February, 2009

This Week in Storage (2-27-09)

See:

• Tweek N Storage 2-27-09
• Taylor’s Take on Delicious
• The Storage Buzz:

In: “The Current Environment” | 5 Minutes Ago: “These Economic Times” | Out: “The Recession”

This Week’s Blog:

SRM Tools – an Extreme Cash Cow?
I have personally seen raised frustrations around SRM tools from end-users ever since the “Single-Pane-of-Glass” glory days – pitched by every storage vendor under the sun…

Storage News:

VMware makes world takeover bid
VMware Infrastructure 4 will now be called “vSphere.” VMware CEO Paul Maritz at VMworld related vSphere to a “giant software mainframe” with management at the service level. This is exciting, in my StorageTek days I helped open-source StorageTek’s first an only open source initiative – OpenTMS. The thought was to embed data management services in the OS-layer, similar to Mainframe’s DFSMS offerings. At Sun, I became an Open Storage advocate with the agenda of seeing DFSMS-like functionality embedded in OpenSolaris. But with Mr. Maritz’s latest keynote, I now see that VMware “gets it” and may just have the technology, resource, and momentum to actually pull it off…

Chuck’s Blog: It’s Happening Again
Chuck sees a new trend happening that looks like an old one - the Golden Age of UNIX was in the mid-1980’s. Will the new Golden Age of the 2000’s be VMware???

Will the SAN Market become a Feature?
A bright engineer at StorageTek used to say, “Never put a product where a feature should be.” He was talking about tape encryption, when we put an encryption chip right next to the compression chip on the STK T10000. This was a better approach than a separate appliance. My friend, Mr. John McArthur, asks a similar question. And it looks like StorMagic is trying to turn a SAN into a feature…

Products of the Year 2008
And the winners are….VMware Site Recovery Manager takes Gold for Backup & DR software; Data Domain DD690 wins Gold for Backup hardware; BlueArc Titan 3200 takes Gold for Disk systems; Riverbed Optimization System (RiOS) takes Gold for Networking; and VMware VMotion brings home Gold for Storage management tools.

EMC beefs up Celerra NAS
The Celerra NS-120, NS-480, and NS-960 models pull in hashing codes from Avamar for file-level dedupe, but no block-level dedupe yet. Additionally, code from the Kashya file-system crawler was pulled into Celerra to locate inactive files for dedup and compression. On the hardware side, larger disk systems were added from Clariion CX4 (NS-960 has up to 960 drives & 8 blades) – and the new NS series will support Flash drives. Also see Chuck’s blog, NAS Evolved.

HP Joins Solaris Community (Live Free or Die)
Sun just inked a deal with HP’s ProLiant server business. Now you can get Solaris on HP, IBM, and Dell servers. Good for Sun’s Solaris business (and a testament to Solaris’ strength as an OS). Good for customers. Good for HP because they can now access customers that won’t move off of Solaris. But I suspect difficult for Sun’s server business - if you want Solaris, but are happy with your HP hardware, no need to change. On the other hand, if you are not happy with your HP hardware and like Solaris, you may look at Sun’s now.

Latest Sun/NetApp clash: SPEC SFS
Yet another benchmark debate. I managed the Sun Storage benchmark team for a short stint, and in that time I learned a lot about benchmarks, SPEC, and SPC. Without a lengthy post, I can make two general observations: 1. There is a LOT of science that goes behind these benchmarks and a lot off good people that try to make them fair. 2. If a vendor’s product performs well, then there is little complaint. But if it does not, that vendor will always discredit the benchmark and/or try to change the “criteria” so that vendor’s product performs better.

Iron Mountain opens file archiving service
Iron Mountain Digital rolled out a new cloud storage offering this week with a service called Virtual File Store (VFS).

SRM Tools – an Extreme Cash Cow?

In the storage blogosphere, Storagebod’s posts hold particular weight for me because he is one of the few bloggers that are NOT working for a storage vendor. He writes from an end-user perspective…because he is one.

I found his latest post representative of storage user’s thoughts on the topic of Storage Resource Management (SRM). In his Extreme Cash Cow – Redux post, he writes about challenges he had with ECC, but his comments are geared towards general SRM providers.

I have personally seen raised frustrations around SRM tools from end-users ever since the “Single-Pane-of-Glass” glory days – pitched by every storage vendor under the sun.

What’s going on?

My take on SRM can be summed up on a recent client call. We were talking about developing a storage strategy and storage infrastructure optimization plan:

Client: We already deployed a Storage Optimization plan.

Me: Great! How did you do it?

Client: We bought an SRM tool from XYZ vendor (one of the big disk vendors)

Me: Great, so how did it go? Did you return wasted space to free pool? Did you locate allocated but unused space, orphaned space and files, inert or unreferenced data, etc.?

Client: Well, no. It didn’t work.

Me: Why? What happened?

Client: Well…we bought the tool, and had some issues with deployment. And we couldn’t get the tool to accurately identify inert space. And we needed some information from our application admins, but they wouldn’t cooperate.

