Category: big data

Posted on

Server Storage I/O Network Benchmark Winter Olympic Games

Storage I/O trends

Server Storage I/O Network Benchmark Winter Olympic Games

It is time for the 2014 Winter Olympic games in Sochi Russia where competitors including some athletes come together in what has become a mix of sporting and entertainment engaging activities.

Games of inches and seconds, performance and skill

Some of these activities including real Olympic game events are heavier on sports appeal, some with artistic and others pure entertainment with a mix of beauty, braun and maybe even a beast or two. Then there are those events that have been around since the last ice age, while others being post global warming era.

Hence some have been around longer than others showing a mix of old, new in terms of the sports, athletes not to mention technology and their outfits.

I mean how about some of the new snow boarding and things on skis being done, can you image if they brought in as a new "X" sport roller derby on the short speed skating track sponsored by Red Bull or Bud light? Wait, that sounds like the Red Bull Crashed Ice event (check this out if not familiar with) think motto cross, hockey, down hill on ice. How about getting some of the south African long distance sprinters to learn how to speed skate, talk about moving some gold metal as in medals back to the african continent! On the other hand, the current powers to be would lodge protest, change the benchmark or rules to stay in power, hmm, sound familiar with IT?

Ok, enough of the fun stuff (for now), let’s get back on track here (catch that pun?).

Metrics that matter, winners and losers

Since these are the Olympics, lets also remember that there still awards for personal and team winners (along with second and third place), after all, if all Olympians were winners, there would be no losers and if no losers, how could there be a winner?

Who or what decides the winners vs. losers involves metrics that matter, something that also applies to servers, storage I/O networking hardware, software and services.

In the case of the Olympics, some of the sports or events are based on speed or how fast (e.g. time) something is done, or how much is accumulated or done in that amount of time while in other events the metrics that matter may be more of a mystery based on judging that maybe subjective.

The technologies to record times, scores, movements and other things that go into scoring have certainly improved, as have the ability for fans to engage and vote their choice, or opposition via social media venues from twitter to face book among others.

What about server storage I/O networking benchmarks

There could easily be an Information Technology (IT) or data infrastructure benchmarking Olympics with events such as faster server (physical, virtual or cloud, personal or consortium team), storage, I/O and networking across hardware, software or services. Of course there would be different approaches favored by the various teams with disputes, protests and other things sometimes seen during Olympic games. One of the challenges however is what would be the metrics that matter particularly to the various marketing groups of each organization or their joint consortium?

Just like with sports, which of the various industry trade groups or consortiums would be the ruling party or voice for a particular event specifying the competition criteria, scoring and other things. What happens when there is a break away group that launches their own competing approach yet when it comes time for the IT benchmarking Olympics, which of the various bodies does the Olympic committee defer to? In case you are not familiar with in sports there are various groups and sub-groups who can decide the participants for various supports perhaps independent of an overall group, sound like IT?

Storage I/O trends

Let the games begin

So then the fun starts, however which of the events are relevant to your needs or interest, sure some are fun or entertaining while others are not practical. Some you can do yourself, while others are just fun to watch, both the thrill of victory and agony of defeat.

This is similar to IT industry benchmarking and specmanship competitions, some of which is more relevant than others, then there are those that are entertaining.

Likewise some benchmarks or workload claims can be reproduced to confirm the results or claims, while others remain more like the results of figure skating judges.

Hence some of the benchmark games are more entertaining, however for those who are not aware or informed, they may turn out to be more misinformation or lead to poor decision-making.

Consequently benchmarks and metrics that matter are those that most closely aging with what your environment is or will be doing.

If your environment is going to be running a particularly simulation or script, than so be it, otoh, look for comparisons that are reflective.

On the other hand, if you can’t find something that is applicable, then look at tools and results that have meaning along with relevance, not to mention that provide clarity and repeatable. Being repeatable means that you can get access to the tools, scripts or scenario (preferably free) to run in your own environment.

There is a long list of benchmarks and workload simulation tools, as well as traces available, some for free, some for fee that apply to components, subsystems or complete application systems from server, storage I/O networking applications and hardware. These include those for Email such as Microsoft Exchange related, SQL databases, , LoginVSI for VDI, VMmark for VMware, Hadoop and HDFS related for big data among many others (see more here).

Apples to Apples vs. Apple pie vs. Orange Jello

Something else that matters are apples to apples vs. apples to oranges or worse, apple pie to orange Jello.

This means knowing or gaining insight into the pieces as we as how they behave under different conditions as well as the entire system for a baseline (e.g normal) vs. abnormal.

Hence its winter server storage I/O networking benchmark games with the first event having been earlier this week with team Brocade taking on Cisco. Here is a link to a post by Tony Bourke (@tbourke) that provides some interesting perspectives and interactions, along with a link here to the Brocade sponsored report done by Evaluator Group.

In this match-up, Team Brocade (with HP servers, Brocade switches and an unnamed 16GFC SSD storage system) take on Team Cisco and their UCS (also an un-named 16GFC SSD system that I wonder if Cisco even knows whose’s it was?). Ironic that it was almost six years to the date that there was a similar winter benchmark wonder event when NetApp submitted an SPC result for EMC (read more about that cold day here).

The Brocade FC (using HP servers and somebody’s SSD storage) vs. Cisco FCoE using UCS (and somebody else’s storage) comparison is actually quite entertaining, granted it can also be educational on what to do or not do, focus on or include among others things. The report also raises many questions that seem more wondering why somebody won in an ice figuring skating event vs. the winner of a men’s or women’s hockey game.

Closing thoughts (for now)

So here’s my last point and perspective, let’s have a side of context with them IOPs, TPS, bandwidth and other metrics that matter.

Take metrics and benchmarks with a grain of salt however look for transparency in both how they are produced, information provided and most important, does it matter or is it relevant to your environment or simply entertaining.

Lets see what the next event in the ongoing server storage I/O networking benchmark 2014 winter Olympic games will be.

Some more reading:
SPC and Storage Benchmarking Games
Moving Beyond the Benchmark Brouhaha
More storage and IO metrics that matter
Its US Census time, What about IT Data Centers?
March Metrics and Measuring Social Media (keep in mind that March Madness is just around the corner)
PUE, Are you Managing Power, Energy or Productivity?

How many IOPS can a HDD, HHDD or SSD do?
Part II: How many IOPS can a HDD, HHDD or SSD do with VMware?

You can also take part in the on-going or re-emerging FC vs. FCoE hype and fud events by casting your vote here and see results below.

Note the following poll is from a previous StorageIOblog post (Where has the FCoE hype and FUD gone? (with poll)).

Disclosure: I used to work for Evaluator Group after working for a company called Inrange that competed with, then got absorbed (via CNT and McData) into Brocade who has been a client as has Cisco. I also do performance and functionality testing, audits, validation and proof of concepts services in my own as well as in client labs using various industry standard available tools and techniques. Otoh, not sure that I even need to disclose anything however its easy enough to do so why not ;).

Ok, nuff said (for now)

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

Removing complexity and cost to drive return on innovation the new ROI

Storage I/O trends

Removing complexity and cost to drive return on innovation the new ROI

There is no such thing as an information recession however there the realities of economic challenges in IT data centers also known as information factories.

Likewise, people and data are living longer with increased dependency on information being available and reliable when needed. Hence the need for data infrastructures that protect, preserve and serve information in a cost-effective productive way.

Return on innovation, the new ROI, doing more with what you have without compromise
Driving return on innovation (the new ROI) to support growth

A common challenge for organizations of all size is how to support business and data growth while working within budget constraints without compromising on customer service expectations. Simply cutting cost at the price of reliability, availability, serviceability or performance is not an option for most environments.

Driving data center and data infrastructure sustainability

The solution is to find and remove complexity and thus remove costs. How to carry out the above goal is to leverage various tools and techniques to streamline IT and data infrastructures in creative ways.

Cloud, virtual and traditional computing building blocks image, servers, storage, networking hardware and software
Core IT building blocks (servers, storage and networking, hardware and software)

With data storage along with servers, networks and associated software management tools being the fundamental building blocks for traditional, virtual and cloud environments, it makes sense to apply some focus there.

How you use different tools and technologies to address various challenges while enabling your organization to be more effective and productive will decide your return on innovation, the new ROI. The new ROI is a companion reflecting qualitative business benefits vs. traditional black and white quantitative spreadsheet numbers based indicators.

garbage in, garbage out roi tco
Watch out for Garbage In, Garbage Out ROI and TCO analysis

Return on innovation reflects how various tools and technologies, joined with different processes, procedures, and best practices and people skills are combined to address a problem or challenge and enable some benefit. An example is deploying storage optimization techniques to support growth by finding and removing complexities, boosting effectiveness (as well as efficiency) without negatively affecting productivity.

Where financial based ROI looks at a number that may show impacts to customer service, return on innovation highlights the business benefit (e.g. perhaps non-financial) such as getting more work done in same amount of time or keeping customers satisfied.

Keep in mind, that when you can find and remove complexity, cost savings are the usual benefit vs. finding and moving or masking problems that end up costing more over time.

Ok, nuff said (for now)

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

StorageIO data infrastructure industry vendors links page updated with over 1,200 entries

Storage I/O trends

StorageIO data infrastructure industry vendors links page updated with over 1,200 entries

Is your company, organization or one that you are a fan of, or represent listed on the StorageIO industry links page?

The StorageIO industry links page has been updated with over thousand different industry related companies, vendors, vars, trade groups, part and solution suppliers along with cloud and managed service providers. The common theme with these industry links is information and data infrastructures which means severs, storage, IO and networking, hardware, software, applications and tools, services, products and related items for traditional, virtual and cloud environments.

