Continuing coverage of my week in Washington DC for the annual [2010 System Storage Technical University], I attended several XIV sessions throughout the week. There were many XIV sessions. I could not attend all of them. Jack Arnold, one of my colleagues at the IBM Tucson Executive Briefing Center, often presents XIV to clients and Business Partners. He covered all the basics of XIV architecture, configuration, and features like snapshots and migration. Carlos Lizarralde presented "Solving VMware Challenges with XIV". Ola Mayer presented "XIV Active Data Migration and Disaster Recovery".
Here is my quick recap of two in particular that I attended:
- XIV Client Success Stories - Randy Arseneau
Randy reported that IBM had its best quarter ever for the XIV, reflecting an unexpected surge shortly after my blog post debunking the DDF myth last April. He presented successful case studies of client deployments. Many followed a familiar pattern. First, the client would only purchase one or two XIV units. Second, the client would beat the crap out of them, putting all kinds of stress from different workloads. Third, the client would discover that the XIV is really as amazing as IBM and IBM Business Partners have told them. Finally, in the fourth phase, the client would deploy the XIV for mission-critical production applications.
- A large US bank holding company managed to get 5.3 GB/sec from a pair of XIV boxes for their analytics environment. They now have 14 XIV boxes deployed in mission-critical applications.
- A large equipment manufacturer compared the offerings among seven different storage vendors, and IBM XIV came out the winner. They now have 11 XIV boxes in production and another four boxes for development/test. They have moved their entire VMware infrastructure to IBM XIV, running over 12,000 guest instances.
- A financial services company bought their first XIV in early 2009 and now has 34 XIV units in production attached to a variety of Windows, Solaris, AIX, Linux servers and VMware hosts. Their entire Microsoft Exchange was moved from HP and EMC disk to IBM XIV, and experienced noticeable performance improvement.
- When a University health system replaced two competitive disk systems with XIV, their data center temperature dropped from 74 to 68 degrees Fahrenheit. In general, XIV systems are 20 to 30 percent more energy efficient per usable TB than traditional disk systems.
- A service provider that had used EMC disk systems for over 10 years evaluated the IBM XIV versus upgrading to EMC V-Max. The three year total cost of ownership (TCO) of EMC's V-Max was $7 Million US dollars higher, so EMC counter-proposed CLARiiON CX4 instead. But, in the end, IBM XIV proved to be the better fit, and now the customer is happy having made the switch.
- The manager of an information communications technology service provider was impressed that the XIV was up and running in just a couple of days. They now have over two dozen XIV systems.
- Another XIV client had lost all of their Computer Room Air Conditioning (CRAC) units for several hours. The data center heated up to 126 degrees Fahrenheit, but the customer did not lose any data on either of their two XIV boxes, which continued to run in these extreme conditions.
- Optimizing XIV Performance - Brian Cormody
This session was an update from the [one presented last year] by Izhar Sharon. Brian presented various best practices for optimizing the performance when using specific application workloads with IBM XIV disk systems.
- Oracle ASM: Many people allocate lots of small LUNs, because this made sense a long time ago when all you had was just a bunch of disks (JBOD). In fact, many of the practices that DBAs use to configure databases across disks become unnecessary with XIV. Wth XIV, you are better off allocating a few number of very large LUNs from the XIV. The best option was a 1-volume ASM pool with 8MB AU stripe. A single LUN can contain multiple Oracle databases. A single LUN can be used to store all of the logs.
- VMware: Over 70 percent of XIV customers use it with VMware. For VMFS, IBM recommends allocating a few number of large LUNs. You can specify the maximum of 2181 GB. Do not use VMware's internal LUN extension capability, as IBM XIV already has thin provisioning and works better to allow XIV to do this for you. XIV Snapshots provide crash-consistent copies without all the VMware overhead of VMware Snapshots.
- SAP: For planning purposes, the "SAPS" unit equates roughly to 0.4 IOPS for ERP OLTP workloads, and 0.6 IOPS for BW/BI OLAP workloads. In general, an XIV can deliver 25-30,000 IOPS at 10-15 msec response time, and 60,000 IOPS at 30 msec response time. With SAP, our clients have managed to get 60,000 IOPS at less than 15 msec.
- Microsoft Exchange: Even my friends in Redmond could not believe how awesome XIV was during ESRP testing. Five Exchange 2010 servers connected two a pair of XIV boxes using the new 2TB drawers managed 40,000 mailboxes at the high profile (0.15 IOPS per mailbox). Another client found four XIV boxes (720 drives) was able to handle 60,000 mailboxes (5GB max), which would have taken over 4000 drives if internal disk drives were used instead. Who said SANs are obsolete for MS Exchange?
- Asynchronous Replication: IBM now has an "Async Calculator" to model and help design an XIV async replication solution. In general, dark fiber works best, and MPLS clouds had the worst results. The latest 10.2.2 microcode for the IBM XIV can now handle 10 Mbps at less than 250 msec roundtrip. During the initial sync between locations, IBM recommends setting the "schedule=never" to consume as much bandwidth as possible. If you don't trust the bandwidth measurements your telco provider is reporting, consider testing the bandwidth yourself with [iPerf] open source tool.
Several members of the XIV team thanked me for my April 5th post [Double Drive Failure Debunked: XIV Two Years Later]. Since April 5th, IBM has sold more XIV units this quarter than any prior quarters. I am glad to have helped!
technorati tags: IBM, Technical University, XIV, HP, EMC, CLARiiON, VMAX, TCO, CRAC, JBOD, SAP, Oracle, ASM, Microsoft Exchange, ESRP
Continuing my week in Chicago, for the IBM Storage Symposium 2008, I attended two presentations on XIV.
- XIV Storage - Best Practices
Izhar Sharon, IBM Technical Sales Specialist for XIV, presented best practices using XIV in various environments.He started out explaining the innovative XIV architecture: a SATA-based disk system from IBM can outperformFC-based disk systems from other vendors using massive parallelism. He used a sports analogy:
"The men's world record for running 800 meters was set in 1997 by Wilson Kipketer of Denmark in a time of 1:41.11.
However, if you have eight men running, 100 meters each, they will all cross the finish line in about 10 seconds."
