Posts Tagged ‘CloudArray’

« Older Entries

Cloud Storage Accelerates into 2012 IT Priorities

Tuesday, January 31st, 2012

Every year, our friends at ESG post results of their annual Spending Intentions Survey, indicating where many businesses are likely to spend their IT dollars over the coming year. Recently Steve Duplessie posted an article on his blog entitled Cloud – The Cost Containment Strategy that concludes cloud has finally “crossed the chasm” in IT. According to preliminary data, cloud represents the largest % projected spending increase for 2012 IT initiatives– a very exciting turn.

Truth is, cloud storage addresses long-standing IT priorities, with three of these priorities topping the list nearly every year:

  • Improving backup and recovery: Tapes and offsite backup continue to be a struggle and do not offer the reliability or recovery times that many businesses demand. Moving off-site backups to the cloud improves the recoverability of backups without tape or dedicated infrastructure. Moreover, it offers the choice of leveraging existing backup software or modernizing backup software and processes.
  • Managing data growth effectively: As capacity grows, storage array life cycles mandate adding, replacing and decommissioning storage arrays whenever they run out of capacity, all involving considerable capital expense and internal administration. Cloud storage can instead provide an unlimited pool of storage that is on-demand and pay-as-you-go. For the financially minded, this enables replacing capital and administrative expense with pure operating expense (opex) and near-zero administration.
  • Improving business continuity and disaster recovery: For many businesses, it has become standard practice to duplicate on-site storage equipment expenses to build out a disaster recovery facility. For others, it may mean skimping on disaster recovery because of the high costs. Cloud storage enables turning disaster recovery expenses into opex while maintaining recovery time objectives that rival dedicated solutions.

So what is the challenge for cloud becoming an initiative for businesses? Let’s think of the early days of server virtualization. Priorities such as server consolidation and reducing server hardware footprint existed well before server virtualization. However, it took some time before virtualization gained mainstream acceptance. Indeed we may be in the midst of the same type of transition, with cloud storage moving from an adopter solution to a mainstream initiative.

What’s even more exciting about cloud storage is that it’s extremely simple for businesses to get started. Whereas traditional storage infrastructure requires a forklift to deliver and install, a software download of CloudArray and 10-15 minutes of configuration nets you Terabytes or Petabytes of secure storage capacity that’s ready to use. If you haven’t tried cloud storage, consider adding it to your 2012 initiatives.

Tags: , , ,
Posted in Cloud Storage | No Comments »

Measuring Cloud Storage Performance

Wednesday, January 18th, 2012

There are many excellent reasons to use cloud storage, but fast and efficient transfer of large amounts of data isn’t usually listed as a benefit. That’s one of the reasons why people use cloud storage gateways: to speed up cloud storage access. Recently, I realized we’ve never published any details on the performance gains that one should expect when using the CloudArray storage gateway, so I decided to create a simple illustrative test. In this article, I describe the results and explain some cloud storage implementation details that contribute to performance differences.

I came up with a quick test: copy one gigabyte of fully random data to the cloud, broken up into 32768 32k files. The questions are, how long would it take for a user to copy that much data to a CloudArray volume, and how soon before all of that data is safely stored in the cloud?

To set up the test, I used an old, slow laptop to run CloudArray. (That’s what I had handy in my office…) I used just the default basic configuration of a 25G cache to configure a single 100G encrypted volume, attached to Amazon S3, and mapped to a linux client. I formatted the volume with an ext3 file system and used the ‘cp’ command to copy the files. As a basis for comparison, I used an open-source file transfer utility, CyberDuck, to transfer exactly the same files to exactly the same the S3 account.

I’ve broken the CloudArray results down into two events: the data was “usable” when the ‘cp’ operation completes, and “complete” once all of the data had been copied to the cloud. At the usable point, any host attached to the CloudArray could access any of the files, as they were all stored in the local cache. In the background, the CloudArray busily pushed the data to the cloud, and when it was done, I considered the test complete. Of course, for the transfer utility, there’s no such split. The data was either copied to the cloud, or not.

The results of running the test were, well, dramatic:

Write performance comparison

For the record, that’s 6:22 (min:sec) for the CloudArray to reach the usable state and another 3:19 to reach the complete state, while it took the file transfer 110:05 to transfer exactly the same data.

What’s the reason for the huge difference? Well, I confess that I did set up this test to highlight one of the advantages of CloudArray; because we’re block-based, we’re not sensitive to the kinds of problems that plague file-based approaches.

The caching accounts for the rapid time to usability, but the more significant part of the equation is the aggregation that CloudArray performs due to the block-level IO. We send out all data in large, cloud-optimized chunks. Cloud storage provider systems store a single 1M object faster than they store a 32k object, so sending them 1024 1M objects is easier for them to handle. That same arithmetic applies to the number of requests, so that we sent 1024 PUT requests as opposed to the 32768 PUTs that CyberDuck (and, indeed, any file-based cloud utility) must send to handle this particular workload.

In other words, regardless of the size or number of files that you store on a CloudArray volume, traffic to the cloud is optimized to give the best performance.

To test read performance, I just copied the same files back from the cloud. Using CloudArray, that once again gave two separate cases: either all of the files were already in local cache, which meant that it was roughly the same as a local file copy, or they weren’t, in which case the data had to be read back from the cloud. Again, the data was automatically read from the cloud in large chunks, giving the best performance. The copy was performed with the ‘cp’ command on the linux host, and compared to CyberDuck transferring the files back.

The results are actually pretty symmetrical with respect to the original write performance:

Read performance comparison

Copying all the files from the local CloudArray cache took 6:05, while invalidating the cache and doing the same copy again took 11:42. On the other hand, the utility transfer took 112:24.

None of the numbers that I’ve given are all that useful for comparison with other environments. A large number of factors affect actual performance, e.g. WAN speed, LAN speed, and local disk speed, and I made no attempt to optimize any of them. A faster local disk or SSD, for example, would substantially reduce the time to usability. The importance of these results is the relative performance of CloudArray when compared to the raw transfer, and those results are impressive: 17.3x faster to usability, 11.4x faster to durability, and 9.6x faster to reload (18.4x if the data is in cache).

That’s minutes versus hours.

It’s a quick cup of coffee versus a three-martini lunch.

It’s renewing online versus waiting at the DMV.

It’s time saved.

Tags: , ,
Posted in Cloud Storage | 2 Comments »

User at 35,000 feet gives new meaning to “Cloud Storage”

Wednesday, January 11th, 2012

This week, a CloudArray user sent us this email, and he gave me permission to share it. CloudArray has been installed in lots of countries, but I think this is the first airborne installation! We love getting product feedback (good and bad) to help us improve the CloudArray user experience. Thanks to Phil Flores and Magnus IT Solutions for sharing.

Good morning Ann and Phil,

How are you doing? I am groovy. I thought I would send over a couple of data points you can share with your team and/or prospective customers that might be useful.

On Friday night, I boarded a 5 hour flight that had WiFi access on board. As you know, I have had absolutely no formal training or experience with TwinStrata or the CloudArray portal at all.  However, I wanted to see if I could get your software up and running since I had plenty of time on my hands. From start to finish, and using your VM instance on my laptop, I had 400 GB provisioned in the Amazon S3 cloud (using the license information your team provided) within 35 minutes…and that was with no previous experience or knowledge about setting up your virtual appliance!


Last night, I put your AMI EC2 instance up within 5 minutes and provisioned a 17 GB data store, a 25 GB data store, and a 30 GB data store and attached them to my Windows box. Total time from start to finish for all of the connections to be made was 10 minutes. Formatting the drives took longer because they were so large…but that has nothing to do with the TwinStrata software.

Overall…a very impressive software package and kudos to your development team for making the rollout/deployment so easy and seamless. Please let me know if you have any questions or need more information. Take care and I hope you are having a great weekend!

