Ceph Day Amsterdam 2012 (Object and cloud storage)

StorageIO industry trends cloud, virtualization and big data

Recently while I was in Europe presenting some sessions at conferences and doing some seminars, I was invited by Ed Saipetch (@edsai) of Inktank.com to attend the first Ceph Day in Amsterdam.

Ceph day image

As luck or fate would turn out, I was in Nijkerk which is about an hour train ride from Amsterdam central station plus a free day in my schedule. After a morning train ride and nice walk from Amsterdam Central I arrived at the Tobacco Theatre (a former tobacco trading venue) where Ceph Day was underway, and in time for lunch of Krokettens sandwich.

Attendees at Ceph Day

Lets take a quick step back and address for those not familiar what is Ceph (Cephalanthera) and why it was worth spending a day to attend this event. Ceph is an open source distributed object scale out (e.g. cluster or grid) software platform running on industry standard hardware.

Dell server supporting ceph demoSketch of ceph demo configuration

Ceph is used for deploying object storage, cloud storage and managed services, general purpose storage for research, commercial, scientific, high performance computing (HPC) or high productivity computing (commercial) along with backup or data protection and archiving destinations. Other software similar in functionality or capabilities to Ceph include OpenStack Swift, Basho Riak CS, Cleversafe, Scality and Caringo among others. There are also the tin wrapped software (e.g. appliances or pre-packaged) solutions such as Dell DX (Caringo), DataDirect Networks (DDN) WOS, EMC ATMOS and Centera, Amplidata and HDS HCP among others. From a service standpoint, these solutions can be used to build services similar Amazon S3 and Glacier, Rackspace Cloud files and Cloud Block, DreamHost DreamObject and HP Cloud storage among others.

Ceph cloud and object storage architecture image

At the heart of Ceph is RADOS a distributed object store that consists of peer nodes functioning as object storage devices (OSD). Data can be accessed via REST (Amazon S3 like) APIs, Libraries, CEPHFS and gateway with information being spread across nodes and OSDs using a CRUSH based algorithm (note Sage Weil is one of the authors of CRUSH: Controlled, Scalable, Decentralized Placement of Replicated Data). Ceph is scalable in terms of performance, availability and capacity by adding extra nodes with hard disk drives (HDD) or solid state devices (SSDs). One of the presentations pertained to DreamHost that was an early adopter of Ceph to make their DreamObjects (cloud storage) offering.

Ceph cloud and object storage deployment image

In addition to storage nodes, there are also an odd number of monitor nodes to coordinate and manage the Ceph cluster along with optional gateways for file access. In the above figure (via DreamHost), load balancers sit in front of gateways that interact with the storage nodes. The storage node in this example is a physical server with 12 x 3TB HDDs each configured as a OSD.

Ceph dreamhost dreamobject cloud and object storage configuration image

In the DreamHost example above, there are 90 storage nodes plus 3 management nodes, the total raw storage capacity (no RAID) is about 3PB (12 x 3TB = 36TB x 90 = 3.24PB). Instead of using RAID or mirroring, each objects data is replicated or copied to three (e.g. N=3) different OSDs (on separate nodes), where N is adjustable for a given level of data protection, for a usable storage capacity of about 1PB.

Note that for more usable capacity and lower availability, N could be set lower, or a larger value of N would give more durability or data protection at higher storage capacity overhead cost. In addition to using JBOD configurations with replication, Ceph can also be configured with a combination of RAID and replication providing more flexibility for larger environments to balance performance, availability, capacity and economics.

Ceph dreamhost and dreamobject cloud and object storage deployment image

One of the benefits of Ceph is the flexibility to configure it how you want or need for different applications. This can be in a cost-effective hardware light configuration using JBOD or internal HDDs in small form factor generally available servers, or high density servers and storage enclosures with optional RAID adapters along with SSD. This flexibility is different from some cloud and object storage systems or software tools which take a stance of not using or avoiding RAID vs. providing options and flexibility to configure and use the technology how you see fit.

Here are some links to presentations from Ceph Day:
Introduction and Welcome by Wido den Hollander
Ceph: A Unified Distributed Storage System by Sage Weil
Ceph in the Cloud by Wido den Hollander
DreamObjects: Cloud Object Storage with Ceph by Ross Turk
Cluster Design and Deployment by Greg Farnum
Notes on Librados by Sage Weil

Presentations during ceph day

While at Ceph day, I was able to spend a few minutes with Sage Weil Ceph creator and founder of inktank.com to record a pod cast (listen here) about what Ceph is, where and when to use it, along with other related topics. Also while at the event I had a chance to sit down with Curtis (aka Mr. Backup) Preston where we did a simulcast video and pod cast. The simulcast involved Curtis recording this video with me as a guest discussing Ceph, cloud and object storage, backup, data protection and related themes while I recorded this pod cast.

One of the interesting things I heard, or actually did not hear while at the Ceph Day event that I tend to hear at related conferences such as SNW is a focus on where and how to use, configure and deploy Ceph along with various configuration options, replication or copy modes as opposed to going off on erasure codes or other tangents. In other words, instead of focusing on the data protection protocol and algorithms, or what is wrong with the competition or other architectures, the Ceph Day focused was removing cloud and object storage objections and enablement.

Where do you get Ceph? You can get it here, as well as via 42on.com and inktank.com.

Thanks again to Sage Weil for taking time out of his busy schedule to record a pod cast talking about Ceph, as well 42on.com and inktank for hosting, and the invitation to attend the first Ceph Day in Amsterdam.

View of downtown Amsterdam on way to train station to return to Nijkerk
Returning to Amsterdam central station after Ceph Day

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

HDS buys BlueArc, any surprises here?

Technically here in the northern hemisphere it is still summer, so there is another summer wedding to announce.

The other day Hitachi Data Systems (aka HDS) announced that they finally tied the knot buying their Network Attached Storage (NAS) partner BlueArc whom they have been in a OEM premarital arrangement for the last five years or so (wow, was that a long engagement or what?). HDS being a subsidiary of Hitachi Ltd. a Japanese company it should be no surprise that they operate in a cool, calculated conservative manner with products that have over the past several decades been known for delivering resiliency, functionality, performance and value.

To those in the IT and specifically data storage industry, the only surprise about HDS buying BlueArc should be what took them so long to do so myself included. With unstructured data, big data, high performance computing, high productivity computing (aka HPC), and big bandwidth needs expanding, it only makes sense that HDS finally ties the knot formally acquiring BlueArc signaling what I hope are a few things for their collective future together.

Things that I hope HDS can accomplish with their acquisition of BlueArc include among others:

  • Leverage the BlueArc hardware and performance combine with the HDS software suite to expand further upstream (and downstream) as well as into different adjacent markets leveraging their success over the long courtship where both parties got to know each other more.
  • Signal to the industry that they are truly committed to a long term NAS product solution strategy. HDS has been doing a good job of sticking with BlueArc for the past five or so years having had several previous NAS partner relationships including with NetApp, NSS and others besides their own internal projects.
  • Expand their focus to lead with NAS pulling storage with it in addition to using NAS to accessorize (or bling aka Mr. T starter kit to go with Mr. T storage videos) storage systems which means of course, going more direct toe to toe with the likes of former partner NetApp, EMC, HP (with IBRIX), IBM and Dell among many others. Ironically former HDS partner NetApp acquired the Engenio storage group from LSI whose products competed with HDS in some spaces, while BlueArc was a Engenio partner.
  • Continue to develop both the hardware and software feature functionality around the BlueArc products in addition to further integration across the joint product lines for both traditional, as well as clustered, scale out, bulk, big data, big bandwidth and HPC environments.
  • Sharpen their NAS message and solution offerings including providing the support, tools and programs to enable both their joint direct sales forces as well as their partner value added reseller (VAR) and channel networks.

Check out (here) some additional comments and perspectives by Ray Lucchesi (aka twitter @raylucchesi) over on his blog pertaining to HDS buying BlueArc.

Congratulations to both HDS and BlueArc along with best wishes, this is a deal that is good for both, now, or once the honeymoon is over, lets see how this is executed upon building on their prior joint success to expand into new market opportunities on a global basis. HDS has tools and people to move into and leverage these new as well as existing opportunities, lets see how they can execute on those hopefully not spending too much time or money on the honeymoon while their competitors are out being busy in some of those same accounts in this last month of an important sales quarter (all quarters are important when it comes to sales).

