Businesses now collect, analyse and store more data than ever and this is set to increase exponentially as technology advances. One of the problems this creates is where to store the data. The question, of course, covers more than the simple need for storage space: it also means looking at accessibility, availability, security and recovery. …
Virtual computing has created a tremendous opportunity for businesses to offload their IT requirements to cloud providers. Today, businesses with very large storage requirements, such as distributors of video media, can use the cloud as a way to implement management-free storage. They no longer have to worry about matching capacity to the changing market, of providing proper physical environments for storage servers, or deal with security issues.
However, in a sense a virtual storage system is the exact opposite of a KISS (keep it simple system). With increased complexity, the ability to control input, throughput, and output patterns is severely limited. Virtual clients do not have to deal with this problem, but web hosts must be able to efficiently handle all the performance issues associated with a virtual environment.
The Cloud Environment: Perception versus Reality
Virtual systems providers have done a terrific job of marketing the cloud. The average person knows their data is “somewhere out there” just like rain in a cloud. However, even an advanced architect does not know exactly where any particular set of data is stored. Storage is performed algorithmically – even cloud technicians cannot map specific data any more than the Westworld employees knew exactly what was happening with their virtual people.
Watch Your Defragmenter
To get an idea of the difference between managing traditional data as opposed to controlling and optimizing virtual data, watch a computer’s disk defragmenter in action. The defragmenter shows a very different (and realistic) picture of how files are stored on media. The average computer user uses a file cabinet paradigm, and often imagines files are stored in computer memory in a way somehow similar to how they are stored in their desk drawers. However, the defragmenter shows how files are split and spread all over the hard drive. Only the disk manager knows the rhyme and reason behind the way the files are stored.
Beyond the Disk Manager
Although the files may look like they’ve been dropped in a blender and spread over the landscape of the hard drive, in reality, they are stored in a very precise and efficient manner which allows the computer to access data files in a smooth speedy fashion. However, the data manager is essentially blind to the virtual system running on top of it. It cannot manage the resources in the virtual environment in the same efficient way it does the underlying media. The ability to manage virtualized workloads is the challenge for the modern hosting provider.
In the Heat of Battle
It would be advantageous for hosting providers to be able to deal with the increased storage requirements for virtual applications in the future, but unfortunately, as far as virtualization is concerned, the future is now. The IDC states the currently 72% of workloads are now virtualized. In addition, they estimate that this value will grow to 86% by the year 2018. Physical workloads already comprise only a small part of all workloads. Hosting providers must hit the ground running with a VM management solution.
Input/output Management Challenges
Improper I/O management can lead to several potential problems, including:
- Insufficient control cache – cache provides a buffer for the short-term dynamics of the I/O flow. However, the unpredictability of virtual data flow can overwhelm this buffer.
- Read/write array scheduling – read/write scheduling has a major influence on performance. The increased number of read/write operations can cause a significant degradation.
- File locking – VM environments manage large blocks of data by locking files. Locking and unlocking files can add a significant performance hit.
- LUN alignment – this process aligns operating system data block sizes with disk storage blocks. Misalignment can also cause serious performance degradations.
Measuring VM Performance
Providers plan virtual performance capacity through a parameter called IOPS. This allows system planners to effectively measure virtual throughput. This was an easy task when data streams originated from a single computer. However, VM environments break large data blocks into small read/write data packets. For this type of transmission, a bits/sec measurement is not meaningful. Instead, VM planners use Input/output Operations per Second (IOPS).
How Hosting Providers Maximize IOPS
VM administrators calculate their required IOPS by monitoring performance over some period of time, commonly 30 days. This gives a good idea of how many IOPS are being used by the application server.
In order to boost IOPS capacity, designers often implement platforms with an extra 40 to 60 percent excess storage over what they need. Many providers upgrade spinning disk systems with flash storage technology. The improved performance of flash gives an equivalent boost in IOPS. This is an attractive strategy due to the plummeting prices of flash storage. Administrators can increase IOPS further by using data compressions and duplication to optimize their flash drives.
Managing the Virtual Environment Challenges
- Match VMs to workloads – similar workloads make planning and scheduling more predictable. Designers can modify SAN configurations in order to group like-workloads instead of simply using a single array of disks.
- Take advantage of storage offloading functions – modern hypervisor systems are designed to coordinate with the underlying storage functions in order to offload as many storage functions as possible. This increases the efficiency of storage operations, eases the burden on the hypervisor, and helps reduce congestion on the storage connections.
- Profile workloads – planners must more fully analyze the nature of the workloads to ensure proper like-workload grouping. This helps ensure optimal performance and prevent unexpected capacity constraints.
- Extend storage systems – the storage infrastructure must be expandable and extendible to meet future needs.
