Subscribe to the RSS feed

In a conversation I had a few weeks ago with Pillar Data’s CEO, Mike Workman, we discussed his recent blog entry on the “Auto Tiering of Data”. In this blog he brings up several important considerations as vendors and users begin to examine automated tiering. One I’d like to elaborate on is QoS in Automated Tiering.

Comment on this blog entry

There is a case of piling on going on right now as it relates to cloud storage. While I agree that the term has been hijacked, stretched and bent by more than a few storage vendors, that does not mean that the whole concept is bad. While the name is as poorly chosen as “social media”, the concept is dead on.

Comments(3)

One of the concerns about adopting Solid State Disk (SSD) is that it can be disruptive to the overall data management process that you may have in your data center. SSD is obviously a new and fast but somewhat more expensive alternative to your good old mechanical drives. However, when implemented correctly the addition of SSD can be relatively non-disruptive.

Comments(1)

As the Cloud Compute and Cloud Storage markets continue to mature, some of those vendors are going to go out of business. It is the natural order of things. The strong (or well funded) survive. You either need to be very sure that the cloud vendor is not going to be one of those that does or you need to make sure you are getting your data out of the cloud on a regular basis.

Comment on this blog entry

A few entries ago we opened up the subject of Automated Tiering with an explanation of why the technology is becoming so needed. As this series of entries continues we will review various storage vendors specific approach to automated tiering, but first it is helpful to understand the common methods that are employed.

Comment on this blog entry

Cloud storage may end up being the great storage repository in the sky. The destination that holds all our data and gets it off of our local storage. Whether you use this as a fourth tier of storage that your internal archive spills over too or as your sole archive, someday you are going to need to find data in it. Should we be indexing cloud storage to find the needle in the haystack?

Comments(2)

Every few years you are going to need to replace your enterprise storage system. A challenge that many storage managers face is what to do with the old system. Today you have laws that require you to make sure information is not readable when that storage leaves your walls and you have individuals that want to see what trouble they can dig up by resurrecting old systems.

Comments(1)

As the use of cloud storage becomes more prevalent this year one of the key challenges is what data should go to cloud storage, when that data should be moved there and how should that data be moved there?

Comments(1)

The concept of multiple tiers of storage has been around for almost as long as there has been storage, but the subject became more discussed in early 2000 when Serial Advanced Technology Attachment (SATA) hard drives began to come to market. They were higher capacity and less expensive than their fibre channel counterparts but not as fast. The question that still plagues storage managers is how to get data to them.

Comments(2)

Tiered storage often means the development of a storage strategy that moves data from fast, expensive storage to slower SATA based storage. Tiered storage can also refer to the quality of the storage. A tier 1 storage system may have a higher level of reliability and DR functionality than a tier 2 system. The delta between the quality and capabilities of these tiers is quickly eroding, which makes the question a fair one to ask.

Comments(2)

The storage component is changing, becoming either dramatically faster with Solid State Disk (SSD) technology or fundamentally more cost effective thanks to capacity-efficient disk archiving or overhead-efficient cloud storage. In addition all current storage will still need to be managed. A four-tier storage strategy will allow storage managers to develop a storage environment that is both cost efficient and meets increasing performance demands.

Comments(1)

In 2010 cloud storage will continue to grow in use but like my other 2010 entries, next year won’t be the “year” of cloud storage. As we discussed in our article “What is Cloud Storage”, people and organizations will use cloud storage differently. What is important is that they will use the architectures they are developing from cloud storage requirements more so than they had previously.

Comments(6)

Will 2010 be the year of Fibre Channel-Over-Ethernet (FCoE)? I am always hesitant to predict that any particular year with be “the year” but I do think that FCoE will move out of conversation and testing phases and more into production.

Comments(1)

When data center managers are looking at cloud storage solutions the primary focus is on the monthly cloud storage capacity cost. One of the hidden charges is the transfer or bandwidth costs. This is the cost essentially for the amount of data you access over the cloud. We have seen cases where this cost can be as much or more than the cost of the capacity!

Comments(3)

This time of year I am always asked what storage trends will take off during the next year. I often resist because it is very hard to get it right. What I try to do is see what is likely to gain traction in the coming year. Over the next few entries we will explore some of the 2010 storage trends that you ought to be paying attention to. One of those is scale out storage.

Comments(1)

Automated tiering, the transparent movement of data based on activity or type, is quickly proving itself to be a hot consideration for storage managers but why stop at automated tiering? Can’t we make the entire storage ecosystem respond automatically based on environmental conditions and its available resources?

