Safe Harbor Statement: The information on IBM products is intended to outline IBM's general product direction and it should not be relied on in making a purchasing decision. The information on the new products is for informational purposes only and may not be incorporated into any contract. The information on IBM products is not a commitment, promise, or legal obligation to deliver any material, code, or functionality. The development, release, and timing of any features or functionality described for IBM products remains at IBM's sole discretion.
Tony Pearson is a an active participant in local, regional, and industry-specific interests, and does not receive any special payments to mention them on this blog.
Tony Pearson receives part of the revenue proceeds from sales of books he has authored listed in the side panel.
Tony Pearson is a Master Inventor and Senior IT Specialist for the IBM System Storage product line at the
IBM Executive Briefing Center in Tucson Arizona, and featured contributor
to IBM's developerWorks. In 2011, Tony celebrated his 25th year anniversary with IBM Storage on the same day as the IBM's Centennial. He is
author of the Inside System Storage series of books. This blog is for the open exchange of ideas relating to storage and storage networking hardware, software and services. You can also follow him on Twitter @az990tony.
(Short URL for this blog: ibm.co/Pearson
Yesterday, I promised I would cover other products from the Feb 12 announcement. Today I will focus on the IBM SAN768B director. Some people are confused on the differences between switchesand directors. I find there are three key differences:
Directors are designed to be 24x7 operation, highly available with no single points of failure or repair. Generally, all components in directors are redundant and hot-swappable, including Control Processors. In switches, some components are redundant and hot-swappable, such as fans and power supplies), but not the “motherboard” or controller. Often you have to take down a switch to make firmware or major hardware changes or upgrades.
Directors are designed to take in "blades" with different features, port counts, or protocol capabilities. You can add or remove blades while the system is up and running. Switches have a fixed number of ports. (A Small Form-factor Pluggable optical transceiver [SFP] is the component that turns electric pulses into light pulses (and visa versa). You plug the SFP into the switch, and then the fiber optic cable is plugged into the SFP).
With switches, you often start with a base number of active ports, and then can enable the rest of the ports as you need them.
Directors have hundreds of ports. Switches tend to have 64 ports or less.
Last year, Brocade acquired McDATA. Both were OEMs for IBM, and IBM distinguished that in the naming convention. The IBM SAN***B name was used to denote products manufactured for IBM by Brocade, and a SAN***M name was used to denote products manufactured by McDATA.
At that time, Brocade and McDATA equipment did not mix very well on the same fabric, so IBM retained the naming convention so that you as a customer knew what it worked with.
Brocade now has released with new levels of both operating systems--Brocade's FOS and McDATA's EOS--and their respective fabric managers--Brocade Fabric Manager (FM) and McDATA's Enterprise Fabric Connectivity Manager (EFCM)--so that they have full interoperability.
Brocade's goal is to enhance EFCM to be a common software management platform for all of their products going forward.
IBM used the maximum port count in the name to provide some clue as to the size of the switch or director. The SAN16B-2 or the SAN32B-3 are switches that have a maximum of 16 and 32 ports. The SAN256B supports a maximumeight blades of your choosing.Two different types were supported for FC ports, a 16-port blade and a 32-port blade.If all eight were 32-port blades then the maximum was 256 ports, hence the name. But then Brocade began offering 48-port blades. Should IBM change the name? No, it decided to leave itthe SAN256B even though it can now have a maximum of 384 ports.
Not to confuse anyone, the SAN768B also has a maximum of 384 ports, in the same 14U dimensions, but with a special twist. Normally to connect two directors together you use up ports from each, in what are called "inter-switch links" (ISL).These are ports you are taking away from availability from the servers and storage controllers. The SAN768Boffers a new alternative called "inter-chassis links". Each SAN768B has two processing blades, and each has two ICL ports, so with just four two-meter (2m) cables, you get the equivalent of 128 FC 8 Gbps ISL links without using 128 individual ports on each side. That is like giving you 256 ports back for use with servers and storage!
Since IBM directors require 240 volt power, IBM TotalStorage SAN Cabinet C36 include power distribution units (PDUs). PDUs are just glorified power strips, but a new intelligent PDU (iPDU) option introduces additional intelligence to monitor energy consumption for customers looking to measure, and perhaps charge back, energy consumption to the rest of the business. You can stack two SAN768B in one cabinet, one on top of the other, and connected via ICLs, it wouldlook like one huge 768-port backbone.
As a backbone for your data center, the SAN768B is positioned for two emerging technologies:
8 Gbps Fibre Channel (FC)
The SAN768B is powerful enough to have 32-port blades run full speed on all ports off-blade without oversubscription. Oversubscription is an emotional topic.
Normally, blades (like switches) can handle all traffic at full speed without delays provided the in-bound and out-bound ports involved are all on the same blade. In a director, however, if you need to communicate from a port on one blade to a port on a different blade, it is possible that off-blade traffic might be constrained or delayed in its transit across the backplane.
On the SAN768B, both the 16-port and 32-port blades can run at full 8 Gbps speed, and the 48-port is exposed to oversubscription only if you have more than 32-ports running at full 8 Gbps transferring data off-blade concurrently.
The new 8 Gbps SFPs support auto-negotiation at N-1 and N-2 generation link speeds. This means that they will automatically slow down when communicating with 4Gpbs and 2 Gbps devices, but they cannot communicate with 1 Gbps devices. If you are still using 1 Gbps devices in your data center, you will need to use 4 Gbps SFPs (which also support 2 Gbps and 1 Gbps link speeds) to communicate with those older devices.
Basically, this new technology enables transport of Fibre Channel packets over 10 Gbps Ethernet links. This 10 Gbps Ethernet can also be used to carry traditional iSCSI and TCP/IP traffic. FCoE introduces new extensions to provide Fibre Channel characteristics, like being lossless, and offering consistent performance. The ANSI T11 team is driving FCoE as an open standard, and at the moment it is not fully baked. I suggest you don't buy any FCoE equipment prematurely, as pre-standard devices or host bus adapters could get you burned later when the standard is finalized.
