMC's benchmarks compare favorably against previous CIFS tests from other vendors.
On the NFS side, however, EMC is still behind Avere, BlueArc, Exanet, and IBM/NetApp. For example, EMC's combination of Celerra gateways in front of V-Max disk systems resulted in 110,621 OPS with overall response time of 2.32 milliseconds. By comparison, the IBM N series N7900 (tested by NetApp under their own brand, FAS6080) was able to do 120,011 OPS with 1.95 msec response time.
Even though Sun invented the NFS protocol in the early 1980s, they take an EMC-like approach against standard benchmarks to measure it. Last year, fellow blogger Bryan Cantrill (Sun) gives his [Eulogy for a Benchmark]. I was going to make points about this, but fellow blogger Mike Eisler (NetApp) [already took care of it]. We can all learn from this. Companies that don't believe in standard benchmarks can either reverse course (as EMC has done), or continue their downhill decline until they are acquired by someone else.
(My condolences to those at Sun getting laid off. Those of you who hire on with IBM can get re-united with your former StorageTek buddies! Back then, StorageTek people left Sun in droves, knowing that Sun didn't understand the mainframe tape marketplace that StorageTek focused on. Likewise, many question how well Oracle will understand Sun's hardware business in servers and storage.)
- What's in a Protocol?
Both CIFS and NFS have been around for decades, and comparisons can sometimes sound like religious debates. Traditionally, CIFS was used to share files between Windows systems, and NFS for Linux and UNIX platforms. However, Windows can also handle NFS, while Linux and UNIX systems can use CIFS. If you are using a recent level of VMware, you can use either NFS or CIFS as an alternative to Fibre Channel SAN to store your external disk VMDK files.
- The Bigger Picture
There is a significant shift going on from traditional database repositories to unstructured file content. Today, as much as [80 percent of data is unstructured]. Shipments this year are expected to grow 60 percent for file-based storage, and only 15 percent for block-based storage. With the focus on private and public clouds, NAS solutions will be the battleground for 2010.
So, I am glad to see EMC starting to cite standard benchmarks. Hopefully, SPC-1 and SPC-2 benchmarks are forthcoming?
technorati tags: IBM, tape, EMC, Mark+Twomey, Storagezilla, CIFS, NFS, Celerra, V-Max, N7900, VMware, VMDK, Sun, Oracle, StorageTek, tape, benchmarks, SPEC, SPECsfs, SPECsfs2008, SPC, SPC-1, SPC-2, NetApp, FAS6080
This week I am in Orlando, Florida for the IBM Edge conference. This is the last day, so it ends early for people who want to get home to their
datacenters (er.. families) for the weekend.
- How Real-Time Compression Can Maximize Storage Efficiency for Production Applications
This was a split session with two speakers. First, Ian Rimmer, Senior IT Engineer and Architect at iBurst, presented their experience with the IBM Real-Time Compression Appliance in front of NetApp NAS storage arrays. Second, Jerry Haigh, IBM offering manager for IBM System Storage, presented the new Real-Time compression feature announced this week on IBM SAN Volume Controller (SVC) and Storwize V7000.
iBurst is the #1 Wireless Telecom for South Africa. The also offer cable broadband and VOIP. They have 200 employees servicing 120,000 subscriber/households. They need to keep five years' worth of text files, and have chosen real-time compression of their NAS storage. This was before IBM acquired the Storwize company, as they have been using it for the past six years.
The monetary savings from compression was used to purchase Performance Accelerator Modules (PAM) cards for their NetApp NAS gear, which benefit from the compression (more data stored in SSD to improve performance).
For backup, they use NDMP with Symantec NetBackup that keeps data in its compressed form as it is written to tape. They have an IBM TS3100 library with LTO tape as the backup repository.