The industry links page is accessed from the StorageIO main web page via the Tools and Links menu tab, or via the URL https://storageio.com/links. An example of the StorageIO industry links page is shown below with six different menu tabs in alphabetical order.

storage I/O and data infrastructure cloud, virtual and software defined links

Know of a company, service or organization that is not listed on the links page, if so, send an email note to info at storageio.com. If your company or organization is listed, contact StorageIO to discuss how to expand your presence on the links page and other related options.

Visit the updated StorageIO industry links page and watch for more updates, and click here to learn more about the links page.

Ok, nuff said (for now)

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

Part II Until the focus expands to data protection – What to do about it

Storage I/O trends

Part II – Until the focus expands to data protection – What to do about it

This is the second of a three-part series (read part I here) about how vendors are keeping backup alive, however what they can and should do to shift and expand the conversation to data protection and related themes.

Modernizing data protection and what to do about it

Building off of what was mentioned in the first post, lets take a look at what can be done including expanding the conversation around data protection in support of business continuance (BC), disaster recovery (DR), high availability (HA), business resiliency (BR) not to mention helping backup to actually retire (someday). Now when I backup retire, I’m not necessarily talking about a technology such as hardware, software or a service including clouds, rather when, where, why and how data gets protected. What I mean by this is to step back from looking at the tools and technologies to how they are used and can be used in new and different ways moving forward.

People convergenceStorageIO people convergence
Converged people and technology teams

All to often I see where new technologies or tools get used in old ways which while providing some near-term relief, the full capabilities of what is being used may not be fully realized. This also ties into the theme of people not technologies can be a barrier to convergence and transformation that you can read more about here and here.

Whats your data protection strategy, business or technology focused?

expand focus beyond tools
Data protection strategy evolving beyond tools looking for a problem to solve

Part of modernizing data protection is getting back to the roots or fundamentals including revisiting business needs, requirements along with applicable threat risks to then align application tools, technologies and techniques. This means expanding focus from just the technology, however also more importantly how to use different tools for various scenarios. In other words having a tool-box and know how to use it vs. everything looking like a nail as all you have is a hammer. Check out various webinars, Google+ hangouts and other live events that I’m involved with on the StorageIO.com events page on data protection and related data infrastructure themes including BackupU (getting back to the basics and fundamentals).

data protection options

Everything is not the same, leverage different data protection approaches to different situations

Wrap up (for now)

Continue reading part three of this series here to see what can be done (taking action) about shifting the conversation about modernizing data protection. Also check out conversations about trends, themes, technologies, techniques perspectives in my ongoing data protection diaries discussions (e.g. www.storageioblog.com/data-protection-diaries-main/).

Ok, nuff said

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

 

Posted on

Until the focus expands to data protection, backup is staying alive!

Storage I/O trends

Until the focus expands to data protection, backup is staying alive!

This is the first of a three-part series discussing how and why vendors are keeping backup alive, read part two here.

Some vendors, Value Added Resellers (VARs), pundits (consultants, analysts, media, bloggers) and their followers want backup to not only be declared dead, they also want to attend (or send flowers) to the wake and funeral not to mention proof of burial so to speak.

Yet many of these same vendors, VARs and their pundits also are helping or causing backup to staying alive.

Sure there are plenty of discussion including industry adoption and customer deployment around modernizing backup and data protection that are also tied to disaster recovery (DR), business continuance (BC), high availability (HA) and business resiliency (BR).

On the other hand the usual themes are around talking about product or technology deployment to modernize backup by simply swapping out hardware (e.g. disk for tape, cloud for disk), applying data footprint reduciton (DFR) including archiving, compression and dedupe or, another common scenario of switching from one vendors tool to another.

How vendors are helping backup staying alive?

One of the routine things I hear from vendors among others is that backup needs to move from the 70’s or 80’s or 90’s to the current era when the John Travolta and Oliva Newton John movie Saturday Night Fever and the Bee Gees song "Stayin Alive" appeared (click here to hear the song via Amazon).

Stayin Alive Image via Amazon.com

Some vendors keep talking and using the term backup instead of expanding the conversation to data protection that includes backup/restore, business continuance (BC), disaster recovery (DR) along with archiving and security. Now let’s be that we can not expect something like backup to be removed from the vocabulary overnight as its been around for decades, hence it will take time.

IMHO: The biggest barrier to moving away from backup is the industry including vendors, their pundits, press/media, vars and customers who continue to insist on using or referring to back up vs. expanding the conversation to data protection. – GS @StorageIO

Until there’s a broad focus on shifting to and using the term data protection including backup, BC, DR and archiving, people will simply keep referring to what they know, read or hear (e.g. backup). On the other hand if the industry starts putting more focus on using data protection with backup, people will stat following suit using the two and over time backup as a term can fade away.

Taking a step back to move forward

Some of the modernizing backup discussions is actually focused on take a step back to reconsider why, when, where, how and with what different applications, systems and data gets protected. certainly there are the various industry trends, challenges and opportunities some of which are shown below including more facts to protect, preserve and service for longer periods of time.

Likewise there are various threat risks or scenarios to protect information assets from or against, not all of which are head-line news making event situations.

data protection threat risk scenarios

Not all threat risks are headline news making events

There is an old saying in and around backup/restore, BC, DR, BR and HA of never letting a disaster go to waste. What this means is that if you have never noticed, there is usually a flurry of marketing and awareness activity including conversations about why you should do something BC, DR and other data protection activities right around, or shortly after a disaster scenario. However not all disasters or incidents are headline news making events and hence there should be more awareness every day vs. just during disaster season or situations. In addition, this also means expanding the focus on other situations that are likely to occur including among others those in the following figure.

data protection headline news and beyond

Continue reading part two of this series here to see what can be done about shifting the conversation about modernizing data protection. Also check out conversations about trends, themes, technologies, techniques perspectives in my ongoing data protection diaries discussions (e.g. www.storageioblog.com/data-protection-diaries-main/).

Ok, nuff said

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

Part III Until the focus expands to data protection – Taking action

Storage I/O trends

Part III – Until the focus expands to data protection – Taking action

This is the thrid of a three-part series (read part II here) about how vendors are keeping backup alive, however what they can and should do to shift and expand the conversation to data protection and related themes.

Modernizing is more than simply swapping one technology for another

As I have said for a couple of years now, modernizing data protection, or data protection modernization if you prefer is more than simply deduping or swapping out media, mediums, tape, disk, clouds, software or services like a recurring flat tire on an automobile. If you keep getting flat tires, instead of treating the symptom, find and fix the problem which means for backup, taking a step back and realizing that what is really being done is protecting data (e.g. data protection).

Granted the security people may not like sharing the term data protection as some of them prefer to keep that unique, just like some of the compliance people want to keep archiving exclusive to their focus areas, however lets move on.

On the other hand, data protection also means that, protect, preserve and enable data and information to be accessed and served when and were needed in a cost-effective way with consistency and coherency.

Sure there is still the act of making a copy or a backup at time intervals (frequency) with various coverage (how much gets copied) to multiple locations (copies) with versions kept for different amounts of time (retention) to support RTO and RPO, not to mention SLA and SLO for ITSM (how’s that for some buzzword bingo ;).

Buzzword bingo

This means using copies, sync (or rsync), snapshots, replication and CDP, discrete copies such as backups along with all the other buzzword bingo enabling tools, technologies and techniques (e.g. Agent or Agent less, Archive, Availability zones. Not to mention Bare metal, virtual bare metal, Block based, CDP, Compression, Consolidation, Deletion, Data management, Dedupe, eDiscovery, durability, erasure coding/parity, file level, meta data and policy management, replication, snapshots, RAID, plugin, object storage, NAS, VTL, disk, tape, cloud, virtual among others). In addition to taking a step back, this also means rethinking why, how, when, where data (and information) gets protected to meet various threat risks as well as diverse business requirements.

Storage I/O toolbox
No tools in the toolbox (physical, virtual or cloud)

Part of the rethinking is expanding the focus from what are the tools, who makes what’s, how do they work, their features and functions to how to use the tool or technology for different things.

Storage I/O backup and data protection tools
Various tools (hardware, software, services) for different physical, virtual and cloud tasks

This is like going into a store like Lowe’s or Home Depot and talking to the sales people their (ok, associates or team members) who can tell you everything thing there is to know about the tool or technology, however they can’t tell you how to use it.

Sometimes you can get lucky and there will be somebody working at the tool (hardware or software) store who will ask you what you are trying to do and give you advice based on their experience of a different approach with another tool or tools and some supporting material or parts and supplies.

Does this sound familiar to data infrastructure or IT in general, not to mention server, storage, backup and data protection among other areas of interest?

If all you have, or know how to use is a hammer, then everything or situation starts to look like a nail. Expand your toolbox with more tools AND learn how to use or apply them in new and different ways. Align the right tool, technology and technique to the task at hand!

Expand from talking new technology to using new (and old) things in new ways

In addition to focusing on new tools and technology along with their associated terminologies across physical, virtual and cloud environments, it is also time to expand the discussion and awareness to using new (and old) things in new ways. This also means expanding the terminology from backup/restore to more comprehensive data protection as part of modernizing your environment.

For example some people (and vendors) use the term or phrase "Modernizing Data Protection" to mean swap out tape for disk, or disk for cloud, or one cloud for another cloud, or upgrade from one software version to another, or simply swap one vendors software or tool for another, yet continue to use it for all practical purposes in the same way.

Sure, moving from hourly or daily copies to tape over to direct to disk and then either redeploying tape where it is better suited (streaming large amounts of data, powering off to save energy, e.g. deep cold archive). This also means leveraging fast random access to small files that need to be recovered (usually within first hours or days of being protected).

technology alignment
Aligning tools, technologies, techniques to various threat risk scenarios

Modernizing data protection (also known as transformation) also means recognizing that not everything is the same in the data center or information factory regardless of size, and that there are also different and evolving data access patterns. Another reason and trend to consider is that there is no such thing as an information recession and that people plus data are living longer as well as getting larger.