Comment on this blog entry

What are the chances of a controller failing in a storage system? I don’t know the exact statistic but its safe to assume that its pretty low. When they do fail, the ramifications can be extreme, especially in the increasingly virtualized data center that counts on shared storage. Active-Active controllers provide the protection from controller failure but they are a bit of a misnomer. Both controllers are being used but they are assigned to specific workloads.

Comment on this blog entry

Don MacVittie in his blog over at F5 commented recently on an article that we have written “What is File Virtualization?” indicating that we missed a key issue in dealing with how to handle it when your virtualization box goes down. While my defense could be that the subject is beyond the scope of a primer, it is not beyond the scope of this blog. If you are considering a tiered storage model then what do you do when your data mover fails?

Comments(1)

As we described in the last few entries, adding storage software to standard servers or even to virtual servers is making more sense for a variety of data centers because of the increased performance capabilities of the Intel processor family. Despite this there may still be times in certain environments where there is a need for specialized storage hardware.

Comment on this blog entry

Cloud storage is constantly being discussed in the IT media today. When you get right down to it, what can businesses really use cloud storage for now? The small office, individual user has embraced cloud storage for backups and for collaboration, but what can larger businesses use these services for?

Comments(2)

In our last few entries we looked at what can be done today with storage software running as virtual machines. In this entry we will consider what the future holds for storage as a virtual machine. Storage as a virtual machine may be the only way you apply data services in the future.

Comment on this blog entry

Completing our storage as a virtual machine re-interviews were conversations we had with EMC and Nexenta. While our last entry focused on systems that leveraged virtual machines to deliver block I/O storage services these two companies are delivering something a little different, NAS services and backup services.

Comment on this blog entry

There are countless ways to manage data available to the storage manager today but most of these solutions look at data as a problem. Few take an asset view of data, understanding that it is something to be cultivated and leveraged for future use. Storage managers should do more than just manage their data, they should know it.

Comment on this blog entry

As we dive deeper into the storage as a virtual machine concept we went back and re-interviewed some of the players in the storage as a virtual machine market, focusing specifically on what they provide. The first two conversations were with DataCore and HP. We will cover more suppliers as the series unfolds.

Comment on this blog entry

Data storage capacity is cheap. For most environments obtaining enough capacity is no longer a challenge, it is managing that capacity that becomes the problem. Growth, especially in unstructured data, continues unabated. Deciding what data should be where is one of the biggest challenges that the storage manager has to face today. Users don’t want to think about where data should be stored and storage managers don’t have the time to think about it.

Comment on this blog entry

Traditionally storage systems and other storage related services have been delivered as customized systems. This was done to maintain performance and to reduce support costs to the manufacturers. As server technology continues to increase in performance, the concept of providing storage services as a standalone application installed on your own server hardware is becoming increasingly popular. Now with virtualization the storage as an application concept is being applied to virtual machines.

Comment on this blog entry

I recently concluded a series that examined the components of the storage environment that can impact overall storage I/O performance. There was storage I/O bandwidth, controllers and drives. What if you are like many data centers and you don’t need to wring out every drop of storage I/O performance from your storage infrastructure? What should you do with too much storage performance?

Comments(1)

Most of the major Solid State Disk (SSD) manufacturers and providers are reporting record sales both in terms of units and capacity being purchased. Much of this success is being driven by cost reductions in the technology and an increased understanding of how to best implement the technology. Mainstreaming SSD is going to require more than just price drops, its going to require intelligent leveraging of the technology.

Comments(1)

In our last entry we talked about the use of cloud storage as a backup target, but another ideal use case for cloud storage is to use it as an archive area. Almost every IT organization has old data that they want or must keep, but are struggling with where to keep it. Its ability to identify, automatically move and transparently recall data could make file virtualization the ultimate cloud gateway.

Comment on this blog entry

Cloud based backup services have been successful in the consumer space. Companies like Mozy, Carbonite and others are protecting thousands of laptops and home desktops, but can cloud based backups services move beyond protecting consumer or prosumer data and into the data center? Are cloud based backups ready for business?

Comment on this blog entry

The storage component of a virtualized server infrastructure has been labeled as complex and expensive. In our prior entries about selecting a storage foundation we discussed what systems and protocols are available that might help simplify and reduce costs for storage in a virtualized environment. Beyond physical hardware you need software tools that can link the abstract virtual machine to the physical storage.

Comments(1)

In the last performance entries we discussed understanding storage bandwidth and understanding storage controllers. Next up is to understand the performance characteristics of the hard drive itself and how the mechanical hard drive can be the performance bottleneck.

Comment on this blog entry

Whether your company's data center is a couple of servers stashed in a closet or a gleaming, state-of-the-art climate-controlled facility, you're still facing the same set of challenges: how to keep the IT lights on while controlling costs, take advantage of new technologies to stay competitive, and position your company for an economic recovery in the midst of the toughest times for IT that many of us can remember.