Since XIV is already self-tuning, what kind of best practices are left to present? Izhar presented best practicesfor software, hosts, switches and storage virtualization products that attach to the XIV. Here's some quickpoints:
- Use as many paths as possible.
IBM does not require you to purchase and install multipathing software as other competitors might. Instead, theXIV relies on multipathing capabilities inherent to each operating system.For multipathing preference, choose Round-Robin, which is now available onAIX and VMware vSphere 4.0, for example. Otherwise, fixed-path is preferred over most-recently-used (MRU).
- Encourage parallel I/O requests.
XIV architecture does not subscribe to the outdated notion of a "global cache". Instead, the cache is distributed across the modules, to reduce performance bottlenecks. Each HBA on the XIV can handle about 1400requests. If you have fewer than 1400 hosts attached to the XIV, you can further increase parallel I/O requests by specifying a large queue depth in the host bus adapter (HBA).An HBA queue depth of 64 is a good start. Additional settings mightbe required in the BIOS, operating system or application for multiple threads and processes.
For sequential workloads, select host stripe size less than 1MB. For random, select host stripe size larger than 1MB. Set rr_min_io between ten(10) and the queue depth(typically 64), setting it to half of the queue depth is a good starting point.
If you have long-running batch jobs, consider breaking them up into smaller steps and run in parallel.
- Define fewer, larger LUNs
Generally, you no longer need to define many small LUNs, a practice that was often required on traditionaldisk systems. This means that you can now define just 1 or 2 LUNs per application, and greatly simplifymanagement. If your application must have multiple LUNs in order to do multiple threads or concurrent I/O requests, then, by all means, define multiple LUNs.
Modern Data Base Management Systems (DBMS) like DB2 and Oracle already parallelize their I/O requests, sothere is no need for host-based striping across many logical volumes. XIV already stripes the data for you.If you use Oracle Automated Storage Management (ASM), use 8MB to 16MB extent sizes for optimal performance.
For those virtualizing XIV with SAN Volume Controller (SVC), define manage disks as 1632GB LUNs, in multiple of six LUNs per managed disk group (MDG), to balance across the six interface modules. Define SVC extent size to 1GB.
XIV is ideal for VMware. Create big LUNs for your VMFS that you can access via FCP or iSCSI.
- Organize data to simplify Snapshots.
You no longer need to separate logs from databases for performance reasons. However, for some backup productslike IBM Tivoli Storage Manager (TSM) for Advanced Copy Services (ACS), you might want to keep them separatefor snapshot reasons. Gernally, putting all data for an application on one big LUNgreatly simplifies administration and snapshot processing, without losing performance.If you define multiple LUNs for an application, simply put them into the same "consistencygroup" so that they are all snapshot together.
OS boot image disks can be snapshot before applying any patches, updates or application software, so that ifthere are any problems, you can reboot to the previous image.
- Employ sizing tools to plan for capacity and performance.
The SAP Quicksizer tool can be used for new SAP deployments, employing either the user-based orthroughput-based sizing model approach. The result is in mythical unit called "SAPS", which represents0.4 IOPS for ERP/OLTP workloads, and 0.6 IOPS for BI/BW and OLAP workloads.
If you already have SAP or other applications running, use actual I/O measurements. IBM Business Partners and field technical sales specialists have an updated version of Disk Magic that can help size XIV configurations fromPERFMON and iostat figures.
- XIV Performance
Lee La Frese, IBM STSM for Enteprise Storage Performance Engineering, presented internal lab test results forthe XIV under various workloads, based on the latest hardware/software levels [announced two weeks ago]. Three workloadswere tested:
The results were quite impressive. There was more than enough performance for tier 2 application workloads,and most tier 1 applications. The performance was nearly linear from the smallest 6-module to the largest 15-module configuration. Some key points:
- Web 2.0 (80/20/40) - 80 percent READ, 20 percent WRITE, 40 percent cache hits for READ.YouTube, FlickR, and the growing list at [GoWeb20] are applications with heavy read activity, but because of[long-tail effects], may not be as cache friendly.
- Social Networking (50/50/50) - 50 percent READ, 50 percent WRITE, 50 percent cache hits for READ.Lotus Connections, Microsoft Sharepoint, and many other [social networking] usage are more write intensive.
- Database (70/30/50) - 70 percent READ, 30 percent WRITE, 50 percent cache hits for READ.The traditional workload characteristics for most business applications, especially databases like DB2 andOracle on Linux, UNIX and Windows servers.
- A full 15-module XIV overwhelms a single SVC 8F4 node-pair. For a full XIV, consider 4 to 8 nodes 8F4 models, or 2 to 4 nodes of an 8G4. For read-intensive cache-friendly workloads, an SVC in front of XIV was able to deliver over 300,000 IOPS.
- A single node TS7650G ProtecTIER can handle 6 to 9 XIV modules. Two nodes of TS7650G were needed to drivea full 15-module XIV. A single node TS7650 in front of XIV was able to ingest 680 MB/sec on the seventh day with17 percent per-day change rate test workload using 64 virtual drives. Reading the data back got over 950 MB/sec.
- For SAP environments where response time 20-30 msec are acceptable, the 15-module XIV delivered over 60,000 IOPS. Reducing this down to 25,000-30,000 cut the msec response time to a faster 10-15 msec.
These were all done as internal lab tests. Your mileage may vary.
Not surprisingly, XIV was quite the popular topic here this week at the Storage Symposium. There were many moresessions, but these were the only two that I attended.
technorati tags: IBM, XIV, SATA, best practices, performance, Wilson Kipketer, massive parallelism, HBA, DBMS, Oracle, ASM, DB2, SVC, VMware, VMFS, TSM, Tivoli, SAP, Quicksizer, SAPS, PERFMON, iostat, Disk+Magic, TS7650G, ProtecTIER
This week I was aboard the Queen Mary in Long Beach, California! This was a business event organized by [Key Info Systems], a valued IBM Business Partner. Key Info resells IBM servers, storage and switches.