Disclosure for those interested and FWIW: BlueArc had been a client of StorageIO a few years ago, however not currently. HDS is not nor have they been a client of StorageIO, however in prior life I was a customer of theirs in addition to being a partner and supplier when I was on the vendor side of the table.

 

Ok, nuff said for now.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2011 StorageIO and UnlimitedIO All Rights Reserved

Getting SASy, the other shared storage option for disk and SSD systems

Here is a link to a recent guest post that I was invited to do over at The Virtualization Practice (TVP) pertaining to Getting SASsy, the other shared server to storage interconnect for disk and SSD systems. Serial Attached SCSI (SAS) is better known as an interface for connecting hard disk drives (HDD) to servers and storage systems; however it is also widely used for attaching storage systems to physical as well as virtual servers. An important storage requirement for virtual machine (VM) environments with more than one physical machine (PM) server is shared storage. SAS has become a viable interconnect along with other Storage Area Network (SAN) interfaces including Fibre Channel (FC), Fibre Channel over Ethernet (FCoE) and iSCSI for block access.

Read more here.

Ok, nuff said for now.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2011 StorageIO and UnlimitedIO All Rights Reserved

Virtual Storage and Social Media: What did EMC not Announce?

Synopsis: EMC made a vision statement in a recent multimedia briefing that has a social networking angle as well as storage virtualization, virtual storage, public and private clouds.

Basically EMC provided a vision preview of in a social media networking friendly manner of a vision being refereed to initially as EMC Virtual Storage (aka twitter hash tag #emcvs) which of course sounds similar to a pharmacy chain.

The vision includes stirring up the industry with a new discussion around virtual storage compared to the decade old coverage of storage virtualization.

The underlying theme of this vision is similar to that of virtual serves vs. server virtualization including the ability to move servers around, so to should there be the ability to move data around more freely on a local or global basis and in real or near real time. In other words, breaking the decades long affinity that has existed between data storage and the data that exists on it (Figure 1). Buzzword bingo themes include federated storage, virtual storage, public and private cloud along with global cache coherency among others.


Figure 1: EMC Virtual Storage (EMCVS) Vision

The rest of the story

On Thursday March 11th 2010 Pat Gelsinger (EMC President and COO, Information Infrastructure Products) held an interactive briefing with the global analyst community pertaining to future EMC trajectory or visions. One of the interesting things about this session was that it was not unique to industry analysts nor was it under NDA.

For example, here is a link that if still active, should provide access to the briefing material.

The vision being talked about include those that EMC has talked about in the past such as virtualized data centers, or, putting a spin on the phrase data center virtualization, along with public and private clouds as well as  infrastructure  resource management virtualization (Figure 2):


Figure 2: Public and Private Clouds along with Virtual Data Centers

Figure 2 is a fairly common slide used in many EMC discussions positing public and private clouds along with virtualized data centers.


Figure 3: Tenants of the EMC Virtual Storage (EMCVS) vision


Figure 4: Enabling mobile data, breaking data and storage affinity


Figure 5: Enabling teleporting and virtual storage

Thus setting up the story for the need and benefit of distributed cache coherency, similar to distributed lock management (DLM) used on local and wide area clustered file systems for maintain data integrity.


Figure 6: Leveraging distributed cache coherency

This discussion around distributed cache coherency should ring Dejavu of IBM GDPS (Global Dispersed Parallel Sysplex) for Mainframe, OpenVMS distributed lock management for VAX and Alpha clusters, Oracle RAC, or other parallel and clustered file systems among others. Likewise for those familiar with technology from Yotta Yotta, this should also ring familiar.

However while many are jumping on the Yotta Yotta familiarity bandwagon given comments made by Pat Gelsinger, something that came to mind is what about EMC GDDR? Do not worry if that is an acronym or product you are not up on as an EMC follower as it stands for EMC Geographically Dispersed Disaster (GDDR) solution that is an alternative to IBMs proprietary GDPS. Perhaps there is none, perhaps this is some, however what role if any including lessons learned will come from EMCs experience with GDDR not to mention other clustered file systems?


Figure 7: The EMC vision as presented

One of the interesting things about the vision announcement and perhaps part of floating it out for discussion was a comment made by Pat Gelsinger. That comment was about enabling the wild Wild West for IT, something that perhaps one generation might enjoy, however a notion another would soon forget. Im sure the EMC marke3ting team including their new chief marketing officer (CMO) Jeremy Burton can fine tune with time.
 

More on the social networking and non NDA angle

As is often the case with many other vendors, these types of customer, partner, analyst or media briefings (either online or in person) are under some form of NDA or embargo as they contain forward looking, yet to be announced products, solutions, technologies or other business initiatives. Note, these types of NDA discussions are not typically the same as those that portray or pretend to be NDA in order to sound more important a few days before an announcement that has already been leaked to get extra coverage or what are also known as media embargos.

After some amount of time, usually the information is formerly made public that was covered in advanced briefings, along with additional details. Sometimes material covered under NDA is done so in advanced such that third parties can prepare reports, deep dive analysis or assessment and other content that is made available at announcement or shortly there. The material is often prepared partners, vars, media, analysts, consultants, customers or others outside of the announcing company via different venues ranging from print, online columns, blogs, tweets videos and more.

Lately there has been some confusion in the broader IT as well as other industries as to where and how to classify bloggers, tweeters or other social media practionier. After all, is a blogger an analyst, journalist, free lance writer, advisor, vendor, consultant, customer, var, investor, hobbyist, competitor not to mention how does information get feed to them?

Likewise, NDAs and embargo have joined the list of fodder topics that some do not like for various reasons yet like to complain about for others. There is a time and place for real NDAs that cover and address material, discussions and other information that should not be shared. However all to often NDAs get watered down particularly on the press release games where a vendor or public relations firm (PR) will dangle an announcement briefing a couple of days or perhaps a week or two prior to an announcement under the guise that it not be disclosed prior to formal announcement.

Where these NDAs get tricky is that often they are honored by some and ignored by others, thus, those who honor the agreement get left behind by those who break the story. Personally I do not mind real NDA that are tied to real confidential material, discussion or other information that needs to be kept under wraps for various reasons. However the value or issues of NDA is whole different discussion, for now, lets get back to what EMC did not announce in their recent non-NDA briefing.

Different organizations are addressing social media in various ways, some ignoring it, others embracing it regardless of what it is. EMC is an example of a vendor who has embraced social networking and social media along with traditional means of developing and maintaining relations with the media (media or press relations), customers, partners, vars, consultants, investors (e.g. investor relations) as well as analysts (analyst relations).

For example, EMC works with analysts in traditional ways as they do with the media and other groups, however they also recognize that while some analysts (or media or investors or partners or customers or vars etc) blog and tweet (among other social networking mediums), not all do (as is also the case with media, customers, vars and so forth). Likewise EMC from a social media and networking perspective does not appear to define audiences based on the medium or tool that they use, rather, in a matrix or multi dimensional approach.

That is, an analyst with a blog is a blogger, a var or independent consultant with a blog is a blogger, or a media person including free lance writers, journalist, reporters or publisher with a blog is a blogger as are vars, advisors, partners and competitors with blogs also treated as bloggers.



Some of the 2009 EMC Bloggers Lounge Visitors

Thus at their EMCworld event, admission to the bloggers lounge is as simple and non exclusive as having a blog to join regardless of what your role or usage of a blog happens to be. On the other hand, information is communicated via different channels such as for traditional press via public relations folks, investors through investors relations, analysts via analyst relations, partners and customers through their venues and so forth.

When you think about it, makes sense as after all, EMC sells and attaches storage to mainframes, open systems Windows, UNIX, Linux as well as virtual servers that use different tools, protocols, languages and points of interest. Thus it should not be surprising that their approach to communicating with different audiences leverage various mediums for diverse messages at multiple points in time.

 

What does all of this social media discussion have to do with the March 11 EMC event?

In my opinion, this was an experiment of sorts of EMC to test the waters by floating a new vision to their traditional  pre brief audience in advance of talking with media prior to an actual announcement.

That is, EMC did not announce a new product, technology, initiative, business alliance or customer event, rather a vision and trajectory or signaling what they may be doing in the future.

