Subscribe to the RSS feed

Power-efficient drives are drives that slow down and go into a standby or idle mode and do exactly what they say they will do -- they save power. The challenge with these drives is that many manufacturers are putting these drives into standard array shelves, typically with the same power supplies and the same fans. The array shelf still has to be designed to assume that the drives will spin up at full power, because at some point they probably will.

Comment on this blog entry

As part of my normal routine I try to speak with as many data center managers as possible. A trend has appeared lately that I believe we are on the front end of. I am calling the trend power rationing. We have been told several times now over the past few weeks that data center managers are being given a hard limit as to how much power they can use. This is a shift from the more common "Reduce power consumption by x%" to "You can use X watts of power."

Comments(1)

Tiered storage no longer has the hype surrounding it that it did a few years ago. The concept was simple -- move data from expensive Fibre drives to inexpensive SATA drives. SATA drive technology was just coming into its own and the price and modest capacity made it a good fit for the concept. As a result, every storage manufacturer on the planet was proposing a tiered storage strategy. There were seminars, Webinars, white papers (guilty as charged, I wrote more than a few of them), yet only a fraction of accounts ever implemented the strategy.

Comment on this blog entry

Storage will be one of the first steps many will make in using cloud services. In fact, many users have already taken that first step without even knowing it. They are using services like online storage, backup, and archive. Online backup is there, because of block-level incremental and data deduplication technologies; sending backup data over a network connection is not the impossibility that it was even a few years ago. Also, these companies have been in existence for quite some time, so there's comfort in using them.

Comment on this blog entry

VMware had its first bad day yesterday and in what amounted to piling on, by the time you got through all the blogs and articles, you would think they were folding up the VMware tent.

Comments(1)

Last week we had an entry introducing everyone to cloud computing and cloud storage. As promised, it was and will be the first of many entries on the topic. In this entry we're going to start looking at some of the plumbing that will sustain the cloud. The look won't be exhaustive, and my intent is not to mention everyone that may have a role to play. I may simply not know them all yet or be unaware of the role they think they play in cloud storage.

Comment on this blog entry

Another form of data mover is the out-of-band data mover. Unlike Global Namespaces or agent-based data movers, these data movers crawl selected servers when doing their analysis. As they access each file, they analyze it to see if meets any criteria that you might have set for data movement. Since this crawl is merely a scan of the file system, as long as the out-of-band data mover supports the type of network file system that your servers use, then it will work. Not surprisingly, most of the players in the space support both NFS (for Unix systems) and CIFS (for Windows systems). Companies that offer this type of solution include Enigma Data Solutions with its Smartmove product and Arkivio's Autostor (recently acquired by Rocket Software).

Comment on this blog entry

As I've been following the devastating floods in the Midwest and specifically Iowa, I can’t help but say something from a disaster recovery viewpoint. Clearly my heart goes out to the personal losses being suffered by thousands of people in the area, but part of my nature is always to look for ways that companies survive. I have seen a number of stories with company’s stock price being affected by not being able to maintain business operations. In some cases, this makes sense, especially in agriculture for the region but for others it does not. In all sizes of business, there is some requirement to protect data but it does differ. This entry we will focus on SMB Strategies.

Comment on this blog entry

Today Adaptec dumped their money loosing Snap Appliance division, once as much a mindshare leader in NAS as NetApp, to Overland Storage for $3.6 million after buying it just 4 years ago for $100 million. Overland gets a quality line of NAS appliances to add to its mix of tape libraries, REO VTL/disk backup appliances and Ultamus Fibre Channel RAID arrays along with a sublet of Snap's plant and around 50 employees. Adaptec will keep the top of the line 700 series iSCSI arrays and get to concentrate on RAID controllers.

Comment on this blog entry

It seems like the hype-o-meter on cloud computing and cloud storage has been turned up a few notches lately. How real is this emerging market and how will the players begin to settle in? At its most simplistic, cloud storage is disk at the end of a wire that resides outside of your data center. It creates a "storage as a service" model that is delivered over the Internet. Many are positioning this as storage for your older digital assets, essentially an archive.

Comment on this blog entry

Storage virtualization is often billed as what I call a "Time To" product, meaning that it reduces the time it takes IT to respond to demands on the business. Virtualization shortens the amount of time that it takes to respond to a provisioning request, allowing for more rapid deployment of storage assets. IT departments also should consider storage virtualization if they need to flatten or shrink their budget.

