Posts from category "Storage Management Blog"

Interesting Infographic on LTO Tape

From Spectra Logic, this infographic tracks the evolution of LTO Ultrium Tape through its many generations.  Check it out:

LTO Infographic from Spectra Logic

The company is also preparing a  webinar for 2 November, 2017 on the Future of Tape Technology.  Register HERE if you want to attend.

Tape and Clouds? New Besties in the Storage Realm

With data growth measured in the tens of zettabytes, the combined capacities of disk and flash storage will be insufficient to store all the bits.  That's where tape comes in, with its long runway of capacity growth milestones on the horizon.  

Even the cloudies, who are among the first to encounter the data deluge, get the need for tape.  IBM told us some stories about tape in the cloud when we went to Tucson, AZ recently to hear about their LTO-8 tape drive announcement.



Thanks to Colleen Sanchez, Lee Jesionowski, Tony Pearson and Ed Childers for their time and their insights.


IBM Announces LTO-8 Tape Drive

At IBM's invitation, the Data Management Institute traveled to the Executive Briefing Center in Tucson, AZ a couple of weeks ago to shoot a video blog with IBM smart folks, Calline Sanchez, Lee Jesionowski, Tony Pearson and Ed Childers.  The subject was tape and we were receiving a preview of Big Blue's forthcoming announcement of supporting technology for LTO Ultrium tape Generation 8.

While LTO-8 is not yet available, that hasn't stopped IBM from getting ready with a new drive and support for the new standard in its Spectrum Archive software and various storage enclosures.  Here is the full interview:



Thanks to IBM for having us out for this advanced briefing.

A Zettabyte Apocalypse?

Trends in data growth are downright scary.  Per Barry M. Ferrite, as well as leading IT analysts, data is on pace to grow from current levels to more than 60 zettabytes (ZBs) by 2020 and to more than 163 ZBs by 2025.  Driving this data growth are three trends:  the digitization of information formerly stored in analog formats (the so-called digital democracy), the mobile commerce phenomenon, and the Internet of Things.


This tsunami of new data will challenge large organizations and those that are data intensive.  One prominent cloud architect has noted that the current manufacturing output of the disk industry in terms of capacity is around 780 exabytes per year.  The flash industry produces approximately 500 exabytes of capacity annually.  Even with forecasted capacity improvements, the world will still confront a severe capacity shortage by 2020. 

Tape could help fill the void, with demonstrations of over 300 TB per cartridge coming from IBM and tape manufacturers.  How soon tape drives and cartridges supporting these capacities will come to market remains to be seen.


Teaching Storage Fundamentals? Why Not Make It Fun?

DMI has begun using an avatar, Barry M. Ferrite, "your trusted storage AI", to provide entertaining and informative public service announcements about storage technology and data management.  This follows a series of "edutainment" videos we made in 2012-2013 to talk about the state of storage industry infighting at that time. 

Each episode of Storage Wars was a mash-up of Star Wars and Annoying Orange. For their "historical value," here was our version of Storage Wars -- Episodes IV, V and VI (labeled Storage Wars, Storage Wars 2 and Storage Wars 3 for YouTube storage.}





 Hope you enjoy the trip down memory lane.  DMI will be creating more edutainment videos in the future to teach storage fundamentals.

Why Not Used Gear?

Barry M. Ferrite responded last May to inquiries from many DMI members regarding how to bend the cost curve of storage, which currently accounts for between 30 to 70 cents of every dollar spent annually for IT hardware.  He talked about the secondary market, a place where you could buy used hardware at a fraction of the price of new gear, and build out your capacity without breaking the bank.  

Barry introduced us to ASCDI, an organization for secondary market equipment sales that imposes a code of ethics on members to ensure that consumers get the products they were promised and in good working order.  Have a listen.



DMI thanks Joe Marion of ASCDI for offering his perspective for this video.

Barry M. Ferrite Talks Tape

Tape?  What's that?

Scary as it seems, this is actually not an uncommon question from novice IT personnel, especially those who have been taught their trade at schools offered by hypervisor computing vendors or flash technology companies.  Yet, tape storage is coming back into vogue in industrial clouds, large data centers and certain vertical industry markets.

Barry M. Ferrite, our trusted storage AI, offered this public service announcement on LTO-7 tape about a year ago to help acquaint newbies with the merits of tape technology.  He will likely revisit this subject shortly with the release of LTO-8.



Don't count out tape as part of your storage infrastructure.


Slow VMs? Adaptive Parallel I/O Tech May Be the Solution

A little over a year ago, DataCore Software's late Chief Scientist, Ziya Aral, released a groundbreaking piece of technology he called adaptive parallel I/O that showed the way to alleviate RAW I/O congestion causing applications, especially virtual machines running in hypervisor environments, to run slowly.  

Demonstrations of the effectiveness of adaptive parallel I/O in reducing latency and boosting performance of VMs demonstrated the silliness of arguments by leading hypervisor vendors that slow storage was to blame for poor VM perfomance.  Storage was not the problem; the decreasing rate at which I/Os could be placed onto the I/O bus (RAW I/O speed) was the problem.

The problem was that hypervisor vendors really don't seem to want to place blame where it belongs -- with hypervisors and how they use logical cores in multi-core processors.  In better times, the error of such an assertion (that storage was responsible for application performance) could be shown just by looking at queue depths on the hosting server.  If the queue depth was deep, then slow storage I/O was to blame.  Conversely, if queue depths were shallow, as they typically are in hypervisor computing settings we've seen, then the problem lies elsewhere.