Cheers,
Phil

Tags: , ,
Posted in Cloud Storage | No Comments »

5 Cloudy Resolutions for Your Data Storage

Wednesday, January 4th, 2012

With 2012 already upon us, the time has come to make resolutions for the New Year. In the world of IT, this means resolving to abandon bad habits, unreliable processes and cumbersome tasks that often get in the way of business priorities. With the emergence of cloud storage as a viable means to address growing data storage needs, IT administrators can abandon storage headaches of years past in favor of better, faster and easier processes for managing data.

Cloud storage, in combination with enterprise-class gateways like CloudArray, offers security, availability, and performance that rivals local storage with no fear of vendor lock-in. Moreover, it makes it possible to fulfill New Year’s IT resolutions that were once considered unattainable. With this in mind, here are 5 resolutions that you can live up to by augmenting existing storage infrastructure with the cloud.

  1. Never run out of storage capacity again: Cloud storage provides unlimited, elastic capacity that grows or shrinks with your business needs on a pay-as-you go basis. Not only do you never run out of storage capacity, but more importantly, you can avoid the never-ending cycle of replacing storage arrays that includes complex migrations, costly capital and maintenance expenditures. Even better, on-premise hardware footprint never needs to increase.
  2. Kiss tape backup goodbye: While tape may always have a use for long term archives, many businesses can do away with regular daily tape backups by storing backups in the cloud. With cloud storage you can continue using existing backup software and policies without the hassle, unreliability and manual labor of tape.
  3. Stop purchasing dedicated hardware for disaster recovery: Nothing depletes an IT budget faster than buying data storage systems in pairs in order to have a second system ready for disaster recovery. Typically, dedicated secondary storage systems are only active during disaster test or disaster recovery. The advantage of cloud is that storage and compute infrastructure is available when you need it on a pay-as-you go basis at a fraction of the cost.
  4. Centralize storage management across sites: It’s not easy managing storage in a decentralized environment where every site is a silo with a private storage footprint as there is no easy way to reallocate capacity across sites or cobble a unified disaster recovery strategy. Cloud storage using enterprise-class gateways centralizes storage management across remote offices, offering unlimited, elastic capacity that never requires upgrades/replacements along with built-in centralized disaster recovery to the cloud. Managing multiple sites from a central location is now a reality.
  5. Retain access to a broad ecosystem of solutions: Everyone wants an open ecosystem of solutions including cloud providers and solution providers. Whether you are looking for a private cloud solution, a public cloud solution, or a combination of both, an enterprise-class storage gateway offers you options and provides you the opportunity to choose best-of-breed solutions that meet your needs. Alternatively, if you are looking to leverage your existing storage infrastructure as a starting point, enterprise-class storage gateways can help you enjoy the attributes of cloud storage.

You should look closely at the recent advances in cloud storage and enterprise-class gateway technology.  2012 may just be the year to see your “cloudy” resolutions to fruition.

Tags: , , , , ,
Posted in Cloud Storage | No Comments »

The Remote Office Data Storage Quandary: Is Cloud the Answer?

Wednesday, December 14th, 2011

If you ask IT administrators about their goals for storage infrastructure at remote and/or branch office (ROBO) locations, you’ll likely hear that they want to improve application performance and, at the same time, minimize the footprint of remote office storage infrastructure.  However, maximizing performance and minimizing footprint are competing priorities and optimizing both can be a challenge.

Having a goal to remove or minimize remote office storage infrastructure makes a lot of sense. Given most remote locations no longer have dedicated IT staffing onsite, an increased and significant burden can be avoided for the administrators working at main locations.

Improving overall application performance at remote offices also makes a lot of sense to maximize productivity of remote workers. The good news?  There currently exists in the marketplace a category of devices that provides local speed data storage access with a very small footprint: cloud storage gateways. Even better, CloudArray, an enterprise storage gateway from TwinStrata, enables local speed iSCSI access to a broad choice of public cloud storage providers, private cloud storage providers and/or existing storage, representing one of the the industry’s most flexible storage solutions.