- Maintain infrastructure – VM administrators should continually update existing systems in order to take advantage of the latest technologies in order to reduce or eliminate data flow bottlenecks.
Moving the Focus to the Virtual Level
Once the platform hardware is deployed and configured, cloud administrators completely move their management focus to the virtual level. This means that performance measurements such as snapshots, replication, and statistics gathering must be done at the virtual machine level. By employing the proper management systems, this strategy allows the system to monitor and fine tune itself.
In this way, cloud providers can tame the I/O management problem. Technicians view a dashboard with the following specifications:
- CPU usage
- RAM usage
- Network saturation
- IOPS usage
By monitoring these simple outputs, technicians can see in a glance that their virtual system is healthy and robust.
Top image ©GL Stock Images
It’s mind-blowing to think of how far IT technology has come since the PC first began to be marketed to a mass audience. It’s hard to fathom looking back just how we were able to get along without this technology that has now becomes so ingratiated into all aspects of our everyday lives. Yet the rise of computer technology certainly didn’t happen by accident; as is the case with all solution systems, this technology arose out of a demand to perform tasks more efficiently. To that end, the earliest products performed brilliantly, storing vast amounts of data and making it available for near-immediate retrieval.
Yet as is the case with most new technologies, once computer technology and its accompanying data storage potential was introduced, developers quickly went to work to improve it. Today’s users may think it laughable to contemplate a time when room-sized computers held only bytes of memory, particularly since in today’s world, discussions involving data storage are reaching both the terabyte and petabyte levels. Yet despite an emphasis on advancement, the earliest years of IT proliferation saw relatively slow steps taken to improve the efficiency of data storage devices. For almost 20 years, hard drive technology created by IBM has the workhorse of the data storage industry, and made possible the explosion in popularity of the PC. These earliest drives allowed for storage of up to 60 megabytes on a dual-disk hard drive.
The Advent of Portable Storage Technology
Yet this technology was not without its limitations. Enter Syed Iftikar and his accompanying contribution to the pantheon on data storage devices: the SyQuest drive. What set this technology apart from the others of its day was that it was the first to introduce the concept of removable storage. This offered a number of advantages over fixed drives, chief among them being the ability to expand storage capacity. The first SyQuest drive debuted in 1982 with a 6.38 megabyte storage capacity. By 1987, that capacity was up to 44.5 megabytes on a single removable cartridge drive.
While initially introduced to only the IBM-compatible market, SyQuest actually has Apple to thank for the skyrocketing in popularity that it experienced in the late 80’s. The desktop publishing revolution that began with Apple’s Macintosh line created new demands for greater data storage capacity to support the heavy use of graphics that users now demanded. The typical 80 megabyte capacities of the fixed drives of the day simply couldn’t keep up, and SyQuest drives soon became the data storage solution of choice in the industry.
1995: A Groundbreaking Year
Yet 1995 saw a new dawn in the IT market, when “multimedia” became all the craze in computer technology. Iomega was able to wrestle control of the data storage market away from SyQuest with a product that would revolutionize the storage solution world: the Zip drive. The Zip drive capitalized on the current desire that users had to have a single, easy-to-use storage device on which they could store their personal and business files, as well as their graphics, music, and videos. Originally offered with 100 megabyte storage capacities, the Zip disks would eventually grow to accommodate as many as 750.
Yet while the Zip drive took the portable data storage market by storm, its capacity paled in comparison to the digital video disk, which also first gained a foothold in the market in 1995. Rewritable DVD technologies such as DVD-RAM offered excellent data integrity and storage capacities that where among the first to get up into the gigabyte range. Even today, DVD-RAM technology continues to be utilized in many computers and personal video recorders such as camcorders.
Today’s Data Storage Technologies
The evolution of data storage took a new turn in 2006 when Amazon Web Services began offering a collection of remote computing services that quickly became known as the cloud computing platform. Rather than using a local server to process, manage, and store data, cloud computing uses a network of remote servers hosted on the Internet. After Amazon launched AWS, other software companies soon followed with cloud platforms of their own, such as Microsoft Azure and Google Drive. Today, it’s estimated that the Cloud currently holds more than 1 Exabyte of data.