Expand your awareness and focus beyond simply knowing what the tools are and who makes them to how, when, where, why along with pros/cons of using them to discuss different situations. This means having multiple tools in your data protection toolbox as well as knowing how to use different tools for various tasks instead of always using a hammer. – GS @StorageIO

data protection continuum
The data protection continuum, more than tools and technoligiues

Call to action, stop talking about it, start walking the talk

If you or somebody else is tired of hearing about backup, then stop complaining about it and take some action. Following are some things to expand your thinking, awareness, discussions and activities around modernizing data protection (and moving beyond traditional backup).

  • Take a step back and check the basics or fundamentals of data protection which when enabled, allows your organization to move forward after a small or big incident (or disaster).
  • Start thinking beyond backup tools and technologies (hardware, software, services) particular how its been done, to why it needs to be done, how can it be done differently.
  • Revisit why you are protecting different things, realize that not everything is the same, so does that mean you have to protect everything the same way?
  • Learn about how to use different tools and technologies which is different from learning about the tools, features and functions.
  • Also keep in mind that a barrier is often people and process (along with organizational politics) that also result in new (and old) technologies being used in old ways.
  • Think about using different tools and technologies in different e.g. hybrid ways.
  • This means start using new (and old) tools, techniques, techniques in new ways, start to apply your return on innovation by using things to discuss issues, vs. simply using them for the sake of using them.

In addition to the above items, here are some added links on various topics and themes mentioned here:

BackupU – Vendor and technology neutral series of on-line webinars, Google+ hangouts, book chapter downloads and other content (Sponsored by Dell Data Protection Software, that’s a disclosure btw )

Via StorageIOblog – Only You Can Prevent Cloud Data Loss,
Cloud conversations: confidence, certainty and confidentiality,
Modernizing data protection with certainty,
More Data Footprint Reduction (DFR) Material,
More modernizing data protection, virtualization and clouds with certainty,
EMC Evolves Enterprise Data Protection with Enhancements and Data protection modernization, more than swapping out media.

Via StorageIO Reports/Resources Page – backup, restore, BC, DR and archiving available here including presentations and book chapter downloads

Via Internet evolution – People, Not Tech, Prevent IT Convergence.

Closing comments (for now)

Now having said all of that, It would be unrealistic to think that we can simply overnight drop the term backup and switch to data protection, after all, we need backwards compatibility. However until the industry which means from vendors, their pundits (analyst, bloggers, consultants, evangelists), press/media, vars, investors and customers start thinking and speaking in the broader context of data protection, life beyond backup, guess what, we will still be talking about backup. Start calling it (e.g. backup) data protection and perhaps within a generation (or sooner), the term backup will have been ILM, compressed, deduped, tiered, spun down, put into deep cold archive storage to take a long REST on object storage with a NAS interface in a software defined hybrid virtualized cloud ;).

Watch for more data protection conversations about related trends, themes, technologies, techniques perspectives in my ongoing data protection diaries discussions (e.g. www.storageioblog.com/data-protection-diaries-main/).

Ok, nuff said

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

Lenovo buys IBM’s xSeries aka x86 server business, what about EMC?

Storage I/O trends

Lenovo buys IBM’s xSeries x86 server business for $2.3B USD, what about EMC?

Once again Lenovo is new owner of some IBM computer technology, this time by acquiring the x86 (e.g. xSeries) server business unit from big blue. Today Lenovo announced its plan to acquire the IBM x86 server storage business unit for $2.3B USD.

Research Triangle Park, North Carolina, and Armonk, New York – January 23, 2014

Lenovo (HKSE: 992) (ADR: LNVGY) and IBM (NYSE: IBM) have entered into a definitive agreement in which Lenovo plans to acquire IBM’s x86 server business. This includes System x, BladeCenter and Flex System blade servers and switches, x86-based Flex integrated systems, NeXtScale and iDataPlex servers and associated software, blade networking and maintenance operations. The purchase price is approximately US$2.3 billion, approximately two billion of which will be paid in cash and the balance in Lenovo stock.

IBM will retain its System z mainframes, Power Systems, Storage Systems, Power-based Flex servers, and PureApplication and PureData appliances.

Read more here

If you recall (or didn’t’t know) around a decade or so ago IBM also spun off its Laptop (e.g. Thinkpads) and workstation business unit to Lenovo after being one of the early PC players (I still have a model XT in my collection along with Mac SE and Newton).

What this means for IBM?

What this means is that IBM is selling off a portion of its systems technology group which is where the servers, storage and related hardware, software technologies report into. Note however that IBM is not selling off its entire server portfolio, only the x86 e.g. Intel/AMD based products that make up the xSeries as well as companion Blade and related systems. This means that IBM is retaining its Power based systems (and processors) that include the pSeries, iSeries and of course the zSeries mainframes  in addition to the storage hardware/software portfolio.

However as part of this announcement, Lenovo is also licensing from IBM the Storwize/V7000 technology as well as tape summit resources, GPFS based scale out file systems used in SONAS and related products that are part of solution bundles tied to the x86 business.

Again to be clear, IBM is not selling off (or at least at this time) Storwize, tape or other technology to Lenovo other than x86 server business. By server business, this means the technology, patents, people, processes, products, sales, marketing, manufacturing, R&D along with other entities that form the business unit, not all that different from when IBM divested the workstation/laptop aka PC business in the past.

Storage I/O trends

What this means for Lenovo?

What Lenovo gets are an immediate (once the deal closes) expansion of their server portfolio including high-density systems for cloud, HPC as well as regular enterprise, not to mention also for SME and SMB. Lenovo also gets blade systems as well as converged systems (server, storage, networking, hardware, software) hence why IBM is also licensing some technology to Lenovo that it is not selling. Lenovo also gets the sales, marketing, design, support and other aspects to also expand their server business. By gaining the server business unit, Lenovo will now be in a place to take on Dell (who was also rumored to be in the market for the IBM servers), as well as HP, Oracle and other x86 system based suppliers.

What about EMC and Lenovo?

Yes, EMC, that storage company who is also a primary owner of VMware, as well as partner with Cisco and Intel in the VCE initiatives, not to mention who also entered into a partnership with Lenovo a year or so ago.

In case you forgot or didn’t’t know, EMC after breaking up with Dell, entered into a partnership with Lenovo back in 2012.

This partnership and initiatives included developing servers that in turn EMC could use for their various storage and data appliances which continue to leverage x86 type technology. In addition, that agreement found the EMC Iomega brand transitioning over into the Lenovo line-up for both domestic North America, as well as international including the chinese market. Hence I have an older Iomega IX4 that says EMC, and a newer one that says EMC/Lenovo, also note that at CES a few weeks ago, some new Iomega products were announced.

In checking with Lenovo today, they indicated that it is business as usual and no changes with or to the EMC partnership.

Via email from Lenovo spokesperson today:

A key piece to Lenovo’s Enterprise strategy has always included strong partnerships. In fact today’s announcements reinforce that strategy very clearly.

Given the new scale, footprint and Enterprise credibility that this server acquisition affords Lenovo, we see great opportunity in offering complimentary storage offerings to new and existing customers.

Lenovo’s partnership with EMC is multifaceted and stays in-tact as an important part of Lenovo’s overall strategy to offer customers compelling solutions built on world-class technology.

Lenovo will continue to offer Lenovo/EMC NAS products from our joint venture as well as resell EMC stand-alone storage platforms.

IBM Storwize storage and other products are integral to the in-scope platforms and solutions we acquired. In order to ensure continuity of business and the best customer experience we will partner with IBM for storage products as well.

We believe this is a great opportunity for all three companies, but most importantly these partnerships are in place and will remain healthy for the benefit for our customers.

Hence it is my opinion that for now it is business as usual, the IBM x8x business unit has a new home, those people will be getting new email addresses and business cards similar to how some of their associates did when the PC group was sold off a few years ago.

Otoh, there may also be new products that might become opportunities to be placed into he Lenovo EMC partnership, however that is just my speculation at this time. Likewise while there will be some groups within Lenovo focused on selling the converged Lenovo solutions coming from IBM that may in fact compete with EMC (among others) in some scenarios, that should be no more and hopefully less than what IBM has with their server groups at times competing with themselves.

Storage I/O trends

What does this mean for Cisco, Dell, HP and others?

For Cisco, instead of competing with one of their OEMs (e.g. IBM) for networking equipment (note IBM also owns some of its own networking), the server competition shifts to Lenovo who is also a Cisco partner (its called coopitition), and perhaps business as usual in many areas. For Dell, in the mid-market space, things could get interesting and the Round Rock folks need to get creative and beyond VRTX.

For HP, this is where IMHO it’s going to get really interesting as Lenovo gets things transitioned. Near-term, HP could have a disruptive upper hand, however longer-term, HP has to get their A-Game on. Oracle is in the game as are a bunch of others from Fujitsu to SuperMicro to outside of North America and in particular china there is also Huawei. Back to EMC and VCE, while I expect the Cisco partnership to stay, I also see a wild card where EMC can leverage their Lenovo partnership into more markets, while Cisco continues to move into storage and other adjacent areas (e.g. more coopitition).

What this means now and going forward?

Thus this is as much about enterprise, SME, SMB as it is HPC, cloud and high-density where the game is about volume. Likewise there is also the convergence or data infrastructure angle combing server, storage, networking hardware, software and services.

One of the things I have noticed about Lenovo as a customer using ThinkPads for over 13 years now (not the same one) is that while they are affordable, instead of simply cutting cost and quality, they seem to have found ways to remove cost which is different then simply cutting to go cheap.