How this ties to social media and networking is that rather than being an event only for those media, bloggers, tweeters, customers, consultants, vars, free lancers, partners or others who agreed to do so under NDA, EMC used the venue as an advance sounding board of sorts.

That is, by sticking to broad vision vs. propriety and confidential or sensitive topics, the discussion has been put out in advance in the open to stimulate discussion in traditional reports, articles, columns or related venues not to mention in temporal real time via twitter not to mention via blogs and beyond.

Does this mean EMC will be moving away from NDAs anytime soon? I do not think so as there is still very much a need for advanced (and not a couple of weeks prior to announcement) types of discussion around sensitive information. For example with the trajectory or visionary discussion last week by EMC, the short presentation and discussion, limited slides prompt more questions than they address.

Perhaps what we are seeing is a new approach or technique of how organizations can use and bring social networking mediums into the mainstream business process as opposed to being perceived as niche or experimental mediums.

The reason I think it was an experiment is that EMC practices both traditional analyst/media relations along with emerging social media networking relations that includes practioners that span both audiences. For some the social media bloggers and tweeters are a different audience than traditional media, writers, consultants or analysts, that is, they are a separate and unique audience.

Thus, it is in my opinion and like human knees, elbows, feet, hands, ears as well as, well, you get the picture I think that there are many different views or thoughts not to mention interpretations of social media, social networking, blogging, analysts, consultants, advisors, media or press, customers, partners, and so on with diverse roles, functions and needs.

Where this comes back to the topic of last weeks discussion is that of storage virtualization vs. virtual storage. Rest assured in the time since the EMC briefing and certainly in the weeks or months to come, there will be penalty of knees, elbows, hands and other body parts flying and signaling what is a particular view or definition of storage virtualization vs. virtual storage.

Of course, some of these will be more entertaining than others ranging from well rehearsed, in some cases over the past decade or more to new and perhaps even revolutionary ones of what is and what is not storage virtualization vs. virtual storage, let alone cloud vs. cluster vs. grid vs. federated and beyond.

 

Additional Comments and thoughts

In general, I like the trajectory vision EMC is rolling out even if it causes confusion between what is virtual storage vs. storage virtualization, after all, we have been hearing about storage virtualization for over a decade now if not longer. Likewise, there has been plenty of talk about public clouds so it is refreshing to see more discussion and less cloud ware or cloud marketecture and how to actually leverage what you have to adopt private cloud practices.

I suspect that as the EMC competition starts to hear or piece together what they think this vision is or is not, we should also start to hear some interesting stories, spins, counter pitches, debates, twitter fights, blog slams and YouTube videos, all of which also happen to consume more storage.

I also like what EMC is doing with social media and networking as a means or medium for building and maintain relationships as well as for information exchange complimenting traditional means and mediums.  

In other words, EMC is succeeding with social networking by not using it just as another megaphone to talk at or over people, rather, as a means to engage, to get to know, to challenge, to exchange regardless of if you are a so called independent blogger, twitter, analyst, medial, constant, customer, var, investor, partner among others.

If you are not already doing so, here are some EMC folks who actively participate in two way dialogues across different areas with @lendevanna helping to facilitate and leverage the masses of various people and subject matter experts including @chuckhollis @c_weil @cxi @davegraham @gminks @mike_fishman @stevetodd @storageanarchy @storagezilla @Stu and @vcto among many others.

Note that for you non twitter types, the previous are twitter handles (names or addresses) that can be accessed by putting https://twitter.com in place of the @ sign. For example @storageio = https://twitter.com/storageio

 

Additional Comments and thoughts:

Some comments and thoughts among others that I posted via twitter last week during the briefing event:

Here are some twitter comments that I posted last week during the event with hash tag #emcvs:

Is what was presented on the #emcvs #it #storage #virtualization call NDA material = Negative
Is what was presented on the #emcvs #it #storage #virtualization call a product announcement = NOpe
Is what was presented on the #emcvs #it #storage #virtualization call a statement of direction = Kind of
Is what was presented on the #emcvs #it #storage #virtualization call a hint of future functionality = probably
Is what was presented on the #emcvs #it #storage #virtualization call going to be shared with general public = R U reading this?
Is what was presented on the #emcvs #it #storage #virtualization call going to be discussed further = Yup
Is what was presented on the #emcvs #it #storage #virtualization call going to confuse the industry = Maybe
Is what was presented on the #emcvs #it #storage #virtualization call going to confuse customers = Depends on story teller
Is what was presented on the #emcvs #it #storage #virtualization call going to confuse competition = probably
Is what was presented on the #emcvs #it #storage #virtualization call going to provide fodder/fuel for bloggers = Yup
Anything else to add about #emcvs #it #storage #virtualization call today = Stay tuned, watch and listen for more!

Some additional questions and my perspectives on those include:

  • What did EMC announce? Nothing, it was not an announcement; it was a statement of vision.
  • Why did EMC hold a briefing without an NDA and yet nothing was announced? It is my opinion that EMC has a vision that they want to float an idea or direction, thus, sharing a vision to get discussions going without actually announcing a specific product or technology.
  • Is this going to be a repackaged version of the Invista storage virtualization platform? I do not believe so.
  • Is this going to be a repackaged version of the intellectual property (IP) assets that EMC picked up from the defunct startup called Yotta Yotta? Given some references to, along with what some of the themes and discussions center around, it is my guess that there is some Yotta Yotta IP along with other technologies that may be part of any future possible solution.
  • Who or what is YottaYotta? They were a late dot com startup founded in 2000 that went through various incarnations and value propositions with some solutions that shipped. Some of the late era IP included distributed cache coherency and distance enablement of large scale federated storage on a global basis.
  • Can the Yotta Yotta (or here) technology really scale? That remains to be seen, Yotta Yotta had some interesting demos, proof of concept, early adopters and big plans, however they also amounted to Nada Nada, perhaps EMC can make a Lotta Lotta out of it!

 

Other questions are still waiting for answers including among others:

  • Will EMC Virtual Storage (aka emcvs) become a common cure for typical IT infrastructure ailments?
  • Will this restart the debate around the golden rule of virtualization being whoever controls the virtualization controls the gold and thus vendors lock in?
  • Will this be a members only vision where only certain partners can participate?
  • What will other competitors respond with, technology, and marketecture, FUD or something else?
  • What are the specific details of when, where and how the vision is implemented?
  • What will all of this cost, will it work with existing products or is a forklift upgrade needed?
  • Has EMC bitten off more than they can chew or deliver on or is Pat Gelsinger and his crew racing down a mountain and out in front of their skis, or, is this brilliance beyond what we mere mortals can yet comprehend?
  • Can global data cache coherency really be deployed with data integrity on a global and large scale without negatively impacting performance?
  • Can EMC make Lotta Lotta with this vision?

 

Here is what some of the EMC bloggers have had to say so far:

Chuck Hollis aka @chuckhollis had this to say

Stuart Miniman aka @stu had this to say

 

Summing it up for now

Lets see how the rest of the industry responds to this as the vision rolls out and perhaps sooner vs. later becomes technology that gets deployed and used.

Im skeptical until more details are understood, however I also like it and intrigued by it if it can actually jump from Yotta Yotta slide ware to Lotta Lotta deployments.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

Post Holiday IT Shopping Bargains, Dell Buying Exanet?

For consumers, the time leading up to the holiday Christmas season is usually busy including door busters as well as black Friday among other specials for purchasing gifts and other items. However savvy shoppers will wait for after Christmas or the holidays altogether perhaps well into the New Year when some good bargains can become available. IT customers are no different with budgets to use up before the end of the year thus a flurry of acquisitions that should become evident soon as we are entering earnings announcement season.

However there are also bargains for IT organizations looking to take advantage of special vendor promotions trying to stimulate sales, not to mention for IT vendors to do some shopping of their own. Consequently, in addition to the flurry of merger and acquisition (M and A) activity from last summer through the fall, there has been several recent deals, some of which might make Monty Hall blush!