Comment on this blog entry

In last week's entry I discussed Global Name Spaces as a data mover for moving data to and from a disk-based archive. In addition to a Global Name Space there are other tools to move data to and archive. I find that the other solutions typically fall into one of two camps; Agent-based data movers or crawl-based data movers. There's also another category of monitoring tools that don't actually move the data but tell you what should be moved, leaving the rest up to you. In this entry we'll focus on agent-based data movers.

Comment on this blog entry

In speaking with an IT manager the other day, he was complaining about running out of drive letters and the difficulty that moving away from using drive letters was causing his users. He was looking into Microsoft DFS and was looking for other solutions since he had a mixed environment of Unix and Windows. Global Name Space solutions like those available from Acopia or built into OnStor NAS products are ideal for solving the complexity of managing multiple drive letters or teaching users different paths to servers while supporting multiple protocols like CIFS and NFS.

Comment on this blog entry

I saw a recent claim by Sun that Solid State Disk Drives (SSDs) consume 20% of the energy that traditional storage systems do. While I can't verify that to be the case, it makes sense. Texas Memory Systems, the veteran of the SSD space, recommends that for real power savings, companies should compare a SSD with a storage array that is configured to deliver the same level of performance that an SSD can.

Comments(2)

As a business grows and the demands on IT increase, there comes a point where the young data center has to consider such initiatives as server virtualization, advanced backup software, disk-to-disk backup, and deployment of its first SAN or NAS. Storage consolidation via a networked storage solution (be it SAN, NAS, or both) provides a foundation for those other early initiatives and is a logical first step.

Comment on this blog entry

In this third segment on reducing backup windows, the focus will be on getting rid of the data that no longer needs to be backed up. If you're like most of the customers we speak with, well over 85% of the data that you backup during your full backup hasn't changed since the last backup and 70% hasn't changed in the last few years. Yet, every week, it's methodically backed up. If you could eliminate this data, that means in a 10 TB environment you could reduce your full backup set to 1.5 TBs, or worst case to 3 TBs. That will have a dramatic and positive impact on your backup window.

Comment on this blog entry

As major vendors ready for entry into the solid-state disk (SSD) market with Flash memory systems, don't count out the traditional RAM SSD. Even though RAM SSDs are more expensive per capacity, companies like Texas Memory Systems are seeing continued growth in RAM-based SSD systems. Why? RAM SSDs have two advantages: speed and reliability.

Comments(3)

Your company (probably) has rules about how frequently systems get backed up, e-mail gets deleted, and other data-retention issues. But would those policies hurt if your company was suddenly yanked into litigation, especially noncompete, patent infringement, or trade-secret cases?

Comments(2)

In a recent entry I pronounced 'speed is dead' as it relates to solving the backup window problem. As the entry indicates, the NEED to reduce the backup window continues to be a desire. The ABILITY to reduce the backup window is the challenge. Due to the network infrastructure, the ability of the servers being protected to send that data fast enough, as well as a host of other issues, are the big limiters now in backup window reduction.

Comment on this blog entry

The company teams with Citrix to carve out a chunk of the server virtualization market.

Comment on this blog entry

Answering the question "Why would anyone want to dedupe as a post process" with a data-ingestion rate of a whopping 9.5 GB/s (Yes, that's GigaBYTES per second), Sepaton announced its newer, bigger faster virtual tape library, imaginatively named the S2100-ES2 VTL Series 1000 at the Symantec (formerly Veritas) Vision conference in Las Vegas this week.

Comment on this blog entry

The VTL company says its new products can deduplicate and store petabytes of data.

Comment on this blog entry

In storage, there's always discussion about consolidation; taking all your dispersed storage assets and consolidating them to a single storage system. But there's a different kind of storage fragmentation going almost unnoticed in metadata, or data about data. Many applications create metadata -- backup systems, data movement or archive applications, data management applications, and content search applications -- but only a few consolidate them.

