Category: Education

Posted on

StorageIO Momentus Hybrid Hard Disk Drive (HHDD) Moments

This is the third in a series of posts that I have done about Hybrid Hard Disk Drives (HHDDs) along with pieces about Hard Disk Drives (HDD) and Solid State Devices (SSDs). Granted the HDD received its AARP card several years ago when it turned 50 and is routinely declared dead (or read here) even though it continues to evolve along SSD maturing and both expanding into different markets as well as usage roles.

For those who have not read previous posts about Hybrid Hard Disk Drives (HHDDs) and the Seagate Momentus XT you can find them here and here.

Since my last post, I have been using the HHDDs extensively and recently installed the latest firmware. The release of new HHDD firmware by Seagate for the Momentus XT (SD 25) like its predecessor SD24 cleaned up some annoyances and improved on overall stability. Here is a Seagate post by Mark Wojtasiak discussing SD25 and feedback obtained via the Momentus XT forum from customers.

If you have never done a HDD firmware update, its not as bad or intimidating as might be expected. The Seagate firmware update tools make it very easy, that is assuming you have a recent good backup of your data (one that can be restored) and about 10 to 15 minutes of time for a couple of reboots.

Speaking of stability, the Momentus XT HHDDs have been performing well helping to speed up accessing large documents on various projects including those for my new book. Granted an SSD would be faster across the board, however the large capacity at the price point of the HHDD is what makes it a hybrid value proposition. As I have said in previous posts, if you have the need for speed all of the time and time is money, get an SSD. Likewise if you need as much capacity as you can get and performance is not your primary objective, then leverage the high capacity HDDs. On the other hand, if you need a balance of some performance boost with capacity boost and a good value, then check out the HHDDs.

Image of Momentus XT courtesy of www.Seagate.com

Lets shift gears from that of the product or technology to that of common questions that I get asked about HHDDs.

Common questions I get asked about HHDDs include:

What is a Hybrid Hard Disk Drive?

A Hybrid Hard Disk Drive includes a combination of rotating HDD, solid state flash persistent memory along with volatile dynamic random access memory (DRAM) in an integrated package or product. The value proposition and benefit is a balance of performance and capacity at a good price for those environments, systems or applications that do not need all SSD performance (and cost) vs. those that need some performance in addition to large capacity.

How the Seagate Momentus XT differs from other Hybrid Disks?
One approach is to take a traditional HDD and pair it with a SSD using a controller packaged in various ways. For example on a large scale, HDDs and SSDs coexist in the same tiered storage system being managed by the controllers, storage processors or nodes in the solution including automated tiering and cache promotion or demotion. The main difference however between other storage systems, tiering and pairing and HHDDs is that in the case of the Momentus XT the HDD, SLC flash (SSD functionality) and RAM cache and their management are all integrated within the disk drive enclosure.

Do I use SSDs and HDDs or just HHDDs?
I have HHDDs installed internally in my laptops. I also have HDDs which are installed in servers, NAS and disk to disk (D2D) backup devices and Digital Video Recorders (DVRs) along with external SSD and Removable Hard Disk Drives (RHDDs). The RHDDs are used for archive and master or gold copy data protection that go offsite complimenting how I also use cloud backup services as part of my data protection strategy.

What are the technical specifications of a HHDD such as the Seagate Momentus XT?
3Gbs SATA interface, 2.5 inch 500GB 7,200 RPM HDD with 32MB RAM cache and integrated 4GByte SLC flash all managed via internal drive processor. Power consumption varies depending what the device is doing such as initial power up, idle, normal or other operating modes. You can view the Seagate Momentus XT 500GB (ST95005620AS which is what I have) specifications here as well as the product manual here.


One of my HHDDs on a note pad (paper) and other accessories

Do you need a special controller or management software?
Generally speaking no, the HHDD that I have been using plugged and played into my existing laptops internal bay replacing the HDD that came with those systems. No extra software was needed for Windows, no data movement or migration tools needed other than when initially copying from the source HDD to the new HHDD. The HHDD do their own caching, read ahead and write behind independent of the operating system or controller. Now the reason I say generally speaking is that like many devices, some operating systems or controllers may be able to leverage advanced features so check your particular system capabilities.

How come the storage system vendors are not talking about these HHDDs?
Good question which I assume it has a lot to do with the investment (people, time, engineering, money and marketing) that they have or are making in controller and storage system software functionality to effectively create hybrid tiered storage systems using SSD and HDDs on different scales. There have been some packaged HHDD systems or solutions brought to market by different vendors that combine HDD and SSD into a single physical package glued together with some software and controllers or processors to appear as a single system. I would not be surprised to see discrete HHDDs (where the HDD and flash SSD and RAM are all one integrated product) appear in lower end NAS or multifunction storage systems as well as for backup, dedupe or other system that requires large amounts of capacity space and performance boost now and then.

Why do I think this? Simple, say you have five HHDDs each with 500GB of capacity configured as a RAID5 set resulting in 2TByte of capacity. Using as a hypothetical example the Momentus XT yields 5 x 4GByte or 20GByte of flash cache helps accelerate write operations during data dumps, backup or other updates. Granted that is an overly simplified example and storage systems can be found with hundreds of GByte of cache, however think in terms of value or low cost balancing performance and capacity to cost for different usage scenarios. For example, applications such as bulk or scale out file and object storage including cloud or big data, entertainment, Server (Citrix/Xen, Microsoft/HyperV, VMware/vSphere) and Desktop virtualization or VDI, Disk to Disk (D2D) backup, business analytics among others. The common tenets of those applications and usage scenario is a combination of I/O and storage consolidation in a cost effective manner addressing the continuing storage capacity to I/O performance gap.