Some recent acquisition activity include among others:

  • Dell bought Perot systems for $3.9B
  • DotHill bought Cloverleaf
  • Texas Memory Systems (TMS) bought Incipient
  • HP bought IBRIX and 3COM among others
  • LSI bought Onstor
  • VMware bought Zimbra
  • Micron bought Numonyx
  • Exar bought Neterion

Now the industry is abuzz about Dell, who is perhaps using some of the lose change left over from holiday sales as being in the process of acquiring Israeli clustered storage startup Exanet for about $12M USD. Compared to previous Dell acquisitions including EqualLogic in 2007 for about $1.4B or last years Perot deal in the $3.9B range, $12M is a bargain and would probably not even put a dent in the selling and marketing advertising budget let alone corporate cash coffers which as of their Q3-F10 balance sheet shows about $12.795B in cash.

Who is Exanet and what is their product solution?
Exanet is a small Israeli startup providing a clustered, scale out NAS file serving storage solution (Figure 1) that began shipping in 2003. The Exanet solution (ExaStore) can be either software based, or, as a package solution ExaStore software installed on standard x86 servers with external RAID storage arrays combining as a clustered NAS file server.

Product features include global name space, distributed metadata, expandable file systems, virtual volumes, quotas, snapshots, file migration, replication, and virus scanning, and load balancing, NFS, CIFS and AFP. Exanet scales up to 1 Exabyte of storage capacity along with supporting large files and billions of file per cluster.

The target market that Exanet pursues is large scale out NAS where performance (either small random or large sequential I/Os) along with capacity are required. Consequently, in the scale out, clustered NAS file serving space, competitors include IPM GPFS (SONAS), HP IBRIX or PolyServe, Sun Lustre and Symantec SFS among others.

Clustered Storage Model: Source The Green and Virtual Data Center (CRC)
Figure 1 Generic clustered storage model (Courtesy The Green and Virtual Data Center(CRC)

For a turnkey solution, Exanet packaged their cluster file system software with various vendors storage combined with 3rd party external Fibre Channel or other storage. This should play well for Dell who can package the Exanet software on its own servers as well as leverage either SAS or Fibre Channel  MD1000/MD3000 external RAID storage among other options (see more below).

Click here to learn more about clustered storage including clustered NAS, clustered and parallel file systems.

Dell

Whats the dell play?

  • Its an opportunity to acquire some intellectual property (IP)
  • Its an opportunity to have IP similar to EMC, HP, IBM, NetApp, Oracle and Symantec among others
  • Its an opportunity to address a market gap or need
  • Its an opportunity to sell more Dell servers, storage and services
  • Its an opportunity time for doing acquisitions (bargain shopping)

Note: IBM also this past week announced their new bundled scale out clustered NAS file serving solution based on GPFS called SONAS. HP has IBRIX in addition to their previous PolyServe acquisition, Sun has ZFS and Lustre.

How does Exanet fit into the Dell lineup?

  • Dell sells Microsoft based NAS as NX series
  • Dell has an OEM relationship with EMC
  • Dell was OEMing or reselling IBRIX in the past for certain applications or environments
  • Dell has needed to expand its NAS story to balance its iSCSI centric storage story as well as compliment its multifunction block storage solutions (e.g. MD3000) and server solutions.

Why Exanet?
Why Exanet, why not one of the other startups or small NAS or cloud file system vendors including BlueArc, Isilon, Panasas, Parascale, Reldata, OpenE or Zetta among others?

My take is that probably because those were either not relevant to what Dell is looking for, lack of seamless technology and business fit, technology tied to non Dell hardware, technology maturity, the investors are still expecting a premium valuation, or, some combination of the preceding.

Additional thoughts on why Exanet
I think that Dell simply saw an opportunity to acquire some intellectual property (IP) probably including a patent or two. The value of the patents could be in the form of current or future product offerings, perhaps a negotiating tool, or if nothing else as marketing tool. As a marketing tool, Dell via their EqualLogic acquisition among others has been able to demonstrate and generate awareness that they actually own some IP vs. OEM or resell those from others. I also think that this is an opportunity to either fill or supplement a solution offering that IBRIX provided to high performance, bulk storage and scale out file serving needs.

NAS and file serving supporting unstructured data are a strong growth market for commercial, high performance, specialized or research as well as small business environments. Thus, where EqualLogic plays to the iSCSI block theme, Dell needs to expand their NAS and file serving solutions to provide product diversity to meet various customer applications needs similar to what they do with block based storage. For example, while iSCSI based EqualLogic PS systems get the bulk of the marketing attention, Dell also has a robust business around the PowerVault MD1000/MD3000 (SAS/iSCSI/FC) and Microsoft multi protocol based PowerVault NX series not to mention their EMC CLARiiON based OEM solutions (E.g. Dell AX, Dell/EMC CX).

Thus, Dell can complement the Microsoft multi protocol (block and NAS file) NX with a packaged (Dell servers and MD (or other affordable block storage) powered with Exanet) solution. While it is possible that Dell will find a way to package Exanet as a NAS gateway in front of the iSCSI based EqualLogic PS systems, which would also make for an expensive scale out NAS solution compared to those from other vendors.

Thats it for now.

Lets see how this all plays out.

Cheers gs

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

Technorati tags: Dell

Does IBM Power7 processor announcement signal storage upgrades?

IBM recently announced the Power7 as the latest generation of processors that the company uses in some of its mid range and high end compute servers including the iSeries and pSeries.


IBM Power7 processor wafers (chips)

 

What is the Power7 processor?
The Power7 is the latest generation of IBM processors (chips) that are used as the CPUs in IBM mid range and high end open systems (pSeries) for Unix (AIX) and Linux as well as for the iSeries (aka AS400 successor). Building on previous Power series processors, the Power7 increases the performance per core (CPU) along with the number of cores per socket (chip) footprint. For example, each Power7 chip that plugs into a socket on a processor card in a server can have up to 8 cores or CPUs. Note that sometimes cores are also known as micro CPUs as well as virtual CPUs not to be confused with their presented via Hypervisor abstraction.

Sometimes you may also here the term or phrase 2 way, 4 way (not to be confused with a Cincinnati style 4 way chili) or 8 way among others that refers to the number of cores on a chip. Hence, a dual 2 way would be a pair of processor chips each with 2 cores while a quad 8 way would be 4 processors chips each with 8 cores and so on.


IBM Power7 with up to eight cores per processor (chip)

In addition to faster and more cores in a denser footprint, there are also energy efficiency enhancements including Energy Star for enterprise servers qualification along with intelligent power management (IPM also see here) implementation. IPM is implanted in what IBM refers to as Intelligent Energy technology for turning on or off various parts of the system along with varying processor clock speeds. The benefit is when there is work to be done, get it down quickly or if there is less work, turn some cores off or slow clock speed down. This is similar to what other industry leaders including Intel have deployed with their Nehalem series of processors that also support IPM.

Additional features of the Power7 include (varies by system solutions):

  • Energy Star for server qualified providing enhanced performance and efficiency.
  • IBM Systems Director Express, Standard and Enterprise Editions for simplified management including virtualization capabilities across pools of Power servers as a single entity.
  • PowerVM (Hypervisor) virtualization for AIX, iSeries and Linux operating systems.
  • ActiveMemory enables effective memory capacity to be larger than physical memory, similar to how virtual memory works within many operating systems. The benefit is to enable a partition to have access to more memory which is important for virtual machines along with the ability to support more partitions in a given physical memory footprint.
  • TurboCore and Intelligent Threads enable workload optimization by selecting the applicable mode for the work to be done. For example, single thread per core along with simultaneous threads (2 or 4) modes per core. The trade off is to have more threads per core for concurrent processing, or, fewer threads to boost single stream performance.

IBM has announced several Power7 enabled or based server system models with various numbers of processors and cores along with standalone and clustered configurations including:

IBM Power7 family of server systems

  • Power 750 Express, 4U server with one to four socket server supporting up to 32 cores (3.0 to 3.5 GHz) and 128 threads (4 threads per core), PowerVM (Hypervisor) along with main memory capacity of 512GB or 1TByte of virtual memory using Active Memory Expansion.
  • Power 755, 32 3.3Ghz Power7 cores (8 cores per processor) with memory up to 256GB along with AltiVec and VSX SIMD instruction set support. Up to 64 755 nodes each with 32 cores can be clustered together for high performance applications.
  • Power 770, Up to 64 Power7 cores providing more performance while consuming less energy per core compared to previous Power6 generations. Support for up to 2TB of main memory or RAM using 32GB DIMM when available later in 2010.
  • Power 780, 64 Power7 cores with TurboCore workload optimization providing performance boost per core. With TurboCore, 64 cores can operate at 3.8 GHz, or, enable up to 32 cores at 4.1 GHz and twice the amount of cache when more speed per thread is needed. Support for up to 2TB of main memory or RAM using 32GB DIMM when available later in 2010.