A recent 2011 ESG survey of remote office and branch office environments revealed that a third of remote offices with over 25 employees had an average of 25TB of data at each remote office, a considerable amount of storage to maintain and manage. Taking a closer look, the following pie chart breaks down remote office storage infrastructure by type:

According to the survey results, 56% of storage deployed at ROBOs consists of SAN or NAS storage, reflecting the priority for local speed data access at those locations. The tradeoff is that managing enterprise storage infrastructure at those locations can lead to a number of headaches around

  • Hardware life cycles and upgrades
  • Running out of and replenishing capacity
  • Providing backup, replication or disaster recovery for the data stored at each site

Enterprise storage gateways are a great way to consolidate remote site storage footprint to software-only installations or small form-factor appliances while, at the same time, maintaining the plug-compatibility, speed and capacity of local storage infrastructure. Moreover, consolidation allows administrators to centralize data storage at a primary data center or in the cloud with the following advantages

  • A local iSCSI interface at each site without the iSCSI storage array footprint
  • Data reduction (compression and deduplication) before data is sent to the primary site or cloud, increasing usable centralized capacity
  • Ability to re-allocate capacity simply and dynamically between remote sites without moving hardware
  • Ability to maintain a cache or a full local copy that is replicated to the primary site or cloud for a multi-site disaster recovery strategy

Finally, a software enterprise storage gateway can be deployed virtually anywhere in the world in minutes, without additional hardware, allowing IT to rapidly meet ever-changing business needs.

If you are concerned about making the tradeoff between infrastructure footprint and performance for ROBO environments, it may be time to consider the benefits of an enterprise storage gateway solution.

Tags: , , , , ,
Posted in Cloud Storage | No Comments »

Is it Time to Look Beyond the Cloud?

Thursday, December 1st, 2011

For many businesses that haven’t yet formulated their cloud adoption plans, the notion of looking beyond the cloud may sound a bit peculiar. After all, isn’t cloud the final frontier that promises to transform traditional IT infrastructure into a control panel offering limitless resources on-demand? That is certainly the outcome that many businesses aspire to. The truth is, regardless of the outcome, much can be gleaned from examining how cloud infrastructure influences business IT efficiencies.

Let’s take a look at public cloud storage and how it has inspired new ways of thinking when it comes to storage infrastructure management. For some, it may be difficult to look beyond the logistics of public cloud storage which often dictate moving data into a distant data center and relinquishing a certain amount of control. However, the benefits of adopting the cloud bring IT efficiencies that could not be otherwise realized, eliminating one of the more burdensome aspects of data storage management.

What burdensome aspect is that? Specifically, the sprawl of storage infrastructure

  • In the primary data center – Storage arrays have a recurring life cycle that demands upgrading and replacing equipment on a regular basis as capacity needs increase.  The process is costly, disruptive, risky and causes overlap of equipment costs, underutilization and overpayment for unused capacity. Read all about the storage array lifecycle here and learn how a large school system changed that pattern once and for all.
  • In the remote office or branch office – While recent surveys such as ESG’s Remote Office/Branch Office Technology Trends show that a large number of businesses would prefer to centralize their data storage, the numbers reveal that most still have data storage at remote sites, primarily consisting of SAN or NAS devices. This not only perpetuates the management lifecycle described above, but does so for unmanned sites with no dedicated administrative staff, clearly an IT management nightmare.
  • For disaster recovery – Replicated storage infrastructure for disaster recovery costs as much to purchase, run and maintain as primary storage infrastructure and has the same life cycle issues described above, not to mention redundant and costly facilities.
  • For peaks and valleys in demand – Here, storage infrastructure remains primarily idle and unused except when capacity needs increase for certain projects, testing, development or analytics that may occur seasonally

The solution for this sprawl does not necessarily involve moving all storage infrastructure to the cloud. For many businesses, that is simply not a practical, realistic or fathomable near-term solution. However, the consolidation of storage infrastructure is clearly a viable strategy.

A reasonable approach might be to leave the main data center as is but start to address data storage sprawl that is occurring in remote locations. What if you could reduce the remote and branch office storage footprint to a single piece of software per site?  What if you could substantially reduce the storage capacity required for disaster recovery while at the same time pooling storage resources to address peaks and valleys in demand? Sprawl would diminish, utilization would improve and administrative burden would lessen.

