Subscribe to the RSS feed

Storage compute is the amount of processing power that the storage system/array has to be able to handle storage I/O tasks. How powerful your storage processor is directly affects how many drives can be sustained by your system while maintaining full performance and how long it will be before you need to add an additional storage system. The flexibility and efficiency of storage compute engines can maximize the storage dollars you have in your budget.

Comment on this blog entry

Getting the most out of every storage dollar is critical in this economy and as we discussed in our last entry, viable options for optimizing file based primary storage are available now but as of yet solutions that can compress and deduplicate block I/O storage are not yet readily available. But all is not lost, there are things you can do to lower your primary storage block I/O costs.

Comment on this blog entry

In this economy, maximizing what you have and cost justifying what you need now becomes a much sought-after skill. The IT budget and the storage budget along with it are not growing in many organizations and I often hear that the budget is the same but they are not allowed to spend right now, which is worse than the budget being cut. Regardless spendable IT dollars are a precious commodity.

Comment on this blog entry

How does your organization look at storage in the data center? Is it something you have to live with or is it something that can increase the organization's revenue or improve customer satisfaction? How do you make storage strategic to your organization?

Comments(1)

There are many reasons to justify storage encryption; tapes falling off the back of a truck on the way to a vault for disaster recovery purposes is one, but when it comes to disk encryption not many have made the effort to encrypt disk based data. While that disk array is in your environment it should be relatively secure, except from internal threats, but what about when you decommission a storage array?

Comment on this blog entry

When an application is slowing down because of poor storage I/O performance, the first step most IT professionals will take to solve the problem is to increase the physical drive count on the RAID group assigned to that application. How do you know when this will work and what are the best ways to implement this?

Comments(3)

When vendors talk about thin provisioning you will hear how it reduces CAPEX and how it increases storage admin efficiency. What you don't hear very often is how thin provisioning can reduce the cost of failure.

Comments(1)

The Backup Accelerator appliance works with Isilon's NAS cluster to speed up backups of file-based data.

Comments(1)

Cloud storage for the most part is being used today as a backup medium or for collaboration, but the next big step and where cloud storage may be at it's best is an archive repository to meet the enterprise's growing data retention and compliance demands.

Comments(1)

A couple of days ago I was speaking at an event in Dallas and was reminded that sometimes those of us in storage get too wrapped up in, well, storage and that IT professionals have other things to worry about than just storage. I asked the audience how many of them had done anything with deduplication. Only 30% had, although 100% wanted to know more.

Comment on this blog entry

A week ago I wrote about the user impact of NetApp buying Data Domain. Today we are back at it with EMC making a bid for Data Domain. The first take away for a user: Data Domain has to be one of the safest technology purchases you can make. Clearly the company has something that other companies want, and it's not likely to go anywhere anytime soon.

Comment on this blog entry

Backups have long been a source of pain and frustration for enterprises of all sizes; they are constantly causing problems because the growth and value of data is increasing faster than the network's ability to deal with that data. The problem keeps many IT professionals awake at night and most surveys indicate a low confidence in the ability to recovery from a disaster, but how can backups be made obsolete?

Comments(3)

Wrapping up our series on choosing storage projects, part of the conversation has to be what is more important, CAPEX or OPEX? Almost every storage project you decide to embark on will have to be brought to management as something that is going to either reduce your capital expenditures or lower your operational expenditures. Which part of these projects are more important?

Comment on this blog entry

In a prior entry we discussed how to select your next storage project and suggested that most IT professionals are going to focus on smaller projects. Basically filling in pot holes as opposed to paving a new road. There are times however, even when staffing is scarce and money is tight that you need to undertake a big storage project to fix the problem, essentially putting a new road in.

Comment on this blog entry

With yesterdays announcement of NetApp’s intention to buy Data Domain, a question that needs to be answered by IT professionals is how does this affect them? In our blog on Information Week's sister publication Byte and Switch we looked at the industry impact, but what about the users? There are current customers, companies that were thinking about buying Data Domain and of course companies that were using an alternative solution. How should each of these parties take this news?

Comments(3)

Unfortunately the reality is often that the storage project you are going to work on next is based on the one that users are screaming the loudest for that you can also afford and it usually contains "add capacity". Is there a better way to go about selecting your next storage project?

Comment on this blog entry

EMC launches a new online storage service based on Atmos, its cloud storage platform. AT&T also announces it will sell online storage using Atmos.