The idea is that FCoE blades can be installed in a SAN768B along with traditional FC blades, allowing routing of traffic between traditional FC and new FCoE ports. Those who have invested in FCIP for long distance replication will be able to continue using either FC or FCoE inputs.
One of the big drivers of FCoE is IBM BladeCenter. Currently, most BladeCenter blades support both Ethernet and FC connectivity and are connected to both Ethernet and FC switches on the back of each BladeCenter chassis. With FCoE, we have the potential to run both FC and IP traffic across simpler all-Ethernet blades, connecting through all-Ethernet switches on the backs of each chassis.
For more information on the IBM SAN768B, see the [IBM Press Release]. For more detailson Brocade's strategy, here is an 8-page white paper on their[Data Center Fabric] vision.
It's official! My "blook" Inside System Storage - Volume I is now available.
This blog-based book, or “blook”, comprises the first twelve months of posts from this Inside System Storage blog,165 posts in all, from September 1, 2006 to August 31, 2007. Foreword by Jennifer Jones. 404 pages.
IT storage and storage networking concepts
IBM strategy, hardware, software and services
Disk systems, Tape systems, and storage networking
Storage and infrastructure management software
Second Life, Facebook, and other Web 2.0 platforms
IBM’s many alliances, partners and competitors
How IT storage impacts society and industry
You can choose between hardcover (with dust jacket) or paperback versions:
This is not the first time I've been published. I have authored articles for storage industry magazines, written large sections of IBM publications and manuals, submitted presentations and whitepapers to conference proceedings, and even had a short story published with illustrations by the famous cartoon writer[Ted Rall].
But I can say this is my first blook, and as far as I can tell, the first blook from IBM's many bloggers on DeveloperWorks, and the first blook about the IT storage industry.I got the idea when I saw [Lulu Publishing] run a "blook" contest. The Lulu Blooker Prize is the world's first literary prize devoted to "blooks"--books based on blogs or other websites, including webcomics. The [Lulu Blooker Blog] lists past year winners. Lulu is one of the new innovative "print-on-demand" publishers. Rather than printing hundredsor thousands of books in advance, as other publishers require, Lulu doesn't print them until you order them.
I considered cute titles like A Year of Living Dangerously, orAn Engineer in Marketing La-La land, or Around the World in 165 Posts, but settled on a title that matched closely the name of the blog.
In addition to my blog posts, I provide additional insights and behind-the-scenes commentary. If you go to the Luluwebsite above, you can preview an entire chapter in its entirety before purchase. I have added a hefty 56-page Glossary of Acronyms and Terms (GOAT) with over 900 storage-related terms defined, which also doubles as an index back to the post (or posts) that use or further explain each term.
So who might be interested in this blook?
Business Partners and Sales Reps looking to give a nice gift to their best clients and colleagues
Managers looking to reward early-tenure employees and retain the best talent
IT specialists and technicians wanting a marketing perspective of the storage industry
Mentors interested in providing motivation and encouragement to their proteges
Educators looking to provide books for their classroom or library collection
Authors looking to write a blook themselves, to see how to format and structure a finished product
Marketing personnel that want to better understand Web 2.0, Second Life and social networking
Analysts and journalists looking to understand how storage impacts the IT industry, and society overall
College graduates and others interested in a career as a storage administrator
And yes, according to Lulu, if you order soon, you can have it by December 25.
The keynote was led by Phil Tasker, IBM Business Unit Executive (BUE) for STG Education Programs in Growth Markets, then Joe Screnci, head of IBM Storage Sales for Australia. IBM is in the Top 10 Training Hall of Fame, and conducts over 40,000 classes worldwide, resulting in over 1.3 million student days of instructions. IBM Systems Lab and Training technical hosts over three dozen conferences like this one every year.
Next was Clod Barrera, Distinguished Engineer and Chief Technical Strategist for the IBM System Storage product line. He covered future trends in storage as they relate to IBM's Smarter COmputing initiative.
Storage for the Clouds
Clod Barrera presented this break-out session on Cloud Storage. He covered why clouds matter, the various types and purposes of cloud, technology and architectures, and where IBM is headed to support this trend.
Storage for Cloud computing was $1 Billion USD business in 2010, and is expected to grow 32 percent CAGR through, compared to 3.8 percent for non-cloud storage. Clod estimates that 10 to 15 percent of all storage will be in cloud deployments by 2015. Of this storage, analysts expect 50 percent in private clouds, and the other 50 percent in public clouds. For private clouds, clients are looking to "Cloudify" their existing IT infrastructures. For public clouds, the projects are mostly green field.
IBM is also looking to the "arms dealer" of choice for Telcos and other companies looking to launch their own Cloud Services. IBM has a Cloud Services Provider Platform (CSP2) specifically to provide all the tools and technologies needed to make this possible.
Last month, IBM launched several new solutions for Cloud. The IBM Starter Kit for Cloud will help existing IT environments adopt cloud technologies. The IBM Service Agility Accelerator for Cloud is available for more advanced deployments. IBM Service Delivery Manager (ISDM) integrates a collection of software to provide complete integrated service management. IBM CloudBurst provides an integrated hardware-and-software stack for both x86 and POWER chipsets.
Multi-tenancy is also a big issue, and this varies depending on deployment model: IaaS, PaaS, or SaaS. Multi-tenancy is needed to help divide up management tasks, and to ensure that shared resources are paid for and meet SLA requirements accordingly.
Clod feels there are good reasons to use high performance, transactional SAN storage for VMware environments, versus NAS which many people consider simpler to deploy. IBM is also active in open standards, including SNIA's Cloud Data Management Interface [CDMI].
Journey to the Private Cloud
Gary Luke from Brocade provided this session on IBM's SAN384B-2 and SAN768B-2 SAN directors. Brocade is one of IBM's suppliers for SAN switches, and thanks to TRILL being adopted last August by IETF, supports multi-hop FCoE configurations! However, Gary did not talk about FCoE, but rather native FCP and FICON support in these new directors.
According to VMware, only 30 percent of x86 workloads are virtualized by any hypervisor. Gary feels that server virtualization and the use of Solid-State Drives (SSD) in disk arrays are driving existing 8 Gbps SAN to upgrade to 16 Gbps. Gary feels that Fibre-Channel based SANs are best positioned to handle unpredictable peaks in a 24-by-7 world.
The SAN384B-2 can house up to 256 ports (8 Gbps) or 192 ports (16 Gbps) in four slots, 9U chassis. The SAN768B-2 can handle twice these, in a 12U chassis. The nice thing about the 16Gbps ports is that they can auto-negotiate down to 10, 8, 4 and 2 Gbps. This is far better than typical N-2 support, often referred to as the speeds supported, such as 4/2/1 and 8/4/2. An upcoming FOS release will allow people with previous generation SAN384B-1/SAN768B-1 directors to move their 8Gbps blades over to the new SAN384B-2/SAN768B-2 generation models.
Since most CWDM and DWDM only support maximum 10 Gbps FC and 10GbE, Brocade's 16Gbps can automatically drop down to 10 Gbps for direct attachment to CWDM/DWDM, rather than having a step-down box normally required.
A major advancement is the change from copper to optical "Inter-Chassis Links" (ICL). Unlike Inter-switch links (ISL) that use up SAN ports on each box, the ICL is faster, more efficient and does not consume ports. Normally, clients would connect two directors together, but now you can connect up to six chassis together! For example, you can have four SAN368B-2 connected to your host servers, ICL attached to two SAN768B-2, that are then connected to your disk and tape storage devices. The fiber optic ICL allow for up to 50 meters distance. Combining six chassis together would allow the complex to support over 3,000 ports (8 Gbps) or 2,300 ports (16 Gbps).
The SAN384B-2 and SAN768B-2 supports "virtual SAN" logical switches, traffic isoliation (TI) zones, fabric-assigned WWNNs, and fabric-based QoS.
Lastly, Brocade offers a free utility called [SANhealth] that will gather data from your b-type, m-type and even Cisco MDS-based SAN. The data can then be sent to Brocade for analysis, and Brocade will then email back some nice Visio graphs, spreadsheets and other analysis results on the health of your SAN.
I always try to catch a session from Jim Blue, who works in our "SAN Central" center of competency team. This session was a long list of useful hints and tips, based on his many years of experience helping clients.
SAN Zoning works by inclusion, limiting the impact of failing devices. The best approach is to zone by individual initiator port. The default policy for your SAN zoning should be "deny".
Ports should be named to identify who, what, where and how.
While many people know not to mix both disk and tape devices on the same HBA, Jim also recommends not mixing dissimilar disks, test and production, FCP and FICON.
The sweet spot is FOUR paths. Too many paths can impact performance.
When making changes to redundant fabrics, make changes to the first fabric, then allow sufficient time before making the same changes to the other fabric.
Use software tools like Tivoli Storage Productivity Center (Standard Edition) to validate all changes to your SAN fabric.
Do not mix 62.5 and 50.0 micron technology.
Use port caps to disable inactive ports. In one amusing anecdote, he mention that an uncovered port was hit by sunlight every day, sending error messages that took a while to figure out.
Save your SAN configuration to non-SAN storage for backup
Consider firmware about two months old to be stable
Rule of thumb for estimating IOPS: 75-100 IOPS per 7200 RPM drive, 120-150 IOPS per 10K RPM drive, and 150-200 IOPS per 15K RPM drive.
Decide whether your shop is just-in-time or just-in-case provisioning. Just-in-time gets additional capacity on demand as needed, and just-in-case over-provisions to avoid scrambling last minute.
Avoid oversubscribing your inter-switch links (ISL). Aim for around 7:1 to 10:1 ratio.
Don't go cheap on bandwidth between sites for long-distance replication
Next Generation Network Fabrics - Strategy and Innovations
Mike Easterly, IBM Director of Global Field Marketing, presented IBM System Networking strategy, in light of IBM's recent acquisition of Blade Network Technologies (BNT). BNT is used in 350 of the Fortune 500 companies, and is ranked #2 behind Cisco in sales of non-core Ethernet switches (based on number of units sold).
Based on a recent survey, companies are upgrading their Ethernet networks for a variety of reasons:
56 percent for Live Partition Mobility and VMware Vmotion
45 percent for integrated compute stacks, like IBM CloudBurst
43 percent for private, public and hybrid cloud computing deployments
40 percent for network convergences
Many companies adopt a three-level approach, with core directors, distribution switches, and then access switches at the edge that connect servers and storage devices. IBM's BNT allows you to flatten the network to lower latency by collapsing the access and distribution levels into one.
IBM's strategy is to focus on BNT for the access/distribution level, and to continue its strategic partnerships for the core level.
IBM BNT provides better price/performance and lower energy consumption. To help with hot-aisle/cold-aisle rack deployments, IBM BNT provides both F and R models. F models have ports on the front, and R models have ports in the rear.
IBM BNT supports virtual fabric and HW-offload iSCSI traffic, and future-enabled for FCoE. Support for TRILL (transparent interconnect of lots of links) and OpenFlow will be implemented through software updates to the switches.
While Cisco Nexus 1000v is focused on VMware Enterprise Plus, IBM BNT's VMready works with VMware, Hyper-V, Linux KVM, XEN, OracleVM, and PowerVM. This allows single pane of management of VMready and ESX vSwitches.
In preparation for Converged Enhanced Ethernet (CEE), IBM BNT will provide full 40GbE support sometime next year, and offer switches that support 100GbE uplinks. IBM offers extended length cables, including passive SFP+ DAC at 8.5 meters, and 10Gbase-T Cat7 cables up to 100 meters.
Inter-datacenter Workload Mobility with VMware vSphere and SAN Volume Controller (SVC)
This session was co-presented between Bill Wiegand, IBM Advanced Technical Services, and Rawley Burbridge, IBM VMware and midrange storage consultant. IBM is the leader in storage virtualization product (SVC), and is the leading reseller of VMware.
Like MetroCluster on IBM N series, or EMC's VPLEX Metro, the IBM SAN Volume Controller can support a stretched cluster across distance that allows virtual machines to move seamlessly from one datacenter to another. This is a feature IBM introduced with SVC 5.1 back in 2009. This can be used for PowerVM Live Partition Mobility, VMware vMotion, and Hyper-V Quick Migration.
SVC stretched cluster can help with both Disaster Avoidance and Disaster Recovery. For Disaster Avoidance, in anticipation of an outage, VMs can be moved to the secondary datacenter. For Disaster Recover, additional automation, such as VMware High Availability (HA) is needed to restart the VMs at the secondary datacenter.
IBM stretched cluster is further improved with a feature called Volume Mirroring (formerly vDisk Mirroring) which creates two physical copies of one logical volume. To the VMware ESX hosts, there is only one volume, regardless of which datacenter it is in. The two physical copies can be on any kind of managed disk, as there is no requirement or dependency of copy services on the back-end storage arrays.
Another recent improvement is the idea of spreading the three quorum disks to three different locations or "failure domains". One in each data center, and a third one in a separate building, somewhere in between the other two, perhaps.
Of course, there are regional disasters that could affect both datacenters. For this reason, SVC stretched cluster volumes can be replicated to a third location up to 8000 km away. This can be done with any back-end disk arrays, as again there is not requirement for copy services from the managed devices. SVC takes care of it all.
Networking is going to be very important for a variety of transformational projects going forward in the next five years.
While most of the post is accurate and well-stated, two opinions particular caught my eye. I'll be nice and call them opinions, since these are blogs, and always subject to interpretation. I'll put quotes around them so that people will correctly relate these to Hu, and not me.
"Storage virtualization can only be done in a storage controller. Currently Hitachi is the only vendor to provide this." -- Hu Yoshida
Hu, I enjoy all of your blog entries, but you should know better. HDS is fairly new-comer to the storage virtualization arena, so since IBM has been doing this for decades, I will bring you and the rest of the readers up to speed. I am not starting a blog-fight, just want to provide some additional information for clients to consider when making choices in the marketplace.
First, let's clarify the terminology. I will use 'storage' in the broad sense, including anything that can hold 1's and 0's, including memory, spinning disk media, and plastic tape media. These all have different mechanisms and access methods, based on their physical geometry and characteristics. The concept of 'virtualization' is any technology that makes one set of resources look like another set of resources with more preferable characteristics, and this applies to storage as well as servers and networks. Finally, 'storage controller' is any device with the intelligence to talk to a server and handle its read and write requests.
Second, let's take a look at all the different flavors of storage virtualization that IBM has developed over the past 30 years.
IBM introduces the S/370 with the OS/VS1 operating system. "VS" here refers to virtual storage, and in this case internal server memory was swapped out to physical disk. Using a table mapping, disk was made to look like an extension of main memory.
IBM introduces the IBM 3850 Mass Storage System (MSS). Until this time, programs that ran on mainframes had to be acutely aware of the device types being written, as each device type had different block, track and cylinder sizes, so a program written for one device type would have to be modified to work with a different device type. The MSS was able to take four 3350 disks, and a lot of tapes, and make them look like older 3330 disks, since most programs were still written for the 3330 format. The MSS was a way to deliver new 3350 disk to a 3330-oriented ecosystem, and greatly reduce the cost by handling tape on the back end. The table mapping was one virtual 3330 disk (100 MB) to two physical tapes (50 MB each). Back then, all of the mainframe disk systems had separate controllers. The 3850 used a 3831 controller that talked to the servers.
IBM invents Redundant Array of Independent Disk (RAID) technology. The table mapping is one or more virtual "Logical Units" (or "LUNs") to two or more physical disks. Data is striped, mirrored and paritied across the physical drives, making the LUNs look and feel like disks, but with faster performance and higher reliability than the physical drives they were mapped to. RAID could be implemented in the server as software, on top or embedded into the operating system, in the host bus adapter, or on the controller itself. The vendor that provided the RAID software or HBA did not have to be the same as the vendor that provided the disk, so in a sense, this avoided "vendor lock-in".Today, RAID is almost always done in the external storage controller.
IBM introduces the Personal Computer. One of the features of DOS is the ability to make a "RAM drive". This is technology that runs in the operating system to make internal memory look and feel like an external drive letter. Applications that already knew how to read and write to drive letters could work unmodified with these new RAM drives. This had the advantage that the files would be erased when the system was turned off, so it was perfect for temporary files. Of course, other operating systems today have this feature, UNIX has a /tmp directory in memory, and z/OS uses VIO storage pools.
This is important, as memory would be made to look like disk externally, as "cache", in the 1990s.
IBM AIX v3 introduces Logical Volume Manager (LVM). LVM maps the LUNs from external RAID controllers into virtual disks inside the UNIX server. The mapping can combine the capacity of multiple physical LUNs into a large internal volume. This was all done by software within the server, completely independent of the storage vendor, so again no lock-in.
IBM introduces the Virtual Tape Server (VTS). This was a disk array that emulated a tape library. A mapping of virtual tapes to physical tapes was done to allow full utilization of larger and larger tape cartridges. While many people today mistakenly equate "storage virtualization" with "disk virtualization", in reality it can be implemented on other forms of storage. The disk array was referred to as the "Tape Volume Cache". By using disk, the VTS could mount an empty "scratch" tape instantaneously, since no physical tape had to be mounted for this purpose.
Contradicting its "tape is dead" mantra, EMC later developed its CLARiiON disk library that emulates a virtual tape library (VTL).
IBM introduces the SAN Volume Controller. It involves mapping virtual disks to manage disks that could be from different frames from different vendors. Like other controllers, the SVC has multiple processors and cache memory, with the intelligence to talk to servers, and is similar in functionality to the controller components you might find inside monolithic "controller+disk" configurations like the IBM DS8300, EMC Symmetrix, or HDS TagmaStore USP. SVC can map the virtual disk to physical disk one-for-one in "image mode", as HDS does, or can also map virtual disks across physical managed disks, using a similar mapping table, to provide advantages like performance improvement through striping. You can take any virtual disk out of the SVC system simply by migrating it back to "image mode" and disconnecting the LUN from management. Again, no vendor lock-in.
The HDS USP and NSC can run as regular disk systems without virtualization, or the virtualization can be enabled to allow external disks from other vendors. HDS usually counts all USP and NSC sold, but never mention what percentage these have external disks attached in virtualization mode. Either they don't track this, or too embarrassed to publish the number. (My guess: single digit percentage).
Few people remember that IBM also introduced virtualization in both controller+disk and SAN switch form factors. The controller+disk version was called "SAN Integration Server", but people didn't like the "vendor lock-in" having to buy the internal disk from IBM. They preferred having it all external disk, with plenty of vendor choices. This is perhaps why Hitachi now offers a disk-less version of the NSC 55, in an attempt to be more like IBM's SVC.
IBM also had introduced the IBM SVC for Cisco 9000 blade. Our clients didn't want to upgrade their SAN switch networking gear just to get the benefits of disk virtualization. Perhaps this is the same reason EMC has done so poorly with its "Invista" offering.
So, bottom line, storage virtualization can, and has, been delivered in the operating system software, in the server's host bus adapter, inside SAN switches, and in storage controllers. It can be delivered anywhere in the path between application and physical media. Today, the two major vendors that provide disk virtualization "in the storage controller" are IBM and HDS, and the three major vendors that provide tape virtualization "in the storage controller" are IBM, Sun/STK, and EMC. All of these involve a mapping of logical to physical resources. Hitachi uses a one-for-one mapping, whereas IBM additionally offers more sophisticated mappings as well.
Well, this week I am in Maryland, just outside of Washington DC. It's a bit cold here.
Robin Harris over at StorageMojo put out this Open Letter to Seagate, Hitachi GST, EMC, HP, NetApp, IBM and Sun about the results of two academic papers, one from Google, and another from Carnegie Mellon University (CMU). The papers imply that the disk drive module (DDM) manufacturers have perhaps misrepresented their reliability estimates, and asks major vendors to respond. So far, NetAppand EMC have responded.
I will not bother to re-iterate or repeat what others have said already, but make just a few points. Robin, you are free to consider this "my" official response if you like to post it on your blog, or point to mine, whatever is easier for you. Given that IBM no longer manufacturers the DDMs we use inside our disk systems, there may not be any reason for a more formal response.
Coke and Pepsi buy sugar, Nutrasweet and Splenda from the same sources
Somehow, this doesn't surprise anyone. Coke and Pepsi don't own their own sugar cane fields, and even their bottlers are separate companies. Their job is to assemble the components using super-secret recipes to make something that tastes good.
IBM, EMC and NetApp don't make DDMs that are mentioned in either academic study. Different IBM storage systems uses one or more of the following DDM suppliers:
Seagate (including Maxstor they acquired)
Hitachi Global Storage Technologies, HGST (former IBM division sold off to Hitachi)
In the past, corporations like IBM was very "vertically-integrated", making every component of every system delivered.IBM was the first to bring disk systems to market, and led the major enhancements that exist in nearly all disk drives manufactured today. Today, however, our value-add is to take standard components, and use our super-secret recipe to make something that provides unique value to the marketplace. Not surprisingly, EMC, HP, Sun and NetApp also don't make their own DDMs. Hitachi is perhaps the last major disk systems vendor that also has a DDM manufacturing division.
So, my point is that disk systems are the next layer up. Everyone knows that individual components fail. Unlike CPUs or Memory, disks actually have moving parts, so you would expect them to fail more often compared to just "chips".
If you don't feel the MTBF or AFR estimates posted by these suppliers are valid, go after them, not the disk systems vendors that use their supplies. While IBM does qualify DDM suppliers for each purpose, we are basically purchasing them from the same major vendors as all of our competitors. I suspect you won't get much more than the responses you posted from Seagate and HGST.
American car owners replace their cars every 59 months
According to a frequently cited auto market research firm, the average time before the original owner transfers their vehicle -- purchased or leased -- is currently 59 months.Both studies mention that customers have a different "definition" of failure than manufacturers, and often replace the drives before they are completely kaput. The same is true for cars. Americans give various reasons why they trade in their less-than-five-year cars for newer models. Disk technologies advance at a faster pace, so it makes sense to change drives for other business reasons, for speed and capacity improvements, lower power consumption, and so on.
The CMU study indicated that 43 percent of drives were replaced before they were completely dead.So, if General Motors estimated their cars lasted 9 years, and Toyota estimated 11 years, people still replace them sooner, for other reasons.
At IBM, we remind people that "data outlives the media". True for disk, and true for tape. Neither is "permanent storage", but rather a temporary resting point until the data is transferred to the next media. For this reason, IBM is focused on solutions and disk systems that plan for this inevitable migration process. IBM System Storage SAN Volume Controller is able to move active data from one disk system to another; IBM Tivoli Storage Manager is able to move backup copies from one tape to another; and IBM System Storage DR550 is able to move archive copies from disk and tape to newer disk and tape.
If you had only one car, then having that one and only vehicle die could be quite disrupting. However, companies that have fleet cars, like Hertz Car Rentals, don't wait for their cars to completely stop running either, they replace them well before that happens. For a large company with a large fleet of cars, regularly scheduled replacement is just part of doing business.
This brings us to the subject of RAID. No question that RAID 5 provides better reliability than having just a bunch of disks (JBOD). Certainly, three copies of data across separate disks, a variation of RAID 1, will provide even more protection, but for a price.
Robin mentions the "Auto-correlation" effect. Disk failures bunch up, so one recent failure might mean another DDM, somewhere in the environment, will probably fail soon also. For it to make a difference, it would (a) have to be a DDM in the same RAID 5 rank, and (b) have to occur during the time the first drive is being rebuilt to a spare volume.
The human body replaces skin cells every day
So there are individual DDMs, manufactured by the suppliers above; disk systems, manufactured by IBM and others, and then your entire IT infrastructure. Beyond the disk system, you probably have redundant fabrics, clustered servers and multiple data paths, because eventually hardware fails.
People might realize that the human body replaces skin cells every day. Other cells are replaced frequently, within seven days, and others less frequently, taking a year or so to be replaced. I'm over 40 years old, but most of my cells are less than 9 years old. This is possible because information, data in the form of DNA, is moved from old cells to new cells, keeping the infrastructure (my body) alive.
Our clients should approach this in a more holistic view. You will replace disks in less than 3-5 years. While tape cartridges can retain their data for 20 years, most people change their tape drives every 7-9 years, and so tape data needs to be moved from old to new cartridges. Focus on your information, not individual DDMs.
What does this mean for DDM failures. When it happens, the disk system re-routes requests to a spare disk, rebuilding the data from RAID 5 parity, giving storage admins time to replace the failed unit. During the few hours this process takes place, you are either taking a backup, or crossing your fingers.Note: for RAID5 the time to rebuild is proportional to the number of disks in the rank, so smaller ranks can be rebuilt faster than larger ranks. To make matters worse, the slower RPM speeds and higher capacities of ATA disks means that the rebuild process could take longer than smaller capacity, higher speed FC/SCSI disk.
According to the Google study, a large portion of the DDM replacements had no SMART errors to warn that it was going to happen. To protect your infrastructure, you need to make sure you have current backups of all your data. IBM TotalStorage Productivity Center can help identify all the data that is "at risk", those files that have no backup, no copy, and no current backup since the file was most recently changed. A well-run shop keeps their "at risk" files below 3 percent.
So, where does that leave us?
ATA drives are probably as reliable as FC/SCSI disk. Customers should chose which to use based on performance and workload characteristics. FC/SCSI drives are more expensive because they are designed to run at faster speeds, required by some enterprises for some workloads. IBM offers both, and has tools to help estimate which products are the best match to your requirements.
RAID 5 is just one of the many choices of trade-offs between cost and protection of data. For some data, JBOD might be enough. For other data that is more mission critical, you might choose keeping two or three copies. Data protection is more than just using RAID, you need to also consider point-in-time copies, synchronous or asynchronous disk mirroring, continuous data protection (CDP), and backup to tape media. IBM can help show you how.
Disk systems, and IT environments in general, are higher-level concepts to transcend the failures of individual components. DDM components will fail. Cache memory will fail. CPUs will fail. Choose a disk systems vendor that combines technologies in unique and innovative ways that take these possibilities into account, designed for no single point of failure, and no single point of repair.
So, Robin, from IBM's perspective, our hands are clean. Thank you for bringing this to our attention and for giving me the opportunity to highlight IBM's superiority at the systems level.
Jim is an IBM Fellow for IBM Systems and Technology Group. There are only 73 IBM Fellows currently working for IBM, and this is the highest honor IBM can bestow on an employee. He has been working with IBM since 1968.
He is tasked with predicting the future of IT, and help drive strategic direction for IBM. Cost pressures, requirements for growth, accelerating innovation and changing business needs help influence this direction.
IBM's approach is to integrate four different "IT building blocks":
Scale-up Systems, like the IBM System Storage DS8000 and TS3500 Tape Library
Resource Pools, such as IBM Storage Pools formed from managed disks by IBM SAN Volume Controller (SVC)
Integrated stacks and appliances, integrated software and hardware stacks, from Storwize V7000 to full rack systems like IBM Smart Analytics Server or CloudBurst.
Mobility of workloads and resources requires unified end-to-end service management. Fortunately, IBM is the #1 leader in IT Service Management solutions.
Jim addressed three myths:
Myth 1: IT Infrastructures will be homogenous.
Jim feels that innovations are happening too rapidly for this to ever happen, and is not a desirable end-goal. Instead, a focus to find the right balance of the IT building blocks might be a better approach.
Myth 2: All of your problems can be solved by replacing everything with product X.
Jim feels that the days of "rip-and-replace" are fading away. As IBM Executive Steve Mills said, "It isn't about the next new thing, but how well new things integrate with established applications and processes."
Myth 3: All IT will move to the Cloud model.
Jim feels a substantial portion of IT will move to the Cloud, but not all of it. There will always be exceptions where the old traditional ways of doing things might be appropriate. Clouds are just one of the many building blocks to choose from.
Jim's focus lately has been finding new ways to take advantage of virtualization concepts. Server, storage and network virtualization are helping address these challenges through four key methods:
Sharing - virtualization that allows a single resource to be used by multiple users. For example, hypervisors allow several guest VM operating systems share common hardware on a single physical server.
Aggregation - virtualization that allows multiple resources to be managed as a single pool. For example, SAN Volume Controller can virtualize the storage of multiple disk arrays and create a single storage pool.
Emulation - virtualization that allows one set of resources to look and feel like a different set of resources. Some hypervisors can emulate different kinds of CPU processors, for example.
Insulation - virtualization that hides the complexity from the end-user application or other higher levels of infrastructure, making it easier to make changes of the underlying managed resources. For example, both SONAS and SAN Volume Controller allow disk capacity to be removed and replaced without disruption to the application.
In today's economy, IT transformation costs must be low enough to yield near-term benefits. The long-term benefits are real, but near-term benefits are needed for projects to get started.
What set's IBM ahead of the pack? Here was Jim's list:
100 Years of Innovation, including being the U.S. Patent leader for the last 18 years in a row
IBM's huge investment in IBM Research, with labs all over the globe
Leadership products in a broad portfolio
Workload-optimized designs with integration from middleware all the way down to underlying hardware
Comprehensive management software for IBM and non-IBM equipment
Clod is an IBM Distinguished Engineer and Chief Technical Strategist for IBM System Storage. His presentation focused on trends and directions in the IT storage industry. Clod started with five workload categories:
To address these unique workload categories, IBM will offer workload-optimized systems. The four drivers on the design for these are performance, efficiency, scalability, and integration. For example, to address performance, companies can adopt Solid-State Drives (SSD). Unfortunately, these are 20 times more expensive dollar-per-GB than spinning disk, and the complexity involved in deciding what data to place on SSD was daunting. IBM solved this with an elegant solution called IBM System Storage Easy Tier, which provides automated data tiering for IBM DS8000, SAN Volume Controller (SVC) and Storwize V7000.
For scalability, IBM has adopted Scale-Out architectures, as seen in the XIV, SVC, and SONAS. SONAS is based on the highly scalable IBM General Parallel File System (GPFS). File systems are like wine, they get better with age. GPFS was introduced 15 years ago, and is more mature than many of the other "scalable file systems" from our competition.
Areal Density advancements on Hard Disk Drives (HDD) are slowing down. During the 1990s, the IT industry enjoyed 60 to 100 percent annual improvement in areal density (bits per square inch). In the 2000s, this dropped to 25 to 40 percent, as engineers are starting to hit various physical limitations.
Storage Efficiency features like compression have been around for a while, but are being deployed in new ways. For example, IBM invented WAN compression needed for Mainframe HASP. WAN compression became industry standard. Then IBM introduced compression on tape, and now compression on tape is an industry standard. ProtecTIER and Information Archive are able to combine compression with data deduplication to store backups and archive copies. Lastly, IBM now offers compression on primary data, through the IBM Real-Time Compression appliance.
For the rest of this decade, IBM predicts that tape will continue to enjoy (at least) 10 times lower dollar-per-GB than the least expensive spinning disk. Disk and Tape share common technologies, so all of the R&D investment for these products apply to both types of storage media.
For integration, IBM is leading the effort to help companies converge their SAN and LAN networks. By 2015, Clod predicts that there will be more FCoE purchased than FCP. IBM is also driving integration between hypervisors and storage virtualization. For example, IBM already supports VMware API for Array Integration (VAAI) in various storage products, including XIV, SVC and Storwize V7000.
Lastly, Clod could not finish a presentation without mentioning Cloud Computing. Cloud storage is expected to grow 32 percent CAGR from year 2010 to 2015. Roughly 10 percent of all servers and storage will be in some type of cloud by 2015.
As is often the case, I am torn between getting short posts out in a timely manner versus spending some more time to improve the length and quality of information, but posted much later. I will spread out the blog posts in consumable amounts throughout the next week or two, to achieve this balance.
Special thanks to Anthony Vandewerdt, who sent me his version of this presentation that he planned to present in Australia next week. I "smartened it up" (or whatever the appropriate phrase is the opposite of "dumbed it down") for the technical audience.
Recovery procedures for single and double drive failures. A double drive failure on an XIV typically involves less recovery effort than traditional RAID5-based disk systems, and in many cases results in no data loss whatsoever. I provided details on this in my blog post [Double Drive Failure Debunked: XIV Two Years Later], so no need to repeat myself here.
Replacing the Automatic Transfer Switch (ATS) non-disruptively. To support either single-phase and triple-phase power sources, the XIV uses an ATS to take two independent power feeds, and distribute this out to the three Uninterruptible Power Supplies (UPS).
Built-in Migration capability to copy data off other disk systems over to the XIV.
Configuring Synchronous and Asynchronous mirroring using either the Fibre Channel or Internet Protocol ports.
Optimizing the use of XIV for VMware, AIX and other operating systems.
The IBM XIV Storage System is quite popular in New Zealand, with four times more boxes sold per capita than the other countries in the Asia Pacific region. I covered both the A14 model as well as the new Gen3 model.
Business Continuity/Disaster Recovery (BC/DR) Update: Lessons, Planning, Solutions
My colleague Vic Peltz from IBM Almaden presented on lessons learned from Hurricane Katrina and various other natural disasters. Unlike tradtional presentations the focus on technology, Vic took a different approach, focusing on people and procedures. I was here last year when the earthquake hit Christchurch on the south island, so I was well aware that BC/DR was top of mind for many of the attendees. Throughout this week, I have felt tremors, and many of the locals told me that these happen all the time.
Introduction to IBM Storwize V7000
I knew I was in trouble when the request for me to present Storwize sounded like something from [Mission Impossible]:
"Good morning, Mr. Pearson. Your mission, should you choose to accept it, involves presenting Storwize V7000 in Auckland, New Zealand. You may also present the Storwize V7000 Unified, but it is essential that you not cover the SAN Volume Controller or SONAS products from which they are based upon, as you will not have enough time. The audience is very technical, so be careful. As always, should any questions come up that you cannot answer, the conference coordinators will disavow all knowledge of your actions, nor reimburse your laundry charges. This message will self-destruct in five seconds."
Well, I accomplished my mission in 75 minutes. I was able to cover the block-only version of the IBM Storwize V7000, with support for clustering the control enclosures, expansion drawers and external storage virtualization. I then spent a few minutes on the block-and-file Storwize V7000 Unified, which adds support for CIFS, NFS, HTTPS, FTP and SCP protocols through two new "file modules", with integrated support for backup and anti-virus checking. I covered both IBM Easy Tier for sub-LUN automated tiering between Solid-State Drives (SSD) and spinning disk, as well as Active Cloud Engine for file-based movement between disk and tape.
Many people have asked me if there was any logic with the IBM naming convention of IBM Systems branded servers. Here's your quick and easy cheat sheet:
System x -- "x" for cross-platform architecture. Technologies from our mainframe and UNIX servers were brought into chips that sit next to the Intel or AMD processors to provide a more reliable x86 server experience. For example, some models have a POWER processor-based Remote Supervisor Adapter (RSA).
System p -- "p" for POWER architecture.
System z -- "z" for Zero-downtime, zero-exposures. Our lawyers prefer "near-zero", but this is about as close as you get to ["six-nines" availability] in our industry, with the highest level of security and encryption, no other vendor comes close, so you get the idea.
But what about the "i" for System i? Officially, it stands for "Integrated" in that it could integrate different applications running on different operating systems onto a [COMMON] platform. Options were available to insert Intel-based processor cards that ran Windows, or attach special cables that allowed separate System x servers running Windows to attach to a System i. Both allowed Windows applications to share the internal LAN and SAN inside the System i machine. Later, IBM allowed [AIX on System i] and [Linux on Power] operating systems to run as well.
From a storage perspective, we often joked that the "i" stood for "island", as most System i machines used internal disk, or attached externally to only a fewselected models of disk from IBM and EMC that had special support for i5/OS using a special, non-standard 520-byte disk block size. This meant only our popular IBM System Storage DS6000 and DS8000 series disk systems were available. This block size requirement only applies to disk. For tape, i5/OS supports both IBM TS1120 and LTO tape systems. For the most part,System i machines stood separate from the mainframe, and the rest of the Linux, UNIX and Windows distributed serverson the data center floor.
Often, when I am talking to customers, they ask when will product xyz be supported on System z or System i?I explained that IBM's strategy is not to make all storage devices connect via ESCON/FICON or support non-standard block sizes, but rather to get the servers to use standard 512-byte block size, Fibre Channel and other standard protocols.(The old adage applies: If you can't get Mohamed to move to the mountain, get the mountain to move to Mohamed).
On the System z mainframe, we are 60 percent there, allowing three of the five operating systems (z/VM, z/VSE and Linux) to access FCP-based disk and tape devices. (Four out of six if you include [OpenSolaris for the mainframe])But what about System i? As the characters on the popular television show [LOST] would say: It's time to get off the island!
Last week, IBM announced the new [i5/OS V6R1 operating system] with features that will greatly improve the use of external storage on this platform. Check this out:
POWER6-based System i 570 model server
Our latest, most powerful POWER processor brought to the System i platform. The 570 model will be the first in the System i family of servers to make use of new processing technology, using up to 16 (sixteen!) POWER6 processors (running at 4.7GHZ) in each machine.The advantage of the new processors is the increased commercial processing workload (CPW) rating, 31 percent greater than the POWER5+ version and 72 percent greater than the POWER5 version. CPW is the "MIPS" or "TeraFlops" rating for comparing System i servers.Here is the[Announcement Letter].
Fibre Channel Adapter for System i hardware
That's right, these are [Smart IOAs], so an I/O Processor (IOP) is no longer required! You can even boot the Initial Program Load (IPL) direclty from SAN-attached tape.This brings System i to the 21st century for Business Continuity options.
Virtual I/O Server (VIOS)
[VirtualI/O Server] has been around for System p machines, but now available on System i as well. This allows multiplelogical partitions (LPARs) to access resources like Ethernet cards and FCP host bus adapters. In the case of storage, the VIOS handles the 520-byte to 512-byte conversion, so that i5/OS systems can now read and write to standard FCP devices like the IBM System Storage DS4800 and DS4700 disk systems.
IBM System Storage DS4000 series
Initially, we have certified DS4700 and DS4800 disk systems to work with i5/OS, but more devices are in plan.This means that you can now share your DS4700 between i5/OS and your other Linux, UNIX and Windowsservers, take advantage of a mix of FC and SATA disk capacities, RAID6 protection, and so on.
To call [IBM PowerVM] the "VMware for the POWER architecture" would not do it quite justice. In combination with VIOS, IBM PowerVM is able to run a variety of AIX, Linux and i5/OS guest images.The "Live Partition Mobility" feature allows you to easily move guest images from one system to another, while they are running, just like VMotion for x86 machines.
And while we are on the topic of x86, PowerVM is also able to represent a Linux-x86 emulation base to run x86-compiled applications. While many Linux applications could be re-complied from source code for the POWER architecture "as is", others required perhaps 1-2 percent modification to port them over, and that was too much for some software development houses. Now, we can run most x86-compiled Linux application binaries in their original form on POWER architecture servers.
BladeCenter JS22 Express
The POWER6-based [JS22 Express blade] can run i5/OS, taking advantage of PowerVM and VIOS to access all of the BladeCenterresources. The BladeCenter lets you mix and match POWER and x86-based blades in the same chassis, providing theultimate in flexibility.
A lot of people ask me about IBM branding, as we have recently changed brands. In the past we had two separate brands, one for servers (eServer) and one for storage (TotalStorage). These would be fine if we wanted to promote their independence, but customers today want synergy between servers and storage, they want systems that work well together.
Last year, in response to market feedback, we crated a new brand, "IBM Systems" and put all the server and storage product lines under one roof. Over time, we will transition from TotalStorage to System Storage naming. This will occur with new products, and major versions of existing products.
Two other phrases you will hear in the names of our offerings are "Virtualization Engine" and "Express". These are portfolio identifiers. The Virtualization Engine identifier was created to emphasize our leadership in system virtualization, and we have products that span product lines with this identifier.
The Express identifier was created to emphasize our focus on Small and Medium sized business (SMB). It spans not just servers and storage, but across other offerings from other IBM divisions.
Of course, just renaming products and services isn't enough. Systems don't work together just because they have similar names, are covered in similar "Apple white" plastic, or have similar black bezels. Obviously, thoughtful and collaborative design are needed, with the appropriate amounts of engineering and testing. IBM is aligning its server and storage development so that the IBM Systems brand keeps its promise.