Me: So what did you do?

Client: We told management we needed another headcount. To manage the SRM tool and extract and interpret the data from it. It turned out to be a full-time job.

Me: What did management say?

Client: No. They said they freed resource to buy the tool, but can’t justify more headcount to manage it.

In essence, this optimization/SRM tool turned into Shelfware. Storagebod sums up part of the problem on his blog – this stuff isn’t easy. It’s pretty complex and each environment is different, so building one tool to management everything is extremely hard to do.

So what’s the solution?

The solution is this: You need an expert with your expert SRM tool. It may not be what you want to hear (we all want a magic bullet solution) - but it is reality. Consider these tasks:

• First you need to install it and deploy it correctly (not always easy).
• Next you need to configure it based on your needs and priorities.
• Then you need to collect data and usage patterns for a set period, so you monitor all the peak and valley times.
• Then you need to write a clear and digestible PLAN based on the data that leads to ACTIONS that will lead to RESULTS.
• Then you need to align your organization around this plan.
• Then you need to deploy the plan, track metrics, and report on its success.

A single tool can’t do this. A person with a tool has to. So, we have two choices here

1. Justify headcount to go with the tool
2. Buy the tool and storage expert together as a service

Storagebod cautions in his blog post that the service cost should be more than just fixing the tool and getting it to work properly. What clients need is a fact-based Storage Optimization Plan and Roadmap based on tool findings.

If you are not buying that (the reason why you want an SRM tool in the first place) then you are buying Shelfware.

What SRM tool do I use?

Again, it’s not about the tool alone, but the interpretation of the tool’s data. But, if you are interested, the best tool I have seen is from pure-play SRM vendor Tek-Tools. They cover primary, backup, and virtualized environments. The folks there are great and the tool continues to improve. But again, make sure you have a storage expert or service to go with that tool to accomplish what you are really looking for.

This Week in Storage (2-20-09)

• See the Tweek N Storage (2-20-09)
• Taylor’s Take on Delicious (2-20-09)
• Listen to Beth’s Storage Headlines
• The Storage Buzz:   In: RAID 6 | 5 Minutes Ago: RAID 5 | Out: RAID 10

Sun jumbles key management picture
Right after EMC/RSA, HP, and IBM proposed a new Key Management protocol through OASIS, Sun releases an open-source protocol. Sun says the proposed OASIS protocol is lower-level – which wouldn’t surprise me. But OASIS claims its protocol will address more devices (disk, tape, laptops, mobile devices, switches, applications). This also doesn’t surprise me as the Sun protocol got its roots in Tape Drive encryption, and OASIS members (esp RSA) play in multiple areas of the market. Another standards battle to watch, although the majority of vendors are with OASIS…

Brocade sees slowdown in convergence demand
Quick primer: iSCSI sends SCSI commands in TCP/IP over Ethernet = cheaper SANs. FCoE maps FC natively over Ethernet = iSCSI competitor. Stephen Foskett gives a great summary of the FCoE vs. iSCSI battle. So now Brocade has slowed its FCoE rollout – but is this because market demand is low; or Brocade is focusing more on its FC roots in this tough economy? (Be sure to read Scott Lowe’s excellent question on his blog post, “Is Unified Fabric an Inevitability?” 

Storagezilla: Emulex converges
While we are talking convergence, Mr. Zilla gives a great summary of the recent Emulex convergence announcements. It was a good week for the HBA player – they celebrated their 30th anniversary, rang the bell at the NYSE, and announced a ton of new products. New products include their Universal Converged Network Adapter (CNA) called OneConnect which handles multiple network protocols (Ethernet, FC, iSCSI); as well as their EmulexSecure Encryption HBA.

Storage industry debates standardized cloud API
Moving on from Key Management protocols…..now we need to hash out Cloud protocols! A standard API for moving data in and out of the cloud. My take is that it is way too early for this. Startups will try to make a standards play to get more traction, Amazon won’t play unless they really need to. And today Amazon is the furthest ahead in the Cloud race – so they don’t need to. How easy Clouds are to access and utilize is still a differentiator for companies – so any standard is far off in my book.

This Week in Storage (2-13-09)

• See the Tweek N Storage (2-13-09)
• Listen to Beth’s Storage Headlines
• The Storage Buzz:

In: Cloud Storage | 5 Minutes Ago: Utility Storage | Out: Grid Storage

Storage Explained: Cloud storage
Is your definition of Cloud Storage…cloudy? This article gives a good general overview and definition. Cool stat: Amazon S3 held 800,000 objects at the end Q2 06, grew to 5 billion in a year, and then to 40 billion by the end of 2008.

HP releases first LeftHand iSCSI SAN products
Good to see after last year’s $360M acquisition. The new SAN product comes in a two-node configuration (with HP ProLiant servers of course), is SAS-based (15,000 rpm), and offers 4.8TB at $35,000. HP is positioning LeftHand products for the server virtualization market.