Additional Power7 specifications and details can be found here.

 

What is the DS8000?
The DS8000 is the latest generation of a family of high end enterprise class storage systems supporting IBM mainframe (zSeries), Open systems along with mixed workloads. Being high end open systems or mainframe, the DS8000 competes with similar systems from EMC (Symmetrix/DMX/VMAX), Fujitsu (Eternus DX8000), HDS (Hitachi) and HP (XP series OEM from Hitachi). Previous generations of the DS8000 (aka predecessors) include the ESS (Enterprise Storage System) Model 2105 (aka Shark) and VSS (Versatile Storage Server). Current generation family members include the Power5 based DS8100 and DS8300 along with the Power6 based DS8700.

IBM DS8000 Storage System

Learn more about the DS8000 here, here, here and here.

 

What is the association between the Power7 and DS8000?
Disclosure: Before I go any further, lets be clear on something, what I am about to post on is based entirely on researching, analyzing, correlating (connecting the dots) of what is publicly and freely available from IBM on the Web (e.g. there is no NDA material being disclosed here that I am aware of) along with prior trends and tendency of IBM and their solutions. In other words, you can call it speculation, a prediction, industry analysis perspective, looking into the proverbial crystal ball or educated guess and thus should not be taken as an indicator of what IBM may actually do or be working on. As to what may actually be done or not done, for that you will need to contact one of the IBM truth squad members.

As to what is the linkage between Power7 and the DS8000?

The linkage between the Power7 and the DS8000 is just that, the Power processors!

At the heart of the DS8000 are Power series processors coupled or clustered together in pairs for performance and availability that run IBM developed storage systems software. While the spin doctors may not agree, essentially the DS8000 and its predecessors are based on and around Power series processors clustered together with a high speed interconnect that combine to host an operating system and IBM developed storage system application software.

Thus IBM has been able to for over a decade leverage technology improvement curve advantages with faster processors, increased memory and I/O connectivity in denser footprints while enhancing their storage system application software.

Given that the current DS8000 family members utilize 2 way (2 core) or 4 way (4 core) Power5 and Power6 processors, similar to how their predecessors utilized previous generation Power4, Power3 and so forth processors, it only makes sense that IBM might possibly use a Power7 processor in a future DS8000 (or derivative perhaps even with a different name or model number). Again, this is just based all on historical trends and patterns of IBM storage systems group leveraging the latest generation of Power processors; after all, they are a large customer of the Power systems group.

Consequently it would make sense for IBM storage folks to leverage the new Power7 processors and features similar to how EMC is leveraging Intel processor enhances along with what other vendors are doing.

There is certainly room in the DS8000 architecture for growth in terms of supporting additional nodes or complexes or controllers (or whatever your term preference of choice is for describing a server) each equipped with multiple processors (chips or sockets) that have multiple cores. While IBM has only commercially released two complex or dual server versions of the DS8000 with various numbers of cores per server, they have come nowhere close to their architecture limit of nodes. In fact with this release of Power7, as an example, the model 755 can be clustered via InfiniBand with up to 64 nodes, with each node having 4 sockets (e.g. 4 way) with up to 8 cores each. That means on paper, 64 x 4 x 8 = 2048 cores and each core could have up to 4 threads for concurrency, or half as many cores for more cache performance. Now will IBM ever come out with a 64 node DS8000 on steroids?

Tough to say, maybe possibly some day to play specmanship vs EMC VMAX 256 node architectural limit, however Im not holding my breath just yet. Thus with more and faster cores per processor, ability to increase number of processors per server or node, along with architectural capabilities to boost the number of nodes in an instance or cluster, on paper alone, there is lots of head room for the DS8000 or a future derivative.

What about software and functionality, sure IBM could in theory simply turn the crank and use a new hardware platform that is faster, more capacity, denser, better energy efficiency, however what about new features?

Can IBM enhance its storage systems application software that it evolved from the ESS with new features to leverage underlying hardware capabilities including TurboCore, PowerVM, device and I/O sharing, Intelligent Energy efficiency along with threads enhancements?

Can IBM leverage those and other features to support not only scaling of performance, availability, capacity and energy efficiency in an economical manner, however also add features for advanced automated tiering or data movement plus other popular industry buzzword functionality?

 

Additional thoughts and perspectives
One of the things I find interesting is that some IBM folks along with their channel partners will go to great lengths to explain why and how the DS8000 is not just a pair of Power enabled based servers tightly coupled together. Yet, on the other hand, some of those folks will go to great lengths touting the advantages of leveraging off the shelf or commercial enabled servers based on Intel or AMD based systems such as IBMs own XIV storage solution.

I can understand in the past when the likes of EMC, Hitachi and Fujitsu were all competing with IBM building bigger and more function rich monolithic systems, however that trend is shifting. The trend now as is being seen with EMC and VMAX is to decouple and leverage more off the shelf commercially available technology combined with custom ASICs where and when needed.

Thus at a time where more attention and discussion is around clustered, grid, scalable storage systems, will we see or hear the IBM folks change their tune about the architectural scale up and out capabilities of the Power enabled DS8000 family?

There had been some industry speculation that the DS8000 would be the end of the line if the Power7 had not been released which will now (assuming that IBM leverages the Power7 for storage) shift to if there will be a Power8 or Power9 and so forth.

From a storage perspective, is the DS8K still relevant?

I say yes given its installed base and need for IBM to have an enterprise solution (sorry, IMHO XIV does not fit that bill just yet) of their own, lest they cut an OEM deal with the likes of Hitachi or Fujitsu which while possible, I do not see it as likely near term. Another soft point on its relevance is to gauge reaction from their competitors including EMC and HDS.

From a server perspective, what is the benefit of the new Power7 enabled servers from IBM?

Simple, increase scale of performance for single thread as well as concurrent or parallel application workloads.

In other words, supporting more web sites, partitions for virtual machines and guest operating system instances, databases, compute and other applications that demand performance and economy of scale.

This also means that IBM has a platform to aggressively go after Sun Solaris server customers with a lifeline during the Oracle transition, not to mention being a platform for running Oracle in addition to its own UDB/DB2 database. In addition to being a platform for Unix AIX as well as Linux, the Power7 series also are at the heart of current generation iSeries (the server formerly known as the AS400).

Additional links and resources:

Closing comments (for now):
Given IBMs history of following a Power chip enhancement with a new upgraded version of the DS8000 (or ESS/2105 aka Shark/VSS) and its predecessors by a reasonable amount of time, I would be surprised if we do not see a new DS8000 (perhaps even renamed or renumbered) within the year.

This is similar to how other vendors leverage new processor chip technology evolution to pace their systems upgrades for example how many vendors who leverage Intel processes have done announcements over the past year since the Nehalem series rolled out including EMC among others.

Lets see what the IBM truth squads have to say, or, not have to say :)

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

StorageIO in the News Update V2010.1

StorageIO is regularly quoted and interviewed in various industry and vertical market venues and publications both on-line and in print on a global basis.

The following are some coverage, perspectives and commentary by StorageIO on IT industry trends including servers, storage, I/O networking, hardware, software, services, virtualization, cloud, cluster, grid, SSD, data protection, Green IT and more since the last update.

Realizing that some prefer blogs to webs to twitter to other venues, here are some recent links among others to media coverage and comments by me on a different topics that are among others found at www.storageio.com/news.html:

  • SearchSMBStorage: Comments on EMC Iomega v.Clone for PC data syncronization – Jan 2010
  • Computerworld: Comments on leveraging cloud or online backup – Jan 2010
  • ChannelProSMB: Comments on NAS vs SAN Storage for SMBs – Dec 2009
  • ChannelProSMB: Comments on Affordable SMB Storage Solutions – Dec 2009
  • SearchStorage: Comments on What to buy a geek for the holidays, 2009 edition – Dec 2009
  • SearchStorage: Comments on EMC VMAX storage and 8GFC enhancements – Dec 2009
  • SearchStorage: Comments on Data Footprint Reduction – Dec 2009
  • SearchStorage: Comments on Building a private storage cloud – Dec 2009
  • SearchStorage: Comments on SSD in storage systems – Dec 2009
  • SearchStorage: Comments on slow adoption of file virtualization – Dec 2009
  • IT World: Comments on maximizing data security investments – Nov 2009
  • SearchCIO: Comments on storage virtualization for your organisation – Nov 2009
  • Processor: Comments on how to win approval for hardware upgrades – Nov 2009
  • Processor: Comments on the Future of Servers – Nov 2009
  • SearchITChannel: Comments on Energy-efficient technology sales depend on pitch – Nov 2009
  • SearchStorage: Comments on how to get from Fibre Channel to FCoE – Nov 2009
  • Minneapolis Star Tribune: Comments on Google Wave and Clouds – Nov 2009
  • SearchStorage: Comments on EMC and Cisco alliance – Nov 2009
  • SearchStorage: Comments on HP virtualizaiton enhancements – Nov 2009
  • SearchStorage: Comments on Apple canceling ZFS project – Oct 2009
  • Processor: Comments on EPA Energy Star for Server and Storage Ratings – Oct 2009
  • IT World Canada: Cloud computing, dot be scared, look before you leap – Oct 2009
  • IT World: Comments on stretching your data protection and security dollar – Oct 2009
  • Enterprise Storage Forum: Comments about Fragmentation and Performance? – Oct 2009
  • SearchStorage: Comments about data migration – Oct 2009
  • SearchStorage: Comments about What’s inside internal storage clouds? – Oct 2009
  • Enterprise Storage Forum: Comments about T-Mobile and Clouds? – Oct 2009
  • Storage Monkeys: Podcast comments about Sun and Oracle- Sep 2009
  • Enterprise Storage Forum: Comments on Maxiscale clustered, cloud NAS – Sep 2009
  • SearchStorage: Comments on Maxiscale clustered NAS for web hosting – Sep 2009
  • Enterprise Storage Forum: Comments on whos hot in data storage industry – Sep 2009
  • SearchSMBStorage: Comments on SMB Fibre Channel switch options – Sep 2009
  • SearchStorage: Comments on using storage more efficiently – Sep 2009
  • SearchStorage: Comments on Data and Storage Tiering including SSD – Sep 2009
  • Enterprise IT Planet: Comments on Data Deduplication – Sep 2009
  • SearchDataCenter: Comments on Tiered Storage – Sep 2009
  • Enterprise Storage Forum: Comments on Sun-Oracle Wedding – Aug 2009
  • Processor.com: Comments on Storage Network Snags – Aug 2009
  • SearchStorageChannel: Comments on I/O virtualizaiton (IOV) – Aug 2009
  • SearchStorage: Comments on Clustered NAS storage and virtualization – Aug 2009
  • SearchITChannel: Comments on Solid-state drive prices still hinder adoption – Aug 2009
  • Check out the Content, Tips, Tools, Videos, Podcasts plus White Papers, and News pages for additional commentary, coverage and related content or events.

    Ok, nuff said.

    Cheers gs

    Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

    twitter @storageio

    All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

    StorageIO in the news

    StorageIO is regularly quoted and interviewed in various industry and vertical market venues and publications both on-line and in print on a global basis. The following is coverage, perspectives and commentary by StorageIO on IT industry trends including servers, storage, I/O networking, hardware, software, services, virtualization, cloud, cluster, grid, SSD, data protection, Green IT and more.

    Realizing that some prefer blogs to webs to twitters to other venues, here are some recent links among others to media coverage and comments by me on a different topics that are among others found at www.storageio.com/news.html:

  • Virtualization Review: Comments on Clouds, Virtualizaiton and Cisco move into servers – July 2009
  • SearchStorage: Comments on Storage Resource Managemet (SRM) and related tools – July 2009
  • SearchStorage: Comments on flash SSD – July 2009
  • SearchDataBackup: Comments on Data backup reporting tools’ trends – July 2009
  • SearchServerVirtualization: Comments on Hyper-V R2 matches VMware with 64-processor support – July 2009
  • SearchStorage: Comments on HP buying IBRIX for clustered and Cloud NAS – July 2009
  • Enterprise Storage Forum: Comments on HP buying IBRIX for clustered and Cloud NAS – July 2009
  • eWeek: Comments on NetApps next moves after DDUP and EMC – July 2009
  • Enterprise Storage Forum: Comments on NetApps next moves after DDUP and EMC – July 2009
  • SearchStorage: Comments on EMC buying DataDomain, NetApps next moves – July 2009
  • SearchVirtualization: Comments on Microsft HyperV features and VMware – July 2009
  • SearchITchannel: Comments on social media for business – June 2009
  • SearchSMBstorage: Comments on Storage Resource Management (SRM) for SMBs – June 2009
  • Enterprise Storage Forum: Comments on IT Merger & Acquisition activity – June 2009
  • Evolving Solutions: Comments on Storage Consolidation, Networking & Green IT – June 2009
  • Enterprise Storage Forum: Comments on EMC letter to DDUP – June 2009
  • SearchStorage: Comments on best practices for effective thin provisioning – June 2009
  • Processor: Comments on Cloud computing, SaaS and SOAs – June 2009
  • Serverwatch: Comments in How EMC’s World Pulls the Data Center Together – June 2009
  • Processor: Comments on Virtual Security Is No Walk In The Park – May 2009
  • SearchStorage: Comments on EPA launching Green Storage specification – May 2009
  • SearchStorage: Comments on Storage Provisioning Tools – May 2009
  • Enterprise Systems Journal: Comments on Tape: The Zombie Technology – May 2009
  • Enterprise Storage Forum: Comments on Oracle Keeping Sun Storage Business – May 2009
  • IT Health Blogging: Discussion about iSCSI vs. Fibre Channel for Virtual Environments – May 2009
  • IT Business Edge: Discussion about IT Data Center Futures – May 2009
  • IT Business Edge: Comments on Tape being a Green Technology – April 2009
  • Big Fat Finance Blog: Quoted in story about Green IT for Finance Operaitons – April 2009
  • SearchStorage: Comments on FLASH and SSD Storage – April 2009
  • SearchStorage AU: Comments on Data Classificaiton – April 2009
  • IT Knowledge Exchange: Comments on FCoE and Converged Networking Coming Together – April 2009
  • SearchSMBStorage: Comments on Data Deduplicaiton for SMBs – April 2009
  • SearchSMBStorage: Comments on Blade Storage for SMBs – April 2009
  • SearchStorage: Comments on MAID technology remaining underutilized – April 2009
  • SearchDataCenter: Closing the green gap: Expanding data centers with environmental benefits – April 2009
  • ServerWatch: Comments on What’s Selling In the Data Storage Market? – April 2009
  • ServerWatch: Comments on Oracle Buys Sun: The Consequences – April 2009
  • SearchStorage: Comments on Tiered Storage – April 2009
  • SearchStorage: Comments on Data Classification for Storage Managers – April 2009
  • wsradio.com Interview closing the Green Gap