Data Center and I/O Bottlenecks

Storage and I/O performance gap

Do you have to backup HHDDs?
Yes, just as you would want to backup or protect any SSD or HHD device or system.

How does data get moved between the SSD and the HDD?
Other than the initial data migration from the old HDD (or SSD) to the HHDD, unless you are starting with a new system, once your data and applications exist on the HHDD, it automatically via the internal process of the device manages the RAM, flash and HDD activity. Unlike in a tiered storage system where data blocks or files may be moved between different types of storage devices, inside the HHDD, all data gets written to the HDD, however the flash and RAM are used as buffers for caching depending on activity needs. If you have sat through or listened to a NetApp or HDS use of cache for tiering discussion what the HHDDs do is similar in concept however on a smaller scale at the device level, potentially even in a complimentary mode in the future? Other functions performed inside the HHDD by its processor includes reading and writing, managing the caches, bad block replacement or re vectoring on the HDD, wear leveling of the SLC flash and other routine tasks such as integrity checks and diagnostics. Unlike paired storage solutions where data gets moved between tiers or types of devices, once data is stored in the HHDD, it is managed by the device similar to how a SSD or HDD would move blocks of data to and from the specific media along with leveraging RAM cache as a buffer.

Where is the controller that manages the SSD and HDD?
The HHDD itself is the controller per say in that the internal processor that manages the HDD also directly access the RAM and flash.

What type of flash is used and will it wear out?
The XT uses SLC (single level cell) flash which with wear leveling has a good duty cycle (life span) and is what is typically found in higher end flash SSD solutions vs. lower cost MLC (multi level cell)

Have I lost any data from it yet?
No, at least nothing that was not my own fault from saving the wrong file in the wrong place and having to recover from one of my recent D2D copies or the cloud. Oh, regarding what have I done with the HDDs that were replaced by the HHDDs? They are now an extra gold master backup copy as of a particular point in time and are being kept in a safe secure facility, encrypted of course.

Have you noticed a performance improvement?
Yes, performance will vary however in many cases I have seen performance comparable to SSD on both reads and writes as long as the HDDs keep up with the flash and RAM cache. Even as larger amounts of data are written, I have seen better performance than compared to HDDs. The caveat however is that initially you may see little to marginal performance improvement however over time, particularly on the same files, performance tends to improve. Working on large tens to hundreds of MByte size documents I noticed good performance when doing saves compared to working with them on a HDD.

What do the HHDDs cost?
Amazon.com has the 500GB model for about $100 which is about $40 to $50 less than when I bought my most recent one last fall. I have heard from other people that you can find them at even lower prices at other venues. In the theme of disclosures, I bought one of my HHDDs from Amazon and Seagate gave me one to test.

Will I buy more HHDDs or switch to SSDs?
Where applicable I will add SSDs as well as HDDs, however where possible and practical, I will also add HHDDs perhaps even replacing the HDDs in my NAS system with HHDDs at some time or maybe trying them in a DVR.

What is the down side to the HHDDs?
Im generating and saving more data on the devices at a faster rate which means that when I installed them I was wondering if I would ever fill up a 500GB drive. I still have hundreds of GBytes free or available for use, however I also am able to cary more reference data or information than in the past. In addition to more reference data including videos, audio, images, slide decks and other content, I have also been able to keep more versions or copies of documents which has been handy on the book project. Data that changes gets backed up D2D as well as to my cloud provider including while traveling. Leveraging compression and dedupe, given that many chapters or other content are similar, not as much data actually gets transmitted when doing cloud backups which has been handy when doing a backup from a airplane flying over the clouds. A wish for the XT type of HHDD that I have is for vendors such as Seagate to add Self Encrypting Disk (SED) capabilities to them along with applying continued intelligent power management (IPM) enhancements.

Why do I like the HHDD?
Simple, it solves both business and technology challenges while being an enabler, it gives me a balance of performance for productivity and capacity in a cost effective manner while being transparent to the systems it works with.

Here are some related links to additional material:
Data Center I/O Bottlenecks Performance Issues and Impacts
Has SSD put Hard Disk Drives (HDDs) On Endangered Species List?
Seagate Momentus XT SD 25 firmware
Seagate Momentus XT SD25 firmware update coming this week
A Storage I/O Momentus Moment
Another StorageIO Hybrid Momentus Moment
As the Hard Disk Drive (HDD) continues to spin
Has SSD put Hard Disk Drives (HDDs) On Endangered Species List?
Funeral for a Friend
As the Hard Disk Drive (HDD) continues to spin
Seagate Momentus XT product specifications
Seagate Momentus XT product manual
Technology Tiering, Servers Storage and Snow Removal
Self Encrypting Disks (SEDs)

Ok, nuff said for now

Cheers Gs

Greg Schulz – Author The Green and Virtual Data Center (CRC), Resilient Storage Networks (Elsevier) and coming summer 2011 Cloud and Virtual Data Storage Networking (CRC)
twitter @storageio

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

Posted on

Spring 2011 Server and StorageIO News Letter

StorageIO News Letter Image
Spring 2011 Newsletter

Welcome to the Spring 2011 edition of the Server and StorageIO Group (StorageIO) newsletter. This follows the Winter 2011 edition.

You can access this news letter via various social media venues (some are shown below) in addition to StorageIO web sites and subscriptions.

 

Click on the following links to view the Spring 2011 edition as an HTML or PDF or, to go to the newsletter page to view previous editions.

Follow via Goggle Feedburner here or via email subscription here.

You can also subscribe to the news letter by simply sending an email to newsletter@storageio.com

Enjoy this edition of the StorageIO newsletter, let me know your comments and feedback.

Cheers gs

Nuff said for now

Cheers
Gs

Greg Schulz – Author The Green and Virtual Data Center (CRC), Resilient Storage Networks (Elsevier) and coming summer 2011 Cloud and Virtual Data Storage Networking (CRC)
twitter @storageio

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

Posted on

Buzzword Bingo and Acronym Update V2.011

R U (e.g. Are you) JASSD about JACD or do you have a case of JAID and JACBUS?

Will RAID RAIN on your cloud parade?

For those who like to keep up on buzzwords (for buzzword bingo) and acronyms, perhaps even FTW (e.g. For the Win), here are some old and new, fun and real ones to ponder.

As to which are real or new, fun or old, I will leave that up to you.

  • BD = Business Development or Big Data or Backup Device
  • CEO = Chief Evangelist Officer or Change Everything Often
  • CJO = Chief Jailable Officer or anyone who is a legal Chief of a company
  • CMO = Creative Movie Officer or Chief Marketing Officer (same thing)
  • CNOC = Cloud network operations center
  • CPOP = Cloud point of presence aka cloud gateway, cloud appliance, cloud middle ware, cloud shims
  • DC = Direct Current or Diet Coke or Data Center
  • DTDS+ = Disaster Tolerant Disk Subsystem (Plus)
  • EMC = Entertaining Movie Creations
  • HP = Has printers and PCs
  • IBM = Itty Bitty Machine company or I Buy Mainframes
  • iHop = International House of pancakes or iPhone bouncing on floor
  • JACBUS = Just Another Cloud Backup Service
  • JACD = Just Another Cloud Device
  • JAFD = Just Another Flash Device
  • JAiD = Just Another iSCSI Device or Just Another iProduct Device
  • JAM = Producer of Tree size SRM tools or a U.S. concert promoter
  • JASSD = Just Another SSD
  • MIA = Missing In Action or airport code for Miami International Airport
  • MSP = My Storage Please or Minneapolis St. Paul Airport code
  • NetApp = Neat effective technology And product portfolio
  • PIROMA = Ask someone you know who has been in capacity planning
  • RAID = Redundant Array of Independent Disks or bug spray
  • RAIN = Redundant Array of Independent Nodes or something that falls from the clouds
  • RPD = Revenue prevention department: Groups, entities or management layers that get in the way of getting results done
  • Truth Squads = Teams representing various vendors or organizations that try to get you to see things their way
  • WATN = Where Are They Now: Former vendors or service providers that are now MIA
  • XaaS = Plug in what ever you like for X as a Service

Ok, nuff said and fun for now

Cheers
Gs

Greg Schulz – Author The Green and Virtual Data Center (CRC), Resilient Storage Networks (Elsevier) and coming summer 2011 Cloud and Virtual Data Storage Networking (CRC)
twitter @storageio

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

Posted on

Happy Earth Day 2011

Let me keep this simple, efficient and effective, Happy Earth Day 2011 April 22, 2011.

Be smart, practical, conscious, aware, recycle, cut down on waste, work smarter and more effective.

Ok, nuff said for now, go hug a tree, your computer, hybrid car, droid, ipad, spouse, partner, kid, dog, cat or whatever suits your needs.

Cheers gs

Greg Schulz – Author The Green and Virtual Data Center (CRC), Resilient Storage Networks (Elsevier) and coming summer 2011 Cloud and Virtual Data Storage Networking (CRC)
twitter @storageio

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

Posted on

The new Green IT: Efficient, Effective, Smart and Productive

Given the buzz about big data and conversations or confusion around clouds along with virtualizing virtually anything possible, Green IT has fallen off the Buzzword Bingo Bandwagon.

Green IT like so many other buzzwords and trends typically go through a hype cycle before getting tired, worn out, or disillusioned (see here and here). Often these buzzwords will go to Some Day Isle for some rest and recuperation before reappearing later as part of a second or third buzzword wave either making it to broad adoption which means the plateau of profitability (for vendors or vars) and productivity (for customers) or disappearing.

Some Day Isle for those not familiar with it is a visional or fictional place that some day you will go to, a wishful happy place so to speak that is perfect for hyperbole R and R. After some R and R, these trends, technologies or techniques often reappear well rested and ready for the next wave of buzz, FUD, hype and activity.

Keep in mind that industry adoption (e.g. everybody is talking about it) can differ from industry deployment (e.g. some people have actually paid for, deployed and using the technology) to broad customer adoption (e.g. many people are actually paying for, deploying and using the technology on a routine basis).

Confusion still reigns around Green IT not surprising given the heavy dose of Green Washing that has occurred.

Consequently Green IT themes or pitches often fall on deaf ears as people have either become numb or ignore the Green washing hype or FUD. For example many people will skip reading this post because the word Green is in the title assuming that it is another CO2 or related themed piece missing out on the other themes or messages here. Unfortunately as I have discussed in the past, there remains a Green Gap that results in missed opportunities for vendors, vars, service providers, IT organizations along with those who would like to see environmental benefits or change.

Another example of a Green gap is messaging around energy avoidance as being efficient vs. using energy in a more productive or effective manner (doing more work with the same or fewer resources) shown in the figure below.

Tiered Storage
Expanding focus from energy avoidance to energy usage effectiveness

In routine conversations with IT professionals it is clear that the Green Gap and thus missed opportunities will continue for some time until the business and economic values of efficient, effective, smart and productive IT are understood to have environmental benefits as a by product and thus being Green. Watch for more missed messaging around CO2 and related themes popular with so called Greenies (or if you prefer environmentalists) that miss the mark with most business and IT organizations.