Jerry Haigh presented Real-Time compression for primary disk data. Unlike the competition, this is designed to be used with primary data, including databases, and does this real-time, not post-process. In some performance tests, DB2 compressed on 48 drives out-performed the same data uncompressed on 96 drives. In another test focused on VMware Vmark benchmark, the compressed data was able to be same or better performance as uncompressed. In a third test with SVC virtualizing XIV running Oracle ORION test, the Oracle databases compressed 50 to 64 percent, and had better performance.
For those who already have SVC or Storwize V7000, consider a 45-day trial to check out compression for yourself.
- NAS File Systems: Access and Authentication
Mark Taylor, IBM Technical Specialist for SONAS, N series and Storwize V7000 Unified, presented the nuances of authentication and authorization for NAS file systems. The differences between these two are:
- Authentication - Yes, you are who you are.
- Authorization - Yes, you are permitted to do what you are trying to do
(Prior to working with SONAS, my only experience with access and authentication in NAS was setting up my LAN at home, which I have connecting my Mac, Linux and Windows machines. I have both N series and SONAS at the IBM Executive Briefing Center in Tucson, Arizona, so I know first-hand how complicated NAS access and authentication systems can be.
A few months ago, I taught "Intro to NAS" as one of my topics at the Top Gun class in Argentina and Brazil. Several of the students had mentioned they thought they knew NAS solutions but had not realized all the technical issues with access and authentication that I discussed in my presentation.)
Mark explained the differences between Windows NTFS-style System identifiers (SID), versus UNIX-style user and group identifiers (UID, GID). For NAS solutions that support both CIFS and NFS, there are four options:
- Microsoft Active Director (AD) extended with Identity Management for UNIX, formerly known as Services for UNIX (SFU). AD servers normally store SID information, but the extensions add extra columns to hold UID/GID mappings.
- AD with Network Information Service (NIS) server. The problem with this approach is that AD and NIS are separate databases, and you need to coordinate updates to them, and their backups.
- Lightweight Directory Access Protocol (LDAP) with SAMBA extensions. LDAP holds UID/GID information, and the SAMBA extensions adds extra columns to hold SID mapping.
- Local mapping. The dangerous part of local mapping is that the storage admin is also the security admin, and you may want different people doing these roles.
Of these four methods, Mark recommends the first and third as best practices for multi-protocol authentication.
|N series||NTFS-style||SID-to-UID mapping,|
|SONAS and Storwize V7000||SID-to-UID/GID mapping, NFS v4 ACLs||NFS v4 ACLs|
Mark then explained how NFS v4 ACLs work, basically an ordered collection of "Access Control Elements" or ACEs. Each ACE on the ACL may "allow" or "deny" the request. You want to avoid "Inheritance" as that can cause problems and unxpected results.
That's it folks. Next week, I am spending time with my research buddies at the Almaden Research Center near San Jose, California, and then it is off to Moscow, Russia to kick off a series of IBM events called "Edge Comes to You" (ECTY).
The ECTY conferences will be a smaller subset of the Edge conference here in Orlando, but offered in other countries for those who were unable to travel to the United States.
technorati tags: IBM, Edge2012, Real-Time Compression, NetApp, SVC, Storwize V7000, iBurst, PAM, NDMP, SONAS, Active Directory, NIS, LDAP, SAMBA, Acess Control Lists, NFS, CIFS, ECTY
Continuing my coverage of the [IBM System x and System Storage Technical Symposium], I thought I would start with some photos. I took these with cell phone, and without realizing how much it would cost, uploaded them to Flickr at international data roaming rates. Oops!
Here are some of the banners used at the conference. Each break-out session room was outfitted with a "Presentation Briefcase" that had everything a speaker might need, including power plug adapters and dry-erase markers for the whiteboard. What a clever idea!
Here is a recap of the last and final day 3:
- Understanding IBM's Storage Encryption Options
Special thanks to Jack Arnold for providing me his deck for this presentation. I presented IBM's leadership in encryption standards, including the [OASIS Key Management Interoperability Protocol] that allows many software and hardware vendors to interoperate. IBM offers the IBM Tivoli Key Lifecycle Manager (TKLM v2) for Windows, Linux, AIX and Solaris operating systems, and the IBM Security Key Lifecycle Manager (v1.1) for z/OS.