The Evolving Costs of Data Storage
In the case of most technological revolutions, new technologies command top dollar when first introduced, yet tend to regress to lower prices over times as that technology becomes more readily available to a much broader customer base. The same concept has held true for data storage technologies. In the early days of the industry’s evolution, storing large amounts of data came with a hefty price tag, as it’s estimated that average storage cost per gigabyte was as high as $ 437,500 in 1980. Yet according to the research site Statistic Brain, this is how those costs have trended since:
- 1985: $ 105,000/Gig
- 1990: $ 11,200/Gig
- 1995: $ 1,120/Gig
- 2000: $ 11/Gig
- 2005: $ 1.24/Gig
- 2010: $ 0.09/Gig
- 2014: $ 0.03/Gig
Looking back throughout the history of data storage devices gives us the perfect example of technology at work, with needs being identified and products being developed to fill those needs. Yet as technological history has shown us, innovators are constantly looking to build a better mousetrap. Not only is this evident from looking at the progression of data storage devices and their capabilities over the last 20 years, but it makes one wonder of what the future of data storage will be. Developers have already taken basketball-sized disks and drives and been able to drastically reduce them in size while also dramatically increasing their storage capacity. As we move forward, the question on everyone’s mind undoubtedly will be how much more efficient data storage technology can get.
The amount of data generated by the homo sapiens is growing exponentially and so is the appetite to store them. And this appetite is the playing ground of the storage vendors. The marketing and sales departments of the vendors know this very well and they really act accordingly. That means, they know when to talk and when to hush. Here are the tricks you need to know.
Storage products are considered with a three to five year usage span. After that period, the electricity and the maintenance costs come on par with the new storage acquisition cost. During this time frame you are betting some or all of your valuable data on the storage you are purchasing. The top three decision points are: quality, upgrades and scalability.
Quality is a very generic term. It is obvious that your IT budget is tight and most probably you may not get the best storage in the market. However there should be some quality points which you should not forsake. First, be extremely careful of a storage that uses consumer grade hardware no matter what the vendor tells you. The differences between the consumer and the enterprise grade components are huge, such as the quality of the components and the tests carried out. One of the net results of the differences is the annual failing rate. And guess which one has higher failing rates. The low cost of acquisition may be appealing but the operational costs and the risks may easily exceed the savings that you are making with the purchase.
Next comes the upgrades. Think very carefully of what the storage vendor is offering in upgrades. Are they costly? Do they require too much downtime? Are they complex? Does the storage support background migration? What about firmware updates? These are the questions that you will face after purchasing the storage. Don’t even think about not making firmware updates, you will not be able to receive support and you will be asked to update before going on with the support case. And what if the storage vendor requires firmware updates to be carried out with its partner? Of course, don’t forget to ask about the live migration options.
Ask your vendor about the scale-out and scale-up possibilities: Your business requirements may ask you to add another storage to your infrastructure or grow on your existing infrastructure. To what point will you be able to expand your storage – how many enclosures, how many disks? Similarly, you may want to introduce another storage to ensure high availability at the hardware side. Or maybe you want to create one large storage pool by adding all of your existing storages. Ask if the storage supports these scenarios, and under which circumstances.
In today’s private clouds and highly-virtualized data centers, I have seen many companies having difficulties in managing their fabric. Often this is neither the companies nor the software vendor’s fault. I have seen one successful implementation of System Center Virtual Machine Manager (VMM), together with Operations and Configurations Manager applications. The company wanted to introduce its brand-new acquired storages to the VMM. The two products were listed as compatible storage arrays in VMM’s. The company asked for support from the vendors, resulting in failure. Neither the vendors, the partners nor the consultants knew about this support, let alone how to implement it. When you are selecting your storage, ask if it is compatible with the infrastructure management application you are using – VMM, OpenStack, whatever it is.
Vendors will tell you that the flash storage is on the rise and it is the future of storage and you have to invest today. This is partially true. Flash is the future of storage for many devices but today in the enterprise it is not suitable for all the jobs. Consider jobs which require large sequential data operations – such as multimedia files – where traditional disks excel. You also have to consider your overall storage infrastructure and if it can support the throughput of the flash disks. Does your backplane, your controllers, your software support the speeds? If not you will have bottlenecks. And if you are unlucky, you may have buffering issues. Today, the correct solution is tiered storages, where you have flash disks and traditional spinning disks.
Storages are also affected from the software defined networking: the industry is shifting to software defined storages (SDS). With SDS, many of the functionalities that came with the storage itself is shifted to the hypervisors, operating systems and applications. Now the vendors are trying to lock the customers to proprietary solutions that only work in one platform; this is exactly taking the customer’s freedom and locking him to certain features. I advise you to be careful with this trap: go with open standards to keep your bargaining power and to focus on performance and reliability.
Unfortunately today, enterprise storage market is shaped by the trends. Vendors try to take advantage of these trends with their matching products. On the other side, the enterprises need security and reliability. Sadly, vendors’ salespeople are trying to match their goals and they are using the trends and the flashy “success stories” to achieve their targets. Enterprises need salespeople who are straightforward and “fuss-free” to assist them in selecting the most suitable platform. Again unfortunately, this type of salespeople are one of the endangered species in business.
For some businesses the burden of having an in-house service provider or IT department may be too much for the budget so a third party option needs to be considered.
Find Articles, Free Articles Directory | Web Hosting Articles