Comments(1)

What if "do more with less" was more than a marketing phrase? What if you really could do more with less? There are storage solutions available now that really let you improve efficiency but one of the key components of deciding if a do more with less project is successful, is to measure the return on efficiency. For the dollars invested are you X more effective at your job?

Comment on this blog entry

Continuing our examination of the resurgence of direct attached storage (DAS), in this entry we look at the ever-increasing internal capacity of DAS in servers. One of the key reasons users begin looking at a SAN or NAS is when the capacity demands of a single server outpace its internal storage capabilities. This may no longer be justification enough to make the move to networked storage or to continue to expand the network storage you have.

Comment on this blog entry

Capacity presents two challenges to the Storage Area Network (SAN) vs. Direct Attached Storage (DAS) debate. A traditional knock against DAS and a reason that many data centers get a SAN is because of these two capacity challenges. The first is can you get enough capacity and the second is can you use that capacity efficiently in a performance sensitive environment? DAS however now has the ability to address both of these issues.

Comment on this blog entry

Remember the Storage Area Network vs. Network Attached Storage debate? There were books written about it, articles and forum debates (this is before we had blogs). Eventually NAS vendors like NetApp become SAN vendors and SAN vendors either created their own gateway NAS front ends as did EMC or partnered with someone that offered a NAS Gateway like ONStor or BlueArc. Now there is a new debate; Direct Attached Storage vs. Shared Storage.

Comments(1)

In storage, its easy to forget that it is all about the application, especially when it comes to protection and more importantly recovery of that application. There is a wide variety of storage data protection from basic RAID to snapshots. There is an even wider variety of data protection software that provides multiple levels of protection, but between the two there is only rudimentary understanding of the application.

Comment on this blog entry

Vembu Technologies lets managed service providers resell storage services on top of Amazon's cloud.

Comment on this blog entry

In a recent entry we discussed the impact of Solid State Disk (SSD) on the IO infrastructure. Where SSD may have the most significant impact is on the adoption of 8GB fibre vs. Fibre Channel over Ethernet (FCoE). SSD has a performance profile that is worthy of the 10GB speeds of FCoE but will FCoE be adopted quickly enough by IT prior to SSD on 8GB Fibre establishing a foot hold?

Comment on this blog entry

There is a growing trend in storage lately, the concept of a manufacturer tapping another developer to help them compete in the market. This allows two smaller suppliers to team up against the larger suppliers. One of the best examples of this is NAS vendors adding deduplication functionality to their systems.

Comments(2)

In a recent review of Symantec's 2009 Stop Buying Storage Survey, an odd result on thin provisioning might get overlooked. 42% of users are essentially disappointed in their thin provisioning investment, and another 37% only indicated seeing moderate improvement. If you aren't in the small group that saw significant improvement, you may have invested in the wrong thin provisioning technology.

Comment on this blog entry

I dialed in recently to an online technology discussion sponsored by Wikibon.org, a community of technology professionals. Speaking was Rich Avila, director of server and network operations at California State, who said saving power wasn't a fuzzy, feel good goal for him. It was a necessity.

Comments(4)

In a recent blog on InformationWeek's sister site Internet Evolution, David Vellante's "Flash Drives Set to Give Internet a Performance Boost" suggests that fibre drives might be replaced by flash drives within the next three years. In our presentation last year on "The State of SSD" we made a similar prediction. Since David and I agree that this is a forgone conclusion, what will the impact of a rapid acceleration be on the infrastructure?

Comments(1)

Symmetrix V-Max, which targets high-end virtualized data centers, offers more capacity and lower power consumption than its previous high-end product.

Comment on this blog entry

Primary file system storage optimization, i.e. squeezing more data into the same space, continues to grow in popularity. The challenge is that the deduplication of primary storage is not without its rules. You can't dedupe this, you can dedupe that and you have to be cognizant of the performance impact on a deduplicated volume.

Comment on this blog entry

In our last entry we discussed the growing importance of efficiency. Tools and better storage systems can help make IT Administrators more efficient. The other option is to keep throwing new technology at the problem. Cloud Storage, Flash Storage and Deduplication are great examples.

Comment on this blog entry

2009, more so than any year, IT professionals are looking for ways to drive out costs. Technologies like deduplication, compression and server virtualization all try to lower the IT expenditures and these technologies have been successful at doing just that. The challenge however is that each of these technologies potentially compounds the challenge of making IT Operations more efficient by putting more workload in the same space.