On Wednesday, October 21, 2009, help is on the way.

Comment on this blog entry

At Storage Networking World, at least one new category in storage is coming to the forefront; Automated Storage Tiering. These are typically devices that can sit in front of your existing storage platform and allow some of it to leverage a high speed solid state front end without you manually having to move data to a Solid State Disk (SSD).

Comment on this blog entry

Storage controllers are the engine that drives the storage system you own. They are essentially a compute engine for storage arrays. Understanding storage controller performance and what can impact storage controllers is an important step in the optimization of your storage environment. It is also something that many storage managers assume is good enough.

Comment on this blog entry

HDS announces a move into public and private cloud storage, primarily through rebranding

Comment on this blog entry

Storage bandwidth is the connectivity between servers and the storage they are attached to. When it comes to understanding storage bandwidth performance you have two challenges to deal with. The first and most obvious is can the storage get the data to the application or user fast enough? The second and less obvious is can the applications and hardware those applications run on take advantage of that bandwidth?

Comment on this blog entry

For most storage managers improving storage performance is an endless loop of upgrades that are taken until the problem goes away. Understanding where to look and how to configure the environment is often a series of "best guesses" instead of a thorough understanding of it. In today's economy best guesses are not allowed. Making the right move, the first time, is critical.

Comment on this blog entry

In our last entry we discussed selecting the right storage foundation and I advised that you may want to initially ignore what protocol to use. That said, part of building a storage foundation for server virtualization is selecting the protocol.

Comment on this blog entry

The storage component of a virtualized server infrastructure has been labeled as complex. The storage and server virtualization suppliers have both tried to deliver solutions that reduce storage complexity in server virtualization projects. The challenge for virtual infrastructure administrators is that there are so many options that it can be confusing. There are several steps to take when selecting a storage foundation for virtualized servers and our next series of entries will cover these steps.

Comment on this blog entry

Storage scalability in a virtualized environment is quickly becoming a concern for some data centers. Unlike the very predictable single server world which had a single application, single NIC card and single host bus adapter, the virtualized host can have dozens of virtual machines and multiple network interface cards. This leads to a very unpredictable and random workload that can push storage controllers to their limits.

Comment on this blog entry

One of the most expensive components of a server virtualization project is the storage which it is attached to. This is one of the reasons that VMworld seems more like a storage event than a server virtualization event. One of the key themes from vendors at this years event was reducing the storage costs in server virtualization projects.

Comments(2)

Most green storage methods really allow you to store more data in the same physical space, for the same amount of power consumption. To get serious about power efficiency you have to be able to turn things off. The ideal way to do this is have the drives either spin down or turn them off, but there is limited information about implementing power efficient drives.

Comment on this blog entry

There is an ever increasing emphasis by storage suppliers on the power efficiency of their systems. There is also an increasing interest from IT managers on making their environment more power efficient. This is being driven not so much by the desire to be environmentally sensitive, but more because an increasing number of data centers simply can't get more power to the building.

Comment on this blog entry

One thing suppliers and analysts are quick to point out is that when it comes to data protection it is not about how well you backup, it is about how well you recover. That sounds very catchy and for the most part is accurate. I believe however, that backup is an equally important part of the data protection puzzle. It is after all poor backup strategies that make recovery so hard and unpredictable.

Comment on this blog entry

Solid State Disk (SSD) is often the solution to drive up performance of a particular application, increasing response time to users and thereby increasing revenue or productivity. There can also be significant CAPEX savings by implementing SSD, what is often missing from the discussion is the operational or OPEX savings that comes from implementing SSDs.

Comment on this blog entry

Traditional volumes have been around as long as we have had file systems, but now may be the time to pronounce the end of the storage volume. As data centers get larger and storage systems are populated with more and more physical drives they are growing into a storage manager's nightmare. There are just too many volumes of drives to be managed effectively.

Comments(1)

In my last entry we discussed some of the challenges storage presents to expanding the level at which companies deploy virtualized servers. There is another, potentially larger roadblock to virtualization; staff inefficiency.

Comment on this blog entry

After the initial rollout, server virtualization projects often get stuck as managers and administrators begin to cope with how successful the first phase of the project was and begin to try to grasp how they can increase the number of systems that are virtualized. There are two big roadblocks to a high percentage of virtualization in most data centers; cost and efficiency.

Comments(1)

At VMworld this year there is a lot of emphasis on making the storage easier and less expensive for the small to medium sized businesses that are taking their first steps into the server virtualization market. The focus of these storage vendors is on driving down costs and driving out complexity.

Comment on this blog entry