Case in point about a year and a half ago I dropped my iPhone on my Lenovo X1 keyboard that is back-lit and broke a key. Calling Lenovo after trying to find a replacement key on the web, they said no worries and next morning a new keyboard for the laptop was on my doorstep by 10:30Am with instructions on how to remove the old, put in the new, and do the RMA, no questions asked (read more about this here).

The reason I mention that story about my X1 laptop is that it ties to what I’m curious and watching with their soon to be expanded new server business.

Will they go in and simply look to reduce cost by making cuts from design to manufacturing to part quality, service and support, or, find ways to remove complexity and cost while providing more value?

Now I wonder whose technology will join my HP and Dell systems to fill some empty rack space in the not so distant future to support growth?

Time will tell, congratulations to Lenovo and the IBMers who now have a new home best wishes.

Ok, nuff said

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2014

Posted on

Dell Inspiron 660 i660, Virtual Server Diamond in the rough?

Storage I/O trends

Dell Inspiron 660 i660, Virtual Server Diamond in the rough?

During the 2013 post thanksgiving black friday shopping day, I did some on-line buying including a Dell Inspiron 660 i660 (5629BK) to be used as a physical machine (PM) or VMware host (among other things).

Now technically I know, this is a workstation or desktop and thus not what some would consider a server, however as another PM to add to my VMware environment (or be used as a bare metal platform), it is a good companion to my other systems.

Via Dell.com Dell 660 i660

Taking a step back, needs vs. wants

Initially my plan for this other system was to go with a larger, more expensive model with as many DDR3 DIMM (memory) and PCIe x4/x8/x16 expansion slots as possible. Some of my other criteria were PCIe Gen 3, latest Intel processor generation with VT (Virtualization Technology) and Extended Page Tables (EPT) for server virtualization support without breaking my budget. Heck, I would love a Dell VRTX or some similar types of servers from the likes of Cisco, HP, IBM, Lenovo, Supermicro among many others. On the other hand, I really don’t need one of those types of systems yet, unless of course somebody wants to send some to play with (excuse me, test drive, try-out).

Hence needs are what I must have or need, while wants are those things that would be, well, nice to have.

Server shopping and selection

In the course of shopping around, looking at alternatives and having previously talked with Robert Novak (aka @gallifreyan) and he reminded me to think outside the box a bit, literally. Check out Roberts blog (aka rsts11 a great blog name btw for those of use who used to work with RSTS, RSX and others) including a post he did shortly after I had a conversation with him. If you read his post and continue through this one, you should be able to connect the dots.

While I still have a need and plans for another server with more PCIe and DDR3 (maybe wait for DDR4? ;) ) slots, I found a Dell Inspiron 660.

Candidly normally I would have skipped over this type or class of system, however what caught my eye was that while limited to only two DDR3 DIMM slots and a single PCIe x16 slot, there were three extra x1 slots which while not as robust, certainly gave me some options if I need to use those for older, slower things. Likewise leveraging higher density DIMM’s, the system is already now at 16GB RAM waiting for larger DIMM’s if needed.

VMware view of Inspiron 600

The Dell Inspiron 660-i660 I found had a price of a little over $550 (delivered) with an Intel i5-3330 processor (quad-core, quad thread 3GHz clock), PCIe Gen 3, one PCIe x16 and three PCIe x1 slots, 8GB DRAM (since reallocated), GbE port and built-in WiFi, Windows 8 (since P2V and moved into the VMware environment), keyboard and mouse, plus a 1TB 6Gb SATA drive, I could afford two, maybe three or four of these in place of a larger system (at least for now). While for something’s I have a need for a single larger server, there are other things where having multiple smaller ones with enough processing performance, VT and EPT support comes in handy (if not required for some virtual servers).

Some of the enhancements that I made were once the initial setup of the Windows system was complete, did a clone and P2V of that image, and then redeploying the 1TB SATA drive to join others in the storage pool. Thus the 1TB SATA HDD has been replaced with (for now) a 500GB Momentus XT HHDD which by time you read this could already changed to something else.

Another enhancements was bumping up the memory from 8GB to 16GB, and then adding a StarTech enclosure (See below) for more internal SAS / SATA storage (it supports both 2.5" SAS and SATA HDD’s as well as SSD’s). In addition to the on-board SATA drive port plus one being used for the CD/DVD, there are two more ports for attaching to the StarTech or other large 3.5" drives that live in the drive bay. Depending on what I’m using this system for, it has different types of adapters for external expansion or networking some of which have already included 6Gbps and 12Gbps SAS HBA’s.

What about adding more GbE ports?

As this is not a general purpose larger system with many expansion ports for PCIe slots, that is one of the downsides you get for this cost. However depending on your needs, you have some options. For example I have some Intel PCIe x1 GbE cards to give extra networking connectivity if or when needed. Note however that as these are PCIe x1 slots they are PCIe Gen 1 so from a performance perspective exercise caution when mixing these with other newer, faster cards when performance matters (more on this in the future).

Via Amazon.com Intel PCIe x1 GbE card
Via Amazon.com Intel (Gigabit CT PCI-E Network Adapter EXPI9301CTBLK)

One of the caveats to be aware of if you are going to be using VMware vSphere/ESXi is that the Realtek GbE NIC on the Dell Inspiron D600-i660 may not play well, however there are work around’s. Check out some of the work around’s over at Kendrick Coleman (@KendrickColeman) and Erik Bussink (@ErikBussink) sites both of which were very helpful and I can report that the Realtek GbE is working fine with VMware ESXi 5.5a.

Need some extra SAS and SATA internal expansion slots for HDD and SSD’s?

The StarTech 4 x 2.5″ SAS and SATA internal enclosures supports various speed SSD and HDD’s depending on what you connect the back-end connector port to. On the back of the enclosure chassis there is a connector that is a pass-thru to the SAS drive interface that also accepts SATA drives. This StarTech enclosure fits nicely into an empty 5.2″ CD/DVD expansion bay and then attach the individual drive bays to your internal motherboard SAS or SATA ports, or to those on another adapter.

Via Amazon.com StarTech 4 port SAS / SATA enclosure
Via Amazon.com StarTech 4 x 2.5" SAS and SATA internal enclosure

So far I have used these enclosures attached to various adapters at different speeds as well as with HDD, HHDD, SSHD and SSD’s at various SAS/SATA interface speeds up to 12Gbps. Note that unlike some other enclosures that have SAS or SATA expander, the drive bays in the StarTech are pass-thru hence are not regulated by the expander chip and its speed. Price for these StarTech enclosures is around $60-90 USD and are good for internal storage expansion (hmm, need to build your own NAS or VSAN or storage server appliance? ;) ).

Via Amazon Molex power connector

Note that you will also need to get a Molex power connector to go from the back of the drive enclosure to an available power port such as for expansion DVD/CD that you can find at a Radio Shack, Fry’s or many other venues for couple of dollars. Double check your specific system and cable connector leads to verify what you will need.

How is it working and performing

So far so good, in addition to using it for some initial calibration and validation activities, the D660 is performing very well and no buyers remorse. Ok, sure, would like more PCIe Gen 3 x4/x8/x16 or an extra on-board Ethernet, however all the other benefits have outweighed those pitfalls.

Speaking of which, if you think a SSD (or other fast storage device) is fast on a 6Gbps SAS or PCIe Gen 2 interface for physical or virtual servers, wait until you experience those IOPs or latencies at 12Gbps SAS and PCIe Gen 3 with a faster current generation Intel processor, just saying ;)…

Server and Storge I/O IOPS and vmware

In the above chart (slide scroll bar to view more to the right) a Windows 7 64 bit systems (VMs configured with 14GB DRAM) on VMware vSphere V5.5.1 is shown running on different hardware configurations. The Windows system is running Futuremark PCMark 7 Pro (v1.0.4). From left to right the Windows VM on the Dell Inspiron 660 with 16GB physical DRAM using a SSHD (Solid State Hybrid Drive). Second from the left shows results running on a Dell T310 with an Intel X3470 processor also on a SSHD. Middle is the workload on the Dell 660 running on a HHDD, second from right is the workload on the Dell T310 also on a HHDD, while on the right is the same workload on an HP DCS5800 with an Intel E8400. The workload results show a composite score, system storage, simulating user productivity, lightweight processing, and compute intensive tasks.

Futuremark PCMark Windows benchmark
Futuremark PCMark

Don’t forget about the KVM (Keyboard Video Mouse)

Mention KVM to many people in and around the server, storage and virtualization world and they think KVM as in the hypervisor, however to others it means Key board, Video and Mouse aka the other KVM. As part of my recent and ongoing upgrades, it was also time to upgrade from the older smaller KVM’s to a larger, easier to use model. The benefit, support growth while also being easier to work with. Having done some research on various options that also varied in price, I settled in on the StarTech shown below.

Via Amazon.com StarTech 8 port KVM
Via Amazon.com StarTech 8 Port 1U USB KVM Switch

What’s cool about the above 8 port StarTech KVM switch is that it comes with 8 cables (there are 8 ports) that on one end look like a regular VGA monitor screen cable connector. However on the other end that attached to your computer, there is the standard VGA connection that attached to your video out, and a short USB tail cable that attached to an available USB port for Keyboard and Mouse. Needless to say it helps to cut down on the cable clutter while coming in around $38.00 USD per server port being managed, or about a dollar a month over a little over three years.

Word of caution on make and models

Be advised that there are various makes and models of the Dell Inspiron available that differ in the processor generation and thus feature set included. Pay attention to which make or model you are looking at as the prices can vary, hence double-check the processor make and model and then visit the Intel site to see if it is what you are expecting. For example I double checked that the processor for the different models I looked at were i5-3330 (view Intel specifications for that processor here).