Business and thus IT are driven by economics and as such will invest where they can reduce complexity and costs, become more efficient and effective while increasing productivity and reducing waste by working smarter. In other words, by changing how information services are delivered in a smarter more effective efficient manner maximizes what resources are used enabling more to be done in a denser footprint (budget, people staffing, management, power, cooling, floor space) that have positive environmental benefits. Put another way, a benefit for IT organizations to remove complexity results in lower costs, by becoming more efficient and effective reducing waste results in better productivity and fewer missed opportunities meaning enhanced profits. The net result is that environmental concerns get a free ride or being funded as a result of IT organizations improving their productivity which of course should have a business benefit.

Efficient and Optimized IT Wheel of Oppourtunity
Wheel of Opportunity: Various techniques and technologies for infrastructure optimization

Efficient and effective IT (aka the other Green IT) that links to common technology and business issues with the benefit of helping the environment can be accomplished using a combination approaches. The approaches for enabling an efficient, effective, smarter and productive IT environment includes from a generic perspective various technologies, techniques and best practices shown in the wheel of opportunity figure.

For example:

Here are some related links for additional reading:

Also check out my book for enabling efficient, effective and smart IT The Green and Virtual Data Center (CRC) including a free sample chapter download here.

Ok, nuff said for now, go hug a tree, your computer, hybrid car, droid, ipad or whatever suits your needs.

Cheers gs

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

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

Posted on

StorageIO V20.11 (2011) events seminars and web casts schedule

The V20.11 (e.g. 2011 or follow up from V20.10) Server and StorageIO (StorageIO) out and about events schedule continues to evolve.

In the meantime, here are a few (actually a couple dozen) seminars and web casts currently on the event calendar for 2011 that I will be speaking or presenting at. Topics and themes include Server and Storage Optimization, Clouds, Virtualization, Data Protection Modernization (HA, BC, DR, Backup/restore) along with Data Footprint Reduction (DFR including archive, compression, dedupe), End to End (E2E) Management, efficient IT data centers (and storage) among other related items.

Later this summer watch for the release of my new book Cloud and Virtual Data Storage Networking (CRC) as well as keep an eye on the StorageIO events page for additional events or details to appear. Also check out the news page for commentary on industry activities, announcements, trends or related topics in addition to the tips (or articles) page. You can also view videos, webinars and pod casts along with news letters containing links from while out and about during 2011 activities (or from past events).

WhenVenueEvent Name Location
Nov 10, 2011 Data Center Summit BC and DR Track Key note speaker: Protect, preserve and server your organizations essential applications and information services in an affordable mannerLos Angeles, CA
Nov 8, 2011 Data Center Summit BC and DR Track Key note speaker: Protect, preserve and server your organizations essential applications and information services in an affordable mannerSeattle, WA
Nov 3, 2011 Data Center Summit BC and DR Track Key note speaker: Protect, preserve and server your organizations essential applications and information services in an affordable mannerDenver, CO
Nov 1, 2011 Data Center Summit BC and DR Track Key note speaker: Protect, preserve and server your organizations essential applications and information services in an affordable mannerChicago, IL
Sept 29, 2011 Data Center Summit BC and DR Track Key note speaker: Protect, preserve and server your organizations essential applications and information services in an affordable mannerMinneapolis, MN
Aug 4, 2011 Data Center Summit BC and DR Track Key note speaker: Protect, preserve and server your organizations essential applications and information services in an affordable mannerSan Francisco, CA
Jul 28, 2011 Data Center Summit BC and DR Track Key note speaker: Protect, preserve and server your organizations essential applications and information services in an affordable mannerHouston, TX
Jul 21, 2011 Event keynote Speaker: Data Center Summit: Virtualization, Business Continuity and Cloud ComputingRaleigh, NC
Jun 28, 2011 Data Center Summit BC and DR Track Key note speaker: Protect, preserve and server your organizations essential applications and information services in an affordable mannerBoston, MA
June 23, 2011 Data Center Summit BC and DR Track Key note speaker: Protect, preserve and server your organizations essential applications and information services in an affordable mannerNew York City
June 21, 2011 Event keynote Speaker: Data Center Summit: Virtualization, Business Continuity and Cloud ComputingTampa, FL
May 18, 2011Keynote: 2011 Virtualization Best PracticesIrvine, CA
May 12, 2011Keynote: 2011 Virtualization Best PracticesChicago, IL
May 10, 2011Keynote: 2011 Virtualization Best PracticesDallas, TX
May 5, 2011Keynote: 2011 Virtualization Best PracticesNew York, NY
May 3, 2011Keynote: 2011 Virtualization Best PracticesBoston, MA
Apr 28, 2011 Data Center Summit BC and DR Track Key note speaker: Protect, preserve and server your organizations essential applications and information services in an affordable mannerDallas, TX
Apr 12, 2011 Event keynote Speaker: Data Center Summit: Virtualization, Business Continuity and Cloud ComputingSt. Louis, MO
Mar 29, 2011WebcastCloud and Virtual BC/DRWebcast
Mar 24, 2011WebcastTapes Evolving Data Storage RoleWebcast
Mar 15, 2011Wildfire GrilleKeynote: Virtualization, storage and the enterprise cloudEden Prairie, MN
Feb 10, 2011 Guest participant – Enabling safe and secure SaaSOn demand eSeminar
Jan 31, 2011century CollegeCloud and Virtual Data Storage Networking: Industry TrendsMahtomedi MN
Jan 12, 2011 Presenter – E2E Awareness and insight for cloud, virtualized and legacy IT environments
See more here including viewing the webcast		Virtual event
More information

Watch here for more events updates and information as well as signup for the free StorageIO news letter here.

Nuff said for now, look forward to seeing as well as hearing from you while out and about during 2011.

Cheers gs

Greg Schulz – Author The Green and Virtual Data Center (CRC), Resilient Storage Networks (Elsevier) and coming summer 2011 Cloud and Virtual Data Storage Networking (CRC)
twitter @storageio

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

Posted on

Cloud conversations: Loss of data access vs. data loss

Have you hugged your cloud or MSP lately?

Why give a cloud a hug and what does it have to do with loss of data access vs. loss of data?

First there is a difference between actually losing data and losing access to it.

Losing data means that you have no backup or copy of the information thus it is gone. This means there are no good valid backups, snapshots, copies or archives that can be used to restore or recover the information.

Losing access to data means that there is a copy of it somewhere however it will take time to make it usable (no data was actually lost). How long you have to wait until the data is restored or recovered will vary and during that time it may seem like data was lost.

Second, industry hype for and against clouds serves as a lighting rod for when things happen.

Lighting recently struck (or at least virtually) with some outages (see links below) including at Google Gmail.

Cloud crowd cheerleaders may need a hug to feel good while they or their technology get tossed about a bit. Google announced that they had a service disruption recently however that data was not lost, only loss of access for a period of time.

Lets take a step back before going forward.

With the Google Gmail disruption, following on previous incidents, true cynics and naysayers will probably jump on the anti cloud FUD feeding frenzy. The true cloud cynics will tell the skeptics all about cloud challenges perhaps never having had actually used any service or technology themselves.

Cloud crowd cheerleaders are generally a happy go lucky bunch with virtual beliefs and physical or real emotions. Cloud crowd cheerleaders have a strong passion for their technology or paradigm taking it various serious in some instances perceiving attacks or fud against cloud as an attack on them or their belief. Some cheerleaders will see this post as snarky or cynical (ok, get over it already).


Ongoing poll at StorageIOblog.com, click on the image to cast your vote.

Then there are the skeptics or interested audience who are not complete cynics or cheerleaders (those in the middle 80 percent of the above chart).

Generally speaking they want to learn more, understand issues to work around or take appropriate steps and institute best practices. They see a place for MSP or cloud services for some things to compliment what they are currently doing and tend to be the majority of audiences outside of special interest, vendor or industry trade groups.

Some additional thoughts, comments and perspectives:

  • Loss of data means you cannot get it back to a specific RPO (Recovery Point Objective or how much data you can afford to lose). Loss of access to data means that you cannot get to your data until a specific RTO (Recovery Time Objective).


Tiered data protection, RTO and RPOs, align technique and technology to SLO needs


RTO and RPOs

  • RAID and replication provide accessibility to data not data protection. The good news with RAID and replication or mirroring is if you make a change to the data it is copied or protected. The bad news is if it is deleted or corrupted that error or problem is also replicated.
  • Backup, snapshots, CDP or other time interval based techniques protect data against loss however may require time to restore, recovery or refresh from. A combination of data availability and accessibility along with time interval based protection are needed (e.g. the two previous above items should be combined). CDP should also mean complete, consistent, coherent or comprehensive data protection including data in application or VM buffers.
  • Any technology will fail either on its own or via human intervention or lack of configuration. It is not if rather when as well as how gracefully a failure along with fault isolation occurs and is remediate (corrected). There is generally speaking, no such thing as a bad technology, rather poor or inappropriate use, configuration or deployment of it.
  • Protect onsite data with offsite mediums including MSP or cloud backup services while keeping a local onsite copy. Why keep an onsite local copy when using a cloud? Simple, when you lose access to the cloud or MSP for extended periods of time, if needed you have a copy of data to work with (assuming it is still valid). On other hand, important data that is onsite needs to be kept offsite. Hence cloud and MSP should compliment what is done for data protection and vise versa. Thats what I do, is what you do?
  • The technology golden rule which applies to cloud and virtualization is whoever controls the management of the technology controls the gold. Leverage CDP, which is Commonsense Data Protection or Cloud Data Protection. Hops are great in beer (as well as some other foods) however they add latency including with networks. Aggregation can cause aggravation, not everything can be consolidated, however much can be virtualized.

Here are some related blog posts:

Additional links to related articles and commentary:

Closing thoughts and comments (for now) regarding clouds.

Its not if, rather when, where, why, how and with what will you leverage a cloud or MSP technologies, products, service, solution or architectures to compliment your environment.

How will cloud or MSP work for you vs. you working for it (unless you actually do work for one of them).

Dont be scared of clouds or virtualization, however look before you leap!

BTW, for those in the Minneapolis St. Paul area (aka the other MSP), check out this event on March 15, 2011. I have been invited to talk about optimizing your data storage and virtual environments and be prepared to take advantage of cloud computing opportunities as they mature.

Nuff said for now

Cheers gs

Greg Schulz – Author The Green and Virtual Data Center (CRC), Resilient Storage Networks (Elsevier) and coming summer 2011 Cloud and Virtual Data Storage Networking (CRC) at https://storageio.com/books
twitter @storageio

Posted on

What do you need when its time to buy a new server?

You have been told by someone or determined on your own that it is time for a new server, however what to get?

A blade server, rack mount, floor model, physical or virtual perhaps cloud?

How about one that is fully configured and accessorized to meet your specific environments needs?

There are several considerations involving what type of server or computer is needed to meet your specific needs or application requirements. Options include price, packaging, vendor preferences, blade center, freestanding, 1U rack mount, virtual and cloud support, with or without storage and networking, performance as well as power and cooling among other considerations.

Here is a link (PDF version here, may require registration) to an article that I put together to help determine your needs as well as consider various options for your next server.

Hope you find the information useful!

Nuff said for now

Cheers gs

Greg Schulz – Author The Green and Virtual Data Center (CRC), Resilient Storage Networks (Elsevier) and coming summer 2011 Cloud and Virtual Data Storage Networking (CRC) at https://storageio.com/books
twitter @storageio

Posted on

From bits to bytes: Decoding Encoding

With networking, care should be taken to understand if a given speed or performance capacity is being specified in bits or bytes as well as in base 2 (binary) or base 10 (decimal).

Another consideration and potential point of confusion are line rates (GBaud) and link speed which can vary based on encoding and low level frame or packet size. For example 1GbE along with 1, 2, 4 and 8Gb Fibre Channel along with Serial Attached SCSI (SAS) use an 8b/10b encoding scheme. This means that at the lowest physical layer 8bits of data are placed into 10bits for transmission with 2 bits being for data integrity.

With an 8Gb link using 8b/10b encoding, 2 out of every 10 bits are overhead. To determine the actual data throughput for bandwidth, or, number of IOPS, frames or packets per second is a function of the link speed, encoding and baud rate. For example, 1Gb FC has a 1.0625 Gb per second speed which is multiple by the current generation so 8Gb FC or 8GFC would be 8 x 1.0625 = 8.5Gb per second.

Remember to factor in that encoding overhead (e.g. 8 of 10 bits are for data with 8b/10b) and usable bandwidth on the 8GFC link is about 6.8Gb per second or about 850Mbytes (6.8Gb / 8 bits) per second. 10GbE uses 64b/66b encoding which means that for every 64 bits of data, only 2 bits are used for data integrity checks thus less overhead.

What do all of this bits and bytes have to do with clouds and virtual data storage network?

Quite a bit when you consider what we have talked about the need to support more information processing, moving as well as storing in a denser footprint.

In order to support higher densities faster servers, storage and networks are not enough and require various approaches to reducing the data footprint impact.

What this means is for fast networks to be effective they also have to have lower overhead to avoid moving more extra data in the same amount of time instead using that capacity for productive work and data.

PCIe leverages multiple serial unidirectional point to point links, known as lanes, compared to traditional PCI that used a parallel bus based design. With traditional PCI, the bus width varied from 32 to 64 bits while with PCIe, the number of lanes combined with PCIe version and signaling rate determines performance. PCIe interfaces can have one, two, four, eight, sixteen or thirty two lanes for data movement depending on card or adapter format and form factor.  For example, PCI and PCIx performance can be up to 528 MByte per second with 64 bit 66 MHz signaling rate.

 

PCIe Gen 1

PCIe Gen 2

PCIe Gen 3

Giga transfers per second

2.5

5

8

Encoding scheme

8b/10b

8b/10b

128b/130b

Data rate per lane per second

250MB

500MB

1GB

x32 lanes

8GB

16GBs

32GB

Table 1: PCIe generation comparisons

Table 1 shows performance characteristics of PCIe various generations. With PCIe Gen 3, the effective performance essentially doubles however the actual underlying transfer speed does not double as it has in the past. Instead the improved performance is a combination of about 60 percent link speed and 40 percent efficiency improvements by switching from an 8b/10b to 128b/130b encoding scheme among other optimizations.

Serial interface

Encoding

PCIe Gen 1

8b/10b

PCIe Gen 2

8b/10b

PCIe Gen 3

128b/120b

Ethernet 1Gb

8b/10b

Ethernet 10Gb

64b/66b

Fibre Channel 1/2/4/8 Gb

8b/10b

SAS 6Gb

8b/10b

Table 2: Common encoding

Bringing this all together is that in order to support cloud and virtual computing environments, data networks need to become faster as well as more efficient otherwise you will be paying for more overhead per second vs. productive work being done. For example, with 64b/66b encoding on a 10GbE or FCoE link, 96.96% of the overall bandwidth or about 9.7Gb per second are available for useful work.

By comparison if an 8b/10b encoding were used, the result would be only 80% of available bandwidth for useful data movement. For environments or applications this means better throughput or bandwidth while for applications that require lower response time or latency it means more IOPS, frames or packets per second.

The above is an example of where a small change such as the encoding scheme can have large benefit when applied to high volume or large environments.

Learn more in The Green and Virtual Data Center (CRC), Resilient Storage Networks (Elsevier) and coming summer 2011 Cloud and Virtual Data Storage Networking (CRC) at https://storageio.com/books

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

Winter 2011 Server and StorageIO News Letter

StorageIO News Letter Image
Winter 2011 Newsletter

 Welcome to the Winter 2011 edition of the Server and StorageIO Group (StorageIO) newsletter. This follows the Fall 2011 edition.

You can access this news letter via various social media venues (some are shown below) in addition to StorageIO web sites and subscriptions. Click on the following links to view the Winter 2011 edition as an HTML or PDF or, to go to the newsletter page to view previous editions.

Follow via Goggle Feedburner here or via email subscription here.

You can also subscribe to the news letter by simply sending an email to newsletter@storageio.com

Enjoy this edition of the StorageIO newsletter, let me know your comments and feedback.

Cheers gs

Nuff said for now

Cheers gs

Greg Schulz – Author The Green and Virtual Data Center (CRC), Resilient Storage Networks (Elsevier) and coming summer 2011 Cloud and Virtual Data Storage Networking (CRC)
twitter @storageio

Posted on

What have I been doing this winter?

Its been almost a month since my last post and want to say hello and let you know what I have been doing.

What I have been doing is:

  • Accumulating a long list of ideas for upcoming blog post, article, tips, webinars and other content.
  • Recording some podcasts, web casts doing interviews and commentary along with a few articles here and there.
  • Working with some new venues where if all comes together you should be seeing material or commentary appearing soon.
  • Filling some dates for the 2011 out and about events and activities page.
  • Doing research in several different areas as well as working with clients on various project activities, many of which that are NDA.
  • Getting some recently finished content ready to appear on the main web site as well as in the blog and other venues.
  • Attending vendor events and briefing sessions on solutions some of which are yet to be announced.
  • Enjoying the cold and snowy winter as best as can be (see some videos here) while trying to avoid cold and flue season.

In addition to the above, I have been trying to stay very focused on is getting my new book which is titled Cloud and Virtual Data Storage Networking (CRC) wrapped up for a summer 2011 release. This is my third solo book project that is in addition to co writing or contributing to several other book projects.

Cloud and Virtual Data Storage Networking

Im doing the project the old fashioned way which means writing it myself as opposed to using ghost writers along with a traditional publishing house (CRC, same as my last book) all of which takes a bit more time. For anyone who has done a project like this you know what is involved. For those who have not it includes research, writing, editing, working with editors and copyeditors, subject matter experts doing initial reviews, illustrations and page layouts, markups, more edits and proofs. Then there are the general project management activities along with marketing and rollout plans, companion presentation material working with the publisher and others.

Anyway, hope you are all doing well, look forward to sharing more with you soon, now it is time to get back to work…

Nuff said for now

Cheers gs

Greg Schulz – Author The Green and Virtual Data Center (CRC), Resilient Storage Networks (Elsevier) and coming summer 2011 Cloud and Virtual Data Storage Networking (CRC)
twitter @storageio

Posted on

Are you on the StorageIO IT Data Infrastructure industry links page?

Hey IT data infrastructure vendors, VARs or service providers, are you on the Server and StorageIO IT industry interesting links page?

Dont worry, its free and no obligation!

There are no hidden charges or fees, you will not be obligated to pay a fee or subscribe to a service, or be called or contacted via a sales or account manager person to buy something. Nor will you be required to sign up for a annual or short term retainer, make a donation, honorarium, endowment, contribution, subsidy, renumerate or sponsor in any other manner directly or via indirect means including second, third, fourth or by way of other virtual means or physical means. This also means via other organizations, venues, institutes, associations, communities, events or causes. (Btw, that is some industry humor some will get however to others that feel it is poking fun of their lively hoods, too bad!)

Your contact information will not be sold, bartered, traded, borrowed or abused being kept confidential nor will you be called or bothered (contact me if somebody does reach out to you). However you may get an occasional Server and StorageIO newsletter sent to you via email (privacy and disclosure statement can be found here).

There is however one small caveat and that is no spamming and direct submissions on yours or your companies behalf. If you are a public relations firm feel free to submit on behalf of your own organization, however have your clients submit on their own (or use their identity when doing so on their own behalf).

Why do I make this links page and list available for free to those who read it, as well as to those who are on it?

Simple, I use it myself to keep a list of companies, firms or organizations that are involved with data infrastructures (servers, storage, I/O and networking, hardware, software, services) that I have come across and worth keeping track of that I also feel worth sharing with others.

Of course, if you feel compelled, you can always contact Server and StorageIO to discuss other services or simply buy one of my books including Resilient Storage Networks: Designing Flexible Scalable Data Infrastructures (Elsevier), The Green and Virtual Data Center (CRC) and coming summer 2011 Cloud and Virtual Data Storage Networking (CRC) at Amazon or one of the other many fine global venues.

 

Still interested, all you need to do is the following:

No SPAM submission please

Please do not submit via web or blog page unless you want your contact information known to others.

Send an email to links at storageio dot com that includes the following:

1. Your company name
2. Your company URL
3. Your company contact person (you or someone else) including:
Name
Title or position
Phone or Skype
Email
Optional twitter

4. Brief 40 character or less description of what you do, or solution categories (tip, avoid superlatives, see links page for ideas)

5. Optionally indicate to DND (Do Not Disturb) you with email newsletters, coverage or mentions.

Again, please, No Spam!

Its that simple.

Now its up to you to decide if you want to be included or not.

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

What records will EMC break in NYC January 18, 2011?

What records will EMC break in NYC January 18, 2011?

In case you have not seen or heard, EMC is doing an event next week in New York City (NYC) at the AXA Equitable Center winter weather snow storm clouds permitting (and adequate tools or technologies to deal with the snow removal), that has a theme around breaking records. If you have yet to see any of the advertisements, blogs, tweets, facebook, friendfeed, twitter, yourtube or other mediums messages, here (and here and here) are a few links to learn more as well as register to view the event.

Click on the above image to see more

There is already speculation along with IT industry wiki leaks of what will be announced or talked about next week that you can google or find at some different venues.

The theme of the event is breaking records.

What might we hear?

In addition to the advisor, author, blogger and consultant hats that I wear, Im also in the EMCs analysts relations program and as such under NDA, consequently, what the actual announcement will be next week, no comment for now. BTW, I also wear other hats including one from Boeing even though I often fly on Airbus products as well.

If its not Boeing Im not going, except I do also fly Airbus, Embrear and Bombardiar products
Other hats I wear

However, how about some fun as to what might be covered at next weeks event with getting into a wiki leak situation?

  • A no brainier would be product (hardware, software, services) related as it is mid January and if you have been in the industry for more than a year or two, you might recall that EMC tends to a mid winter launch around this time of year along with sometimes an early summer refresh. Guess what time of the year it is.
  • Im guessing lots of superlatives, perhaps at a record breaking pace (e.g. revolutionary first, explosive growth, exponential explosive growth, perfect storm among others that could be candidates for the Storagebrain wall of fame or shame)
  • Maybe we will even hear that EMC has set a new record of number of members in Chads army aka the vspecialists focused on vSphere related topics along with a growing (quietly) number of Microsoft HyperV specialist.
  • That EMC has a record number of twitter tweeps engaged in conversations (or debates) with different audiences, collectives, communities, competitors, customers, individuals, organizations, partners or venues among others.
  • Possibly that their involvement in the CDP (Carbon Disclosure Project) has resulted in enough savings to offset the impact of hosting the event making it carbon and environment neutral. After all, we already know that EMC has been in the CDP as in Continual or Constant Data Protection as well as Complete or Comprehensive Data Protection along with Cloud Data Protection not to mention Common Sense Data Protection (CSDP) for sometime now.
  • Perhaps something around the number of acquisitions, patents, products, platforms, products and partners they have amassed recently.
  • For investors, wishful thinking that they will be moving their stock into record territories.
  • Im also guessing we will hear or see a record number of tweets, posts, videos and stories.
  • To be fair and balanced, Im also expecting a record number of counter tweets, counter posts, counter videos and counter stories coming out of the event.

Some records I would like to see EMC break however Im not going to hold my breath at least for next week include:

  • Announcement of upping the game in performance benchmarking battles with record setting or breaking various SPC benchmark results submitted on their own (instead of via a competitor or here) in different categories of block storage devices along with entries for SSD based, clustered and virtualized. Of course we would expect to hear how those benchmarks and workload simulations really do not matter which would be fine, at least they would have broken some records.
  • Announcement of having shipped more hard disk drives (HDD) than anyone else in conjunction with shipping more storage than anyone else. Despite being continually declared dead (its not) and SSD gaining traction, EMC would have a record breaking leg to stand on if the qualify amount of storage shipped as external or shared or networked (SAN or NAS) as opposed to collective (e.g. HP with servers and storage among others).
  • Announcement that they are buying Cisco, or Cisco is buying them, or that they and Cisco are buying Microsoft and Oracle.
  • Announcement of being proud of the record setting season of the Patriots, devastated to losing a close and questionable game to the NY Jets, wishing them well in the 2010 NFL Playoffs (Im just sayin…).
  • Announcement of being the first vendor and solution provider to establish SaaS, PaaS, IaaS, DaaS and many other XaaS offerings via their out of this world new moon base (plans underway for Mars as part of a federated offering).
  • Announcement that Fenway park will be rebranded as the house that EMC built (or rebuilt).

Disclosure: I will be in NYC on Tuesday the 18th as one of EMCs many guests that they have picked up airfare and lodging, thanks to Len Devanna and the EMC social media crew for reaching out and extending the invitation.

Other guests of the event will include analysts, advisors, authors, bloggers, beat writers, consultants, columnist, customers, editors, media, paparazzi, partners, press, protesters (hopefully polite ones), publishers, pundits, twitter tweepps and writers among others.

I wonder if there will also be a record number of disclosures made by others attending the event as guests of EMC?

More after (or maybe during) the event.

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

As the Hard Disk Drive HDD continues to spin

As the Hard Disk Drive HDD continues to spin

server storage data infrastructure i/o iop hdd ssd trends

Updated 2/10/2018

Despite having been repeatedly declared dead at the hands of some new emerging technology over the past several decades, the Hard Disk Drive (HDD) continues to spin and evolve as it moves towards its 60th birthday.

More recently HDDs have been declared dead due to flash SSD that according to some predictions, should have caused the HDD to be extinct by now.

Meanwhile, having not yet died in addition to having qualified for its AARP membership a few years ago, the HDD continues to evolve in capacity, smaller form factor, performance, reliability, density along with cost improvements.

Back in 2006 I did an article titled Happy 50th, hard drive, but will you make it to 60?

IMHO it is safe to say that the HDD will be around for at least a few more years if not another decade (or more).

This is not to say that the HDD has outlived its usefulness or that there are not other tiered storage mediums to do specific jobs or tasks better (there are).

Instead, the HDD continues to evolve and is complimented by flash SSD in a way that HDDs are complimenting magnetic tape (another declared dead technology) each finding new roles to support more data being stored for longer periods of time.

After all, there is no such thing as a data or information recession!

What the importance of this is about technology tiering and resource alignment, matching the applicable technology to the task at hand.

Technology tiering (Servers, storage, networking, snow removal) is about aligning the applicable resource that is best suited to a particular need in a cost as well as productive manner. The HDD remains a viable tiered storage medium that continues to evolve while taking on new roles coexisting with SSD and tape along with cloud resources. These and other technologies have their place which ideally is finding or expanding into new markets instead of simply trying to cannibalize each other for market share.

Here is a link to a good story by Lucas Mearian on the history or evolution of the hard disk drive (HDD) including how a 1TB device that costs about $60 today would have cost about a trillion dollars back in the 1950s. FWIW, IMHO the 1 trillion dollars is low and should be more around 2 to 5 trillion for the one TByte if you apply common costs for management, people, care and feeding, power, cooling, backup, BC, DR and other functions.

Where To Learn More

View additional NAS, NVMe, SSD, NVM, SCM, Data Infrastructure and HDD related topics via the following links.

Additional learning experiences along with common questions (and answers), as well as tips can be found in Software Defined Data Infrastructure Essentials book.

Software Defined Data Infrastructure Essentials Book SDDC

What This All Means

IMHO, it is safe to say that the HDD is here to stay for at least a few more years (if not decades) or at least until someone decides to try a new creative marketing approach by declaring it dead (again).

Ok, nuff said, for now.

Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2017 (vSAN and vCloud). Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO. All Rights Reserved. StorageIO is a registered Trade Mark (TM) of Server StorageIO.