Aral and DataCore showed that RAW I/O speeds were to blame and they provided a software shim that converts unused logical CPU cores into a parallel I/O processing engine to resolve the problem.  Here is our avatar, Barry M. Ferrite, reviewing the technology in its early days -- at about the same time as Star Wars Episode VII was about to be released.



Since the initial release of Adaptive Parallel I/O technology, DataCore has steadily improved its results as measured by the Storage Performance Council, reaching millions of IOs per second in SPC benchmarks...on commodity servers from Lenovo and other manufacturers.

So, why isn't adaptive parallel I/O part of software-defined storage?

Introducing Barry M. Ferrite, DMI's Trusted Storage AI

Now a little over a year old, the Data Management Institute's "trusted storage AI" (artificial intelligence) is one Barry M. Ferrite.  Here is his first appearance with many yet to come.



We look forward to Barry's occasional public service announcements on all things storage.

Welcome to the Storage Blog at DMI

Welcome to the Storage Technology and Storage Management Blog at DMI.  This is the centerpiece of a community dedicated to the discussion of all things data storage.

We are hoping to use this space to discuss storage technology and architecture.  We also plan to review specific products and services that are being delivered to market by the storage industry, evaluating the business value and actual performance that they deliver over time. 

We are also passionate about keeping the record straight and separating the marketecture from the architecture in the discussion of storage itself.  Here are a few examples:

  • Storage is part of the original von Neumann machine design (an early architecture for computers).  Storage is often conflated with memory, which is a kind of storage but not one designed for the same purpose.  Memories were originally part of the central processing system, providing a temporary workspace or scratchpad where CPUs could temporarily store and access data being used by application workload.  The actual storage components were used to store data that would serve as inputs to applications and outputs from applications. So, the von Neumann machine is being relegated to the dustbins of history as venodrs push DRAM and NVRAM based storage products.  Those who say storage is dead, killed by NVMe or other memory-based storage approaches, are missing this distinction.
  • Storage currently comes in the form of paper, magnetic, optical and silicon devices.  Some of us are old enough to remember punchcards and punch tape.  These media gave rise to magnetic tape, then hard disk drives of many types, then optical and silcon based random-access media.  Readers will note that we do not count "cloud" as a type of storage media.  Clouds are shorthand for a service delivery model.  Cloud vendors use the same storage media as everyone else; clouds themselves are not a form of storage.  Cloud is a service delivery model -- and an incomplete one, at that (according to the National Institute of Standards and Technology).  Listing cloud as a form of storage is incorrect.
  • Software-defined storage is the "latest thing" -- at least in vendor marketing.  Truth be told, we "old timers" were doing software-defined storage on mainframes in 1993, using IBM's System Managed Storage facility (SMS).  All storage is software-defined, when you get right down to it.  With monolithic storage arrays, the software resides on the array controller.  With SMS and current software-defined storage stacks, the functionality lives on a server and is parsed out to commodity storage kit.  There is no right or wrong approach, but functionality should be provided where it makes sense to do so and where you can spare the cycles to perform the work.  The sad truth is that we have not seen a thorough discussion of the appropriate place to host individual storage functions.  Clearly, some functionality should probably be placed close to the storage devices on which it is acting, but some storage services can be hosted virtually anywhere.
  • The above point leads to another.  It is generally not a good thing to be locked in to any particular vendor's technology as this limits options for solving technical problems or for deriving business advantage from technology generally.  There is a misperception that moving from proprietary storage hardware to commodity hardware with proprietary software-defined storage software eliminates lock-in.  If this is true, why can't you store data from your VMware environment on a different hypervisor vendor's storage stack?  A VMware VSAN and a Microsoft Hyper-V storage spaces environment are both software-defined storage platforms, but you cannot place Hyper-V workload data on the VSAN or vice versa because each vendor wishes to be the dominant hypervisor in your environment.  How is this different from, say, the tricks that EMC used to prevent interoperability between their kit and those of competitors, all of whom were like EMC selling boxes of Seagate hard disks?

These are just a few examples of the misapprehensions about storage, cultivated by certain vendor marketing departments and their paid henchmen in the PR and industry analyst communities.  We want to use this community to keep things straight so that intelligent decision-making can happen.

Our biggest concern, frankly, isn't whose gear wins the day in the marketplace, or whose software you elect to use.  Our biggest concern is that the lack of intelligent debate and discussion is preventing us from advancing the ball, from deploying and using the right storage technology in the best possible way to solve our critical data hosting challenges.

It is interesting that the very vendors who dismissed software-defined storage when DataCore Software and a handful of others championed it in the late 1990s are now the big evangelists.  Yet, they still have yet to embrace storage virtualization as part of the software-defined storage stack.  Instead, they dismiss it out of hand because such a beastie would prevent them from using software-defined storage to lock-in their customers and lock out their competition just as the hardware vendors they delight in villanizing did before them.

This isn't just philosophical.  There is growing evidence that silo'ing storage behind proprietary hypervisor-controlled SDS stacks is leading to the decline of capacity allocation efficiency on an infrastructure-wide basis.  This story is underreported, or is certainly dwarfed by heavy coverage of vendor-sponsored reports portraying SDS as a godsend in terms of storage cost of ownership reduction.  While it may be true that managing a storage silo with a set of tools provided by the hypervisor vendor enables greater efficiency and control of the silo'ed storage, it also has the impact of preventing sane and rational management of capacity amongst and between storage silos created by different hypervisor vendors.

There are no easy answers to some of these issues.  But we want to peel the onion in this blog and hopefully to define some best practices that will benefit our community.  Welcome to the party!