Summary

Thanks to Robert Novak (aka @gallifreyan) for taking some time providing useful tips and ideas to help think outside the box for this, as well as some future enhancements to my server and StorageIO lab environment.

Consequently while the Dell Inspiron D600-i660 was not the server that I wanted, it has turned out to be the system that I need now and hence IMHO a diamond in the rough, if you get the right make and mode.

Ok, nuff said

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2013 StorageIO and UnlimitedIO All Rights Reserved

Posted on

Book review: Rethinking Enterprise Storage by Microsoft/Storsimple Marc Farley

Storage I/O trends

Book review: Rethinking Enterprise Storage – A Hybrid Cloud Model by Marc Farley

The O’Reilly @oreillymedia media folks (oops, excuse me, Microsoft Press) sent me out (that’s a disclosure btw) an real soft cover print copy of Rethinking Enterprise Storage – A Hybrid Cloud Model by Marc Farley aka @MicroFarley of Microsoft/Storsimple that features a forward by Martin Glassborow aka @Storagebod.

Rethinking Enterprise Storage - A Hybrid Cloud Model

Topics and themes covered in the book

  • Understanding scale storage architectures (hmm, great way of saying hybrid ;)
  • Rethinking data protection including disaster recovery (DR) best practices
  • Enhancing data protection using cloud snapshots beyond traditional backups
  • Deterministic thin recovery capabilities while dynamically expanding capacity to the cloud
  • Implement data footprint reduction (DFR) including archiving digital documents to the cloud
  • Insight and awareness into keep performance indicators along with various use cases

Rethinking Enterprise Storage book Details

Publisher: Microsoft Press
Author: Marc Farley
Paper back
Features: Many diagrams, figures, index, glossary
Pages: 101
ISBN: 978-0-7356-7990-3
Published: 2013
MSRP: $9.99 USD

Sample pages of rethinking enterprise storage
One of the many books many figures on the right, on the left i needed to hold a page down ;)!

What’s inside the book

Make no mistake that this is a Microsoft and Storsimple themed book, however IMHO Marc (aka Farley) does a great job of making it more relevant than just another vendor product book (JAVPB). While it is a Microsoft focused book around enabling hybrid cloud storage for various applications, the premises presented could be adapted for other environments or implementations. The book at 101 pages including table of contents (TOC), index, appendix, glossary and other front matter is a very easy and fast read while providing more information or coverage than what might be found in a "Dummies" type themed book.

Looking inside Rethinking Enterprise Storage by Marc Farley
Start thinking outside the box (or cloud), imagine what you can do with a Hybrid cloud!

Summary

Overall I found the book to be good and not just because I know Marc or that the O’Reilly folks sent me a free copy (I had actually previously received the electronic ebook version), rather that it is timely and does a nice job of conveying the topic theme and setting up the conversation, time to rethink storage for enterprise and other environments. IMHO the question is not if hybrid cloud storage is in your future, rather when, where, why, for what, how, with whom and related conversations. While you can buy a copy of the book at various venues, it shouldn’t take a lot of effort to get your own printed soft cover copy, or an ebook version.

Btw, here’s a pod cast discussion with Marc Farley from spring 2013 at SNW, as well as a link to a hybrid cloud and object storage post he did over at Microsoft Technet.

To summarize and quote Marc Farley "Hey now…."

Ok, nuff said

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2013 StorageIO and UnlimitedIO All Rights Reserved

Posted on

IoD, IoT, IoE, IoS, IoP, IoU and IoX are in your future

Storage I/O trends

IoD, IoT, IoE, IoS, IoP, IoU and IoX are in your future

Have you figured out the new buzzword trend for 2014 that starting ramping up in 2013?

Yup, its Internet of Things (IoT) and Internet of Devices’s (IoD)

Assuming that IoT, IoD and other variations catch on which looks like they will, this could bring relief and rest for the over-worked Big Data and Software Defined "X" buzzword bingo bandwagon usage.

Buzzword bingo

Introducing IoX?

For those not familiar with Software Defined "X", simply replace "X" with your favorite term such as Data Center (SDDC), Networking (SDN), Storage (SDS), Marketing, (SDM) among others.as the new IT (and beyond) industry term might just take some pressure from the over-worked software defined "x" usage (you pick "x" such as data center, networking, storage, marketing, etc).

This is good news as we now have IoX where "X" can be leveraged from Things (IoT) and Devices (IoD) to People, Places, Protocols or Platforms (IoP), not to mention APIs, Applications and Apple (IoA).

How about Internet of Items (IoI) or Internet of Objects (IoO)?

We are already seeing Cisco with Internet of Everything (IoE) from CES and rest assured the Big Data folks will want to get all over IoBD while storage folks serve up Internet of Storage (IoS), granted that might be a little close to Apple’s OS for comfort of some.

Of course this should also prompt the question of if instead of Internet of Things (IoT) or IoX as being public, then would a Intranet of Things or other items (e.g. IoX) be considered private?

And if you just said or thought, what hybrid, sure, why not, its 2014 after all…

Here’s my point

There are many other variations particular if you apply some cloud and virtual based Big Data analytics with some software defined marketing creativity.

So what’s your take on IoT, IoD, IoP and other IoX, is it all IoH (Internet of Hype) and Internet of Marketing (IoM), something new to get excited about for those who suffer from technology buzzword ADD?

What say you?

Ok, nuff said

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

Goodbye 2013, hello 2014, predictions past, present and future

Storage I/O trends

Good by 2013 and hello 2014 along with predictions past, present and future

First, for those who may have missed this, thanks to all who helped make 2013 a great year!

2013 season greetings

Looking back at 2013 I saw a continued trend of more vendors and their media public relations (PR) people reaching out to have their predictions placed in articles, posts, columns or trends perspectives pieces.

Hmm, maybe a new trend is predictions selfies? ;)

Not to worry, this is not a wrapper piece for a bunch of those pitched and placed predictions requests that I received in 2013 as those have been saved for a rainy or dull day when we need to have some fun ;) .

What about 2013 server storage I/O networking, cloud, virtual and physical?

2013 end up with some end of year spree’s including Avago acquiring storage I/O and networking vendor LSI for about $6.6B USD (e.g. SSD cards, RAID cards, cache cards, HBA’s (Host Bus Adapters), chips and other items) along with Seagate buying Xyratex for about $374M USD (a Seagate suppliers and a customer partner).

Xyratex is known by some for making the storage enclosures that house hard disk drive (HDD’s) and Solid State Device (SSD) drives that are used by many well-known, and some not so well-known systems and solution vendors. Xyratex also has other pieces of their business such as appliances that combine their storage enclosures for HDD and SSD’s along with server boards, along with a software group focus on High Performance Compute (HPC) Lustre. There is another part of the Xyratex business that is not as well-known which is the test equipment used by disk drive manufacturers such as Seagate as part of their manufacturing process. Thus the Seagate acquisition moves them up market with more integrated solutions to offer to their (e.g. Seagate and Xyratex) joint customers, as well as streamline their own supply chain and costs (not to mention sell equipment to the other remaining drive manufactures WD and Toshiba).

Storage I/O trends

Other 2013 acquisitions included (Whiptail by Cisco, Virident by WD (who also bought several other companies), Softlayer by IBM) along with various mergers, company launches, company shutdowns (cloud storage Nirvanix and SSD maker OCZ bankruptcy filing), and IPO’s (some did well like Nimble while Violin not so well), while earlier high-flying industry darlings such as FusionIO are now the high-flung darling targets of the shareholder sock lawsuit attorneys.

2013 also saw the end of SNW (Storage Network World), jointly produced by SNIA and Computerworld Storage in the US after more than a decade. Some perspectives from the last US SNW held October 2013 can be found in the Fall 2013 StorageIO Update Newsletter here, granted those were before the event was formal announced as being terminated.

Speaking of events, check out the November 2013 StorageIO Update Newsletter here for perspectives from attending the Amazon Web Services (AWS) re:Invent conference which joins VMworld, EMCworld and a bunch of other vendor world events.

Lets also not forget Dell buying itself in 2013.

StorageIO in the news

Click on the following links read (and here) more about various 2013 industry perspectives trends commentary of mine in various venues, along with tips, articles, newsletters, events, pod cast, videos and other items.

What about 2014?

Perhaps 2014 will build on the 2013 momentum of the annual rights of pages refereed to as making meaningless future year trends and predictions as being passe?

Not that there is anything wrong with making predictions for the coming year, particular if they actually have some relevance, practicality not to mention track record.

However that past few years seems to have resulted in press releases along with product (or services) plugs being masked as predictions, or simply making the same predictions for the coming year that did not come to be for the earlier year (or the one before that or before that and so forth).

On the other hand, from an entertainment perspective, perhaps that’s where we will see annual predictions finally get classified and put into perspectives as being just that.

Storage I/O trends

Now for those who still cling to as well as look forward to annual predictions, ok, simple, we will continue in 2014 (and beyond) from where we left off in 2013 (and 2012 and earlier) meaning more (or continued):

  • Software defined "x" (replace "x" with your favorite topic) industry discussion adoption yet customer adoption or deployment question conversations.

  • Cloud conversations shifted from lets all go to the cloud as the new shiny technology to questioning the security, privacy, stability, vendor or service viability not to mention other common sense concerns that should have been discussed or looked into earlier. I have also heard from people who say Amazon (as well as Verizon, Microsoft, Blue host, Google, Nirvanix, Yahoo and the list goes on) outages are bad for the image of clouds as they shake people’s confidences. IMHO people confidence needs to be shaken to that of having some common sense around clouds including don’t be scared, be ready, do your homework and basic due diligence. This means cloud conversations over concerns set the stage for increased awareness into decision-making, usage, deployment and best practices (all of which are good things for continued cloud deployments). However if some vendors or pundits feel that people having basic cloud concerns that can be addressed is not good for their products or services, I would like to talk with them because they may be missing an opportunity to create long-term confidence with their customers or prospects.