Comment on this blog entry

Despite well-received demos at the NAB show in April and promises then to ship its long-awaited Tapestry holographic storage drives and media in May, InPhase Technologies has once again missed a delivery date and is now promising drives and media for December. Since the first promised delivery date was back in 2006, I'm not holding my breath. It's too bad, as we could really use a high-capacity, random access, WORM storage device that didn't draw power when idle like the 300-GB Tapestry promises to be. For now, Plasmon's 60-GB UDO-2 will have to do.

Comment on this blog entry

In our final entry about finding emerging technology, I'll look at the third motivating factor when selecting an emerging technology company -- going with a company that is solving a problem that's not entirely unique, but they are just flat out doing it better.

Comments(1)

A friend of mine runs a small insurance company and they only have two servers, but that data is as critical to them as the hundreds of terabytes that Exxon Mobile stores is to them. While he does backups, it is to another disk drive, and he doesn't take the hard drive home with him. In fact, to be honest, the second drive is installed internally inside one of the servers. What if his office catches on fire or gets flooded?

Comments(1)

In the first entry about deciding on an emerging technology company, I discussed the issue of price being a key motivator. In this entry I'll discuss selecting an emerging technology company because it is the only one that's solving a problem you have.

Comment on this blog entry

In my recent article on data deduplication on InformationWeek's sister site, Byte and Switch, a question of speed impact came up. As we talk to customers throughout the storage community about backup priorities, a surprising trend continues: the importance of shrinking the backup window has become less of a priority for disk to disk backup solutions. Why?

Comment on this blog entry

In the last week another new storage startup is launching a new product, another just received another round of founding, and still another announced it was being purchased. This happens almost every day with technology startup companies, especially in storage.

Comment on this blog entry

Server virtualization helped justify and broaden the use of the SAN by leveraging networked storage to enable features like server motion. In similar fashion, companies such as Scalent Systems are using infrastructure virtualization to further justify and broaden the use of a SAN by bringing those server virtualization capabilities to nonvirtualized systems: the ability to move or start new application instances in a matter of minutes after powering on and booting what was a cold, bare-metal server.

Comment on this blog entry

When iSCSI first began to appear, there were several companies -- LeftHand Networks, EqualLogic (now owned by Dell), and others -- which developed storage solutions based solely on the protocol. But what these companies had really developed was a storage software solution that probably could have run on any protocol, although they choose iSCSI. My opinion is that this was as much a marketing decision to ride the iSCSI wave as it was a technology decision.

Comment on this blog entry

I recently met with a client that had a 45-day retention policy for ALL data. I've heard of this kind of policy for e-mail, but I don't recall ever hearing of it for all the data in the enterprise. Is this realistic and can you get away with that short of a data retention policy? Not really, and here's why.

Comment on this blog entry

After last night's party, which featured the Goo Goo Dolls, EMC World is in full swing. The morning keynotes said about what you'd expect them to say, talking about the huge growth in stored data and all the value that can be gotten from that data. Then, of course, there was a lot of talk about new products. And while I guess I shouldn't have been surprised, I was disappointed to hear almost nothing about interoperability or standards.

Comments(1)

In a recent briefing with a Storage Resource Management Software manufacturer I heard the quote that I have now heard 1,001 times; "Excel is the No. 1 Storage Resource Management software." People are using Excel to do SRM work more often than specific SRM tools. They are manually inputting storage capacity, storage used, and other storage information into Excel spreadsheets.

Comments(1)

As I talk to vendors about storage solutions for non-OLTP applications, from backup and archiving to supporting massive, object-based Web applications like photo sharing, I've been seeing more solutions based on the RAIN (Redundant Array of Independent Nodes) architecture.

Comments(3)

Data deduplication has done much to optimize disk backup storage, but can those same efforts be successful in primary storage? Primary storage is, of course, different than secondary storage. Any latency can cause problems with applications and users. Thin provisioning, which I wrote about last week, can help a great deal, but once the data is actually written, the space is allocated. How can you make primary storage take up less space?

Comment on this blog entry

The current poll on InformationWeek's sister site Byte and Switch, "Sun Down," paints a very bleak outlook for Sun storage. The final question, "Do you think they should exit the storage hardware business?" has a surprising 57% say that it should. Can Sun save itself? Probably not, but I can ...

Comment on this blog entry

As the economy slows down and budgets tighten up, once again IT professionals are being asked to do more with less (does anyone remember when you were allowed to do less with more?). How can you tighten up your storage processes one more time? The first technology that I would count on to help is virtualization. For virtualization to truly pay off it must be more than just server virtualization.

Comments(5)

In a previous entry I wrote about the importance of moving data from primary storage to another platform. The roadblock is how to move that data from expensive storage to secondary storage. The traditional approach of deploying an agent on every server that monitors all the files and then moves files that haven't been accessed to a lower class of storage hasn't worked well in the enterprise. There are a variety of reasons, but most of the issues are the deployment and management of that many agents, plus the challenge of leaving stub files (files that point to where the actual file was moved) and managing those files.

Comment on this blog entry

A few years ago it was easy to divide IT organizations into haves and have nots. The haves used Fibre Channel SANs and array replication to dedicated disaster recovery sites over high bandwidth dedicated links or dark fiber. The have-nots used SCSI DAS (Direct Attached Storage) on their servers and, if they did real time replication at all, used server-based replication solutions like Double-Take or CA's WANsync.

Comments(2)

Will NFS become the predominant storage deployment method for VMware implementations?

NFS didn't need to be saved, but because of VMware its use has been broadened beyond the traditional Unix implementations. Instead of creating a LUN for each VMware Virtual Disk (VMDK), with NFS you manage multiple VMDK files on a single NFS Volume. This makes sense because VMDK's are files, not actual disks.

Comments(9)

Your servers are probably bloated with data that is years old and yet despite your retention policy, if you have one, you keep it all. The relatively inexpensive price of disk capacity has made it easier to keep everything on primary disk storage. When you think of primary storage, you think of active data, databases, current documents, e-mail, etc. -- but because of the affordability of storage, it basically also has become the archive. Data is kept on disk, "just in case." It seems easier to simply add more disk space to primary storage than to force users to manage it; as a result, "Data Keepage" begins.

Comment on this blog entry

With stimulus checks on the way, the question I'm sure you're asking is how you can use yours to help out the storage industry. You are, aren't you?

Comments(6)

As data deduplication matured last year, the constant question I was asked by industry analysts was "Isn't this just a feature?" The question implied that anyone that was specifically in the data deduplication space was going to be erased by the larger manufacturers as they added deduplication to their offerings. It seemed logical, but hasn't occurred. The major manufacturers have struggled putting together viable strategies for data reduction and, to some extent, it's really not in their best interests to reduce the amount of storage required.

Comments(1)

Your storage has holes and the data is leaking right out of it...

Lost tapes continue to capture headlines. Recently I meet with a client that had 300 GB of data worth $500K stolen. How did they know it was worth $500K? That's what they paid for it. The disk was encrypted and the network was pretty well locked down. So how did the master thief hack into the network and steal the data? Through the front door -- with a USB hard drive in his pocket.

Comment on this blog entry

Welcome to the Storage Blog at InformationWeek. As I take over the reins from Terry Sweeney, who has moved on to be editor in chief at TechWeb's Internet Evolution site, the first order of business is a quick introduction. I am a veteran of the storage area from the late '80s. I have worked at almost every angle of the storage space, from customer to supplier to integrator and now finally as analyst and writer. As founder of Storage Switzerland, I'm fortunate to have the opportunity to meet with storage administrators and end-users as well as suppliers from around the world. Part of what we learn during those conversations will make it into this blog.

Comment on this blog entry

When was the last time you got a call from a headhunter? Have those calls cooled down lately? Think it's due to the weak economy, or do you think it's possible that you're just not that "hot" anymore?

Comments(6)

Their success is no guarantee of success for other vendors, but dismal results from these two companies would augur poorly for the rest of the storage industry, to say the least. And quite apart from my glass half-empty outlook, I'm not sure how much weight to give the recent positive financial performance from EMC and IBM.

Comments(1)

If storage were an audio receiver, we'd be flirting with that "9" or "10" mark on that big black dial. But we're talking capacity here (and maybe speed), as vendors appear to bend the rules of physics by cramming more bytes than any space or drive should be able to accommodate.

Comments(1)

Data Domain and Quantum get smacked around pretty good over how "in-line" their products really are. IBM bought Diligent. And deduplication-come-latelies ExaGrid and FalconStor add new gear to the mix. Geez, maybe there really is a market here.

Comment on this blog entry