Comment on this blog entry

New SourceOne platform takes a modular approach to archiving content and focuses strongly on electronic discovery.

Comment on this blog entry

In an earlier post, You Can't DeDupe IT Administration, I discuss the problem with optimizing primary storage. While it is incredibly valuable to be able to squeeze more data into less storage footprint, from an administrative standpoint you still have to manage the data, there is limited increase in efficiency. Archiving however, especially disk based archive can provide tremendous gains in efficiency.

Comment on this blog entry

With Texas Memory Systems’ recent announcement of their RamSan-20 they have joined Fusion-io in the Flash SSD on a card market. What is interesting about these solutions is that they make SSD attractive to a whole new host of users.

Comment on this blog entry

What was interesting about Cisco's entry into blade servers Mar. 16 was the key role that it expects virtualization to play. It trumpeted its convergence of storage and networking data on the blade. But what about its assumption that the blade will be virtualized?

Comment on this blog entry

ParaScale software enables a cloud-like system for tier 2 storage and archiving on commodity hardware and Linux.

Comments(1)

Is commodity storage good for the enterprise and if it is who should be delivering it? A recent post by Hitachi Data Systems, Hu Yoshida claims that I missed an important point in a recent blog that I wrote here about storage virtualization; the ability for virtualization to enhance commodity storage. He's right, I did not mention it at least in that entry, but is it really that important?

Comment on this blog entry

Primary Storage Optimization is about putting more data in the same amount of physical space. Server Virtualization is about putting more virtual servers in the same physical space. These are great advances for the data center, but they do little if anything to make the IT staff more efficient and all the cost savings may go right out the window when you have to hire more people.

Comment on this blog entry

With the recent report that the FTC is considering a request to shut down Google Apps, the question of Cloud Security has come up and with it the question of if data in the cloud is risky. Of course only the government could hold a two day hearing on whether or not data in the cloud is at risk.

Comments(2)

Sick of the phrase "Do more with less"? How about putting the pressure on your storage system? If you have to do more with less, it should at least carry some of the responsibility.

Comment on this blog entry

You are spending too much money on your backup infrastructure. You've built this massive infrastructure specifically to handle one task...The Full Backup. Most enterprises do their entire full backup job over the weekend so they have enough backup-window time to get the job done. We've been doing backups this way for the last 20 years, is it time for change? Could changing it rein in the costs of the backup process?

Comments(3)

As we work our way through the current economic situation, IT staffs are faced with a variety of challenges that are in conflict: maintain or increase services levels, drive out costs and increase efficiency. One of the items that can't be neglected is retention of data. In fact, it may be more critical in tough times than in prosperous times.

Comment on this blog entry

Green storage, or making storage more power efficient, continues to be a hot topic of discussion from storage vendors and for storage consumers. What is interesting and sometimes comical is watching vendors explain how their storage is suddenly green. Let's examine the common claims.

Comment on this blog entry

As cloud storage continues to evolve, clearly the two major initial uses are as backup and archive storage, but where does primary storage fit into this equation? Is primary storage going to be made extinct by the cloud?

Comment on this blog entry

As the initial wave of virtualization projects come to a close, many are finding an odd result. CPU utilization is actually lower than when it started. Now users are looking to pile on more workloads but before they do they need to prioritize storage I/O performance to those workloads; they need a QoS for storage.

Comment on this blog entry

With all the talk about FCoE and NFS it seems that iSCSI has become the odd man out. All reports indicate that Dell continues to do well with the EqualLogic acquisition but what Hewlett-Packard is doing with its LeftHand Networks purchase remains unclear. Don’t count iSCSI out yet, though -- companies are planning iSCSI storage solutions aimed right at the SME market.

Comment on this blog entry

With budgets and IT staff stretched to thinner levels than ever, change is going to come slowly this year and proving the ROI of each project is going to be critical not only to enable the approval of the next project, but possibly to keep your job.

Comment on this blog entry

Backup is the thorn in the side of many otherwise smoothly running IT operations. There is probably little coincidence that the newest hire is almost always assigned the backup process or the ramification for missing the assignments meeting. The truth is that backup should be simple -- all you're doing is copying data to tape. The problem in general has nothing to do with the backup process, it has more to do with how primary storage is managed and optimized.

Comments(1)

In his recent blog, Bycast CTO David Silk provides some insight on how enterprises minimize the risk associated with adopting cloud storage. At the heart of the matter is why does cloud storage or, for that matter, cloud computing, exist at all?

Comment on this blog entry