The Queen Mary retired in 1967, and has been converted into a hotel and events venue. The locals just parked their car and walked on board, but I got to stay Tuesday through Thursday in one of the cabins. It was long and narrow, with round windows! There were four dials for the bathtub: Cold Salt, Hot Fresh, Cold Fresh, and Hot Salt.
Stepping on the boat was like walking back in time through history! If you decide to go see it, check out the [Art Deco bar at the front of the Promenade deck. The ship is still in the water, but is permanently docked. It is sectioned off to prevent the ocean waves from affecting it, so we did not have the nauseous moving back and forth normally associated with cruise ships.
(It is with a bit of irony that we are on the Queen Mary just days after the tragedy of the [Costa Concordia], the largest Italian cruise ship that ran aground near Isola de Giglio. The captain will have to explain how he [fell into a lifeboat] before he had a chance to wait for everyone else to get safely off the shipwreck. He was certainly no [Captain Sulley]! I am thankful that most of the 4,200 people survived the incident.)
- Executive Welcome
Lief Morin, Founder and Chief Executive for Key Info Systems, kicked off the meeting with highlights of 2011 successes. I have known Lief for years, as Key Info comes to the Tucson EBC on a frequent basis. This event was designed to give his sellers an update of what is the latest for each product line, and what to look forward to in the next 12-18 months.
- Power Systems
My colleague Pat O'Rourke from Austin EBC presented [IBM Power Systems], from the smallest [POWER-based blade servers for BladeCenter] to the largest [Power 795 server]. When it comes to UNIX servers, IBM is [kickin' butt and takin' names], leaving HP and Oracle/Sun to fend for scraps.
- Vision Solutions
The next speaker was from Vision Solutions that provides High Availability solutions for IBM i on Power Systems. In 2010, their company nearly doubled in size with the acquisition of Double-Take, which provides data replication for x86 servers running Windows, Linux, VMware, Hyper-V and other hypervisors. The capabilities of Double-Take sounded similar to what IBM offers with [Tivoli Storage Manager FastBack] and [Tivoli Storage Manager for Virtual Environments].
- Dinner at Sir Winston's
Rather than take the "Ghosts and Legends" tour, I opted for dinner at the Queen Mary's signature restaurant, Sir Winston's. This is a fancy place, so dress accordingly. If you want the Raspberry soufflé, order it early as it takes 30 minutes to prepare!
- System Storage
I presented on a variety of storage topics:
Storage is an important part of the Key Info Systems revenue stream, so I was glad to have lots of questions and interactions from the audience.
- Murder Mystery Dinner
The acting troupe from [Dinner Detective] put on quite the show for us! With all that is going on in the world, it is good to laugh out loud every now and then.
In other murder mystery dinners I have participated in, each person is assigned a "character" and given a script of what to say and when to say it. This was different, we got to pick our own characters. I chose "Doctor Watson", from the Sherlock Holmes series. Several attendees thought it was a double meaning with [IBM Watson], the computer that figured out the clues on Jeopardy! television game show, and has since been [put to work at Wellpoint] to help out the Healthcare industry.
After the "murder" happened, two actors portraying policemen selected members of the audience to answer questions. We didn't get a script of what to say, so everyone had to "ad lib". I was singled out as a suspect, and had fun playing along in character. One of the attendees afterwards said he was impressed that I was able to fabricate such amusing and elaborate responses to their personal and embarassing questions. As a public speaker for IBM, I have had a lot of practice thinking quickly on my feet.
- Fibre Channel and Ethernet Switches
The next two speakers gave us an update on Fibre Channel and Ethernet switches, and their thoughts on the inevitability of Fibre Channel over Ethernet (FCoE). One of the exciting new developments is the [Brocade Network Subscription] which creates a flexible pay-per-use Ethernet port rental model for customers. This is especially timely given the Financial Accounting Standards Board proposed [FASB Change 13] that affects operating leases in the balance sheet.
With the Brocade Network Subscription, you pay monthly for the ports you are using. Need more ports, Brocade will install the added gear. Use fewer ports, Brocade will take the equipment back. There is no term endpoint or residual value like tradtional leasing, so when you are done using the equipment, give it back any time. This is ideal for companies that may need to have a lot of Ethernet ports for the next 2-3 years, but then plan to taper down, and don't want to get stuck with a long-term commitment or capital depreciation.
The last speaker was from VMware. IBM is the #1 reseller of VMware, and VMware commands an impressive 81 percent marketshare in the x86 virtualization space. The speaker presented VMware's strategy going forward, which aligns well with IBM's own strategy, to help companies Cloud-enable their existing IT infrastructures, in preparation for eventual moves to Hybrid or Public cloud deployments.
Special thanks to Lief Morin for sponsoring this event, Raquel Hernandez from IBM for coordinating my travel, and Pete, Christina and Kendrell from Key Info Systems for organizing the activities!
technorati tags: IBM, Queen Mary, Key Info, Art Deco, Costa Concordia, Lief Morin, Pat O'Rourke, Power 795, DS8000, XIV, SONAS, Tape, TS1140, LTFS, Storwize V7000, Unified storage, FCoE, BNS, VMware, Cloud Computing
Last year, I started my post[Hu Yoshida should know better
I am still wiping the coffee off my computer screen, inadvertently sprayed when I took a sip while reading HDS' uber-blogger Hu Yoshida's post on storage virtualization and vendor lock-in.
HDS is a major vendor for disk storage virtualization, and Hu Yoshida has been around for a while, so I felt it was fair to disagree with some of the generalizations he made to set the record straight. He's been more careful ever since.
However, his latest post [The Greening of IT: Oxymoron or Journey to a New Reality] mentions an expert panel at SNW that includedMark O’Gara Vice President of Infrastructure Management at Highmark. I was not at the SNW conference last week in Orlando, so I will just give the excerpt from Hu's account of what happened:
"Later I had the opportunity to have lunch with Mark O’Gara. Mark is a West Point graduate so he takes a very disciplined approach to addressing the greening of IT. He emphasized the need for measurements and setting targets. When he started out he did an analysis of power consumption based on vendor specifications and came up with a number of 513 KW for his data center infrastructure....
The physical measurements showed that the biggest consumers of power were in order: Business Intelligence Servers, SAN Storage, Robotic tape Library, and Virtual tape servers....