  • VDI as a technology being deployed continues to grow (e.g. customer adoption) while the industry adoption (buzz or what’s being talked about) has slowed a bit which makes sense as vendors jump from one bandwagon to the new software defined bandwagon.

  • Continued awareness around modernizing data protection including backup/restore, business continuance (BC), disaster recovery (DR), high availability, archiving and security means more than simply swapping out old technology for new, yet using it in old ways. After all, in the data center and information factory not everything is the same. Speaking of data protection, check out the series of technology neutral webcast and video chats that started last fall as part of BackupU brought to you by Dell. Even though Dell is the sponsor of the series (that’s a disclosure btw ;) ) the focus of the sessions is on how to use different tools, technologies and techniques in new ways as well as having the right tools for different tasks. Check out the information as well as register to get a free Data Protection chapter download from my book Cloud and Virtual Data Storage Networking (CRC Press) at the BackupU site as well as attend upcoming events.

  • The nand flash solid state devices (SSD) cash-dash (and shakeout) continues with some acquisitions and IPO’s, as well as disappearances of some weaker vendors, while appearance of some new. SSD is showing that it is real in several ways (despite myths, fud and hype some of which gets clarified here) ranging from some past IPO vendors (e.g. FusiuonIO) seeing exit of their CEO and founders while their stock plummets and arrival of shareholder investor lawsuits, to Violins ho-hum IPO. What this means is that the market is real, it has a very bright future, however there is also a correction occurring showing that reality may be settling in for the long run (e.g. next couple of decades) vs. SSD being in the realm of unicorns.

    • Storage I/O trends

  • Internet of Things (IoT) and Internet of Devices (IoD) may give some relief for Big Data, BYOD, VDI, Software Defined and Cloud among others that need a rest after they busy usage that past few years. On the other hand, expect enhanced use of earlier buzzwords combined with IoT and IOD. Of course that also means plenty of questions around what is and is not IoD along with IoT and if actually relevant to what you are doing.

  • Also in 2014 some will discover storage and related data infrastructure topics or some new product / service thus having a revolutionary experience that storage is now exciting while others will have a DejaVu moment that it has been exciting for the past several years if not decades.

  • More big data buzz as well as realization by some that a pragmatic approach opens up a bigger broader market, not to mention customers more likely to realize they have more in common with big data than it simply being something new forcing them to move cautiously.

  • To say that OpenStack and related technologies will continue to gain both industry and customer adoption (and deployment) status building off of 2013 in 2014 would be an understatement, not to mention too easy to say, or leave out.

  • While SSD’s continue to gain in deployment, after the question is not if, rather when, where, with what and how much nand flash SSD is in your future, HDD’s continue to evolve for physical, virtual and cloud environments. This also includes Seagate announcing a new (Kinetic) Ethernet attached HDD (note that this is not a NAS or iSCSI device) that uses a new key value object storage API for storing content data (more on this in 2014).

  • This also means realizing that large amounts of little data can result in back logs of lots of big data, and that big data is growing into very fast big data, not to mention realization by some that HDFS is just another distributed file system that happens to work with Hadoop.

  • SOHO’s and lower end of SMB begin to get more respect (and not just during the week of Consumer Electronic Show – CES).

  • Realization that there is a difference between Industry Adoption and Customer Deployment, not to mention industry buzz and traction vs. customer adoption.

server storage I/O trends

What about beyond 2014?

That’s easy, many of the predictions and prophecies that you hear about for the coming year have also been pitched in prior years, so it only makes sense that some of those will be part of the future.

  • If you have seen or experienced something you are more likely to have DejaVu.
  • Otoh if you have not seen or experienced something you are more likely to have a new and revolutionary moment!
  • Start using new (and old) things in new ways vs. simply using new things in old ways.
  • Barrier to technology convergence, not to mention new technology adoption is often people or their organizations.
  • Convergence is still around, cloud conversations around concerns get addressed leading to continued confidence for some.
  • Realization that data infrastructure span servers, storage I/O networking, cloud, virtual, physical, hardware, software and services.
  • That you can not have software defined without hardware and hardware defined requires software.
  • And it is time for me to get a new book project (or two) completed in addition to helping others with what they are working on, more on this in the months to come…

Here’s my point

The late Jim Morrison of the Doors said "There are things known and things unknown and in between are the doors.".

The doors via Amazon.com
Above image and link via Amazon.com

Hence there is what we know about 2013 or will learn about the past in the future, then there is what will be in 2014 as well as beyond, hence lets step through some doors and see what will be. This means learn and leverage lessons from the past to avoid making the same or similar mistakes in the future, however doing so while looking forward without a death grip clinging to the past.

Needless to say there will be more to review, preview and discuss throughout the coming year and beyond as we go from what is unknown through doors and learn about the known.

Thanks to all who made 2013 a great year, best wishes to all, look forward to seeing and hearing from you in 2014!

Ok, nuff said (for now)

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

Small Medium Business (SMB) IT continues to gain respect, what about SOHO?

Storage I/O trends

Blog post: Small Medium Business (SMB) IT continues to gain respect, what about SOHO?

Note that in Information Technology (IT) conversations there are multiple meanings for SMB including Server Message Block aka Microsoft Windows CIFS (Common Internet File System) along with its SAMBA implementation, however for this piece the context is Small Medium Business.

A decade or so ago, mention SMB (Small Medium Business) to many vendors, particular those who were either established or focused on the big game enterprise space and you might have gotten a condescending look or answer if not worse.

In other words, a decade ago the SMB did not get much respect from some vendors and those who followed or covered them.

Fast forward to today and many of those same vendors along with their pundits and media followers have now gotten their SMB grove, lingo, swagger or social media footsteps, granted for some that might be at the higher end of SMB also known as SME (Small Medium Enterprise).

Today in general the SMB is finally getting respect and in some circles its down right cool and trendy vs. being perceived as old school, stodgy large enterprise. Likewise the Remote Office Branch Office (ROBO) gained more awareness and coverage a few years back which while the ROBO buzz has subsided, the market and opportunities are certainly there.

What about Small Office Home Office (SOHO) today?

I assert that SOHO today is getting the same lack of respect that SMB in general received a decade ago.

IMHO the SOHO environment and market today is being treated with a similar lack of respect that the larger SMB received a decade ago.

Granted there are some vendors and their followings who are seeing the value and opportunity, not to mention market size potential of expanding their portfolios, not to mention routes to markets to meet their different needs of the SOHO.

relative enterprise sme smb soho positioning

What is the SOHO market or environment

One of the challenges with SMB, SOHO among other classifications are just that, the classifications.

Some classificaitons are based on number of employees, others on number of servers or workstations, while others are based on revenue or even physical location.

Meanwhile some are based on types of products, technologies or tools while others are tied to IT or general technology spending.

Some confuse the SOHO space with the consumer market space or sector which should not be a surprise if you view market segments as enterprise, SMB and consumer. However if you take a more pragmatic approach, between true consumer and SMB space, there lies the SOHO space. For some the definitions of what is consumer, SOHO, SMB, SME and enterprise (among others) will be based on number of employees, or revenue amount. Yet for others the categories may be tied to IT spending (e.g. price bands), number of workstations, servers, storage space capacity or some other metric. On the other hand some definitions of what is consumer vs. SOHO vs. SMB vs. SME or enterprise will be based on product capabilities, size, feature function and cost among other attributes.

Storage I/O trends

Understanding the SOHO

Keep in mind that SOHO can also overlap with Remote Office Branch Office (ROBO), not to mention blend with high-end consumer (prosumer) or lower bounds of SMB.

Part of the challenge (or problem) is that many confuse the Home Office or HO aspect of SOHO as being consumer.

Likewise many also confuse the Small Office or SO part of SOHO as being just the small home office or the virtual office of a mobile worker.

The reality is that just as the SMB space has expanded, there is also a growing area just above where consumer markets exist and where many place the lower-end of SMB (e.g. the bottom limits of where the solutions fit).

First keep in mind that many put too much focus and mistakenly believe that the HO or Home Office part of SOHO means that this is just a consumer focused space.

The reality is that while the HO gets included as part of SOHO, there is also the SO or Small Office which is actually the low-end of the SMB space.

Keep in mind that there are more:
SOHO than SMB
SMB than SME
SME than enterprise
F500 (Fortune 500) than F100
F100 than F10 and so forth.

Here is my point

SOHO does not have to be the Rodney Dangerfield of IT (e.g. gets no respect)!

If you jumped on the SMB bandwagon a decade ago, start paying attention to what’s going on with the SOHO or lower-end SMB sector. The reasons are simple, just as SMBs can grow up to be larger SMBs or SME or enterprise, SOHOs can also evolve to become SMBs either in business size, or in IT and data infrastructure needs, requirements.

For those who prefer (at least for now) look down upon or ignore the SOHO similar to what was done with SMB before converting to SMBism, do so at your own risk.

However let me be clear, this does not mean ignore or shift focus and thus disrupt or lose coverage of other areas, rather, extend, expand and at least become aware of what is going on in the SOHO space.

Ok, nuff said (for now)

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

November 2013 Server and StorageIO Update Newsletter & AWS reinvent info


November 2013 Server and StorageIO Update Newsletter & AWS reinvent info

Welcome to the November 2013 edition of the StorageIO Update (newsletter) containing trends perspectives on cloud, virtualization and data infrastructure topics. Fall (here in North America) has been busy with in-person, on-line live and virtual events along with various client projects, research, time in the StorageIO cloud, virtual and physical lab test driving, validating and doing proof of concept research among other tasks. Check out the industry trends perspectives articles, comments and blog posts below that covers some activity over the past month.