IBM updates DS8000, XIV, deduplication and cloud
Speculation of DS8000’s longevity arose after the XIV acquisition at IBM. But it looks like IBM is still investing - DS8000 will support FC-attached SSDs (from STEC), and DB2 for z/OS will automatically place active database tables on SSD. DS8000 will also offer Seagate disk encryption. Still no thin provisioning however.

HP, IBM, EMC propose encryption key management standard
What happens when you lose your encryption key? You lose your data! So, the “key” to encryption is good Key Management. The right players (major vendors + RSA) are aligned around the newly proposed Key Management Interoperability Protocol (KMIP) spec. This is one area where a standard is needed.

Obama stimulus plan offers funding for storage, IT industries
I like the technology investments in the stimulus plan, for example - $20 billion for digitizing healthcare records. More money coming into our industry is a good thing. But, like a lot of other taxpayers, I’d still like more detail on the planned stimulus spending and anticipated results. That’s a lot of our money going to a lot of different places, thrown together in a very short amount of time…

IBM XIV Announcement, Meh?
Storagebod chimes in on IBM’s XIV announcement…he’s not too excited. IBM launched a smaller version of XIV – it had an 80TB model last year, and now has a 27TB model. Still no added software functionality like replication, dedup, etc. So the jury is still out for XIV and IBM is still looking for a good market for it – maybe it started too high (Moshe would like nothing better than to take out DMX), and they are trying to make it play more down-market.

Quantum holographic storage
Awesome article for the storage geek. If the air I am breathing feels a little too thick, it may be because some scientists have crammed bits of data into the electrons around me…

Top 4 things that impact storage costs
David Merrill is spot on with his potentially wasted space analysis. He talks about four main capacity-draining causes. Although we have identified around 8-10 causes, he hits the nail on the head…

• Get links on Delicious

Getting Real with RELDATA

A couple months ago we had a client that needed to migrate production data from one data center to another across geographies. There were a couple of complications, so our team put their heads together on a solution.

A Client’s Need
We determined it would be faster (and cheaper) to replicate the data from Data Center A’s production environment to some sort of storage repository. Then we would truck/plane that repository to Data Center B – which had a much faster transfer rate than sending the data over the network (given the amount of data we were dealing with). Once at Data Center B, we could copy the data from our storage repository to its new home. But the production data at Data Center A would have changed over the time the replicated copy was on its trip. So once were up at Data Center B, we would need to sync the delta in data to capture all these changes. This could happen over a network line, as the delta in data would be much smaller than the entire production environment.

It sounded like a good plan – and we had everything we needed to do it but a unified appliance that could handle iSCSI, FC, and NAS protocols as well as WAN replication.

Enter RELDATA
We sat down with the folks at RELDATA, troubleshot the problem, threw a couple tough questions their way, and…were very impressed. What stood out to me was the following:

• RELDATA is really a unified storage appliance/gateway built from the ground up – they offer iSCSI, FC SAN, and NAS in a virtualized appliance – in 1GbE and 10GbE flavors. They weren’t a NAS company moving into the SAN market; or a SAN company moving into the NAS market – they set out to build a virtual/unified appliance.
• They offer local & WAN data replication & snapshot functionality. Additionally, the appliance looks very simple to install/manage. In fact, their management council was pretty simple and slick with some cool wizard functionality.
• One for the kickers for me was cost/value. It is priced well (website says MSRP is $40k for a 12TB iSCSI SAN, $85k for a 48TB system with SAS under the hood.) But the real value is in software licensing. It is very simple and has NO capacity licensing, which is refreshing in a world where every new feature seems to come with a complex licensing price tag. In fact, they have all inclusive software pricing - NAS, IP SAN, Global WAN Replication, and Virtualization come included. Pretty cool.

RELDATA is a young company, and its roots started in Europe (although they are now HQ’d in NJ). But they are old enough to have several successful implementations under their belt, and newer versions of their systems are coming out. I also found the people and support in the company to be very good and responsive.

RELDATA’s 9240i System

The 9240i is their latest system, some quick specs and highlights:

• Includes 12TB SAS Storage in 2U that can scale from there. Storage can be added via JBOD expansion shelf. Systems can also be clustered.
• They claim 70,000 IOPS and 820MBps performance.
• You can choose the licensed functionality you need right away (iSCSI SAN, NAS, etc.) and turn on optional licenses when needed.
• Block-level replication + snapshot included with software.
• Offers heterogeneous virtualization to play with existing assets.
• Mix 1GbE and 10GbE connectivity with either six 1GbE ports (expandable up to 16) or up to eight 10GbE ports.

A Solid Appliance
So, if you are looking for a practical, solid unified appliance for iSCSI SAN, NAS, replication, migration, consolidation, etc. take a look at RELDATA. It may not have all the bells and whistles as larger vendors, but it looks to be a well-built and designed gateway/appliance that can get the job done – simply and affordably.