  • IT Knowledge Exchange: Comments on FCoE eco-system maturing – April 2009
  • Internet Revolution: Comments on the Pre-mature death of the disk drive – April 2009
  • Enterprise Storage Forum: Comments on EMC V-MAX announcement – April 2009
  • MSP Business Journal: Greg Schulz named an Eco-Tech Warrior – April 2009
  • Storage Magazine: Comments on Power-smart disk systems – April 2009
  • Storage Magazine: Comments on Replication Alternatives – April 2009
  • StorageIO Blog: Comments and Tape as a Green Storage Medium – April 2009
  • Inside HPC: Recent Comments on Tape and Green IT – April 2009
  • Processor.com: Recent Comments on Green and Virtual – April 2009
  • SearchDataCenter: Interview: Closing the green gap: Expanding data centers with environmental benefits – April 2009
  • Enterprise Systems Journal: Recent Comments and Tips – March 2009
  • Computer Technology Review: Recent Comments on The Green and Virtual Data Center – March 2009
  • VMblog: Comments on The Green and Virtual Data Center – March 2009
  • Sys-con: Comments on The Green and Virtual Data Center – March 2009
  • Server Watch: Comments on IBM possibly buying Sun – March 2009
  • Bnet: Comments on IBM possibly buying Sun – March 2009
  • SearchStorage: Comments on Tiered Storage 101 – March 2009
  • SearchStorage: Comments – Cisco pushes into Servers March 2009
  • Enterprise Storage Forum: Comments – Cisco Entering Server Market March 2009
  • Enterprise Storage Forum: Comments – State of Storage Job Market – March 2009
  • SearchSMBStorage: Comments on SMB Storage Options – March 2009
  • Enterprise Storage Forum: Comments on Sun Proposes New Solid State Storage Spec – March 2009
  • Enterprise Storage Forum: Comments on Despite Economy, Storage Bargains Hard to Find – March 2009
  • TechWorld: Comments on Where to Stash Your Data – February 2009
  • ServerWatch: Green IT: Myths vs. Realities – February 2009
  • Byte & Switch: Going Green and the Economic Downturn – February 2009
  • CTR: Comments on Tape Hardly Being On Way Out – February 2009
  • Processor: Comments on SSD (FLASH and RAM) – February 2009
  • Internet News: Comments on Steve Wozniak joining SSD startup – February 2009
  • SearchServerVirtualization: Comments on I/O and Virtualization – February 2009
  • Technology Inc.: Comments on Data De-dupe for DR – February 2009
  • SearchStorage: Comments on NetApp SMB NAS – February 2009
  • Check out the Tips, Tools and White Papers, and News pages for additional commentary, coverage and related content or events.

    Ok, nuff said.

    Cheers gs

    Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

    twitter @storageio

    All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

    Recent tips, videos, articles and more

    Its been a busy year so far and there is still plenty more to do. Taking advantage of a short summer break, I’m getting caught up on some items including putting up a link to some of the recent articles, tips, reports, webcasts, videos and more that I have eluded to in recent posts. Realizing that some prefer blogs to webs to tweets to other venues, here are some links to recent articles, tips, videos, podcasts, webcasts, white papers and more that can be found on the StorageIO Tips, tools and White Papers pages.

    Recent articles, columns, tips, white papers and reports:

  • ITworld: The new green data center: From energy avoidance to energy efficiency August 2009
  • SearchSystemsChannel: Comparing I/O virtualization and virtual I/O benefits July 2009
  • SearchDisasterRecovery: Top server virtualization myths in DR and BC July 2009
  • Enterprise Storage Forum: Saving Money with Green Data Storage Technology July 2009
  • SearchSMB ATE Tips: SMB Tips and ATE by Greg Schulz
  • SearchSMB ATE Tip: Tape library storage July 2009
  • SearchSMB ATE Tip: Server-based operating systems vs. PC-based operating systems June 2009
  • SearchSMB ATE Tip: Pros/cons of block/variable block dedupe June 2009
  • FedTechAt the Ready: High-availability storage hinges on being ready for a system failure May 2009
  • Byte & Switch Part XI – Key Elements For A Green and Virtual Data Center May 2009
  • Byte & Switch Part X – Basic Steps For Building a Green and Virtual Data Center May 2009
  • InfoStor Technology Options for Green Storage: April 2009
  • Byte & Switch Part IX – I/O, I/O, Its off to Virtual Work We Go: Networks role in Virtual Data Centers April 2009
  • Byte & Switch Part VIII – Data Storage Can Become Green: There are many steps you can take April 2009
  • Byte & Switch Part VII – Server Virtualization Can Save Costs April 2009
  • Byte & Switch Part VI – Building a Habitat for Technology April 2009
  • Byte & Switch Part V – Data Center Measurement, Metrics & Capacity Planning April 2009
  • zJournal Storage & Data Management: Tips for Enabling Green and Virtual Efficient Data Management March 2009
  • Serial Storage Wire (STA): Green and SASy = Energy and Economic, Effective Storage March 2009
  • SearchSystemsChannel: FAQs: Green IT strategies for solutions providers March 2009
  • Computer Technology Review: Recent Comments on The Green and Virtual Data Center March 2009
  • Byte & Switch Part IV – Virtual Data Centers Can Promote Business Growth March 2009
  • Byte & Switch Part III – The Challenge of IT Infrastructure Resource Management March 2009
  • Byte & Switch Part II – Building an Efficient & Ecologically Friendly Data Center March 2009
  • Byte & Switch Part I – The Green Gap – Addressing Environmental & Economic Sustainability March 2009
  • Byte & Switch Green IT and the Green Gap February 2009
  • GreenerComputing: Enabling a Green and Virtual Data Center February 2009
  • Some recent videos and podcasts include:

  • bmighty.com The dark side of SMB virtualization July 2009
  • bmighty.com SMBs Are Now Virtualization’s “Sweet Spot” July 2009
  • eWeek.com Green IT is not dead, its new focus is about efficiency July 2009
  • SearchSystemsChannel FAQ: Using cloud computing services opportunities to get more business July 2009
  • SearchStorage FAQ guide – How Fibre Channel over Ethernet can combine networks July 2009
  • SearchDataCenter Business Benefits of Boosting Web hosting Efficiency June 2009
  • SearchStorageChannel Disaster recovery services for solution providers June 2009
  • The Serverside The Changing Dynamic of the Data Center April 2009
  • TechTarget Virtualization and Consolidation for Agility: Intels Xeon Processor 5500 series May 2009
  • TechTarget Virtualization and Consolidation for Agility: Intels Xeon Processor 5500 series May 2009
  • Intel Reduce Energy Usage while Increasing Business Productivity in the Data Center May 2009
  • WSRadio Closing the green gap and shifting towards an IT efficiency and productivity April 2009
  • bmighty.com July 2009
  • Check out the Tips, Tools and White Papers, and News pages for more commentary, coverage and related content or events.

    Ok, nuff said.

    Cheers gs

    Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

    twitter @storageio

    All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

    Clarifying Clustered Storage Confusion

    Clustered storage can be iSCSI, Fibre Channel block based or NAS (NFS or CIFS or proprietary file system) file system based. Clustered storage can also be found in virtual tape library (VTL) including dedupe solutions along with other storage solutions such as those for archiving, cloud, medical or other specialized grids among others.

    Recently in the IT and data storage specific industry, there has been a flurry of merger and acquisition (M&A) (Here and here), new product enhancement or announcement activity around clustered storage. For example, HP buying clustered file system vendor IBRIX complimenting their previous acquisition of another clustered file system vendor (PolyServe) a few years ago, or, of iSCSI block clustered storage software vendor LeftHand earlier this year. Another recent acquisition is that of LSI buying clustered NAS vendor ONstor, not to mention Dell buying iSCSI block clustered storage vendor EqualLogic about a year and half ago, not to mention other vendor acquisitions or announcements involving storage and clustering.

    Where the confusion enters into play is the term cluster which means many things to different people, and even more so when clustered storage is combined with NAS or file based storage. For example, clustered NAS may infer a clustered file system when in reality a solution may only be multiple NAS filers, NAS heads, controllers or storage processors configured for availability or failover.

    What this means is that a NFS or CIFS file system may only be active on one node at a time, however in the event of a failover, the file system shifts from one NAS hardware device (e.g. NAS head or filer) to another. On the other hand, a clustered file system enables a NFS or CIFS or other file system to be active on multiple nodes (e.g. NAS heads, controllers, etc.) concurrently. The concurrent access may be for small random reads and writes for example supporting a popular website or file serving application, or, it may be for parallel reads or writes to a large sequential file.

    Clustered storage is no longer exclusive to the confines of high-performance sequential and parallel scientific computing or ultra large environments. Small files and I/O (read or write), including meta-data information, are also being supported by a new generation of multipurpose, flexible, clustered storage solutions that can be tailored to support different applications workloads.

    There are many different types of clustered and bulk storage systems. Clustered storage solutions may be block (iSCSI or Fibre Channel), NAS or file serving, virtual tape library (VTL), or archiving and object-or content-addressable storage. Clustered storage in general is similar to using clustered servers, providing scale beyond the limits of a single traditional system—scale for performance, scale for availability, and scale for capacity and to enable growth in a modular fashion, adding performance and intelligence capabilities along with capacity.

    For smaller environments, clustered storage enables modular pay-as-you-grow capabilities to address specific performance or capacity needs. For larger environments, clustered storage enables growth beyond the limits of a single storage system to meet performance, capacity, or availability needs.

    Applications that lend themselves to clustered and bulk storage solutions include:

    • Unstructured data files, including spreadsheets, PDFs, slide decks, and other documents
    • Email systems, including Microsoft Exchange Personal (.PST) files stored on file servers
    • Users’ home directories and online file storage for documents and multimedia
    • Web-based managed service providers for online data storage, backup, and restore
    • Rich media data delivery, hosting, and social networking Internet sites
    • Media and entertainment creation, including animation rendering and post processing
    • High-performance databases such as Oracle with NFS direct I/O
    • Financial services and telecommunications, transportation, logistics, and manufacturing
    • Project-oriented development, simulation, and energy exploration
    • Low-cost, high-performance caching for transient and look-up or reference data
    • Real-time performance including fraud detection and electronic surveillance
    • Life sciences, chemical research, and computer-aided design

    Clustered storage solutions go beyond meeting the basic requirements of supporting large sequential parallel or concurrent file access. Clustered storage systems can also support random access of small files for highly concurrent online and other applications. Scalable and flexible clustered file servers that leverage commonly deployed servers, networking, and storage technologies are well suited for new and emerging applications, including bulk storage of online unstructured data, cloud services, and multimedia, where extreme scaling of performance (IOPS or bandwidth), low latency, storage capacity, and flexibility at a low cost are needed.

    The bandwidth-intensive and parallel-access performance characteristics associated with clustered storage are generally known; what is not so commonly known is the breakthrough to support small and random IOPS associated with database, email, general-purpose file serving, home directories, and meta-data look-up (Figure 1). Note that a clustered storage system, and in particular, a clustered NAS may or may not include a clustered file system.

    Clustered Storage Model: Source The Green and Virtual Data Center (CRC)
    Figure 1 – Generic clustered storage model (Courtesy “The Green and Virtual Data Center  (CRC)”

    More nodes, ports, memory, and disks do not guarantee more performance for applications. Performance depends on how those resources are deployed and how the storage management software enables those resources to avoid bottlenecks. For some clustered NAS and storage systems, more nodes are required to compensate for overhead or performance congestion when processing diverse application workloads. Other things to consider include support for industry-standard interfaces, protocols, and technologies.

    Scalable and flexible clustered file server and storage systems provide the potential to leverage the inherent processing capabilities of constantly improving underlying hardware platforms. For example, software-based clustered storage systems that do not rely on proprietary hardware can be deployed on industry-standard high-density servers and blade centers and utilizes third-party internal or external storage.

    Clustered storage is no longer exclusive to niche applications or scientific and high-performance computing environments. Organizations of all sizes can benefit from ultra scalable, flexible, clustered NAS storage that supports application performance needs from small random I/O to meta-data lookup and large-stream sequential I/O that scales with stability to grow with business and application needs.

    Additional considerations for clustered NAS storage solutions include the following.

    • Can memory, processors, and I/O devices be varied to meet application needs?
    • Is there support for large file systems supporting many small files as well as large files?
    • What is the performance for small random IOPS and bandwidth for large sequential I/O?
    • How is performance enabled across different application in the same cluster instance?
    • Are I/O requests, including meta-data look-up, funneled through a single node?
    • How does a solution scale as the number of nodes and storage devices is increased?
    • How disruptive and time-consuming is adding new or replacing existing storage?
    • Is proprietary hardware needed, or can industry-standard servers and storage be used?
    • What data management features, including load balancing and data protection, exists?
    • What storage interface can be used: SAS, SATA, iSCSI, or Fibre Channel?
    • What types of storage devices are supported: SSD, SAS, Fibre Channel, or SATA disks?

    As with most storage systems, it is not the total number of hard disk drives (HDDs), the quantity and speed of tiered-access I/O connectivity, the types and speeds of the processors, or even the amount of cache memory that determines performance. The performance differentiator is how a manufacturer combines the various components to create a solution that delivers a given level of performance with lower power consumption.

    To avoid performance surprises, be leery of performance claims based solely on speed and quantity of HDDs or the speed and number of ports, processors and memory. How the resources are deployed and how the storage management software enables those resources to avoid bottlenecks are more important. For some clustered NAS and storage systems, more nodes are required to compensate for overhead or performance congestion.

    Learn more about clustered storage (block, file, VTL/dedupe, archive), clustered NAS, clustered file system, grids and cloud storage among other topics in the following links:

    "The Many faces of NAS – Which is appropriate for you?"

    Article: Clarifying Storage Cluster Confusion
    Presentation: Clustered Storage: “From SMB, to Scientific, to File Serving, to Commercial, Social Networking and Web 2.0”
    Video Interview: How to Scale Data Storage Systems with Clustering
    Guidelines for controlling clustering
    The benefits of clustered storage

    Along with other material on the StorageIO Tips and Tools or portfolio archive or events pages.

    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

    Downloads for fall 2008 San Francisco Storage Decisions now available

    The TechTarget Storage Media Group has posted on Bitpipe the session presentations from the recent fall (November 17-19th) 2008 San Francisco Storage Decisions event. If you have never been to a Storage Decisions event, it?s a great venue for meeting with IT and storage professionals as well as vendors who also show up to show their wares and meet with the attendees. Make no mistake about it, Storage Decisions is not a vendor to vendor meet and industry network event like SNW or a vendor sponsored user group like VMworld or EMCworld, rather, its focused on the IT and storage professional and encourages speakers to be frank and candid in their discussions of technologies, techniques and even of vendors and their solutions.

    In addition to doing a keynote session Wednesday evening November 19th on ?Hot Storage Topics for Channel Professionals? at the Storage Strategies for Channel Professionals Dinner event, I also did two presentations at Storage Decisions one in the management and executive track Management and Executive Track on Green and Efficient Storage , an (updated version from what was covered in September 2008 at New York) timely theme given my new book ?The Green and Virtual Data Center? (Auerbach) along with another session in the Storage and capacity management track of  ?Clustered and Grid Storage — From SMB, to Scientific, to Social Networking and Web 2.0? (also updated from September 2008)

    View the entire list of all Storage Decisions sessions here.

    A big thanks to all who came out last week in San Francisco at Storage Decisions and who attended the sessions enabling great discussion and insight both during the sessions, as well as during lunches, breaks and exhibition hours.

    Cheers gs

    Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

    twitter @storageio

    All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

    Time In and Around Clouds

    This past week I spent some time in, around and above the clouds literally and figutively. I was in the Netherlands the past few days doing a seminar with Brouwer Storage as well as key note presentation on Wednesday at the Dutch StorageExpo in Utrecht (a fabulous event with lots of buzz and activity, nice job Marloes!) before flying home today from my favorite airport (Amsterdam Schiphol).

    (Following photo’s were taken this past summer on an early morning flight from my phone camera)
    View of morning clouds from the air
    Getting ready to land on a morning flight going through some clouds

    Another view of morning clouds from the air just before landing
    More morning clouds

    Looking out at the wing of an Northwest Airlines Airbus A320 while in the clouds
    Low visibility as you can barely see the wingtip

    In addition to flying above the clouds over the Atlantic (not the above photos), the fall clouds at home where it was snowing when I left and then raining when I returned, with wind and clouds (some occasional sun) while in Holland, and then the industry buzz around EMC’s cloud and clustered storage solution announcement (also here and here and here and here) called Atmos (aka the solution code named hulk and maui), this week had a strong cloud theme along with a dose of policy management.

    Meeting regularly with IT professionals from organizations of all size as well as various vendors and vars around the world, is a great way to avoid having your thinking end up to much in the clouds, instead, staying rooted as to where IT issues and pain points are vs. where they are perceived to be.

    However, the long plane ride with no cell phone or email or web access also made for some great time to relax and watch the clouds go by. In a few days I?m back in the air again as next week I will be in San Francisco presenting at Storage Decisions. Next weeks topics will include a session updated with new content looking at “Clustered Storage: From SMB, to Scientific, to File Serving, to Commercial, Social Networking and Web 2.0” and grids among other topics.

    If you are in the area, stop by and say hello next Monday and Tuesday at the San Francisco Hilton.

    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