The cloud can indeed be a means to this end. However, there are other options to consider. For instance, you could use CloudArray as your storage gateway and have a choice of consolidating the sprawl to a public cloud, private cloud, existing storage infrastructure or a combination of all three. Bottom line?  You can reduce sprawl without having to rely on any particular type of cloud, realize significant cost and administrative savings, and replace your ever expanding storage footprint with software, thereby eliminating a complex life cycle.

Keep in mind there is nothing magical about the storage infrastructure that backs cloud storage. Rather, cloud storage is all about the methodologies that squeeze the utmost efficiency out of commoditized storage components, culminating from years of experience on the part of cloud providers.  For this reason, businesses need to look beyond adopting cloud — and instead, look to adopt cloud methodologies that can bring them substantial IT efficiencies.

Tags: , , , , , ,
Posted in Cloud Storage | No Comments »

Cloud SANs: What the Data Storage Vendors Forgot

Tuesday, November 15th, 2011

Storage area networks (SANs) have become the ubiquitous deployment model for block data storage systems, interconnecting formerly siloed storage arrays with a common high-speed network running standardized protocols such as Fibre Channel or iSCSI. It was over a decade ago that the ability to connect multi-vendor storage arrays into a common network proved revolutionary and changed the way storage arrays were configured and consumed by businesses. However, with continuing advancements in cloud storage solutions, IT administrators are now rethinking the traditional SAN.

As with many mature technologies, SANs have forced IT administrators to accept a number of limitations. The most notable are

  • The traditional 3-5 year lifecycle of storage arrays, resulting in costly upgrades, frequent migrations and the introduction of considerable business risk
  • The inability to scale performance across geographical distances without storage arrays at each site
  • The inability to easily allocate and re-allocate storage capacity across sites
  • Replication and disaster recovery that require double the number of storage arrays and infrastructure

A combined cloud storage and enterprise cloud storage gateway solution, such as CloudArray, easily overcomes all of these limitations. Pay-as-you-go cloud storage breaks the traditional storage lifecycle offering an unlimited tier of data storage without a need for hardware upgrades, while enterprise storage gateway technology enables secure local-speed performance and iSCSI access from virtually any geographic location with the ability to dynamically allocate/reallocate storage across sites as needed.

TwinStrata’s recent launch of CloudArray 3.0 extends these cloud benefits beyond just public and private clouds — to existing data storage. With CloudArray 3.0, it is easier than ever to build a Cloud SAN that transcends the limitations of existing SANs. Companies can enjoy the attributes of cloud storage immediately using their existing storage as the starting point and, when ready, seamlessly expand their existing storage pool with public and/or private cloud storage.

CloudArray Cloud SAN

Cloud SANs eclipse the limitations of traditional SANs by offering high-performance, optimized data access from virtually anywhere, with a very small local footprint. This makes them ideal for remote offices or other distributed environments. Cloud SANs also offer centralized capacity management and centralized disaster recovery for flexible and robust multi-site deployments.

Key benefits of Cloud SANs include

  • Ability to work with public clouds, private clouds and/or existing storage using software or hardware caching appliances, each with access to virtually unlimited capacity
  • Ability to scale local speed performance across sites without distance limitations
  • Ability to allocate/reallocate storage capacity between sites dynamically, simplifying movement of capacity resources to locations that need them most
  • Built-in consolidated replication and disaster recovery for each caching appliance

As ground-breaking as SANs were when they launched over a decade ago, Cloud SANs represent the next revolutionary step in simplifying deployment of data storage for businesses. Whereas traditional SANs are limited in terms of multi-site scale, capacity utilization and cost, Cloud SANs offer robust, cost-effective solutions that scale geographically and optimize data storage utilization.

Find out just how simple it is to get started with a CloudArray Cloud SAN.

Tags: , , , ,
Posted in Cloud Storage | No Comments »

« Older Entries