Tag: HDD

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.

Posted on

Another StorageIO Hybrid Momentus Moment

Its been a few months since my last post (read it here) about Hybrid Hard Disk Drive (HHDD) such as the Seagate Momentus XT that I have been using.

The Momentus XT HHDD I have been using is a 500GB 7,200RPM 2.5 inch SATA Hard Disk Drive (HDD) with 4GB of embedded FLASH (aka SSD) and 32MB of DRAM memory for buffering hence the hybrid name.

I have been using the XT HHDD mainly for transferring large multi GByte size files between computers and for doing some disk to disk (D2D) backups while becoming more comfortable with it. While not as fast as my 64GB all flash SSD, the XT HHDD is as fast as my 7,200RPM 160GB Momentus HDD and in some cases faster on burst reads or writes. The notion of having a 500GB HDD that was affordable to support D2D was attractive however the ability to get some performance boost now and then via the embedded 4GB FLASH opens many different possibilities particularly when combined with compression.

Recently I switched the role of the Momentus XT HHDD from that of being a utility drive to becoming the main disk in one of my laptops. Despite many forums or bulletin boards touting issues or problems with the Seagate Momentus XT causing system hangs or Windows Blue Screen of Death (BSoD), I continued on with the next phase of testing.

Making the switch to XT HHDD as a primary disk

I took a few precaution including eating some of my own dog food that I routinely talk about. For example, I made sure that the Lenovo T61 where the Momentus XT was going to be installed was backed up. In addition, I synced my traveling laptop so that it was the primary so that I could continue working during the conversion not to mention having an extra copy in addition to normal on and offsite backups.

Ok, lets get back to the conversion or migration from a regular HDD to the HHDD.

Once I knew I had a good backup, I used the Seagate Discwizard (e.g. Acronis based) tool for imaging the existing T61 HDD to the Momentus XT HHDD. Using Discwizard (you could use other tools as well) I configured it to initialize the HHDD which was attached via a Seagate Goflex USB to SATA cable kit as well as image or copy the contents of the T61 HDD partitions to the Momentus XT. During the several hours it took to copy and create a new bootable disk image on the HHDD I continued working on my travel or standby laptop.

After the image copy was completed and verified, it was time to reboot and see how Windows (XP SP3) liked the HHDD which all seemed to be normal. There were some parts of the boot that seemed a bit faster, however not 100 percent conclusive. The next step was to shutdown the laptop and physically swap the old internal HDD with the HHDD and reboot. The subsequent boot did seem faster and programs accessing large files also seemed to run a bit faster.

Keep in mind that the HHDD is still a spinning 7,200RPM disk drive so comparisons to a full time SSD would be apples to oranges as would the cost capacity difference between those devices. However, for what I wanted to see and use, the limited 4GB of flash does seem to provide a performance boost and if I needed full time super fast performance, I could buy a larger capacity SSD and install it. Im going to hold off on buying any more larger capacity flash SSD for the time being however.

Do I see HHDD appearing in SMB, SME or enterprise storage systems anytime soon? Probably not, at least not in primary storage systems. However perhaps in some D2D backup, archive or dedupe and VTL devices or other appliances.

Momentus XT Speed Bumps

Now, to be fair, there have been some bumps in the road!

The first couple of days were smooth sailing other than hearing the mystery chirp the HHDD makes a couple of times a day. Low and behold after a couple of days, just as many forums had indicated, a mystery system hang occurred (and no, not like Windows might normally do so for those Microsoft cynics). Other than the inconvenience of a reboot, no data was lost as files being updated were saved or had been backed up not to mention after the reboot, everything was intact anyway. So far just an inconvenience or so I thought.

Almost 24 hours later, same thing except this time I got to see the BSoD which candidly, I very rarely see despite hearing stories from others. Ok, this was annoying, however as long as I did not lose any data, other than lost time from a reboot, lets chalk this up to a learning experience and see where it goes. Now guess what, about 12 hours later, once again, the system froze up and this time I was in the middle of a document edit. This time I did lose about 8 minutes of typing data that had not been auto saved (I have since changed my auto save from 10 minutes to 5 minutes).

With this BSoD incident, I took some notes and using the X61s, started checking some web sites and verified the BIOS firmware on the T61 which was up to date. However I noticed that the Seagate Momentus XT HHDD was at firmware 22 while there was a 23 version available. Reading through some web sites and forums, I was on the fence on trying firmware 23 given that it appears a newer firmware version for the HHDD is in the works. Deciding to forge forward with the experiment, after all, no real data loss had occurred, and I still had the X61s not to mention the original T61 HDD to fall back to worse case.

Going to the Seagate web site, I downloaded the firmware 23 install kit and ran it to their instructions which was a breeze and then did the reboot.

It has not been quite a week yet, however knocking on wood, while I keep expecting to see one, no BSoD or system freezes have occurred. However having said that and knocking on wood, Im also making sure things are backed up protected and ready if needed. Likewise, if I start to see a rash of BSoD, my plan is to fall back to the original T61 HDD, bring it up to date and use it until a newer HHDD firmware version is available to resume testing.

What is next for my Seagate Momentus XT HHDD?

Im going to wait to see if the BSoD and mystery system hangs disappear as well as for the arrival of the new firmware followed by some more testing. However, when Im confident with it, the next step is to put the XT HHDD into the X61s which is used primarily for travel purpose.

Why wait? Simple, while I can tolerate a reboot or crash or data loss or disruption while in the office given access to copies as well as standby or backup systems to work from, when traveling options are more limited. Sure if there is data loss, I can go to my cloud provider and rapidly recall a file or multiple ones as needed or for critical data, recover from a portable encrypted USB device. Consequently I want more confidence in the XT HHDD before deploying it for travel mode which it is probably safe to do as of now, however I want to see how stable it is in the office before taking it on the road.

What does this all mean?

  • Simple, have a backup of your data and systems
  • Test and verify those backups or standby systems periodically
  • Have a fall back plan for when trying new things
  • Keep productivity in mind, at some point you may have to fall back
  • If something is important enough to protect, have multiple copies
  • Be ready to eat your own dog food or what you talk about
  • Do not be scared, however be prepared, look before you leap

How about you are you using a HHDD yet and if so, what are your experiences? I am curious to hear if anyone has tried using a HHDD in their VMware lab environments yet in place of a regular HDD or before spending a boat load of money for a similar sized SSD.

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 is DFR or Data Footprint Reduction?

What is DFR or Data Footprint Reduction?

What is DFR or Data Footprint Reduction?

Updated 10/9/2018

What is DFR or Data Footprint Reduction?

Data Footprint Reduction (DFR) is a collection of techniques, technologies, tools and best practices that are used to address data growth management challenges. Dedupe is currently the industry darling for DFR particularly in the scope or context of backup or other repetitive data.

However DFR expands the scope of expanding data footprints and their impact to cover primary, secondary along with offline data that ranges from high performance to inactive high capacity.

Consequently the focus of DFR is not just on reduction ratios, its also about meeting time or performance rates and data protection windows.

This means DFR is about using the right tool for the task at hand to effectively meet business needs, and cost objectives while meeting service requirements across all applications.

Examples of DFR technologies include Archiving, Compression, Dedupe, Data Management and Thin Provisioning among others.

Read more about DFR in Part I and Part II of a two part series found here and here.

Where to learn more

Learn more about data footprint reducton (DFR), data footprint overhead and 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

That is all for now, hope you find these ongoing series of current or emerging Industry Trends and Perspectives posts of interest.

Ok, nuff said, for now.

Cheers Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2018. 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.

Posted on

Industry Trends and Perspectives: Tiered Storage, Systems and Mediums

This is part of an ongoing series of short industry trends and perspectives blog posts briefs.

These short posts compliment other longer posts along with traditional industry trends and perspective white papers, research reports, solution brief content found at www.storageio.com/reports.

Two years ago we read about how the magnetic disk drive would be dead in a couple of years at the hand of flash SSD. Guess what, it is a couple of years later and the magnetic disk drive is far from being dead. Granted high performance Fibre Channel disks will continue to be replaced by high performance, small form factor 2.5" SAS drives along with continued adoption of high capacity SAS and SATA devices.

Likewise, SSD or flash drives continue to be deployed, however outside of iPhone, iPod and other consumer or low end devices, nowhere near the projected or perhaps hoped for level. Rest assured the trend Im seeing and hearing from IT customers is that some will continue to look for places to strategically deploy SSD where possible, practical and affordable, there will continue to be a roll for disk and even tape devices on a go forward basis.

Also watch for more coverage and discussion around the emergence of the Hybrid Hard Disk Drive (HHDD) that was discussed about four to five years ago. The HHDD made an appearance and then quietly went away for some time, perhaps more R and D time in the labs while flash SSD garnered the spotlight.

There could be a good opportunity for HHDD technology leveraging the best of both worlds that is continued pricing decreases for disk with larger capacity using smaller yet more affordable amounts of flash in a solution that is transparent to the server or storage controller making for easier integration.

Related and companion material:
Blog: ILM = Has It Losts its Meaning
Blog: SSD and Storage System Performance
Blog: Has SSD put Hard Disk Drives (HDDs) On Endangered Species List
Blog: Optimize Data Storage for Performance and Capacity Efficiency

That is all for now, hope you find this ongoing series of current and emerging Industry Trends and Perspectives interesting.

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 do NAS NASA NASCAR have in common?

What do NAS NASA NASCAR have in common?

server storage I/O data infrastructure trends

Updated 2/10/2018

The other day it dawned on me what do NAS, NASA NASCAR have in common?

Several things in addition to all starting with the letters NAS it turns out.

For example, they all deal with round objects, NAS or Network Attached storage involved with circular spinning disk drives, NASA or National Aeronautical Space Administration besides involved with aircraft that have tires that go round and round, or airplanes circling waiting for landing.

In the case of NASA they are also involved with sending craft or devices to circle other planets or moons and land or crash into them. Sometimes NAS along with other storage systems have disk drives that crash, similar to how NASCAR events see accidents.
NAS

Ceder Lake 3M NASCAR at dirt track - Photo (C) 2008 Karen Schulz all rights reserved

Ceder Lake dirt track 3M NASCAR night (Photo (C) 2008 Karen Schulz)

NASCAR is also involved with vehicles that dont or at least should not fly, however they do go round and round on a track, often paved however sometimes mud or dirt tracks plus high tech exists with computers and various data models, not to mention the NASCAR air force.

In addition to being involved with round objects and activities, all three are also involved in computing, generating, processing, storing and retrieving for analysis of data, not to mention high performance requirements.

NAS based storage can also be relied upon for serving the needs of NASA and NASCAR data and informational needs.

And FWIW, just for fun, look at what you get when you spell NAS, NASA or NASCAR backwards:

RACSAN
ASAN
SAN

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

Not much actually other than to stimulate some thought, discussion as well as perhaps have some fun with technology during the holiday season.

Im sure if I put some more thought to it, more similarities would or will come to mind.

However, for now, thats it for a quick thought, what similarities do you see or know about with NAS, NASA and NASCAR?

Ok, nuf fun for now, time to work on some other posts, content and projects.

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.

Posted on

Has SSD put Hard Disk Drives (HDDs) On Endangered Species List?

Storage I/O trends

Disclosure: I have been a user, vendor, author and analyst covering and a fan (and continue to be) of SSD for over 20 years

I have thought and wanting to post about this for a while, however recently several things popped up including moderating a panel where a vendor representative told the audience that the magnetic hard disk drive (HDD) would be dead in two, at most three years. While there were a few nods from those in the audience, the majority smiled politely, chuckled, looked at their watches or returned to doing email, twitters, texting or simply rolled their eyes in a way like, yeah right, we have heard this before ( ;) ).

Likewise, I have done many events including seminars, keynotes including at a recent CMG event (the performance and capacity planning group that I have been a part of for many years), webcasts and other interactions with IT pros, vendors, vars and media. These interactions have included among other topics, IT optimization, boosting server and storage efficiency, as well as the roll of tiering IT resources to boost efficiency, achieve better productivity while boosting performance in a cost-effective way during touch economic times, in other words, the other green IT!

Then the other day, I received an email from Mary Jander over at Internet Evolution. You may remember Mary from her days over at Byte & Switch. Mary was looking for a point, counter point, perspective and sound bit to a recent blog posting on her site and basically asked if I thought that the high performance HDD would be dead in a couple of years at the cost of FLASH SSD. Having given Mary some sound bits and perspectives which appear in her Article/Blog posting, there has since been a fun and lively discourse in Marys’ Internet Evolution blog comment section which could be seen by some as the pending funeral for high performance HDDs.

There has been a lot of work taking place including by industry trade groups such as the SNIA Solid State Storage Initiative (SSSI) among others, not to mention many claims, discussions, banter and even some trash talk about how the magnetic hard disk drives (HDD) that as a technology is over 50 years old now, is nearing the end of the road and is about to be replaced by FLASH SSD in the next two to three years depending on who you talk with or listen to.

That may very well be the case, however, I have a strong suspicion that while the high performance 3.5" Fibre Channel 15,500 Revolution per minute (15.5K RPM) HDD is nearing the end of the line, I don’t believe that the 2.5" small form factor (SFF) Serial Attached SCSI (SAS) 15.5K (maybe faster in the future?) high performance and larger capacity HDD will have met its demise in the two to three-year timeframe.

The reason I subscribe to this notion is that of a need for balancing performance, availability, capacity, energy to a given power, cooling, floor space and environmental need along with price to meet different tiers of application and data quality of service and service level needs. Simply put, there continues to be a need even with some the new or emerging enhanced intelligence capabilities of storage systems for tiered media. That is tier-0 ultra fast SSD (FLASH or RAM) in a 2.5" form factor with SATA shifting to SAS connectivity, tier-1 fast 2.5" SAS 15.5K large capacity HDDs, tier-2 2.5" SATA and SAS high-capacity, 5.4 to 10K HDDs, or, ultra large capacity SAS and SATA 3.5" HDDs to meet different performance, availability, capacity, energy and economic points.

Why not just use SSD FLASH for all high performance activity, after all it excels in reads correct? Yup, however, take a closer look at write performance which is getting better and better, even with less reliance on intelligent controllers, firmware and RAM as a buffer. However, there is still a need for a balance of Tier-0, Tier-1, Tier-2, Tier-3 etc mediums to balance different requirements and stretch strained IT budgets to do more efficiency.

Maybe I’m stuck in my ways and spend to much time talking with IT professionals including server or storage architects, as well as IT planners, purchasers and others in the trenches and not enough time drinking the cool-aid and believing the evangelists and truth squads ;). However there is certainly no denying that Solid State Devices (SSD) using either RAM or FLASH are back in the spotlight again as SSD has been in the past, this time for many reasons with adoption continuing to grow. I think that its safe to say that some HDDs will fade away like other earlier generations have, such as the 3.5" FC HDD, however other HDDs like the high performance 2.5" SAS HDDs have some time to enjoy before their funeral or wake.

What say you?

BTW, check out this popular (and its Free) StorageIO Industry Trends and Perspectives White Paper Report that looks at various data center performance bottlenecks and how to discuss them to transition towards becoming more efficient. However a warning, you might actually be inclined to jump on the SSD bandwagon.

Oh, and there’s nothing wrong with SSD, after all as I mentioned earlier, I’m a huge fan, however, I’m also a huge fan of spinning HDDs having skipped SSD in my latest computer purchases for fast 7.2K (or faster) HDDs with FLASH for portability (encrypted of course). After all, it’s also about balancing the different tiers of storage mediums to the task at hand, that is, unless you subscribe to the notion that one tool or technique should be used to solve all problems which is fine if that is your cup of tea.

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

Server Storage I/O Network Virtualization Whats Next?

Server Storage I/O Network Virtualization Whats Next?
Server Storage I/O Network Virtualization Whats Next?
Updated 9/28/18

There are many faces and thus functionalities of virtualization beyond the one most commonly discussed which is consolidation or aggregation. Other common forms of virtualization include emulation (which is part of enabling consolidation) which can be in the form of a virtual tape library for storage to bridge new disk technology to old software technology, processes, procedures and skill sets. Other forms of virtualization functionality for life beyond consolidation include abstraction for transparent movement of applications or operating systems on servers, or data on storage to support planned and un-planned maintenance, upgrades, BC/DR and other activities.

So the gist is that there are many forms of virtualization technologies and techniques for servers, storage and even I/O networks to address different issues including life beyond consolidation. However the next wave of consolidation could and should be that of reducing the number of logical images, or, the impact of the multiple operating systems and application images, along with their associated management costs.

This may be easier said than done, however, for those looking to cut costs even further than from what can be realized by reducing physical footprints (e.g. going from 10 to 1 or from 250 to 25 physical servers), there could be upside however it will come at a cost. The cost is like that of reducing data and storage footprint impacts with such as data management and archiving.

Savings can be realized by archiving and deleting data via data management however that is easier said than done given the cost in terms of people time and ability to decide what to archive, even for non-compliance data along with associated business rules and policies to be defined (for automation) along with hardware, software and services (managed services, consulting and/or cloud and SaaS).

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

Ok, nuff said, for now.

Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2018. 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.

Posted on

Industry Trend: Five year HDD (hard disk drive) warranties

Storage I/O trends

I received a note from Seagate the other day (they requested that this be embargoed until today) about changes to their warranty program for their various disk drive products.

Now I get a ton of updates, press releases, briefing notes and other news from vendors, resellers, industry trade groups and public relations folks among others every day (and thats in addition to the spam), all of which help to fill up my hard disk drives and backups stored on removable hard disk drives faster than the hard disk drive on my HD-DVR fills up from HD programming.

However this note from Seagate stood out and I want to share with you my industry trends and perspective. That is, this IMHO signals the realities of how long different storage technologies are used before being discarded (e.g. lifecycle or useful life) as much as what the reliability and endurance of the products is which I explain a bit further down in this post.

So here’s what Seagate is doing and draw your own conclusion and see my additional perspectives and opinions below.

Seagate Warranty Change

Overview
Seagate’s leadership in product quality and reliability has given it an edge in offering customers better value when they need it. Seagate’s current 5-year limited warranty will remain in place for consumer retail products as well as for enterprise-class hard drives, and we will now provide our distributor customers with a 3-year limited warranty for all other hard drives. Based on our data, we know that 95% of all returns take place during the first three years, so by offering a 3-year warranty (which Seagate believes is more in line with the rest of the industry), we can make other aspects of our customer support and warranty programs more attractive with negligible impact to customer product return needs. The 3-year limited warranty on notebook, desktop and consumer electronics bare drives offers new advantages and enhancements to the business proposition for our channel customers while improving cost efficiencies for Seagate. We expect little, if any change for consumers since hard drives used in computer systems other devices are covered by the individual manufacturer’s warranty.

Warranty at a high level:
3-year warranty – Seagate Desktop, Notebook & Consumer Electronics drives sold to customers
5-year warranty – Seagate enterprise drives and certain Seagate and Maxtor branded retail products (both consumer solutions and HDD retail kits)

Q&A

Q. Does this change effect products sold to OEMs?
A. No, there are no changes to our OEM standard warranties in these classes of products

Q. When does this change go into effect?
A. It will begin January 3, 2009

Q. What about products purchased before Jan. 3, 2009? Will Seagate still honor the warranty in place at time of time of original purchase?
A. Yes, any customers who purchase products prior to Jan. 3 will be covered by the warranty in place at the time of purchase.

Q. Why is this change being made now?
A. We have identified the opportunity to offer our customers warranty terms that we believe are in line with industry standard warranty offerings, and that better align to the requirements of our partners and customers.

Q. You say that by moving to a 3-year warranty you can make other aspects of customer and warranty support more attractive. Can you be more specific?
A. Seagate believes that enhancing the declining credit scale in the second year from 75% to 100% will provide customers better value on returns. This means that if a customer returns a drive in the second year, they are eligible to receive a credit, equal to the drive’s price at the time the drive is returned, applied to their replacement drive.

Q. Why are Enterprise-class hard drives still receiving a 5-year warranty?
A. Seagate believes the standard industry warranty for enterprise-class products is 5 years.

Q. Will customers in other countries receive different warranty periods?
A. Customers located in India, Pakistan, Sri Lanka, and Thailand will continue to receive a 5 year limited warranty for selected products.

Q. Why will customers located in these countries still receive a 5-year warranty?
A. In these markets we have determined that business conditions support offering a 5-year warranty period.

Q. Isn’t this a step backward in terms of demonstrating your confidence in the quality of your products?
A. Absolutely not. Our product quality remains excellent, and, as the worldwide leader in drive storage, Seagate is committed to providing our customers with the most reliable storage solutions available anywhere. We know that 95% of all returns take place during the first three years, so by going to a 3-year warranty (which is more in line with the rest of the industry) we can make other aspects of our customer support and warranty programs more attractive with negligible impact to customer product return needs.

Q. Are there exceptions to the 3-year warranty?
A. If a customer believes there is a competitive business case for an exception, they can present their business case to Seagate for review.

Q. What will happen to the inventory authorized distributors currently have?
A. On-hand inventory located at the sites of Seagate distributors will keep the warranty in place at the time of original purchase. The 3-year warranty will apply to products shipped starting Jan 3rd, 2009.

Q. Does this change affect Seagate and Maxtor retail products?
A. Retail drive products will continue with their current 3 or 5 year limited warranty

So what does this all mean?

IMHO, this signals that Seagate is aligning their warranties for different products to the market realities including the life cycle of the product or solution before replacement for what ever reasons. For example, an enterprise class disk drive deployed in an enterprise class storage system may be deployed for a period of from 3 to 5 years, perhaps initially being deployed as primary storage for a couple of years, then being redeployed in a secondary or hand me down role.

Or, in the case of an archive or secondary near-line role, being used for a longer life cycle than would be the case with more traditional storage. It can also signal that many organizations are acquiring and holding on to in general technologies for longer periods of time to maximize ROI and minimize the occurrence of timely and expensive data movement/migration to support technology replacements.

Certainly in general the technologies are much more reliable than previous generations, capacities are increasing as are availability and capacities while power consumption and footprint also improve, not to mention the continued need for more storage and I/O processing capabilities.

On the flip side, non enterprise storage type solutions for example desktops, laptops or other products tend to have shorter lifecycles and thus make sense to align the warranties with the market economic and buying habits taking place not to mention competitive alignment.

Needless to say, despite reports that the magnetic disk drive is now dead at the hands of FLASH SSD (here and here among others) after over 50 years of service, its safe to say the magnetic disk drive will be around for several more years to come as FLASH based SSD will actually help to keep disk drives around, similar to how disk drives are helping to keep magnetic tape around by taking over tasks and enabling true tiered storage and technology alignment to occur.

Heres a link to Seagates Warranty page for more information.

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

Tape Talk – Changing Role of Tape

Storage I/O trends

Here’s a link to a new article over at Enterprise Storage Forum titled “The Changing Role of Tape” for those of you who still use or care to admit to using magnetic tape as part of your data protection (backup, BC, DR) and data preservation (e.g. archiving and compliance) strategies.

Disk based solutions continue to grow in adoption for data protection, however tape remains relevant taking on different roles, similar to how disk drives are taking on different roles as FLASH and RAM based SSD continue to evolve and grow in terms of customer deployment adoption. Consequently, despite the continued hype that tape is dead, the reality is that tape remains on of if not the most energy-efficient or green storage mediums of in-active, off-line data in a given footprint and cost basis.

Tape is still being used in many environments particularly more so in larger environments with a focus shifting towards supporting ultra-dense large full backups that have been copied from disk to disk based backups as well as for archives.

Disk based data protection particularly with virtual tape libraries (VTLs) that combine data footprint reduction techniques such as compression, de-dupe, replication and migration to tape capabilities continue to gain in popularity as a convenient way to migrate from tape based backups to disk based backup preserving investment in existing people skills, policies, rules and software.

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

Will 6Gb SAS kill Fibre Channel?

Storage I/O trends

With the advent of 6Gb SAS (Serial Attached SCSI) which doubles the speed from earlier 3Gb along with other enhancements including longer cable distances up to 10m, does this mean that Fibre Channel will be threatened? Well, I’m sure some conspiracy theorist or iSCSI die hards might jump up and down and say yes, finally, even though some of the FCoE cheering section has already arranged a funeral or wake for FC even while Converged enhanced Ethernet based Fibre Channel over Ethernet (FCoE) and its complete ecosystem completely evolves.

Needless to say, SAS will be in your future, it may not be as a host server to storage system interconnect, however look for SAS high performance drives to appear sometime in the not so distant future. While over time, Fibre Channel based high performance disk drives can be expected to give way to SAS based disks, similar to how Parralel SCSI or even IBM SSA drives gave way to FC disks, SAS as a server to storage system interconnect will at leat for the forseeable future be more for smaller configurations, direct connect storage for blade centers, two server clusters, extremely cost sensitive environments that do not need or can afford a more expensive iSCSI, NAS let alone an FC or FCoE based solution.

So while larger storage systems over time can be expected to support high performance 3.5″ and 2.5″ SAS disks to replace FC disks, those systems will be accessed via FCoE, FC, iSCSI or NAS while mid-range and entry-level systems as they do today will see a mix of SAS, iSCSI, FC, NAS and in the future, some FCoE as well not to mention some InfiniBand based NAS or SRP for block access.

From an I/O virtualization (IOV) standpoint, keep an eye on whats taking place with the PCI SIG and Single Root IOV and multi-root IOV from a server I/O and I/O virtualization standpoint.

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

Comfort Zones – Stating What Might Be Obvious to Some…

Storage I/O trends

Over the past couple of weeks I have talked with many IT professionals who work in IT data centers of varying size from different locations around the world. A couple of interesting patterns or trends if you prefer I have noticed are that while IT and storage professionals in general see disk based backup as the future and for some instances, a good tool today, there is still very much a comfort factor with magnetic tape.

The most cited reasons for continued use of tape being affordability, low power requirements, portability (assuming media is encrypted and secure) and familiar or comfort and confidence with the technology. A related trend or pattern is that while many IT professionals see the value and benefit of SSD including FLASH and RAM, there is also a concern or lack of confidence in the first so called enterprise class FLASH based SSD technology.

A related trend should hardly be a surprise in that enterprise customers I talk to who cling to tape as a data retention medium (even when using disk based backups) are also the most likely to have an early adopter aversion towards FLASH based enterprise storage. During discussions, what I also hear is that given time SSD including both RAM and enhanced or next generation FLASH will be adopted and deployed along magnetic hard disk drives (HDDs) and that HDDs will be used more in the future for backups and other data protection tasks.

Thus the consensus is that while HDDs have been declared dead by some with the arrival of FLASH and SSD, HDDs have joined the “Zombie” list of technologies declared dead, yet that continue to be produced and bought by customers. Other “Zombie” technologies include the IBM Mainframe, Fibre Channel, Magnetic Tapes, Copper based Ethernet and Printers among others. So with the magnetic HDD being over 50 years old, its safe to assume that magnetic HDD will be around for many more years, especially now that HDDs are on the “Zombie” technology list, a rather esteemed list I might add!

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

Mainframe, CMG, Virtualization, Storage and “Zombie Technologies”

In case you missed the news, IBM today announced a new mainframe the z10, yes, that’s right, the mother of all “Zombie Technologies” (and I say this with all due respect), you know, technologies that are declared dead yet are viable, working and still living thus purchasable. Some other examples of Zombie technologies include magnetic tape which was declared dead at least ten years ago if not longer yet continues to evolve, granted a bit slower and with fewer vendors, yet the technology is still economically viable when paired up with disk to disk based backup as an off-line (read no power required) medium for preserving idle and inactive archive data. Another example of a Zombie technology is the printer as you may recall we were supposed to be completely paperless by now, yeh right.

Then there is Fibre Channel which was declared still born over a decade ago yet shows plenty of signs of life in the form of 8GFC (8Gb Fibre Channel) and emerging FCoE even with iSCSI waging another assault to kill the FC beast. Even the venerable 50 year old magnetic disk drive has been declared a dead technology with the re-emergence of SSD in the form of DRAM and FLASH yet magnetic hard disk drives (HDD) continue to be manufactured and shipped in record numbers making it a member of the Zombie technology club, a club that has some pretty esteemed members and more on the way.

I forget how many decades ago it was now that the IBM mainframe was declared dead and granted we have seen the exodus of Hitachi, Amdahl, NEC and others from the active marketplace developing and selling IBM plug compatible mainframes (PCMs). However the venerable mainframe from IBM like the energizer bunny keeps ticking and finding new roles including leveraging its built-in logical partition (LPAR) capabilities to support virtual machines, something that has been available for at least a few decades to enable being leveraged as a consolidation platform of not only legacy zOS (aka revamped MVS) and zVM (not to be confused with VMware) as well native Linux.

Shifting gears a bit, last week I had the pleasure of key-noting at a local Computer Measurement Group (CMG) event, a group that I have been involved with presenting at their events around the world for over a decade. Last weeks theme at the CMG event was Is Storage and I/O Still Important in a Virtual World? If you are not familiar with the CMG folks and you have an interesting in servers, storage, I/O and networking along with performance, capacity planning and virtualization these are some people to get to know. Granted the organization has its roots back in the mainframe era and thus the organization is a gazillion years old, yet, younger than the mainframe however not by much. Over the past several years with the advent of lower cost hardware and the attitude of hardware is cheap, just throw more hardware at the problem has in part led to the decline of what CMG once was as an organization.

However, given the collective knowledge base and broad background, skills and areas of interest spanning servers, storage, I/O, networking, virtualization, hardware, software, mainframe and open systems among others, given the current focus on addressing IT data center power, cooling, floor space and associated ecological and economic related topics (see www.greendatastorage.com) CMG has an opportunity to revive itself even more so than it has over the past few years. That is, CMG assuming its leaders and members can recognize the opportunity can stand up to take a lead role in tying together the skills and knowledge to implement cross technology domain IT infrastructure resource management including working with facilities personal to insure adequate resources (servers, storage, networking, power, cooling and floor space) are available when and where needed moving forward not to mention help shape and guide the server, storage and networking industry groups and forums on applicable metrics and measurement usage. If you are not familiar with CMG, check them out, it’s a good group with a lot of good subject matter expertise to tap into.

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