Encrypting data at rest can be done several ways, by the application at the host server, in a SAN-based switch, or at the storage system itself. I presented how IBM Tivoli Storage Manager, the IBM SAN32B-E4 SAN switch, and various disk and tape devices accomplish this level of protection.
- NAS @ IBM
Rich Swain, IBM Field Technical Sales Specialist for NAS solutions, provided an overview of IBM's NAS strategy and the three products: Scale-Out Network Attached Storage (SONAS), Storwize V7000 Unified, and N series.
- IBM System Networking Convergence CEE/DCB/FCoE
Mike Easterly, IBM Global Field Marketing Manager for IBM System Networking, presented on Network convergence. He wants to emphasize that "Convergence is not just FCoE!" rather it is bringing together FCoE with iSCSI, CIFS, NFS and other Ethernet-based protocols. In his view, "All roads lead to Ethernet!"
There are a lot new standards that didn't exist a few years ago, such as PCI-SIG's Single Root I/O Virtualization [SR-IOV], Virtual Ethernet Port Aggregator [VEPA], and [VN-Tag], Data Center Bridging [DCB], Layer-2 Multipath [L2MP], and my favorite: Transparent Interconnect of Lots of Links [TRILL].
Last year, IBM acquired Blade Network Technologies (BNT), which was the company that made IBM BladeCenter's Advanced Management Module (AMM) and BladeCenter Open Fabric Manager (BOFM). BNT also makes Ethernet switches, so it has been merged with IBM's System Storage team, forming the IBM System Storage and Networking team. Most of today's 10GbE is either fiber optic, Direct Attach Copper (DAC) that supports up to 8.5 meter length cables, or 10GBASE-T which provides longer distances of twisted pair. IBM's DS3500 uses 10GBASE-T for its 10GbE iSCSI support.
Last month, IBM announced 40GbE! I missed that one. The IT industry also expects to deliver 100GbE by 2013. For now, these will be used as up-links between other switches, as most servers don't have the capacity to pump this much data through their buses. With 40GbE and 100GbE, it would be hard to ignore Ethernet as the common network standard to drive convergence.
Fibre Channel, such as FCP and FICON, are still the dominant storage networking technology, but this is expected to peak around 2013 and start declining thereafter in favor of iSCSI, NAS and FCoE technologies. Already the enhancements like "Priority-based Flow Control" made to Ethernet to support FCoE have also helped out iSCSI and NAS deployments as well.
The iSCSI protocol is being used with Microsoft Exchange, PXE Boot, Server virtualization hypervisors like VMware and Hyper-V, as well as large Database and OLTP. IBM's SVC, Storwize V7000, XIV, DS5000, DS3500 and N series all support iSCSI.
IBM's [RackSwitch] family of products can help offload traffic at $500 per port, compared to traditional $2000 per port for IBM SAN32B or Cisco Nexus5000 converged top-of-rack switches.
IBM's System Networking strategy has two parts. For Ethernet, offer its own IBM System Networking product line as well as continue its partnership with Juniper Networks. For Fibre Channel and FCoE, continue strategic partnerships with Brocade and Cisco. IBM will lead the industry, help drive open standards to adopt Converged Enhanced Ethernet (CEE), provide flexibility and validate data center networking solutions that work end-to-end.
Well, that marks the end of this week in Auckland, New Zealand. I am off now to Melbourne, Australia for the [IBM System Storage Technical Symposium] next week.
technorati tags: IBM, EKM, TKLM, SKLM, SONAS, SAN32B-E4, Storwize+V7000, CEE, DCB, FCoE, iSCSI, NAS, CIFS, NFS, Ethernet, PCI-SIG, SR-IOV, VEPA, VN-Tag, DCB, L2MP, TRILL, BNT, BOFM, AMM, DAC, 10GBASE-T, DS3500, 40GbE, , FCP, FICON, PXE, SVC, Cisco, Nexus5000, RackSwitch