Another surprise may be that tape libraries are such large consumers of power. Since tape is not spinning most of the time they should consume much less power than spinning disk - right? Apparently not if they are sitting in a robotic tape library with a lot of mechanical moving parts and tape drives that have to accelerate and decelerate at tremendous speeds. A Virtual Tape Library with de-duplication factor of 25:1 and large capacity disks may draw significantly less power than a robotic tape library for a given amount of capacity.
Obviously, I know better than to sip coffee whenever reading Hu's blog. I am down here in South America this week, the coffee is very hot and very delicious, so I am glad I didn't waste any on my laptop screen this time, especially reading that last sentence!
Last month, in my post [Disk only customers going back to tape], I mentioned some statistics from the Clipper Group's whitepaper[Disk and Tape Square Off Again —Tape Remains King of the Hill with LTO-4] by analysts David Reine and Mike Kahn.
In that report, a 5-year comparison found that a repository based on SATA disk was 23 times more expensive overall, and consumed 290 times more energy, than a tape library based on LTO-4 tape technology. The analysts even considered a disk-based Virtual Tape Library (VTL). Focusing just on backups, at a 20:1 deduplication ratio, the VTL solution was still 5 times per expensive than the tape library. If you use the 25:1 ratio that Hu Yoshida mentions in his post above, that would still be 4 times more than a tape library.
I am not disputing Mark O'Gara's disciplined approach.
It is possible that Highmark is using a poorly written backup program, taking full backups every day, to an older non-IBM tape library, in a manner that causes no end of activity to the poor tape robotics inside. But rather than changing over to a VTL, perhaps Mark might be better off investigating the use of IBM Tivoli Storage Manager, using progressive backup techniques, appropriate policies, parameters and settings, to a more energy-efficient IBM tape library.In well tuned backup workloads, the robotics are not very busy. The robot mounts the tape, and then the backup runs for a long time filling up that tape, all the meanwhile the robot is idle waiting for another request.
(Update: My apologies to Mark and his colleagues at Highmark. The above paragraph implied that Mark was using badproducts or configured them incorrectly, and was inappropriate. Mark, my full apology [here])
If you do decide to go with a Virtual Tape Library, for reasons other than energy consumption, doesn't it make sense to buy it from a vendor that understands tape systems, rather than buying it from one that focuses on disk systems? Tape system vendors like IBM, HP or Sun understand tape workloads as well as related backup and archive software, and can provide better guidance and recommendations based on years of experience. Asking advice abouttape systems, including Virtual Tape Libraries, from a disk vendor is like asking for advice on different types of bread from your butcher, or advice about various cuts of meat at the bakery.
The butchers and bakers might give you answers, but it may not be the best advice.
technorati tags: HDS, Hu Yoshida, Mark O'Gara, Highmark, SNW, Orlando, Florida, de-duplication, deduplication, dedupe, robotic, tape library, virtual, VTL, Clipper Group, David Reine, Mike Kahn, SATA, disk, systems, HP, Sun, backup, archive, workloads, butcher, baker, bakery, meat, bread, advice, IBM, Tivoli Storage Manager, TSM, LTO, LTO-4
For most of us in the United States, it is cold out there, so you better "bundle up!"
Today, IBM announces the [IBM Storwize Rapid Application Storage] bundle, an integrated solution that improves storage efficiency and application availability. It comes in two offerings:
The "Basic" offering includes a single IBM Storwize V7000 controller enclosure, and three year warranty package that includes software licenses for IBM Tivoli Storage FlashCopy Manager (FCM) and IBM Tivoli Storage Productivity Center for Disk - Midrange Edition (MRE). Planning, configuration and testing services for the software are included and can be performed by either IBM or an IBM Business Partner.
The "Standard" offering allows for multiple IBM Storwize V7000 enclosures, provides three year warranty package for the FCM and MRE software, and includes implementation services for both the hardware and the software components. These services can be performed by IBM or an IBM Business Partner.
Why bundle? Here are the key advantages for these offerings:
- Increased storage utilization! First introduced in 2003, IBM SAN Volume Controller is able to improve storage utilization by 30 percent through virtualization and thin provisioning. IBM Storwize V7000 carries on this tradition. Space-efficient FlashCopy is included in this bundle at no additional charge and can reduce the amount of storage normally required for snapshots by 75 percent or more. IBM Tivoli Storage FlashCopy Manager can manage these FlashCopy targets easily.
- Improved storage administrator productivity! The new IBM Storwize V7000 Graphical User Interface can help improve administrator productivity up to 2 times compared to other midrange disk solutions. The IBM Tivoli Storage Productivity Center for Disk - Midrange Edition provides real-time performance monitoring for faster analysis time.
- Increased application performance! This bundle includes the "Easy Tier" feature at no additional charge. Easy Tier is IBM's implementation of sub-LUN automated tiering between Solid-State Drives (SSD) and spinning disk. Easy Tier can help improve application throughput up to 3 times, and improve response time up to 60 percent. Easy Tier can help meet or exceed application performance levels with its internal "hot spot" analytics.
- Increased application availability! IBM Tivoli Storage FlashCopy Manager provides easy integration with existing applications like SAP, Microsoft Exchange, IBM DB2, Oracle, and Microsoft SQL Server. Reduce application downtime to just seconds with backups and restores using FlashCopy. The built-in online migration feature, included at no additional charge, allows you to seamlessly migrate data from your old disk to the new IBM Storwize V7000.
- Significantly reduced implementation time! This bundle will help you cut implementation time in half, with little or no impact to storage administrator staff. This will help you realize your return on investment (ROI) much sooner.
To learn more, check out the IBM [landing page].
technorati tags: IBM, bundle, Storwize V7000, Tivoli, FlashCopy Manager, Productivity Center, TPC, MRE, SSD, Easy Tier, SAP, Exchange, DB2, Oracle, Microsoft, SQL Server
Well, it's Tuesday again, and you know what that means... IBM Announcements!
IBM thought the week that everyone is watching IBM Watson compete against humans on Jeopardy! would be a good week to launch new storage products.
- IBM XIV Storage System
Ever since my post [Double Drive Failure Debunked: XIV Two Years Later], the XIV storage systems have been flying off the shelves. IBM rolls out the new [XIV 10.2.4 microcode level] with some exciting new software features. Here are the highlights:
Full VMware Vstorage API for Array Integration (VAAI). Back in 2008, VMware announced new vStorage APIs for its vSphere ESX hypervisor: vStorage API for Site Recovery Manager, vStorage API for Data Potection, vStorage API for Multipathing. Last July, VMware added a new API called vStorage API for Array Integration [VAAI] which offers three primitives:
- Hardware-assisted Blocks zeroing. Sometimes referred to as "Write Same", this SCSI command will zero out a large section of blocks, presumably as part of a VMDK file. This can then be used to reclaim space on the XIV on thin-provisioned LUNs.
- Hardware-assisted Copy. Make an XIV snapshot of data without any I/O on the server hardware.
- Hardware-assisted locking. On mainframes, this is call Parallel Access Volumes (PAV). Instead of locking an entire LUN using standard SCSI reserve commands, this primitive allows an ESX host to lock just an individual block so as not to interfere with other hosts accessing other blocks on that same LUN.
Plans for a [fourth primitive called "Thin Provisioning Stun"] were mysteriously dropped. For now, VAAI support refers only to the three primitives above.
(Stephen, if you are reading this, please update your [VAAI in Plain English Support Matrix].)
Quality of Service (QoS) Performance Classes.
When XIV was first released, it treated all hosts and all data the same, even when deployed for a variety of different applications. This worked for some clients, such as [Medicare y Mucho Más]. They migrated their databases, file servers and email system from EMC CLARiiON to an IBM XIV Storage System. In conjunction with VMware, the XIV provides a highly flexible and scalable virtualized architecture, which enhances the company's business agility.
However, other clients were skeptical, and felt they needed additional "nobs" to prioritize different workloads. The new 10.2.4 microcode allows you to define four different "performance classes". This is like the door of a nightclub. All the regular people are waiting in a long line, but when a celebrity in a limo arrives, the bouncer unclips the cord, and lets the celebrity in. For each class, you provide IOPS and/or MB/sec targets, and the XIV manages to those goals. Performance classes are assigned to each host based on their value to the business.
Offline Initialization for Asynchronous Mirror.
Internally, we called this Truck Mode. Normally, when a customer decides to start using Asynchronous Mirror, they already have a lot of data at the primary location, and so there is a lot of data to send over to the new XIV box at the secondary location. This new feature allows the data to be dumped to tape at the primary location. Those tapes are shipped to the secondary location and restored on the empty XIV. The two XIV boxes are then connected for Asynchronous Mirroring, and checksums of each 64KB block are compared to determine what has changed at the primary during this "tape delivery time". This greatly reduces the time it takes for the two boxes to get past the initial synchronization phase.
- IBM Storwize V7000 Rapid Application Storage
Last month, IBM announced the [IBM Storwize V7000 Rapid Application Storage] bundle. There is now a [Business Advantage Calculator] to help cost-justify this bundle.
IP-based Replication. When IBM first launched the Storwize V7000 last October, people commented that the one feature they felt missing was IP-based replication. Sure, we offered FCP-based replication as most other Enterprise-class disk systems offer today, but many midrange systems also offer IP-based repliation to reduce the need for expensive FCIP routers. [IBM Tivoli Storage FastBack for Storwize V7000] provides IP-based replication for Storwize V7000 systems.
- Network Attached Storage
IBM announced two new models of the IBM System Storage N series. The midrange N6240 supports up to 600 drives, replacing the N6040 system. The entry-level N6210 supports up to 240 drives, and replaces the N3600 system. Details for both are available on the latest [data sheet].
IBM Real-Time Compression appliances work with all N series models to provide additional storage efficiency. Last October, I provided the [Product Name Decoder Ring] for the STN6500 and STN6800 models. The STN6500 supports 1 GbE ports, and the STN6800 supports 10GbE ports (or a mix of 10GbE and 1GbE, if you prefer). The IBM versions of these models were announced last December, but some people were on vacation and might have missed it. For more details of this, read the [Resources page], the [landing page], or [watch this video].
- IBM System Storage DS3000 series
IBM System Storage [DS3524 Express DC and EXP3524 Express DC] models are powered with direct current (DC) rather than alternating current (AC). The DS3524 packs dual controllers and two dozen small-form factor (2.5 inch) drives in a compact 2U-high rack-optimized module. The EXP3524 provides addition disk capacity that can be attached to the DS3524 for expansion.
Large data centers, especially those in the Telecommunications Industry, receive AC from their power company, then store it in a large battery called an Uninterruptible Power Supply (UPS). For DC-powered equipment, they can run directly off this battery source, but for AC-powered equipment, the DC has to be converted back to AC, and some energy is lost in the conversion. Thus, having DC-powered equipment is more energy efficient, or "green", for the IT data center.
Whether you get the DC-powered or AC-powered models, both are NEBS-compliant and ETSI-compliant.
- New Tape Drive Options for Autoloaders and Libraries
IBM System Storage [TS2900 Autoloader] is a compact 1U-high tape system that supports one LTO drive and up to 9 tape cartridges. The TS2900 can support either an LTO-3, LTO-4 or LTO-5 half-height drive.
IBM System Storage [TS3100 and TS3200 Tape Libraries] were also enhanced. The TS3100 can accomodate one full-height LTO drive, or two half-height drives, and hold up to 24 cartridges. The TS3200 offers twice as many drives and space for cartridges.
For more on this, see the [1Q2011 Storage Announcements page].
technorati tags: IBM, XIV, VAAI, QoS, Performance Class, Offline Initialization, Asynchronous Mirror, NAS, N6240, N6210, SONAS, DC-powered, DS3524, EXP3524, NEBS, ETSI, TS2900, TS3100, TS3200
Well, it's Tuesday, and that means IBM announcements! Today is bigger, as there are a lot of Dynamic Infrastructure announcements throughout the company with a common theme, cloud computing and smart business systems that support the new way of doing things. Today, IBM announced its new "IBM Smart Archive" strategy that integrates software, storage, servers and services into solutions that help meet the challenges of today and tomorrow. IBM has been spending the past few years working across its various divisions and acquisitions to ensure that our clients have complete end-to-end solutions.
IBM is introducing new "Smart Business Systems" that can be used on-premises for private-cloud configurations, as well as by cloud-computing companies to offer IT as a service.
IBM [Information Archive
] is the first to be unveiled, a disk-only or blended disk-and-tape Information Infrastructure solution that offers a "unified storage" approach with amazing flexibility for dealing with various archive requirements:
- For those with applications using the IBM Tivoli Storage Manager (TSM) or IBM System Storage Archive Manager (SSAM) API of the IBM System Storage DR550 data retention solution, the Information Archive will provide a direct migration, supporting this API for existing applications.
- For those with IBM N series using SnapLock or the File System Gateway of the DR550, the Information Archive will support various NAS protocols, deployed in stages, including NFS, CIFS, HTTP and FTP access, with Non-Erasable, Non-Rewriteable (NENR) enforcement that are compatible with current IBM N series SnapLock usage.
- For those using NAS devices with PACS applications to store X-rays and other medical images, the Information Archive will provide similar NAS protocol interfaces. Information Archive will support both read-only data such as X-rays, as well as read/write data such as Electronic Medical Records.
Information Archive is not just for compliance data that was previously sent to WORM optical media. Instead, it can handle all kinds of data, rewriteable data, read-only data, and data that needs to be locked down for tamper protection. It can handle structured databases, emails, videos and unstructured files, as well as objects stored through the SSAM API.
The Information Archive has all the server, storage and software integrated together into a single machine type/model number. It is based on IBM's General Parallel File System (GPFS) to provide incredible scalability, the same clustered file system used by many of the top 500 supercomputers. Initially, Information Archive will support up to 304TB raw capacity of disk and Petabytes of tape. You can read the [Spec Sheet
] for other technical details.
For those who prefer a more "customized" approach, similar to IBM Scale-Out File Services (SoFS), IBM has [Smart Business Storage Cloud
]. IBM Global Services can customize a solution that is best for you, using many of the same technologies. In fact, IBM Global Services announced a variety of new cloud-computing services to help enterprises determine the best approach.
In a related announcement, IBM announced [LotusLive iNotes
], which you can think of as a "business-ready" version of Google's GoogleApps, Gmail and GoogleCalendar. IBM is focused on security and reliability but leaves out the advertising and data mining that people have been forced to tolerate from consumer-oriented Web 2.0-based solutions. IBM's clients that are already familiar with on-premises version of Lotus Notes will have no trouble using LotusLive iNotes.
There was actually a lot more announced today, which I will try to get to in later posts.
technorati tags: IBM, Dynamic Infrastructure, Smart Archive, Information Archive, Information Infrastructure, TSM, SSAM, WORM, NENR, DR550, GMAS, N series, SnapLock, compliance, disk, tape, storage, GPFS, LotusLive, iNotes, SoFS, Google, GoogleApps, Gmail, GoogleCalendar
Earlier this week, EMC announced its Symmetrix V-Max, following two trends in the industry:
- Using Roman numerals. The "V" here is for FIVE, as this is the successor to the DMX-3 and DMX-4. EMC might have gotten the idea from IBM's success with the XIV (which does refer to the number 14, specifically the 14th class of a Talpiot program in Israel that the founders of XIV graduated from).
- Adding "-Max", "-Monkey" or "2.0" at the end of things to make them sound more cool and to appeal to a younger, hipper audience. EMC might have gotten this idea from Pepsi-Max (... a taste of storage for the next generation?)
I took a cue from President Obama and waited a few days to collect my thoughts and do my homework before responding.Special thanks to fellow blogger ChuckH in giving me a [handy list of reactions] for me to pick and choose from. It appears that EMC marketing machine feels it is acceptable for their own folks to claim that EMC is doing something first, or that others are catching up to EMC, but when other vendors do likewise, then that is just pathetic or incoherent. Here are a few reactions already from fellow bloggers:
This was a major announcement for EMC, addressing many of the problems, flaws and weaknesses of the earlier DMX-3 and DMX-4 deliverables. Here's my read on this:
- More ports
Now you can have as many FCP ports (128) as an IBM System Storage DS8300, although the maximum number of FICON ports is still short, and no mention of ESCON support. The Ethernet ports appear to be 1Gb, not the new 10GbE you might expect.
- Support for System z mainframe
V-Max adds some new support to catch up with the DS8000, like Extended Address Volumes (EAV). EMC is still not quite there yet. IBM DS8000 continues to be the best, most feature-rich storage option if you have System z mainframe servers.
- Improved Performance
Both the IBM DS8000 and HDS USP-V beat the DMX-4 in performance, and in some cases the DMX-4 even lost to the IBM XIV, so EMC had to do something about it. EMC chooses not to participate in industry-standard performance benchmarks like those from the [Storage Performance Council], which limits them to vague comparisons against older EMC gear. I'll give EMC engineers the benefit of the doubt and say that now V-Max is now "comparably as fast as HDS and IBM offerings".
- Getting "V" in the name
The "V" appears to be for the roman number five, not to be confused with external heterogeneous storage virtualization that HDS USP-V and IBM SVC provide. There is no mention of synergy with EMC's failed "Invista" product, and I see no support for attaching other vendors disk to the back of this thing.
- Switch to Intel processor
Apple switched its computers from PowerPC to Intel-based, and now EMC follows in the same path. There are some custom ASICs still in V-Max, so it is not as pure as IBM's offerings.
- Modular, XIV-like Scale-out Architecture
Actually, the packaging appears to follow the familiar system bays and storage bays of the DMX-4 and DMX-4 950 models, but architecturally offers XIV-like attachment across a common switch network between "engines", EMC's term for interface modules.
- Non-disruptive data migration
IBM's SoFS, DR550 and GMAS have this already, as does as anything connected behind an IBM SAN Volume Controller.
A long time ago, IBM used to have midrange disk storage systems called "FAStT" which stood for Fibre Array Storage Technology, so this might have given EMC the idea for their "Fully Automated Storage Tiering" acronym. The concept appears similar to what IBM introduced back in 2007 for the Scale-Out-File Services [SofS] which not only provides policy-based placement, movement and expiration on different disk tiers, includes tape tiers as well for a complete solution. I don't see anything in the V-Max announcement that it will support tape anytime soon.
And what ever happend to EMC's Atmos? Wasn't that supposed to be EMC's new direction in storage?
- Zero-data loss Three-site replication
IBM already calls this Metro/Global Mirror for its IBM DS8000 series, but EMC chose to call it SRDF/EDP for Extended Distance Protection.
- Ease of Use
The most significant part of the announcement is that EMC is finally focusing on ease-of-use.In addition to reducing the requirement for "Bin File" modifications, this box has a redesigned user interface to focus on usability issues. For past DMX models, EMC customers had to either hire EMC to do tasks for them that were just to difficult otherwise, or buy expensive software like their EMC Control Center to manage. EMC willcontinue to sell DMX-4 boxes for a while, as they are probably supply-constrained on the V-Max side, but I doubt they will retro-fit these new features back to DMX-3 and DMX-4.
When IBM announced its acquisition of XIV over a year ago now, customers were knocking down our doors to get one. This caught two particular groups looking like a [deer in headlights]:
- EMC Symmetrix sales force: Some of the smarter ones left EMC to go sell IBM XIV, leaving EMC short-handed and having to announce they [were hiring during their layoffs]. Obviously, a few of the smart ones stayed behind, to convince their management to build something like the V-Max.
- IBM DS8000 sales force: If clients are not happy with their existing EMC Symmetrix, why don't they just buy an IBM DS8000 instead? What does XIV have that DS8000 doesn't?
Let me contrast this with the situation Microsoft Windows is currently facing.
|I am often asked by friends to help them pick out laptops and personal computers. I use Linux, Windows and MacOS, so have personal experience with all three operating systems.|
Linux is cheaper, offers the power-user the most options for supporting older, less-powerfulequipment, but I wouldn't have my Mom use it. While distributions like Ubuntu are makinggreat strides, it is just too difficult for some people.
MacOS is nice, I like it, it works out of the box with little or no customization and an intuitive interface. However, some of my friends don't make IBM-level salaries, and have to watch their budget.
In their "I'm a PC" campaign, Microsoft is fighting both fronts. Let's examine two commercials:
- In the first commercial, a young eight-year-old puts together a video from pictures oftoy animals and some background music.The message: "Windows is easier to use than Linux!" If they really wanted to send this message, they should have shown senior citizens instead.
- In the second commercial, a young college student is asked to find a laptop with 17 inchscreen, and a variety of other qualifications, for under $1000 US dollars. The only modelat the Apple store below this price had a 13 inch screen, but she finds a Windows-based system that had this size screen and met all the other qualifications. The message: "Windows-based hardware from a variety of competitors are less expensive than hardware from Apple!"
Both Microsoft and Apple charge a premium for ease-of-use.In the storage world, things are completely opposite. Vendors don't charge a premium forease-of-use. In fact, some of the easiest to use are also the least expensive.
- If you just have Windows and Linux, you can get some entry level system likethe IBM DS3000 series, only a few features, and can be set up in six simple steps.
- Next, if you have a more interesting mix of operating systems, Linux, Windows and some flavorsof UNIX like IBM AIX, HP-UX or Sun Solaris, then you might want the features and functionsof more pricier midrange offerings. More options means that configuration and deploymentis more difficult, however.
- Finally, if you are serious Fortune 500 company, running your mission critical applications on System z or System i centralized systems in a big data center, that you might be willing to pay top dollar for the most feature-rich offerings of an Enterprise-class machine.Thankfully you have an army of highly-trained staff to handle the highest levels of complexity.
IBM's DS8000, HDS USP-V and EMC's Symmetrix are the key players in the Enterprise-classspace. They tried to be ["all things to all people"], er.. perhaps all things to allplatforms. All of the features and functions came at a price, not just in dollars, butin complexity and difficulty. You needed highly skilled storage admins using expensive storage management software, or be willing to hirethe storage vendor's premium services to get the job done.
Alan Cooper wrote a book that would change that mindset, titled[The Inmates Are Running the Asylum: Why High-Tech Products Drive Us Crazy and How to Restore the Sanity]. This book showed why the situation had gotten out ofhand, and to demand better ease-of-use from all vendors. It was required reading for anyone working in or with IBM's "User Centered Design" teams.I highly recommend this book.
IBM recognized this trend early. IBM's SVC, N series and now XIV all offer ease-of-use withenterprise-class features and functions, at lower total cost of ownership than traditional enterprise-class systems. IBM is not the only one, of course, as smaller storage start-ups like 3PAR,Pillar Data Systems, Compellent, and to some extent Dell's EqualLogic all recognized thisand developed clever offerings as well.
While IBM's XIV may not have been the first to introduce a modular, scale-out architectureusing commodity parts managed by sophisticated ease-of-use interfaces, its success might have been the kick-in-the-butt EMC needed to follow the rest of the industry in this direction.
technorati tags: IBM, DS8000, XIV, SVC, EMC, Symmetrix, V-Max, DMX-3, DMX-4, Chuck Hollis, HDS, USP-V, FCP, FICON, ESCON, storage+virtualization, FAStT
Five years ago, I sprayed coffee all over my screen from something I read on a blog post from fellow blogger Hu Yoshida from HDS. You can read what cased my reaction in my now infamous post [Hu Yoshida should know better]. Subsequently, over the years, I have disagreed with Hu on a variety of of topics, as documented in my 2010 blog post [Hu Yoshida Does It Again].
(Apparently, I am not alone, as the process of spraying one's coffee onto one's computer screen while reading other blog posts has been referred to as "Pulling a Tony" or "Doing a Tony" by other bloggers!)
Fortunately, my IBM colleague David Sacks doesn't drink coffee. Last month, David noticed that Hu had posted a graph in a recent blog entry titled [Additional Storage Performance Efficiencies for Mainframes], comparing the performance of HDS's Virtual Storage Platform (VSP) to IBM's DS8000.
For those not familiar with disk performance graphs, flatter is better, lower response time and larger IOPS are always desired. This graph implies that the HDS disk system is astonishingly faster than IBM's DS8000 series disk system. Certainly, the HDS VSP qualifies as a member of the elite [Super High-End club] with impressive SPC benchmark numbers, and is generally recognized as a device that works in IBM mainframe environments. But this new comparison graph is just ridiculous!
(Note: While SPC benchmarks are useful for making purchase decisions, different disk systems respond differently to different workloads. As the former lead architect of DFSMS for z/OS, I am often brought in to consult on mainframe performance issues in complex situations. Several times, we have fixed performance problems for our mainframe clients by replacing their HDS systems with IBM DS8000 series!)
Since Hu's blog entry contained very little information about the performance test used to generate the graph, David submitted a comment directly to Hu's blog asking a few simple questions to help IBM and Hu's readers determine whether the test was fair. Here is David's comment as submitted:
(Disclosure: I work for IBM. This comment is my own.)
I was quite surprised by the performance shown for the IBM DS8000 in the graph in your blog. Unfortunately, you provided very little detail about the benchmark. That makes it rather difficult (to say the least) to identify factors behind the results shown and to determine whether the comparison was a fair one.
Of the little information provided, an attribute that somewhat stands out is that the test appears to be limited to a single volume at least, that's my interpretation of "LDEV: 1*3390-3"? IBM's internal tests for this kind of case show far better response time and I/Os per second than the graph you published.
Here are a few examples of details you could provide to help readers determine whether the benchmark was fair and whether the results have any relevance to their environment.
- What DS8000 model was the test run on? (the DS8000 is a family of systems with generations going back 8 years. The latest and fastest model is the DS8800.)
- What were the hardware and software configurations of the DS8000 and VSP systems, including the number and speed of performance-related components?
- What were the I/O workload characteristics (e.g., read:write ratio and block size(s))?
- What was the data capacity of each volume? (Allocated and used capacity.)
- What were the cache sizes and cache hit ratios for each system? (The average I/O response times under 1.5 milliseconds for each system imply the cache hit ratios were relatively high.)
- How many physical drives were volumes striped across in each system?"
Unlike my blog on IBM, HDS bloggers like Hu are allowed to reject or deny comments before they appear on his blog post. We were disappointed that HDS never posted David's comment nor responded to it. That certainly raises questions about the quality of the comparison.
So, perhaps this is yet another case of [Hitachi Math], a phrase coined by fellow blogger Barry Burke from EMC back in 2007 in reference to outlandish HDS claims. My earliest mention was in my blog post [Not letting the Wookie Win].
By the way, since the test was about z/OS Extended Address Volumes (EAV), it is worth mentioning that IBM's DS8700 and DS8800 support 3390 volume capacities up to 1 TB each, while the HDS VSP is limited to only 223 GB per volume. Larger volume capacities help support ease-of-growth and help reduce the number of volumes storage administrators need to manage; that's just one example of how the DS8000 series continues to provide the best storage system support for z/OS environments.
Personally, I am all for running both IBM and HDS boxes side-by-side and publishing the methodology, the workload characteristics, the configuration details, and the results. Sunshine is always the best disinfectant!
technorati tags: IBM, DS8000, DS8800, HDS, Hu Yoshida, USP, VSP, mainframe, EAV
As a consultant, I am often asked to help design the architecture for the information infrastructure. A usefulanalogy to gather requirements and preferences is the difference between area rugs
and wall-to-wall carpeting
. Arearugs are not secured to the floor and cover only a portion of the floor area. Carpets are generally tacked or cemented to the floor, often with an underlay of cushion padding, stretched across the entire floor surface, out to all four walls of each room.
Each has its pros and cons, and often is a matter of preference. Some people like area rugs because they can choosea different style for each room, match the decor and color scheme of furniture, and use these to define each livingspace. Ever since paleolithic man put animal skins on the floor of their cave, people recognize that cold, hard andugly floors could be covered up with something soft and more attractive.Others prefer wall-to-wall carpeting because they want to walk around the house barefoot, have their young children crawl on their hands and knees, and give the entire house a unified look and feel. This is often an inexpensive option when compared against the cost of individual rugs.
The same is true for an information infrastructure. For some, they prefer the "area rug" approach: this style ofstorage for their email, this other type of storage for their databases, and perhaps a third for their unstructuredfile systems. When customers ask what storage would I recommend for their SAP application, or their Microsoft Exchangeemail environment, or their Business Intelligence (BI) software, I recognize they are taking this "area rug" approach.
Like area rugs, having different storage can focus on specific attributes of the workload characteristics. It alsoinsulates against company-wide changes, the dreaded "rip-and-replace" of replacing all of your storage with somethingfrom a different vendor. With "area rug" storage, you can support a dual-vendor or multi-vendor strategy, and upgrade or replace each on its own schedule.
Thanks to open standards and industry-standard benchmarks, changing out one storage solution for another is assimple as rolling up an area rug, and putting another one in its place that is similar in size dimensions.
|Others may prefer "wall-to-wall carpeting" approach: one disk system type, one tape library type,one network type, that provides unified management and minimizes the needs for unique skills. Generally, the choice of NAS, SAN or iSCSI infrastrucutre is done company-wide, and might strongly influence the set of products that will support that decision. For example, those with a mix of mainframe and distributed servers looking for SAN-attached storage may look at an [IBM System Storage DS8000] and [TS3500 tape library] that can provide support for FICON and FCP.|
Those looking at NAS or iSCSI might consider the IBM System Storage N series products, "unified storage" supporting iSCSI, FCP and NAS protocols. If you want the "wall-to-wall" to stretch across all the sites in your globally integrated enterprise, IBM's scalable NAS product, Scale-Out File Services[SoFS], provides a global name spacein combination with a clustered file system that provides incredible scalability and performance based on field-proven technology used by the majority of the [Top 100 supercomputer] deployments.
IBM can help you design an information infrastructure that fits either approach.
technorati tags: IBM, DS8000, TS3500, NAS, SAN, iSCSI, FCP, FICON, mainframe, distributed, SoFS, supercomputer