Last week I had the chance to attend the second annual AWS re:Invent event in Las Vegas, see my comments, perspectives along with a summary of announcements from that conference below.

Watch for future posts, commentary, perspectives and other information down the road (and in the not so distant future) pertaining to information and data infrastructure topics, themes and trends across cloud, virtual, legacy server, storage, networking, hardware and software. Also check out our backup, restore, BC, DR and archiving (Under the resources section on StorageIO.com) for various presentation, book chapter downloads and other content.

Enjoy this edition of the StorageIO Update newsletter.

Ok, nuff said (for now)

Cheers gs

StorageIO Industry Trends and Perspectives

Industry trends: Amazon Web Services (AWS) re:Invent

Last week I attended the AWS re:Invent event in Las Vegas. This was the second annual AWS re:Invent conference which while having an AWS and cloud theme, it is also what I would describe as a data infrastructure event.

As a data infrastructure event AWS re:Invent spans traditional legacy IT and applications to newly invented, re-written, re-hosted or re-platformed ones from existing and new organizations. By this I mean a mix of traditional IT or enterprise people as well as cloud and virtual geek types (said with affection and all due respect of course) across server (operating system, software and tools), storage (primary, secondary, archive and tools), networking, security, development tools, applications and architecture.

That also means management from application and data protection spanning High Availability (HA), Business Continuance (BC), Disaster Recovery (DR), backup/restore, archiving, security, performance and capacity planning, service management among other related themes across public, private, hybrid and community cloud environments or paradigms. Hmm, I think I know of a book that covers the above and other related topic themes, trends, technologies and best practices called Cloud and Virtual Data Storage Networking (CRC Press) available via Amazon.com in print and Kindle (among other) versions.

During the event AWS announced enhanced and new services including:

  • WorkSpaces (Virtual Desktop Infrastructure – VDI) announced as a new service for cloud based desktops across various client devices including laptops, Kindle Fire, iPad and Android tablets using PCoIP.
  • Kinesis which is a managed service for real-time processing of streaming (e.g. Big) data at scale including ability to collect and process hundreds of GBytes of data per second across hundreds of thousands of data sources. On top of Kinesis you can build your big data applications or conduct analysis to give real-time key performance indicator dashboards, exception and alarm or event notification and other informed decision-making activity.
  • EC2 C3 instances provide Intel Xeon E5 processors and Solid State Device (SSD) based direct attached storage (DAS) like functionality vs. EBS provisioned IOPs for cost-effective storage I/O performance and compute capabilities.
  • Another EC2 enhancement are G2 instance that leverage high performance NVIDIA GRID GPU with 1,536 parallel processing cores. This new instance is well suited for 3D graphics, rendering, streaming video and other related applications that need large-scale parallel or high performance compute (HPC) also known as high productivity compute.
  • Redshift (cloud data warehouse) now supports cross region snapshots for HA, BC and DR purposes.
  • CloudTrail records AWS API calls made via the management console for analytics and logging of API activity.
  • Beta of Trusted Advisor dashboard with cost optimization saving estimates including EBS and provisioned IOPs
  • Relational Database Service (RDS) support for PostgresSQL including multi-AZ deployment.
  • Ability to discover and launch various software from AWS Marketplace via the EC2 Console. The AWS Marketplace for those not familiar with it is a catalog of various software or application titles (over 800 products across 24 categories) including free and commercial licensed solutions that include SAP, Citrix, Lotus Notes/Domino among many others.
  • AppStream is a low latency (STX protocol based) service for streaming resource (e.g. compute, storage or memory) intensive applications and games from AWS cloud to various clients, desktops or mobile devices. This means that the resource intensive functionality can be shifted to the cloud, while providing a low latency (e.g. fast) user experience off-loading the client from having to support increased compute, memory or storage capabilities. Key to AppStream is the ability to stream data in a low-latency manner including over networks normally not suited for high quality or bandwidth intensive applications. IMHO AppStream while focused initially on mobile app’s and gaming, being a bit streaming technology has the potential to be used for other similar functions that can leverage download speed improvements.

    • When I asked an AWS person if or what role AppStream might have or related to WorkSpaces their only response was a large smile and no comment. Does this mean WorkSpaces leverages AppStream? Candidly I don’t know, however if you look deeper into AppStream and expand your horizons, see what you can think up in terms of innovation. Updated 11/21/13 AWS has provided clarification that WorkSpaces is based on PCoIP while AppStream uses the STX protocols.

    Check out AWS Sr. VP Andy Jassy keynote presentation here.

Overall I found the AWS re:Invent event to be a good conference spanning many aspects and areas of focus which means I will be putting it on my must attend list for 2014.

StorageIO Industry Trends and PerspectivesIndustry trends tips, commentary, articles and blog posts
What is being seen, heard and talked about while out and about

The following is a synopsis of some StorageIOblog posts, articles and comments in different venues on various industry trends, perspectives and related themes about clouds, virtualization, data and storage infrastructure topics among related themes.

Storage I/O posts

Recent industry trends, perspectives and commentary by StorageIO Greg Schulz in various venues:

NetworkComputing: Comments on Software-Defined Storage Startups Win Funding

Digistor: Comments on SSD and flash storage
InfoStor: Comments on data backup and virtualization software

ITbusinessEdge: Comments on flash SSD and hybrid storage environments

NetworkComputing: Comments on Hybrid Storage Startup Nimble Storage Files For IPO

InfoStor: Comments on EMC’s Light to Speed: Flash, VNX, and Software-Defined

InfoStor: Data Backup Virtualization Software: Four Solutions

ODSI: Q&A With Greg Schulz – A Quick Roundup of Data Storage Industry

Recent StorageIO Tips and Articles in various venues:

FedTechMagazine: 3 Tips for Maximizing Tiered Hypervisors
InfoStor:
RAID Remains Relevant, Really!

Storage I/O trends

Recent StorageIO blog post:

EMC announces XtremIO General Availability (Part I) – Announcement analysis of the all flash SSD storage system
Part II: EMC announces XtremIO General Availability, speeds and feeds – Part two of two part series with analysis
What does gaining industry traction or adoption mean too you? – There is a difference between buzz and deployment
Fall 2013 (September and October) StorageIO Update Newsletter – In case you missed the fall edition, here it is

StorageIO Industry Trends and Perspectives

Check out our objectstoragecenter.com page where you will find a growing collection of information and links on cloud and object storage themes, technologies and trends.

Server and StorageIO seminars, conferences, web cats, events, activities StorageIO activities (out and about)

Seminars, symposium, conferences, webinars
Live in person and recorded recent and upcoming events

While 2013 is winding down, the StorageIO calendar continues to evolve, here are some recent and upcoming activities.

December 11, 2013 Backup.UData Protection for Cloud 201Backup.U
Google+ hangout
December 3, 2013 Backup.UData Protection for Cloud 101Backup.U
Online Webinar
November 19, 2013 Backup.UData Protection for Virtualization 201Backup.U
Google+ hangout
November 12-13, 2013AWS re:InventAWS re:Invent eventLas Vegas, NV
November 5, 2013 Backup.UData Protection for Virtualization 101Backup.U
Online Webinar
October 22, 2013 Backup.UData Protection for Applications 201Backup.U
Google+ hangout

Click here to view other upcoming along with earlier event activities. Watch for more 2013 events to be added soon to the StorageIO events calendar page. Topics include data protection modernization (backup/restore, HA, BC, DR, archive), data footprint reduction (archive, compression, dedupe), storage optimization, SSD, object storage, server and storage virtualization, big data, little data, cloud and object storage, performance and management trends among others.

Vendors, VAR’s and event organizers, give us a call or send an email to discuss having us involved in your upcoming pod cast, web cast, virtual seminar, conference or other events.

If you missed the Fall (September and October) 2013 StorageIO update newsletter, click here to view that and other previous editions as HTML or PDF versions. Subscribe to this newsletter (and pass it along)

and click here to subscribe to this news letter. View archives of past StorageIO update news letters as well as download PDF versions at: www.storageio.com/newsletter

Ok, nuff said (for now).
Cheers Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved    

Posted on

Part II: EMC announces XtremIO General Availability, speeds and feeds

Storage I/O trends

XtremIO flash SSD more than storage I/O speed

Following up part I of this two-part series, here are more more details, insights and perspectives about EMC XtremIO and it’s generally availability that were announced today.

XtremIO the basics

  • All flash Solid State Device (SSD) based solution
  • Cluster of up to four X-Brick nodes today
  • X-Bricks available in 10TB increments today, 20TB in January 2014
  • 25 eMLC SSD drives per X-Brick with redundant dual processor controllers
  • Provides server-side iSCSI and Fibre Channel block attachment
  • Integrated data footprint reduction (DFR) including global dedupe and thin provisioning
  • Designed for extending duty cycle, minimizing wear of SSD
  • Removes need for dedicated hot spare drives
  • Capable of sustained performance and availability with multiple drive failure
  • Only unique data blocks are saved, others tracked via in-memory meta data pointers
  • Reduces overhead of data protection vs. traditional small RAID 5 or RAID 6 configurations
  • Eliminates overhead of back-end functions performance impact on applications
  • Deterministic  storage I/O performance (IOPs, latency, bandwidth) over life of system

When would you use XtremIO vs. another storage system?

If you need all enterprise like data services including thin provisioning, dedupe, resiliency with deterministic performance on an all-flash system with raw capacity from 10-40TB (today) then XtremIO could be a good fit. On the other hand, if you need a mix of SSD based storage I/O performance (IOPS, latency or bandwidth) along with some HDD based space capacity, then a hybrid or traditional storage system could be the solution. Then there are hybrid scenarios where a hybrid storage system, array or appliance (mix of SSD and HDD) are used for most of the applications and data, with an XtremIO handling more tasks that are demanding.

How does XtremIO compare to others?

EMC with XtremIO is taking a different approach than some of their competitors whose model is to compare their faster flash-based solutions vs. traditional mid-market and enterprise arrays, appliances or storage systems on a storage I/O IOP performance basis. With XtremIO there is improved performance measured in IOPs or database transactions among other metrics that matter. However there is also an emphasis on consistent, predictable, quality of service (QoS) or what is known as deterministic storage I/O performance basis. This means both higher IOPs with lower latency while doing normal workload along with background data services (snapshots, data footprint reduction, etc).

Some of the competitors focus on how many IOPs or work they can do, however without context or showing impact to applications when back-ground tasks or other data services are in use. Other differences include how cluster nodes are interconnected (for scale out solutions) such as use of Ethernet and IP-based networks vs dedicated InfiniBand or PCIe fabrics. Host server attachment will also differ as some are only iSCSI or Fibre Channel block, or NAS file, or give a mix of different protocols and interfaces.

An industry trend however is to expand beyond the flash SSD need for speed focus by adding context along with QoS, deterministic behavior and addition of data services including snapshots, local and remote replication, multi-tenancy, metering and metrics, security among other items.

Storage I/O trends

Who or what are XtremIO competition?

To some degree vendors who only have PCIe flash SSD cards might place themselves as the alternative to all SSD or hybrid mixed SSD and HDD based solutions. FusionIO used to take that approach until they acquired NexGen (a storage system) and now have taken a broader more solution balanced approach of use the applicable tool for the task or application at hand.

Other competitors include the all SSD based storage arrays, systems or appliance vendors which includes legacy existing as well as startups vendors that include among others IBM who bought TMS (flashsystems), NetApp (EF540), Solidfire, Pure, Violin (who did a recent IPO) and Whiptail (bought by Cisco).  Then there are the hybrid which is a long list including Cloudbyte (software), Dell, EMCs other products, HDS, HP, IBM, NetApp, Nexenta (Software), Nimble, Nutanix, Oracle, Simplivity and Tintri among others.

What’s new with this XtremIO announcement

10TB X-Bricks enable 10 to 40TB (physical space capacity) per cluster (available on 11/19/13). 20TB X-Bricks (larger capacity drives) will double the space capacity in January 2014. If you are doing the math, that means either a single brick (dual controller) system, or up to four bricks (nodes, each with dual controllers) configurations. Common across all system configurations are data features such as thin provisioning, inline data footprint reduction (e.g. dedupe) and XtremIO Data Protection (XDP).

What does XtremIO look like?

XtremIO consists of up to four nodes (today) based on what EMC calls X-Bricks.
EMC XtremIO X-Brick
25 SSD drive X-Brick

Each 4U X-Brick has 25 eMLC SSD drives in a standard EMC 2U DAE (disk enclosure) like those used with the VNX and VMAX for SSD and Hard Disk Drives (HDD). In addition to the 2U drive shelve, there are a pair of 1U storage processors (e.g. controllers) that give redundancy and shared access to the storage shelve.

XtremIO Architecture
XtremIO X-Brick block diagram

XtremIO storage processors (controllers) and drive shelve block diagram. Each X-Brick and their storage processors or controllers communicate with each other and other X-Bricks via a dedicated InfiniBand using Remote Direct Memory Access (RDMA) fabric for memory to memory data transfers. The controllers or storage processors (two per X-Brick) each have dual processors with eight cores for compute, along with 256GB of DRAM memory. Part of each controllers DRAM memory is set aside as a mirror its partner or peer and vise versa with access being over the InfiniBand fabric.

XtremIO fabric
XtremIO X-Brick four node fabric cluster or instance

How XtremIO works

Servers access XtremIO X-Bricks using iSCSI and Fibre Channel for block access. A responding X-Brick node handles the storage I/O request and in the case of a write updates other nodes. In the case of a write, the handling node or controller (aka storage processor) checks its meta data map in memory to see if the data is new and unique. If so, the data gets saved to SSD along with meta data information updated across all nodes. Note that data gets ingested and chunked or sharded into 4KB blocks. So for example if a 32KB storage I/O request from the server arrives, that is broken (e.g. chunk or shard) into 8 4KB pieces each with a mathematical unique fingerprint created. This fingerprint is compared to what is known in the in memory meta data tables (this is a hexadecimal number compare so a quick operation). Based on the comparisons if unique the data is saved and pointers created, if already exists, then pointers are updated.

In addition to determining if unique data, the fingerprint is also used for generate a balanced data dispersal plan across the nodes and SSD devices. Thus there is the benefit of reducing duplicate data during ingestion, while also reducing back-end IOs within the XtremIO storage system. Another byproduct is the reduction in time spent on garbage collection or other background tasks commonly associated with SSD and other storage systems.

Meta data is kept in memory with a persistent copied written to reserved area on the flash SSD drives (think of as a vault area) to support and keep system state and consistency. In between data consistency points the meta data is kept in a log journal like how a database handles log writes. What’s different from a typical database is that XtremIO XIOS platform software does these consistency point writes for persistence on a granularity of seconds vs. hours or minutes.

Storage I/O trends

What about rumor that XtremIO can only do 4KB IOPs?

Does this mean that the smallest storage I/O or IOP that XtremIO can do is 4GB?

That is a rumor or some fud I have heard floated by a competitor (or two or three) that assumes if only 4KB internal chunk or shard being used for processing, that must mean no IOPs smaller than 4KB from a server.

XtremIO can do storage I/O IOP sizes of 512 bytes (e.g. the standard block size) as do other systems. Note that the standard server storage I/O block or IO size is 512 bytes or multiples of that unless the new 4KB advanced format (AF) block size being used which based on my conversations with EMC, AF is not supported, yet. (Updated 11/15/13 EMC has indicated that host (front-end) 4K AF support, along with 512 byte emulation modes are available now with XIOS). Also keep in mind that since XtremIO XIOS internally is working with 4KB chunks or shards, that is a stepping stone for being able to eventually leverage back-end AF drive support in the future should EMC decide to do so (Updated 11/15/13 Waiting for confirmation from EMC about if back-end AF support is now enabled or not, will give more clarity as it is recieved).

What else is EMC doing with XtremIO?

  • VCE Vblock XtremIO systems for SAP HANA (and other databases) in memory databases along with VDI optimized solutions.
  • VPLEX and XtremIO for extended distance local, metro and wide area HA, BC and DR.
  • EMC PowerPath XtremIO storage I/O path optimization and resiliency.
  • Secure Remote Support (aka phone home) and auto support integration.

Boosting your available software license minutes (ASLM) with SSD

Another use of SSD has been in the past the opportunity to make better use of servers stretching their usefulness or delaying purchase of new ones by improving their effective use to do more work. In the past this technique of using SSDs to delay a server or CPU upgrade was used when systems when hardware was more expensive, or during the dot com bubble to fill surge demand gaps.  This has the added benefit of stretching database and other expensive software licenses to go further or do more work. The less time servers spend waiting for IOP’s means more time for doing useful work and bringing value of the software license. Otoh, the more time spent waiting is lot available software minutes which is cost overhead.

Think of available software licence minutes (ASLM) in terms of available software license minutes where if doing useful work your software is providing value. On the other hand if those minutes are not used for useful work (e.g. spent waiting or lost due to CPU or server or IO wait, then they are lost). This is like airlines and available seat miles (ASM) metric where if left empty it’s a lost opportunity, however if used, then value, not to mention if yield management applied to price that seat differently. To make up for that loss many organizations have to add extra servers and thus more software licensing costs.

Storage I/O trends

Can we get a side of context with them metrics?

EMC along with some other vendors are starting to give more context with their storage I/O performance metrics that matter than simple IOP’s or Hero Marketing Metrics. However context extends beyond performance to also availability and space capacity which means data protection overhead. As an example, EMC claims 25% for RAID 5 and 20% for RAID 6 or 30% for RAID 5/RAID 6 combo where a 25 drive (SSD) XDP has a 8% overhead. However this assumes a 4+1 (5 drive) RAID , not apples to apples comparison on a space overhead basis. For example a 25 drive RAID 5 (24+1) would have around an 4% parity protection space overhead or a RAID 6 (23+2) about 8%.

Granted while the space protection overhead might be more apples to apples with the earlier examples to XDP, there are other differences. For example solutions such as XDP can be more tolerant to multiple drive failures with faster rebuilds than some of the standard or basic RAID implementations. Thus more context and clarity would be helpful.

StorageIO would like see vendors including EMC along with startups who give data protection space overhead comparisons without context to do so (and applaud those who provide context). This means providing the context for data protection space overhead comparisons similar to performance metrics that matter. For example simply state with an asterisk or footnote comparing a 4+1 RAID 5 vs. a 25 drive erasure or forward error correction or dispersal or XDP or wide stripe RAID for that matter (e.g. can we get a side of context). Note this is in no way unique to EMC and in fact quite common with many of the smaller startups as well as established vendors.

General comments

My laundry list of items which for now would be nice to have’s, however for you might be need to have would include native replication (today leverages Recover Point), Advanced Format (4KB) support for servers (Updated 11/15/13 Per above, EMC has confirmed that host/server-side (front-end) AF along with 512 byte emulation modes exist today), as well as SSD based drives, DIF (Data Integrity Feature), and Microsoft ODX among others. While 12Gb SAS server to X-Brick attachment for small in the cabinet connectivity might be nice for some, more practical on a go forward basis would be 40GbE support.

Now let us see what EMC does with XtremIO and how it competes in the market. One indicator to watch in the industry and market of the impact or presence of EMC XtremIO is the amount of fud and mud that will be tossed around. Perhaps time to make a big bowl of popcorn, sit back and enjoy the show…

Ok, nuff said (for now).

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved