I/O Networking Archives

June 7, 2012November 26, 2023

NetApp on rough ground, or a diamond in the rough?

Storage I/O Industry Trends and Perspectives

In case you missed it, NetApp announced their most recent quarterly earnings a few weeks ago which in themselves were not bad. However what some of their competition jumping up and down for joy while others are scratching their heads is the forward-looking guidance given by NetApp.

NetApp can be seen as being on rough ground given their forward-looking guidance over the next year which could be seen as either very conservative, or an admission that they are not growing as fast as some of their competitors are challenging them.

Reading between the lines, looking at various financial and other resources in addition to factoring in technology items, there is more to NetApp then meets the eye and current stock price or product portfolio.

For example, NetApp is sitting on over $4 Billion USD cash that they could use for an acquisition, buying back stock, launching a major sales and marketing initiative to expand into new or adjacent markets or other activities. Speaking of acquisitions, NetApp has done some in the past including Spinnaker, which is now integrated with Ontap (e.g. clustering), Topio, Decru (security encryption) and Onaro (DCIM and IRM management software tools). More recently, NetApp has acquired Bycast (archiving and policy storage management software), Akorri (capacity management and DCIM and IRM software) and Engenio. NetApp is also maintaining good margins via both direct, channel and OEM activities while launching new products such as the channel and SMB focused FAS 2220.

Its arguable depending upon your point of view (or who you for or are a fan of) if NetApp has all the right product pieces now, in the works, or on their radar for acquisitions. Assuming that NetApp has the pieces, they also need to move beyond selling simply what is on the truck or what is safe and comfortable or perhaps easy to sell. This is not to say that NetApp is not being effective in selling what they have and pushing the envelope, however keeping in mind who their main competitor is, the old sales saying of being able to sell ice to an Eskimo comes to mind.

In the case of NetApp, when the competition makes an issue about scalibility or performance of their flagship storage systems FAS and Ontap storage software, change the playing field leveraging all the tools in their portfolio. NetApp like EMC before them is figuring out how to sell via different channels or venues their complete portfolio with a mix of direct, channel and OEM. After all, it seems like only yesterday that EMC was trying to figure out where and when to sell CLARiiON (e.g. now VNX) as opposed to avoiding competing with the Symmetrix (aka now the VMAX) not to mention expanding from a direct to channel and OEM model. Perhaps NetApp can continue to figure out how to leverage more effectively the Engenio E series for big bandwidth beyond their current OEMs. NetApp can also leverage their existing partners who have embraced Bycast (aka StorageGrid) while finding new ones.

The reality is that NetApp is being challenged by EMC who is moving down market into some of NetApp’s traditional accounts along with in the scale-out NAS and big data sectors. This is where NetApp can leverage their technical capabilities including people combined with some effective sales and marketing execution to change the playing field vs. responding to EMC and others.

NetApp has many of the pieces, parts, products, people, programs and partners so now how can they leverage those to expand both their revenues, as well as support margin to grow the business, unless they are looking to be acquired.

I still subscribe that NetApp and EMC are two similar companies on parallel tracks offset by time, by about a decade or decade and a half.

Storage I/O Industry Trends and Perspectives

Thus, IMHO NetApp is a diamond in the rough, granted I am guessing EMC and some others do not see it that way. However, there was a time when EMC was seen as a diamond in the rough while others discounted that notion, particularly an Itty Bitty Manufacturing company from New York who is now focusing on services among other things.

Keep in mind however, diamonds can also be lost or taken as well as there can be fake gems.

Here are some related links:
Unified storage systems showdown: NetApp FAS vs. EMC VNX
Two companies on parallel tracks moving like trains offset by time: EMC and NetApp
NetApp buying LSI’s Engenio Storage Business Unit

Ok, nuff said for now

Cheers Gs

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

twitter @storageio

June 4, 2012January 23, 2019

Why FC and FCoE vendors get beat up over bandwidth?

Storage I/O Industry Trends and Perspectives

Have you noticed how Fibre Channel (FC) and FC over Ethernet (FCoE) switch and adapter vendors and their followers focus around bandwidth vs. response time, latency or other performance activity? For example, 8Gb FC (e.g. 8GFC), or 10Gb as opposed to latency and response time, or IOPS and other activity indicators.

When you look at your own environment, or that of a customers or prospects or hear of a conversation involving storage networks, is the focus on bandwidth, or lack of it, or perhaps throughput being a non-issue? For example, a customer says why go to 16GFC when they are barely using 8Gb with their current FC environment.

This is not a new phenomenon and is something I saw when working for a storage-networking vendor who had SAN, MAN and WAN solutions (E.g. INRANGE). Those with networking backgrounds tended to focus on bandwidth when discussing storage networks while those with storage, server or applications background also look at latency or IO completion time (response time), queuing, message size, IOPs or frames and packets per second. Thus there are different storage and networking metrics that matter that are also discussed further in my first book Resilient Storage Networks: Designing Flexible Scalable Data Infrastructures.

When I hear a storage networking vendor talk about their latest 16GFC based product I like to ask them what is the biggest benefit vs. 8GFC and not surprisingly, the usual response is like twice the bandwidth. When I ask them about what that means in terms of more IOPS in a given amount of time, or reduced IO completion time, lower latency, sometimes I often get the response along the lines of Yeah, that too, however it has twice the bandwidth.

Ok, I get it, yes, bandwidth is important for some applications, however so too are activity measured in IOPS, transactions, packets, frames, pages, sequences and exchanges among other units of measure along with response time and latency (e.g. different storage and networking metrics that matter).

What many storage networking vendors actually get, however they don’t talk about it for various reasons, perhaps because they are not be asked about it, or engaged in the conversation is that there is an improvement in response time in going from such as 8GFC to 16GFC. Likewise, there can be improvements in response time in addition to the more commonly discussed bandwidth.

If you are a storage networking switch, adapter or other component vendor, var or channel partner expand your conversation to include activity and response time as part of your value proposition. Likewise, if you are a customer, ask your technology providers to expand on the conversation of how new technologies help in areas other than bandwidth.

Ok, nuff said for now

Cheers Gs

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

twitter @storageio

June 4, 2012December 24, 2020

How much SSD do you need vs. want?

Storage I/O Industry Trends and Perspectives

I have been getting asked by IT customers, VAR’s and even vendors how much solid state device (SSD) storage is needed or should be installed to address IO performance needs to which my standard answer is it depends.

I also am also being asked if there is rule of thumb (RUT) of how much SSD you should have either in terms of the number of devices or a percentage; IMHO, the answer is it depends. Sure, there are different RUTs floating around based on different environments, applications, workloads however are they applicable to your needs.

What I would recommend is instead of focusing on percentages, RUTs, or other SWAG estimate’s or PIROMA calculations, look at your current environment and decide where the activity or issues are. If you know how many fast hard disk drives (HDD) are needed to get to a certain performance level and amount of used capacity that is a good starting point.

If you do not have that information, use tools from your server, storage or third-party provider to gain insight into your activity to help size SSD. Also if you have a database environment and are not familiar with the tools, talk with your DBA’s to have them run some reports that show performance information the two of you can discuss to zero in hot spots or opportunity for SSD.

Keep in mind when looking at SSD what is that you are trying to address by installing SSD. For example, is there a specific or known performance bottleneck resulting in poor response time or latency or is there a general problem or perceived opportunity?

Storage I/O Industry Trends and Perspectives

Is there a lack of bandwidth for large data transfers or is there a constraint on how many IO operations per second (e.g. IOPS) or transaction or activity that can be done in a given amount of time. In other words the more you know where or what the bottleneck is including if you can trace it back to a single file, object, database, database table or other item the closer you are to answering how much SSD you will need.

As an example if using third-party tools or those provided by SSD vendors or via other sources you decide that your IO bottleneck are database transaction logs and system paging files, then having enough SSD space capacity to fit those in part of the solution. However, what happens when you remove the first set of bottlenecks, what new ones will appear and will you have enough space capacity on your SSD to accommodate the next in line hot spot?

Keep in mind that you may want more SSD however what can you get budget approval to buy now without having more proof and a business case. Get some extra SSD space capacity to use for what you are confident can address other bottlenecks, or, enable new capabilities.

On other hand if you can only afford enough SSD to get started, make sure you also protect it. If you decide that two SSD devices (PCIe cache or target cards, drives or appliances) will take care of your performance and capacity needs, make sure to keep availability in mind. This means having extra SSD devices for RAID 1 mirroring, replication or other form of data protection and availability. Keep in mind that while traditional hard disk drive (HDD) storage is often gauged on cost per capacity, or dollar per GByte or dollar per TByte, with SSD measure its value on cost to performance. For example, how many IOPS, or response time improvement or bandwidth are obtained to meet your specific needs per dollar spent.

Ok, nuff said for now

Cheers Gs

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

twitter @storageio

May 20, 2012November 26, 2023

Spring (May) 2012 StorageIO news letter

Spring (May) 2012 News letter

Welcome to the Spring (May) 2012 edition of the Server and StorageIO Group (StorageIO) news letter. This follows the Fall (December) 2011 edition.

You can get access to 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 May 2012 edition as an HTML or PDF or, to go to the news letter page to view previous editions.

You can subscribe to the news letter by clicking here.

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

Nuff said for now

Cheers
Gs

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

May 20, 2012January 23, 2019

Various cloud, virtualization, server, storage I/O poll’s

The following are a collection of on-going industry trends and perspectives poll’s pertaining to server, storage, IO, networking, cloud, virtualization, data protection (backup, archive, BC and DR) among other related themes and topics.

In addition to those listed below, check out the comments section where additional poll’s are added over time.

Storage I/O Industry Trends and Perspectives

Here is a link to a poll as a follow-up to a recent blog post Are large storage arrays dead at the hands of SSD? (also check these posts pertaining to storage arrays and SSD and flash SSD’s emerging role).

Poll: Are large storage arrays day’s numbered?

Poll: What’s your take on magnetic tape storage?

Poll: What do you think of IT clouds?

Poll: Who is responsible for cloud storage data loss?

Poll: What are the most popular Zombie technologies?

Storage I/O Industry Trends and Perspectives

Poll: What’s your take on OVA and other alliances?

Poll: Where is most common form or concern of vendor lockin?

Poll: Who is responsible for, or preventing vendor lockin?

Poll: Is vendor lockin a good or bad thing?

Poll: Is IBM V7000 relevant?

Storage I/O Industry Trends and Perspectives

Poll: What is your take on EMC and NetApp on similar tracks or paths?

Poll: What’s your take on RAID still being relevant?

Poll: What do you see as barriers to converged networks?

Poll: Who are you?

Poll: What is your preferred converged network?

Storage I/O Industry Trends and Perspectives

Poll: What is your converged network status?

Poll: Are converged networks in your future?

Poll: What do you think were top 2009 technologies, events or vendors?

Poll: What technologies, events, products or vendors did not live up to 2009 predictions?

Storage I/O Industry Trends and Perspectives

Poll: What do you think of IT clouds?

Poll: What is your take on the new FTC blogger disclosure guidelines?

Poll: Is RAID dead?

Poll: When will you deploy Windows 7? Note: I upgraded all my systems to Windows 7 during summer of 2011

Poll: EMC and Cisco VCE, what does it mean?

Poll: Is IBM XIV still relevant?

Storage I/O Industry Trends and Perspectives

Note: Feel free to share, use and make reference to the above poll’s and their results however please remember to attribute the source.

Ok, nuff said for now

Cheers Gs

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

twitter @storageio

May 17, 2012November 26, 2023

Are large storage arrays dead at the hands of SSD?

Storage I/O trends

An industry trends and perspective.

Are large storage arrays dead at the hands of SSD? Short answer NO not yet.
There is still a place for traditional storage arrays or appliances particular those with extensive features, functionality and reliability availability serviceability (RAS). In other words, there is still a place for large (and small) storage arrays or appliances including those with SSDs.

Is there a place for newer flash SSD storage systems, appliances and architectures? Yes
Similar to how there is a place for traditional midrange storage arrays or appliances have found their roles vs. traditional higher end so-called enterprise arrays. Think as an example EMC CLARiiON/VNX or HP EVA/P6000 or HDS AMS/HUS or NetApp FAS or IBM DS5000 or IBM V7000 among others vs. EMC Symmetrix/DMX/VMAX or HP P10000/3Par or HDS VSP/USP or IBM DS8000. In addition to traditional enterprise or high-end storage systems and midrange also known as modular, there are also specialized appliances or targets such as for backup/restore and archiving. Also do not forget the IO performance SSD appliances like those from TMS among others that have been around for a while.

Is the role of large storage systems changing or evolving? Yes
Given their scale and ability to do large amounts of work in a dense footprint, for some the role of these systems is still mission critical tier 1 application and data support. For other environments, their role continues to evolve being used for high-density tier 2 bulk or even near-line storage for on-line access at scale.

Storage I/O trends

Does this mean there is completion between the old and new systems? Yes
In some circumstances as we have seen already with SSD solutions. Some will place as competing or replacements while others as complementing. For example in the PCIe flash SSD card segment EMC VFCache is positioned is complementing Dell, EMC, HDS, HP, IBM, NetApp, Oracle or others storage vs. FusionIO who positions as a replacement for the above and others. Another scenario is how some SSD vendors have and continue to position their all-flash SSD arrays using either drives or PCIe cards to complement and coexist with other storage systems in an environment (e.g. data center level tiering) vs. as a replacement. Also keep in mind SSD solutions that also support a mix of flash devices and traditional HDDs for capacity and cost savings or cloud access in the same solution.

Does this mean that the industry has adopted all SSD appliances as the state of art?
Avoid confusing industry adoption or talk with industry and customer deployment. They are similar, however one is focused on what the industry talks about or discusses as state of art or the future while the other is what customers are doing. Certainly some of the new flash SSD appliance and storage startups such as Solidfire, Nexgen, Violin, Whiptail or veteran TMS among others have promising futures, some of which may actually be in play with the current SSD market shakeout and consolidation.

Does that mean everybody is going SSD?
SSD customer adoption and deployment continues to grow, however so too does the deployment of high-capacity HDDs.

Storage I/O trends

Do SSDs need HDDs, do HDDs need SSDs? Yes
Granted there are environments where needs can be addressed by all of one or the other. However at least near term, there is a very strong market for tiering and mix of SSD, some fast HDDs and lots of high-capacity HDDs to meet various needs including performance, availability, capacity, energy and economics. After all, there is no such thing, as a data or information recession yet budgets are tight or being reduced. Likewise, people and data are living longer.

What does this mean?
If there, were no such thing as a data recession and budgets a non-issue, perhaps everything could move to all flash SSD storage systems. However, we also know that people and data are living longer along with changing data life-cycle patterns. There is also the need for performance to close the traditional data center IO performance to space capacity gap and bottlenecks as well as store and keep data longer.

There will continue to be a need for a mix of high-capacity and high performance. More IO will continue to gravitate towards the IO appliances, however more data will settle in for longer-term retention and continued access as data life-cycle continue to evolve. Watch for more SSD and cache in the large systems, along with higher density SAS-NL (SAS Near Line e.g. high capacity) type drives appearing in those systems.

If you like new shiny new toys or technology (SNTs) to buy, sell or talk about, there will be plenty of those to continue industry adoption while for those who are focused on industry deployment, there will be a mix of new, and continued evolution for implementation.

Ok, nuff said for now

Cheers Gs

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

twitter @storageio

May 3, 2012December 24, 2020

Is SSD dead? No, however some vendors might be

Storage I/O trends

Is SSD dead? No, however some vendors might be

In a recent conversation with Dave Raffo about the nand flash solid state disk (SSD) market, we talked about industry trends, perspectives and where the market is now as well as headed. One of my comments is, has been and will remain that the industry has still not reached anywhere near full potential for deployment of SSD for enterprise, SMB and other data storage needs. Granted, there is broad adoption in terms of discussion or conversation and plenty of early adopters.

SSD and in particular nand flash is anything but dead, in fact in the big broad picture of things, it is still very early in the game. Sure, for those who cover and crave the newest, latest and greatest technology to talk about, nand flash SSD might seem old, yesterday news, long in the tooth and time for something else. However, for those who are focused on deployment vs. adoption such as customers, in general, nand flash SSD in its many packaging options has still not yet reached its full potential.

Despite the hype, fanfare from CEOs or their evangelist along with loyal followers of startups that help drive industry adoption (e.g. what is talked about), there is still lots of upside growth in the customer drive industry deployment (actually buying, installing and using) for nand flash SSD.

What about broad customer deployments?

Sure, there are the marquee customer success stories that you need a high-capacity SAS or SATA drive to hold the YouTube videos, slide decks, press releases for.

However, have we truly, reached broad customer deployment or broad industry adoption?

Hence, I see more startups coming into the market space, and some exiting on their own, via mergers and acquisition or other means.

Will we see a feeding frenzy or IPO craze as with earlier hype cycles of technologies, IMHO there will be some companies that get the big deal, some will survive as new players running as a business vs. running to be acquired or IPO. Others will survive by evolving into something else while others will join the where are they now list.

If you are a SSD startup, CEO, CxO, or marketer, their PR, evangelist or loyal follower do not worry as the SSD market and even nand flash is far from being dead. On the other hand, if you think that it has hit its full stride, you are missing either the bigger picture, or too busy patting yourselves on the back for a job well done. There is much more opportunity out there and not even all the low hanging fruit has been picked yet.

Check out the conversation with Dave Raffo along with comments from others here.

Related links on storage IO metrics and SSD performance
What is the best kind of IO? The one you do not have to do
Is SSD dead? No, however some vendors might be
Storage and IO metrics that matter
IO IO it is off to Storage and IO metrics we go
SSD and Storage System Performance
Speaking of speeding up business with SSD storage
Are Hard Disk Drives (HDD’s) getting too big?
Has SSD put Hard Disk Drives (HDD’s) On Endangered Species List?
Why SSD based arrays and storage appliances can be a good idea (Part I)
IT and storage economics 101, supply and demand
Researchers and marketers dont agree on future of nand flash SSD
EMC VFCache respinning SSD and intelligent caching (Part I)
SSD options for Virtual (and Physical) Environments Part I: Spinning up to speed on SSD
SSD options for Virtual (and Physical) Environments Part II: The call to duty, SSD endurance
SSD options for Virtual (and Physical) Environments Part III: What type of SSD is best for you?
SSD options for Virtual (and Physical) Environments Part IV: What type of SSD is best for your needs

Ok, nuff said for now

Cheers Gs

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

twitter @storageio

May 3, 2012November 26, 2023

More storage and IO metrics that matter

It is great to see more conversations and coverage around storage metrics that matter beyond simply focusing on cost per GByte or TByte (e.g. space capacity). Likewise, it is also good to see conversations expanding beyond data footprint reduction (DFR) from a space capacity savings or reduction ratio to also address data movement and transfer rates. Also good to see is increase in discussion around input/output operations per section (IOPs) tying into conversations from virtualization, VDI, cloud to Sold State Devices (SSD).

Other storage and IO metrics that matter include latency or response time, which is how fast work is done, or time spent. Latency also ties to IOPS in that as more work arrives to be done (IOPS) of various size, random or sequential, reads or writes, queue depths are an indicator of how well work is flowing. Another storage and IO metric that matters is availability because without it, performance or capacity can be affected. Likewise, without performance, availability can be affected.

Needless to say that I am just scratching the surface here with storage and IO metrics that matter for physical, virtual and cloud environments from servers to networks to storage.

Here is a link to a post I did called IO, IO, it is off to storage and IO metrics we go that ties in themes of performance measurements and solid-state disk (SSD) among others. Also check out this piece about why VASA (VMware storage analysis metrics) is important to have your VMware CASA along with Windows boot storage and IO performance for VDI and traditional planning purposes.

Check out this post about metrics and measurements that matter along with this conversation about IOPs, capacity, bandwidth and purchasing discussion topics.

Ok, nuff said for now

Cheers Gs

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

twitter @storageio

May 3, 2012November 26, 2023

What is the best kind of IO? The one you do not have to do

Updated 2/10/2018

What is the best kind of IO? If no IO (input/output) operation is the best IO, than the second best IO is the one that can be done as close to the application and processor with best locality of reference. Then the third best IO is the one that can be done in less time, or at least cost or impact to the requesting application which means moving further down the memory and storage stack (figure 1).

Figure 1 memory and storage hierarchy

The problem with IO is that they are basic operation to get data into and out of a computer or processor so they are required; however, they also have an impact on performance, response or wait time (latency). IO require CPU or processor time and memory to set up and then process the results as well as IO and networking resources to move data to their destination or retrieve from where stored. While IOs cannot be eliminated, their impact can be greatly improved or optimized by doing fewer of them via caching, grouped reads or writes (pre-fetch, write behind) among other techniques and technologies.

Think of it this way, instead of going on multiple errands, sometimes you can group multiple destinations together making for a shorter, more efficient trip; however, that optimization may also take longer. Hence sometimes it makes sense to go on a couple of quick, short low latency trips vs. one single larger one that takes half a day however accomplishes many things. Of course, how far you have to go on those trips (e.g. locality) makes a difference of how many you can do in a given amount of time.

What is locality of reference?

Locality of reference refers to how close (e.g location) data exists for where it is needed (being referenced) for use. For example, the best locality of reference in a computer would be registers in the processor core, then level 1 (L1), level 2 (L2) or level 3 (L3) onboard cache, followed by dynamic random access memory (DRAM). Then would come memory also known as storage on PCIe cards such as nand flash solid state device (SSD) or accessible via an adapter on a direct attached storage (DAS), SAN or NAS device. In the case of a PCIe nand flash SSD card, even though physically the nand flash SSD is closer to the processor, there is still the overhead of traversing the PCIe bus and associated drivers. To help offset that impact, PCIe cards use DRAM as cache or buffers for data along with Meta or control information to further optimize and improve locality of reference. In other words, help with cache hits, cache use and cache effectiveness vs. simply boosting cache utilization.

Where To Learn More

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

Can we get a side of context with them IOPS and other storage metrics?
WHEN AND WHERE TO USE NAND FLASH SSD FOR VIRTUAL SERVERS
Revisiting RAID storage remains relevant and resources
NVMe overview and primer – Part I
Part 1 of HDD for content servers series Trends and Content Application Servers
Part 2 of HDD for content servers series Content application server decisions and testing plans
Part 3 of HDD for content servers series Test hardware and software configuration
Part 4 of HDD for content servers series Large file I/O processing
Part 5 of HDD for content servers series Small file I/O processing
Part 6 of HDD for content servers series General I/O processing
Part 7 of HDD for content servers series How HDD continue to evolve over different generations and wrap up
As the platters spin, HDD’s for cloud, virtual and traditional storage environments
How many IOPS can a HDD, HHDD or SSD do?
Hard Disk Drives (HDD) for Virtual Environments
Server and Storage I/O performance and benchmarking tools
Server storage I/O performance benchmark workload scripts Part I and Part II
How to test your HDD, SSD or all flash array (AFA) storage fundamentals
What is the best server storage I/O workload benchmark? It depends
I/O, I/O how well do you know about good or bad server and storage I/Os?
Big Files Lots of Little File Processing Benchmarking with Vdbench
Part II – NVMe overview and primer (Different Configurations)
Part III – NVMe overview and primer (Need for Performance Speed)
Part IV – NVMe overview and primer (Where and How to use NVMe)
Part V – NVMe overview and primer (Where to learn more, what this all means)
PCIe Server I/O Fundamentals
If NVMe is the answer, what are the questions?
NVMe Wont Replace Flash By Itself
Via Computerweekly – NVMe discussion: PCIe card vs U.2 and M.2
Intel and Micron unveil new 3D XPoint Non Volatie Memory (NVM) for servers and storage
Part II – Intel and Micron new 3D XPoint server and storage NVM
Part III – 3D XPoint new server storage memory from Intel and Micron
Server storage I/O benchmark tools, workload scripts and examples (Part I) and (Part II)
Data Infrastructure Overview, Its Whats Inside of Data Centers
All You Need To Know about Remote Office/Branch Office Data Protection Backup (free webinar with registration)
Software Defined, Converged Infrastructure (CI), Hyper-Converged Infrastructure (HCI) resources
The SSD Place (SSD, NVM, PM, SCM, Flash, NVMe, 3D XPoint, MRAM and related topics)
The NVMe Place (NVMe related topics, trends, tools, technologies, tip resources)
Data Protection Diaries (Archive, Backup/Restore, BC, BR, DR, HA, RAID/EC/LRC, Replication, Security)
Software Defined Data Infrastructure Essentials (CRC Press 2017) including SDDC, Cloud, Container and more
Various Data Infrastructure related events, webinars and other activities
www.objectstoragecenter.com and Software Defined, Cloud, Bulk and Object Storage Fundamentals
Server Storage I/O Network PCIe Fundamentals

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

What This All Means

What can you do the cut the impact of IO

Establish baseline performance and availability metrics for comparison
Realize that IOs are a fact of IT virtual, physical and cloud life
Understand what is a bad IO along with its impact
Identify why an IO is bad, expensive or causing an impact
Find and fix the problem, either with software, application or database changes
Throw more software caching tools, hyper visors or hardware at the problem
Hardware includes faster processors with more DRAM and fast internal busses
Leveraging local PCIe flash SSD cards for caching or as targets
Utilize storage systems or appliances that have intelligent caching and storage optimization capabilities (performance, availability, capacity).
Compare changes and improvements to baseline, quantify improvement

Ok, nuff said, for now.

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.

April 29, 2012December 31, 2022

More Storage IO momentus HHDD and SSD moments part II

This follows the first of a two-part series on my latest experiences with Hybrid Hard Disk Drives (HHDD’s) and Solid State Devices (SSD’s). In my ongoing last momentus moment post I discussed what I have done with HHDD’s and setting the stage for expanded SSD use. I have the newer HHDD’s, e.g. Seagate Momentus XT II 750GB (8GB SLC nand flash) installed and have since bought another from Amazon as well as having some of the older 500GB (4GB SLC nand flash) in various systems. Those are all functioning great, however still waiting and looking forward to the rumored firmware enhancements to boost write capabilities.

This brings me up to the latest momentus moment which now includes SSD’s.

Well its two years later and I now have a 256GB (usable capacity is lower) Samsung SSD that I bought from Amazon.com and installed in one of my laptops and just as when I made the first switch to HHDD’s, I also have a backup copy/clone to fall back to in case of emergency.

Was it worth the wait? Yes, particularly using the HHDD’s to bridge the gap and enable some productivity gain which more than paid for them based on some different projects. I’m already seeing productivity improvements that will make future upgrades more easy to justify (to myself).

I deviated from my strategy a bit and installed the SSD about six months earlier than I was planning to do so because of a physical barrier. That physical barrier was my new traveling laptop only accepts 7mm height 2.5 inch small form factor devices and the 750GB HHDD that I had planned on installing was 2.5mm to thick which pushed up the SSD installation.

What will become of the 750GB HHDD? Its being redeployed to help speed up file serving, backups and other functions.

Will I replace the HHDD’s in my other workstations and laptops now with SSD’s? Across the board no, not yet, however there is one other system that is a prime candidate to maybe upgrade in a month or two (maybe less).

Will I stick with the Samsung SSD’s or look at other options? I’m keeping my options open and using this as a gauge to test and compare other options in a real world working environment as opposed to a lab bench test simulation. In other words, taking the next step past the lab test and product reviews, gaining comfort and confidence and then trying out with real use activity.

What will happen in the future as I install more SSD’s and have surplus HHDD’s? Redeployed them of course into file or NAS servers, backup targets that in turn will replace HDD’s that will either get retired, or redeployed to replace older, smaller capacity, higher cost to handle HDD’s used for offsite protection.

I tried using the software that came with the SSD to do the cloning and should have known better, however wanted to see what the latest version of ghost was like (it was a waste of time to be polite). Instead I used Seagate Discwizard (aka Acronis) which requires at least one Seagate product (source or target) for cloning.

Cloning from the Seagate HHDD that have been previously cloned from the Hitachi HDD that came with the laptop, was a none issue. However, I wanted to see what would happen if I attached the Samsung SSD to the Seagate Goflex cable and clone directly from the Hitachi HDD, it worked. Hence another reason to have some of the Seagate Goflex cables (USB and eSATA) like the ones I bought at Amazon.com around in your toolbox.

While I do not have concrete empirical numbers to share, cloning from a HDD to a SSD is shall we say fast, however, what’s really fun to watch is cloning from a HHDD to a SSD using an eSata (GoFlex) connector adapter. The reason I say that it is fun is that you don’t have to sit and wait for hours, it’s not minutes to move 100s of GBs, however you can very much see the progress bar move at a good pace.

Also, I put the HHDD on an eSata port and try that out as a backup or data dump target if you have the need for speed, capacity and cost effectiveness, yes its fast, has lots of capacity and so forth. Now if Seagate and Synology or EMC Iomega would get their acts together and add support for the HHDD’s in those different unified SMB and SOHO NAS solutions, that would be way cool.

Will I be racing to put SSD’s in my other laptops or workstations soon? Probably not as there are things in the works and working their way into and through the market place that I wanted to wait for, and thus will wait for now, that is unless a more interesting opportunity pops up.

Related links on SDD, HHDD and HDD
More Storage IO momentus HHDD and SSD moments part I
More Storage IO momentus HHDD and SSD moments part II
IO IO it is off to Storage and IO metrics we go
New Seagate Momentus XT Hybrid drive (SSD and HDD)
Other Momentus moments posts here here, here, here and here
SSD and Storage System Performance
Speaking of speeding up business with SSD storage
Are Hard Disk Drives (HDD’s) getting too big?
Has SSD put Hard Disk Drives (HDD’s) On Endangered Species List?
Why SSD based arrays and storage appliances can be a good idea (Part I)
Why SSD based arrays and storage appliances can be a good idea (Part II)
IT and storage economics 101, supply and demand
Researchers and marketers dont agree on future of nand flash SSD
EMC VFCache respinning SSD and intelligent caching (Part I)
EMC VFCache respinning SSD and intelligent caching (Part II)
SSD options for Virtual (and Physical) Environments Part I: Spinning up to speed on SSD
SSD options for Virtual (and Physical) Environments Part II: The call to duty, SSD endurance
SSD options for Virtual (and Physical) Environments Part III: What type of SSD is best for you?
SSD options for Virtual (and Physical) Environments Part IV: What type of SSD is best for your needs

Ok, nuff said for now.

Cheers Gs

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

twitter @storageio

April 29, 2012December 31, 2022

More Storage IO momentus HHDD and SSD moments part I

This is the first of a two part series on my latest experiences with HHDD and SSD’s

About two years ago I wanted to start installing solid state devices (SSD’s) into my workstations and laptops. Like many others, I found the expensive price for the limited capacity gains of the then generation SSD’s did not make for a good business decision based on my needs. Don’t get me wrong, I have been a huge fan of SSD for decades as an IT user, vendor, analysts, consultant and consumer and still am. In fact I have some SSD’s used for different purposes as well as many Hard Disk Drives (HDD) and Hybrid Hard Disk Drives (HHDD’s). Almost two years ago when I first tested the HHDD’s, I did an first post in this ongoing series and this two-part post is part of that string of experiences observed evolving from HDD’s to HHDD’s to SSD’s

Image courtesy of Seagate.com

As a refresher, HHDD’s like the Seagate Momentus XT combine a traditional 7,200 RPM 2.5 inch 500GB or 750GB HDD with an integrated single level cell (SLC) nand flash SSD within the actual device. The SSD in the HHDD’s is part of the HDD’s controller complementing the existing DRAM buffer by adding 4GB (500GB models) or 8GB (750GB models) of fast nand flash SSD cache. This means that no external special controller, adapter, data movement or migration software are required to get the performance boost over a traditional HDD and the capacity above a SSD at an affordable cost. In other words, the HHDD’s bridge the gap between those who need large capacity and some performance increases, without having to spend a lot on a lower capacity SSD.

However based on my needs or business requirements two years ago I found the justification to get all the extra performance of SSD not quite there when. Back two years ago my thinking was that it would be about two maybe three years before the right point for a mix of performance, availability (or reliability e.g. duty cycles), capacity and economics aligned.

Note that this was based on my specific needs and requirements as opposed to my wants or wishes (I wanted SSD back then, however my budget needed to go elsewhere). My requirements and performance needs are probably not the same as yours or others might be. I also wanted to see the incremental technology, product and integration improvements ranging from duty cycle or program/erase cycles (P/E) with newer firmware and flash translation layers (FTLs) among other things. Particularly with multilevel cell (MLC) or enhanced multilevel cell (eMLC) which helps bring the cost down while boosting the capacity, I’m seeing enough to have more confidence in those devices. Note that for the past couple of years I have used single level cell (SLC) nand flash SSD technology in my HHDD’s, the same SSD flash technology that has been found in enterprise class storage.

While I wanted SSD’s two years ago in my laptops and workstations to improve productivity which involves a lot of content creation in addition to consumption, however as mentioned above, there were barriers. So instead of sitting on the sidelines, waiting for SSD’s to either become lower cost, or more capacity for a given cost, or wishing somebody would send me some free stuff (that may or may not have worked), I took a different route. That route was to try the HHDD’s such as Seagate Momentus XT.

Disclosure: Seagate sent me my first HHDD for first testing and verifications before buying several more from Amazon.com and installing them in all laptops, workstations and a server (not all servers have the HHDD’s, or at least yet).

The main reason I went with the HHDD’s two years ago and continue to use them today is to bridge the gap and gain some benefit vs. waiting and wishing and talking about what SSD’s would enable me to do in the future while missing out on productivity enhancements.

The HHDD’s also appealed to me in that my laptops are space constrained for putting two drives and playing the hybrid configuration game of installing both a small SSD and HDD and migrating data back and forth. Sure I could do that for in the office or carry an extra external device around however been there, done that in the past and want to move away from those types of models where possible.

Ok, nuff said for now, lets resume this discussion in part II.

Cheers Gs

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

twitter @storageio

April 13, 2012March 7, 2022

IT Optimization, efficiency, convergence and cloud conversations from SNW

Recently I did a presentation titled backup, restore, BC, DR and archiving (hmm, I think I know of a book with the same title) at the spring 2012 SNW in Dallas. My presentation was on the first morning of the session as I needed to be in Boston to record a video the following Tuesday morning, thus I missed out on the storm clouds and tornadoes that rolled in the next day.

While I was at SNW, had the honor of being a guest on Calvin Zito (aka @HPStorageguy) pod cast that can be found on his Around the Storage Block Blog or by clicking here.

Cloud and Virtual Data Storage Networking Conversation

Check out our conversations about clouds, related topics and more from a practical perspective cutting through the hype and fud.

Oh, if you are interested in Cloud and Virtual Data Storage Networking, click here to learn more about the book, or backup, restore, BC, DR and archiving to find various backup, restore, BC, DR and archiving, and here to see some upcoming events, activities and venues both in the U.S. and in Europe.

Ok, nuff said for now.

Cheers
Gs

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

twitter @storageio

April 12, 2012November 26, 2023

Part IV: PureSystems, something old, something new, something from big blue

This is the fourth in a five-part series around the recent IBM PureSystems announcements. You can view the earlier post here, and the next post here.

So what does this mean for IBM Business Partners (BPs) and ISVs?
What could very well differentiate IBM PureSystems from those of other competitors is to take what their partner NetApp has done with FlexPods combing third-party applications from Microsoft and SAP among others and take it to the next level. Similar to what helped make EMC Centera a success (or at least sell a lot of them) was inclusion and leveraging third-party ISVs and BPs to add value. Compared to other vendors with object based or content accessible storage (CAS) or online archive platforms that focused on the technology feature, function speeds and feeds, EMC realized the key was getting ISVs to support so that BPs and their own direct sales force could sell the solution.

With PureSystems, IBM is revisiting what they have done in the past which if offer bundled solutions providing incentives for ISVs to support and BPs to sell the IBM brand solution. EMC took an early step with including VMware with their Vblock combing server, storage, networking and software with NetApp taking the next step adding SAP, Microsoft and other applications. Dell, HP, Oracle and others are following suit so it only makes sense that IBM returns to its roots leveraging its DNA to reach out and get their ISVs who are now, have been in the past, or are new opportunities to be on board.

IBM is throwing its resources including their innovation centers for training around the world where business partners can get the knowledge and technical support they need. In other words, workshops or seminars on how to sell deploy and setting up of these systems, application and customer testing or proof of concepts and things one would expect out of IBM for such an initiative. In addition to technology and sales training along with marketing support, IBM is making their financing capabilities available to help customers as well as offer incentives to their business partners to simplify acquisitions.

So what buzzword bingo topics and themes did IBM address with this announcement:
IBM did a fantastic job in terms of knocking the ball out of the park with this announcement pertaining buzzword bingo and deserves an atta boy or atta girl!

So what about how this will affect sales of Bladecenters or other systems?
If all IBM and their BPs do are, encroach on existing systems sales to circle the wagons and protect the installed base, which would be one thing. However if IBM and their BPs can use the new packaging and model approach to reestablish customers and partnerships, or open and expand into new adjacent markets, then the net differences should be more Bladecenters (excuse me, PureFlex) being sold.

So what will this cost?
IBM is citing entry PureSystems Express models starting at around $100,000 USD for base systems with others starting at around $200,000 and $300,000 expandable into larger configurations and budgets. Note that like airlines that advertise a low airfare and then you get to pay extra for peanuts, drinks, extra bag space, changes to reservations and so forth, look at these and related systems not just for the first starting price, also for expansion costs over different time periods. Contact IBM, your BP or ISV to find out what one of these systems will do for and cost you.

So what about VARs and IBM business partners (BPs)?
This could be a boon for those BPs and ISVs that had previously sold their software solutions bundled with IBM hardware platforms who were being challenged by other converged solution stacks or were being forced to unbundled. This will also allow those business partners to compete on par with other converged solutions or continue selling the pieces of what they are familiar with however under a new umbrellas. Of course, pricing will be a focus and concern for some who will want to see what added value exists vs. acquiring the various components. This also means that IBM will have to make incentives available for their partners to make a living while also allowing their customers to afford solutions and maximize their return on innovation (the new ROI) and enablement.

Click here to view the next post in this series, ok nuff said for now.

Here are some links to learn more:
Various IBM Redbooks and related content
The blame game: Does cloud storage result in data loss?
What do you need when its time to buy a new server?
2012 industry trends perspectives and commentary (predictions)
Convergence: People, Processes, Policies and Products
Buzzword Bingo and Acronym Update V2.011
The function of XaaS(X) Pick a letter
Hard product vs. soft product
Buzzword Bingo and Acronym Update V2.011
Part I: PureSystems, something old, something new, something from big blue
Part II: PureSystems, something old, something new, something from big blue
Part III: PureSystems, something old, something new, something from big blue
Part IV: PureSystems, something old, something new, something from big blue
Part V: PureSystems, something old, something new, something from big blue
Cloud and Virtual Data Storage Networking

Cheers
Gs

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

twitter @storageio

April 12, 2012October 18, 2024

Part V: PureSystems, something old, something new, something from big blue

This is the fifth in a five-part series around the recent IBM PureSystems announcements. You can view the earlier post here.

So what about vendor or technology lock in?
So who is responsible for vendor or technology lock in? When I was working in IT organizations, (e.g. what vendors call the customer) the thinking was vendors are responsible for lock in. Later when I worked for different vendors (manufactures and VARs) the thinking was lock in is what was caused by the competition. More recently I’m of the mind set that vendor lock in is a shared responsibility issue and topic. I’m sure some marketing wiz or sales type will be happy to explain the subtle differences of how their solution does not cause lock in.

Vendor lock in can be a shared responsibility. Generally speaking, lock in, stickiness and account control are essentially the same, or at least strive to get similar results. For example, vendor lock in too some has a negative stigma. However vendor stickiness may be a new term, perhaps even sounding cool thus it is not a concern. Remember the Mary Poppins song a spoon full of sugar makes the medicine go down? In other words, sometimes changing and using a different term such as sticky vs. vendor lock in helps make the situation taste better.

So what should you do?
Take a closer look if you are considering converged infrastructures, cloud or data centers in a box, turnkey application or information services deployment platforms. Likewise, if you are looking at specific technologies such as those from Cisco UCS, Dell vStart, EMC Vblock (or via VCE), HP, NetApp FlexPod or Oracle (ExaLogic, ExaData, etc) among others, also check out the IBM PureSystems (Flex and PureApplication). Compare and contrast these converged solutions with your traditional procurement and deployment modes including cost of acquiring hardware, software, ongoing maintenance or service fees along with value or benefit of bundled tools. There may be a higher cost for converged systems in some scenarios, however compare on the value and benefit derived vs. doing the integration yourself.

Compare and contrast how converged solutions enable, however also consider what constraints exists in terms of flexibility to reconfigure in the future or make other changes. For example as part of integration, does a solution take a lowest common denominator approach to software and firmware revisions for compatibility that may lag behind what you can apply to standalone components. Also, compare and contrast various reference architectures with different solution bundles or packages.

Most importantly compare and evaluate the solutions on their ability to meet and exceed your base requirements while adding value and enabling return on innovation while also being cost-effective. Do not be scared of these bundled solutions; however do your homework to make informed decisions including overcoming any concerns of lock in or future costs and fees. While these types of solutions are cool or interesting from a technology perspective and can streamline acquisition and deployment, make sure that there is a business benefit that can be addressed as well as enablement of new capabilities.

So what does this all mean?
Congratulations to IBM with their PureSystems for leveraging their DNA and roots bundling what had been unbundled before cloud and stacks were popular and trendy. IBM has done a good job of talking vision and strategy along lines of converged and dynamic, elastic and smart, clouds and other themes for past couple of years while selling the pieces as parts of solutions or ala carte or packaged by their ISVs and business partners.

What will be interesting to see is if bladecenter customers shift to buying PureFlex, which should be an immediate boost to give proof points of adoption, while essentially up selling what was previously available. However, more interesting will be to see if net overall new customers and footprints are sold as opposed to simply selling a newer and enhanced version of previous components.

In other words will IBM be able to keep up their focus and execution where they have sold the previous available components, while also holding onto current ISV and BP footprint sales and perhaps enabling those partners to recapture some hardware and solution sales that had been unbundled (e.g. ISV software sold separate of IBM platforms) and move into new adjacent markets.

Cheers
Gs

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

twitter @storageio

Here are some links to learn more:
Various IBM Redbooks and related content
The blame game: Does cloud storage result in data loss?
What do you need when its time to buy a new server?
2012 industry trends perspectives and commentary (predictions)
Convergence: People, Processes, Policies and Products
Buzzword Bingo and Acronym Update V2.011
The function of XaaS(X) – Pick a letter
Hard product vs. soft product
Buzzword Bingo and Acronym Update V2.011
Part I: PureSystems, something old, something new, something from big blue
Part II: PureSystems, something old, something new, something from big blue
Part III: PureSystems, something old, something new, something from big blue
Part IV: PureSystems, something old, something new, something from big blue
Part V: PureSystems, something old, something new, something from big blue
Cloud and Virtual Data Storage Networking

Ok, so what is next, lets see how this unfolds for IBM and their partners.

Nuff said for now.

Cheers
Gs

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

twitter @storageio

Share this:

Share this:

Share this:

Share this:

Share this:

Share this:

Share this:

Share this:

What is the best kind of IO? The one you do not have to do

Where To Learn More

What This All Means

Share this:

Share this:

Share this:

Share this:

Share this:

Share this: