EMCworld 2016 EMC Hybrid and Converged Clouds Your Way

EMCworld 2016 EMC Hybrid and Converged Clouds Your Way

server storage I/O trends

This is a quick post looking at a high-level view of today’s EMCworld 2016 announcements.

Following up from yesterdays post covering the set of announcements, today’s theme is around Hybrid, Converged and Clouds your way. In addition to the morning announcements, EMC also yesterday afternoon announced InfoArchive 4.0 and EMC LEAP cloud native content applications for Enterprise Content Management (ECM). However lets focus on today’s announcements with a focus of modernize, transform and automate your date center.

Today’s announcements include:

  • Cloud solution portfolio enhancements with Native Hybrid Cloud (NHC) turnkey developer platform for cloud native application development. NHC editions include those for VMware vSphere, OpenStack and VMware Photo Platform. Read more here.

  • VCE VxRack System 1000 with new Neutrino Nodes which are software defined hyper-converged rack scale solutions to support turnkey cloud (public, private, hybrid) implementations. Read more about VxRack System 1000 with links here.

  • NVMe based DSSD D5 flash SSD system enhancements include ability to stripe two systems together in a single rack to double the IOPs, bandwidth and capacity. Also new is a VCE VxRack system with DSSD. Read more about DSSD D5 enhancements here.

Some Hardware That Gets Software Defined

Rear view of EMC Neutrion node

Rear view of EMC Neutrino node

Where To Learn More

  • Session Streaming For video of keynotes, general sessions, backstage sessions, and EMC TV coverage, click here
  • Social: Follow @EMCWorld,  @EMCCorp, @EMC_News and @EMCStorage, and join conversations with  #EMCWORLD, and like EMC on Facebook
  • Photos: Access event photos via  Flickr and EMC Pulse Blog or visit the special EMC World News microsite here
  • Reflections: Read Core Technologies President, Guy Churchward’s Reflections post on today’s announcements here
  • Visit the EMC Store, the EMC Community Network Site and The Core Blog

What This All Means

For those of you who have installed OpenStack either from scratch, or using one of the appliances, you understand what’s involved with doing so. The point is that for those who are in the business or jobs are based on installing or configuring or software defining the software and cloud configurations, turnkey solutions may not be a fit, or at least yet. On the other hand, if your focus is doing other things and are looking for boosting productivity, then turnkey solutions are a way of fast tracking deployment. Likewise for those who have the need for more speed from bandwidth or IOPs, the DSSD D5 enhancements will help in those environments.

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 2006-2023 Server StorageIO(R) and UnlimitedIO All Rights Reserved

EMCworld 2016 Getting Started on Dell EMC announcements

EMCworld 2016 Getting Started on Dell EMC announcements

server storage I/O trends

It’s the first morning of EMCworld 2016 here in Las Vegas with some items already announced today, and more in the wings. One of the underlying themes and discussions besides what’s new or who’s doing what, is that this is for all practical purpose the last EMCworld with the upcoming Dell acquisition. What’s not clear is will there be a renamed and repackaged Dell/EMCworld?

With current EMC President Jeremy Burton who used to be the Chief Marketing Officer (CMO) at EMC slated to become the CMO across all of Dell, my bet is that there will be some type of new event picking up and moving to a new level of where EMCworld and Dellworld have been. More on the future of EMC and Dell in future posts, however for now, lets see what has unfolded so far today.

Today’s EMCworld theme is modernize the data center which means a mix of hardware, software and services announcements spanning physical, virtual, cloud among others (e.g. how do you want your servers, storage and data infrastructure wrapped). While the themes are still EMC as the Dell acquisition has yet to be completed, however there is a Dell presence, including Michael Dell here in person (more on Dell later).

The first wave of announcements include:

  • Unity All Flash Array (AFA) for small, entry-level environments
  • EMC Enterprise Copy Data Management software tools portfolio
  • ViPR Version 3.0 Controller
  • Virtustream global hyper-scale Storage Cloud for data protection and cloud native object
  • MyService360

  • Datadomain virtual edition and long-term archive

What About The Dell Deal

Michael Dell who is here at EMCworld announced on the main stage that Dell Technologies will be the name of the families of business.

This family of business includes the joint Dell, EMC, VMware, Pivotal, Secureworks, RSA and Virtustream. The Dell client focused business will be called Dell leveraging

that Brand, while the new joint Dell and EMC enterprise business will be called Dell EMC leveraging both of those brands. As a reminder, the Dell servers business unit will be moving into the existing EMC business as part of the enterprise business unit.

Lets move onto the technology announcements from today.

Unity AFA (and Hybrid)

The new Unity all flash array (AFA) is a dual controller storage system optimized for Nonvolatile Memory (NVM) flash SSD, with unified (block and file) access. EMC is positioning Unity as an entry-level AFA starting around $18K USD for a 2U solutions (much capacity that includes is not yet known, more on that in a future post). As well as having a low entry cost, EMC is positioning Unity for a broad, mass market, volume distribution that can be leveraged by their partners, including Dell. More on Unity in future posts. While Unity is new and modern, it comes from the same group who has created the VNXe leveraging that knowledge and skills base.

Note that Unity is positioned for small, mid-sized, remote office branch office (ROBO), departmental and specialized AFA situations, where EMC NVMe based DSSD D5 is positioned for higher-end shared direct attached server flash, while XtremIO and VMAX also positioned for higher-end, higher performance and workload consolidation scenarios.

  • Simple, flexible, easy to use in a 2U packaging that scale up to 80TB of NVM flash SSD storage
  • Scalable up to 3PB of storage for larger expanded configurations
  • Affordable ($18K USD starting price, $10K entry-level hybrid)
  • Modern AFA storage for entry, small, mid-sized, workgroup, departments and specialized environments
  • Unified file, block, and VMware VVOL support for storage access
  • Also available in hybrid, as well as software defined virtual and converged configurations
  • Higher performance (EMC indicates 300,000 IOPs) for given entry-level systems
  • Available in all-flash array, hybrid array, software-defined and converged configurations
  • Native controller based encryption with synchronous and asynchronous replication
  • VMware VASA 2.0, VAAI, VVols and VMware integration
  • Tight integration with EMC Data Protection portfolio tools

Read more about Unity here.

Copy Data Management

Enterprise Copy Data Management (eCDM) spans data copies from data protection including backup, BC, DR as well as for operational, analytics, test, dev, devops among other uses. Another term is Enterprise Copy Data Analytics (eCDA) which includes monitoring and management along with insight, awareness and of course analytics. These new offerings and initiatives tie together various capabilities across storage platforms and software defined storage management. Watch for more activity in and around eCDM and general copy data management. Read more here.

ViPR Controller 3.0

ViPR controller enhancements build on previous announcements, include automation as well as fail over with native replication to a standby ViPR controller. Note that there can actually be two standby controllers that are synchronized asynchronous with software built-in to ViPR. This means that there is no need for RecoverPoint or other products to do the replication of the ViPR controllers. To be clear, this is for high availability of the ViPR controllers themselves and not a replacement for HA or replication of upper layer applications, storage servers or underlying storage services. Also note that ViPR is available via open source (CoprHD via Github here). Read more here.

MyService360

MyService360 is a cloud based dashboard and data infrastructure monitoring management platform. Read more here.

Virtustream Storage Cloud

Viutustream cloud services and software tools compliments EMC (and others) storage systems as back-end for cool, cold or other bulk data storage needs. Focus is to sell primary storage to customers, then leverage back-end public cloud services for backup, archive, copy data management and other applications. This also means that the Virtustream storage cloud is not just for data protection such as archiving, backup, BC, DR it’s also for other big fast data including cloud and object native applications. Does this mean Virtustream is an alternative to other cloud and object storage services such as AWS S3, Google GCS among others? Yup. Read more here.

Where To Learn More

  • Session Streaming For video of keynotes, general sessions, backstage sessions, and EMC TV coverage, click here
  • Social: Follow @EMCWorld,  @EMCCorp, @EMC_News and @EMCStorage, and join conversations with  #EMCWORLD, and like EMC on Facebook
  • Photos: Access event photos via  Flickr and EMC Pulse Blog or visit the special EMC World News microsite here
  • Reflections: Read Core Technologies President, Guy Churchward’s Reflections post on today’s announcements here
  • Visit the EMC Store, the EMC Community Network Site and The Core Blog

What This All Means

With the announcement of Unity and impending Dell deal, some of you might (or should) have a Dejavu moment of over a decade or so ago when Dell and EMC entered into OEM agreement around the then Clariion mid range storage arrays (e.g. predecessors of VNX and VNXe). Unity is being designed as a high performance, easy to use, flexible, scalable, cost-effective storage solutions for a broad high-volume sales and distribution channel market.

What does Unity mean for EMC VNX and VNXe as well as XtremIO? Unity will position near where the VNXe has been positioned, along with some of the competing solutions from Dell among others. There might be some overlap with other EMC solutions, however if executed properly, Unity should open up some new markets, perhaps at the hands of some of the newer popular startups that only offer AFA vs. hybrids. Likewise I would expect Unity to appear in future converged solutions such as those via the EMC Converged business unit (e.g. VCE).

Even with the upcoming Dell acquisition and integration, EMC continues to evolve and innovate in many areas.

Watch for more announcements later today and throughout the week

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 2006-2023 Server StorageIO(R) and UnlimitedIO All Rights Reserved

Ubuntu 16.04 LTS (aka Xenial Xerus) What’s In The Bits and Bytes?

Ubuntu 16.04 LTS (aka Xenial Xerus) What’s In The Bits and Bytes?

server storage I/O trends

Ubuntu 16.04 LTS (aka Xenial Xerus) was recently released (you can get the bits or software download here). Ubuntu is available in various distributions including as a server, workstation or desktop among others that can run bare metal on a physical machine (PM), virtual machine (VM) or as a cloud instance via services such as Amazon Web Services (AWS) as well as Microsoft Azure among others.

Refresh, What is Ubuntu

For those not familiar or who need a refresh, Ubuntu is an open source Linux distribution with the company behind it called Canonical. The Ubuntu software is a Debian based Linux distribution with Unity (user interface). Ubuntu is available across different platform architecture from industry standard Intel and AMD x86 32bit and 64bit to ARM processors and even the venerable IBM zSeriues (aka zed) mainframe as part of LinuxOne.

As a desktop, some see or use Ubuntu as an open source alternative to desktop interfaces based on those from Microsoft such as Windows or Apple.

As a server Ubuntu can be deployed from traditional applications to cloud, converged and many others including as a docker container, Ceph or OpenStack deployment platform. Speaking of Microsoft and Windows, if you are a *nix bash type person yet need (or have) to work with Windows, bash (and more) are coming to Windows 10. Ubuntu desktop GUI or User Interface options include Unity along with tools such as Compiz and LibreOffice (an alternative to Microsoft Office).

What’s New In the Bits and Bytes (e.g. Software)

Ubuntu 16.04 LTS is based on the Linux 4.4 kernel, that also includes Python 3, Ceph Jewel (block, file and object storage) and OpenStack Mitaka among other enhancements. These and other fixes as well as enhancements include:

  • Libvirt 1.3.1
  • Qemu 2.5
  • Open vSwitch 2.5.0
  • NginxLX2 2.0
  • Docker 1.10
  • PHP 7.9
  • MySQL 7.0
  • Juju 2.0
  • Golang 1.6 toolchain
  • OpenSSH 7.2p2 with legacy support along with cipher improvements, including 1024 bit diffie-hellman-group1-sha1 key exchange, ssh-dss, ssh-dss-cert
  • GNU toolchain
  • Apt 1.2

What About Ubuntu for IBM zSeries Mainframe

Ubuntu runs on 64 bit zSeries architecture with about 95% binary compatibility. If you look at the release notes, there are still a few things being worked out among known issues. However (read the release notes), Ubuntu 16.04 LTS has OpenStack and Ceph, means that those capabilities could be deployed on a zSeries.

Now some of you might think wait, how can Linux and Ceph among others work on a FICON based mainframe?

No worries, keep in mind that FICON the IBM zSeries server storage I/O protocol that co-exists on Fibre Channel along with SCSI_FCP (e.g. FCP) aka what most Open Systems people simply refer to as Fibre Channel (FC) works with the zOS and other operating systems. In the case of native Linux on zSeries, those systems can in fact use SCSI mode for accessing shared storage. In addition to the IBM LinuxOne site, you can learn more about Ubuntu running native on zSeries here on the Ubuntu site.

Where To Learn More

What This All Means

Ubuntu as a Linux distribution continues to evolve and increase in deployment across different environments. Some still view Ubuntu as the low-end Linux for home, hobbyist or those looking for a alternative desktop to Microsoft Windows among others. However Ubuntu is also increasingly being used in roles where other Linux distribution such as Red Hat Enterprise Linux (RHEL), SUSE and Centos among others have gained prior popularity.

In someway’s you can view RHEL as the first generation Linux distribution that gained popular in the enterprise with early adopters, followed by a second wave or generation of those who favored Centos among others such as the cloud crowd. Then there is the Ubuntu wave which is expanding in many areas along with others such as CoreOS. Granted with some people the preference between one Linux distribution vs. another can be as polarizing as Linux vs. Windows, OpenSystems vs. Mainframe vs. Cloud among others.

Having various Ubuntu distributions installed across different servers (in addition to Centos, Suse and others), I found the install and new capabilities of Ubuntu 16.04 LTS interesting and continue to explore the many new features, while upgrading some of my older systems.

Get the Ubuntu 16.04 LTS bits here to give a try or upgrade your existing systems.

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 2006-2023 Server StorageIO(R) and UnlimitedIO All Rights Reserved

Happy Earth Day 2016 Eliminating Digital and Data e-Waste

Happy Earth Day 2016 Eliminating Digital and Data e-Waste

With Earth Day 2016 on April 22, here are some thoughts about electronic waste (e-waste).

For those involved in data management or data infrastructures, the following are five tips to help cut the overhead and resulting impact of digital e-waste and later physical e-waste. Most conversations involving e-waste focus on the physical aspects from disposing of electronics along with later impacts. While physical e-waste is an important topic, lets expand the conversation including other variations of e-waste including digital. By digital e-waste I’m referring to the use of physical items that end up contributing to traditional e-waste.

digital and data ewaste

Digital e-waste ranges from the overhead of keeping extra copies of data that result in an expanding data footprint that in turn requires extra physical resources and their impact. Addressing physical e-waste also means keeping digital (not the physical items) including data waste in perspective.

Also note that digital or data waste may in fact not be waste per say if it exists as a by-product of making sure applications, data and resulting information are protected, preserved, secured and served for when needed. The warning is what can be done to make sure there are good useful effective and efficient copy data that has a relative low data footprint overhead impact, more on this later.

Here are six themes to consider to cut the impact without costing or compromising your organization when address e-waste (physical, digital, data).

1. Understand Digital e-waste

You might be familiar with the term e-waste (electronic waste), you know, those physical items that get discarded from supporting your digital lifestyle. The reason awareness around e-waste is important is because of the environmental impacts of discarding all those devices. The more known about the issue, impacts, causes and effects helps to drive awareness as well as insight into what can be done to mitigate those items.

ewaste

Devices range from smart and dumb cell phones, personal digital assistants (PDAs), tablets, notebook and workstation computers, MP3 devices, cameras, video display monitors along with larger servers, storage and networking technology, not to mention all the other Internet of Things (IoT) and Internet of Device (IoD) items. What’s important to know about physical e-waste is the impact of the various components. You can learn more about physical e-waste impact in general with a web search such as Google e-waste impact.

2. Reuse, Repurpose, Redeploy, Reconfigure, Re-Tool, Recycle

Reconfigure and retool where possible by re-driving installing newer, more energy-efficient high-capacity drives, or more performance effective devices. Besides replacing Hard Disk Drives (HDD), Solid State Devices (SSDs), magnetic tape among other mediums, look at the pro’s and con’s of replacing CPU processor sockets, upgrading memory and PCIe I/O cards for networking or storage among other enhancements.

Pro’s include being able to use the chassis longer reducing amount of physical e-waste, however at some point it can be more cost-effective to do a total replacement. However the longer you can use the asset or device the more that has as a positive benefit to cut e-waste.

Repurpose, reuse and redeploy assets such as servers, storage and networking devices in a hand me down approach assuming there is a value or benefit in doing so.

Recycle when done, dispose of the technology properly including for storage secure erase of digital media and later physical handling.

3. Responsible Recycle and Disposition of technology (including secure digital destruction)

What are you doing with, how are you disposing of physical items ranging from laptops, workstations, tablets, phones, MP3 players, TVs and monitors, servers, network and storage devices among others when no longer needed?

Are you securely erasing your digital data on HDDs as well as SSDs or even tape and optical devices before they are disposed of? If not, you should be. For example if you are not yet using or looking at Self Encrypting Drives (SED) including HDDs and SSDs for securing your data, start investigating them. Sure they have a security value proposition for when lost or stolen, however they can also cut the time to secure erase to a given standard from days or hours to minutes or seconds.

These will become e-waste

Smart shopping up front, what you want, what you need, how long can you leverage, spend more up front to get something that can last 3-5 years vs. discarding in 1.5-3 years.
Smart management with insight, know your cost and impacts, not just for PR purpose, for profit and practicality

4. Plan acquisitions with disposition in mind

Redesign and design for replacement, maximizing what you have or will acquire, using it for longer time to cut costs, improve productivity (and profitability) while reducing e-waste overhead contributing footprint.

For example, do you need or want to have the latest in new technology replacing that phone, tablet, watch or other IoT or IoD item as soon as something newer comes along? No worries if you are also doing something responsible with what was new and now old by such as donating or giving it to somebody else who might be able to get a few more years worth of use out of it before it becomes e-waste.

On the other hand, if you are acquiring technology with a 2-3 year useful life plan, what would it take to upgrade that item to a larger or more robust version using it for 3-5 years. Granted, you might not use it in its primary role for the longer duration, however can it be repurposed for some other uses? Also from a technology acquisition perspective, have a forecast and plan that can help you make smart, informed decisions up front knowing when upgrades or extra resources will be needed to prolong the usefulness of the item.

Of course you can also simply move everything to the cloud and out-source your e-waste footprint to the vendor, MSP or cloud provider.

5. Understand Changing Data Value

Keep in mind that data has either no value, some value or unknown value all of which can change over time. For example some data has value for seconds, minutes or hours and can then be discarded. Other data have some value which can be low or high which determines how as well as when, where and how to protect, preserve, secure and serve it when needed. Then there is data that has an unknown value. However, that can change over time.

Different and Changing Data Value

Over time your data may end up having no value meaning it can be discarded, or, it might have some value (low or high) meaning change how it should be protected, preserved, secured and served. Then there is data that may stay in limbo or unknown status indefinitely or until somebody, or some software or via other means decide if it has value or not.

The point is that to cut digital e-waste is to discard data with no value as soon as possible, protect, preserve, secure and serve data with value appropriately. Likewise, for all of that growing data with an unknown value, rethink how it is protected and stored, all of which has an impact on both physical as well as digital e-waste.

This means having insight and awareness into your environment, applications, data, settings, configuration and metadata, not only of the space being used, or when it was last updated. Also, look beyond when data was last modified or changed, look at when it was last read or accessed to decide how protected and secured including virus and other scans.

6. Data Footprint Reduction (DFR)

Implement data footprint reduction (DFR) to lower overhead impact not only at the target or downstream destination using compression, dedupe and other techniques. Also, move upstream to the source where the problem starts and address it there. Addressing at the source leverages various techniques from Archiving, Backup/Data Protection Modernization (rethinking what saved, when, how often, etc), Cleanup, Compression and Consolidation, Data management, Deletion and Dedupe along with storage tiering, RAID/Parity/Mirroring/Replication/Erasure Code and Advanced Parity/LRC/Forward Error Correction and other technologies.

For example if you have 10TB of data, how many copies do you have and why, how are those copies protected and what is their overhead. The issue and concern should not be primarily how many copies, rather, if those copies add or give value, then what can you do to keep them while reducing their overhead impact, besides simply trying to compress or dedupe everything. Hint, start exploring copy management as well as revisiting what you protect, when, where, why, how often along with options for implementing DFR as close to the data source as possible, as well as downstream.

Where To Learn More

What This All Means

Gain insight and awareness into what is occurring with physical and digital ewaste side stepping the greenwashing and other activity. Small steps implemented by many will have a big impact. Every bit, byte, block, blob, bucket file or object along with their copies have an impact, hopefully as well as a benefit, a question is how can you reduce the overhead while increasing your return on innovation reducing costs, complexity and overhead while enhancing organization capabilities. There are many techniques, technologies, tools and approaches to apply to various environments, after all, everything is not the same, yet there are similarities. Happy Earth Day 2016 and happy spring to those of you in the northern hemisphere (as well as elsewhere).

Ok, nuff said, for now

Cheers
Gs

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

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2023 Server StorageIO(R) and UnlimitedIO All Rights Reserved

vSphere Software Defined Beta, Something for free from VMware

vSphere Beta, Something free from VMware (other than your time)

server storage I/O trends

Something free from VMware (other than time)

VMware is looking for candidate beta test sites and environments for an upcoming vSphere release. Target audience or environments are those who have deployed vSphere 5.5 and 6.0 in your environment and looking to test the new software (e.g. bits).

What VMware is looking for

For this private community

vSphere beta, VMware is looking for participants with expectations including:

  • Online acceptance of the Master Software Beta Test Agreement will be required prior to visiting the Private Beta Community
  • Install beta software within 3 days of receiving access to the beta product
  • Provide feedback within the first 4 weeks of the beta program
  • Submit Support Requests for bugs, issues and feature requests
  • Complete surveys and beta test assignments
  • Participate in the private beta discussion forum and conference calls

How to get involved and test the bits?

To get involved (and get the bits), simply fill out the VMware form found here (no credit card or money required, just some of your time).

The VMware vSphere team will grant access to the program to selected candidates in stages. This vSphere Beta Program leverages a private Beta community to download software and share information. VMware will provide discussion forums, webinars, and service requests to enable you to share your opinion with them.

VMware cites the following reasons to participate in this vSphere beta opportunity:

  • Receive early access to the vSphere Beta products
  • Interact with the vSphere Beta team consisting of Product Managers, Engineers, Technical Support, and Technical Writers
  • Provide direct input on product functionality, configurability, usability, and performance
  • Provide feedback influencing future products, training, documentation, and services
  • Collaborate with other participants, learn about their use cases, and share advice and learnings

Where To Learn More

What This All Means

Having been involved in earlier vSphere betas this is a great way to get an early glimpse and hands on behind the wheel real-world experience with new technology for the experience, as well as testing to see how things will work in yours, or in a VMware hosted environment. You are free to use and test the bits (e.g. software) in your environment (or VMware hosted) how you like in a free-form real-world way. In addition to hands on time, you also get exposure and chance to interact with the VMware folks.

This experience can be useful for planning on how to use new feature functionality, as well as strategy planning for deployment once the production bits get released down the road.

Remember to sign up if interested here, see you in the beta.

Ok, nuff said, for now

Cheers
Gs

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

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2023 Server StorageIO(R) and UnlimitedIO All Rights Reserved

Cloud Constellation SpaceBelt – Out Of This World Cloud Data Centers?

Cloud Constellation SpaceBelt – Out Of This World Cloud Data Centers?

server storage I/O trends

A new startup called Cloud Constellation (aka SpaceBelt) has announced and proposes converge space terrestrial satellite technology with IT information and cloud related data infrastructure technologies including NVM (e.g. SSD) and storage class memory (SCM). While announcing their Series A funding and proposed value proposition (below), Cloud Constellation did not say how much funding, who the investors are, or management team leading to some, well, rather cloud information.

Cloud Constellation’s SpaceBelt transforms cybersecurity for enterprise and government operations moving high-value data around the world by:

  • insulating it completely from the Internet and terrestrial leased lines
  • liberating it from cyberattacks and surreptitious activities
  • protecting it from natural disasters and force majeure events
  • addressing all jurisdictional complexities and constraints
  • avoiding risks of violating privacy regulations

Truly secure data transfer: Enterprises and governments will finally be enabled to bypass use of leaky networks and compromised servers interconnecting their sites around the world.

New option for cloud service providers: The service will be a key market differentiator for cloud service providers to offer a transformative, ultra-high degree of network security to clients reliant on moving sensitive, mission-critical data around the world each day.

What is SpaceBelt Cloud Constellation?

From their website www.cloudconstellation.com you will see following.

Cloud Constellation Space Belt
www.cloudconstellation.com

Keeping in mind that today is April 1st which means April Fools day 2016, my motto for the day is trust yet verify. So just for fun, check out this new company that I had a briefing with earlier this week that also announced their Series A funding earlier in March 2016.

The question you have to ask yourself today is if this is an out of this world April Fools prank, an out of this world idea that will eclipse current cloud services such as Amazon Web Services (AWS), Google, IBM Softlayer, Microsoft Azure, Rackspace among others?

Or, will SpaceBelt go the way of earlier cloud high flyers HP Cloud, Nirvanix among others.

Btw, keep in mind that only you can prevent cloud data loss, however cloud and virtual data availability is also a shared responsibility.

Some Questions and Things To Ponder

  • Is this an April Fools Joke?
  • How much Non Volatile Memory (NVM) such as NAND, 3D Nand, 3D XPoint or other Storage Class Memory (SCM) can be physically placed on each bird (e.g. Satellite)
  • What will the solar panels look like to power the birds, plus battery’s for heating and cooling the NVM (contrary to popular myth, NVMs do get warm if not hot)
  • What is the availability, accessibility and durability model, how will data be replicated, mirrored or an out of this world LRC/Erasure Code Advanced Parity model be used?
  • How will the storage be accessed, what will the end-points look like, iSCSI, NDB, FUSE, NFS, CIFS, HDFS, Torrent, JSON, ODBC, REST/HTTP, FTP or something else?
  • Security will be a concern as well as geo placement, after all, its one thing to move data across some borders, how about if the data is hundreds of miles above those borders?
  • Cost will be an interesting model to follow, as well as competitors from SpaceX, Amazon, Boeing, GE, NSA, Google, Facebook or others emerge?
  • What will the uplink and download speeds be, not to mention latency of moving and accessing data from the satellites. For those who have DirectTV or other terrestrial service you know the pros and cons associated with that. Speaking of which, perhaps you have experienced a thunder-storm with DirecTV or Dish, or perhaps a cloud storm due to a cloud provider service or site failure, think about what happens to your cloud data if the satellite dish is disrupted during an upload or download.
  • I also wonder how the various industry trade groups will wrap their head around this one, what kind of new standards, initiatives and out of this world marketing promotions will we see or hear about? You know that some creative marketer will declare surface clouds as dead, just saying.

Where To Learn More

What This All Means

The folks over at cloud constellation say their space belt made up of a constellation (e.g. in orbit cluster) of satellites will be circling the globe around 2019. I wonder if they will be ready to do a proof of concept (poc) technology demonstrator of their IP using TCP based networking, server, storage I/O protocols leveraging a hot air balloon or weather balloon near term, if not, would be a great marketing ploy.

If nothing else, putting their data infrastructure technology on a hot air balloon could be a fun marketing ploy to say their cloud rises above the hot air of other cloud marketing. Or if they do a POC using a weather balloon, they could show and say their cloud rises above traditional cloud storms, oh the fun…

Check out Cloud Constellation and their Spacebelt, see for yourself and then you decide what is going on!

Remember, its April Fools day today, trust, yet verify.

What say you, is this an April Fools Joke or the next big thing?

Ok, nuff said (for now), time to listen to Pink Floyd Dark Side of the Moon ;)

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 2006-2023 Server StorageIO(R) and UnlimitedIO All Rights Reserved

The Future of Ethernet – 2016 Roadmap released by Ethernet Alliance

The Future of Ethernet – 2016 Roadmap released by Ethernet Alliance

server storage I/O trends

The Future of Ethernet – 2016 Roadmap released by Ethernet Alliance

Ethernet Alliance Roadmap

The Ethernet Alliance has announced their 2016 roadmap of enhancements for Ethernet.

Ethernet enhancements include speeds, connectivity interfaces that span needs from consumer, enterprise, to cloud and managed service providers.

Highlights of Ethernet Roadmap

  • FlexEthernet (FlexE)
  • QSFP-DD, microQSFP and OBO interfaces
  • Speeds from 10Mbps to 400GbE.
  • 4 Pair Power over Ethernet (PoE)
  • Power over Data Line (PoDL)

Ethernet Alliance 2016 Roadmap Image
Images via EthernetAlliance.org

Who is the Ethernet Alliance

The Ethernet Alliance (@ethernetallianc) is an industry trade and marketing consortium focused on the advancement and success of Ethernet related technologies.

Where to learn more

The Ethernet Alliance has also made available via their web site two presentations part one here and part two here (or click on the following images).

Ethernet Alliance 2016 roadmap presentation #1 Ethernet Alliance 2016 roadmap presentation #2

Also visit www.ethernetalliance.org/roadmap

What this all means

Ethernet technologies continue to be enhanced from consumer focused, Internet of Things (IoT) and Internet of Devices (IoD) to enterprise, data centers, IT and non-IT usage as well as cloud and managed service providers. At the lower end where there is broad adoption, the continued evolution of easier to use, lower cost, interoperable technologies and interfaces expands Ethernet adoption footprint while at the higher-end, all of those IoT, IoD, consumer and other devices aggregated (consolidate) into cloud and other services that have the need for speeds from 10GbE, 40GbE, 100GbE and 400GbE.

With the 2016 Roadmap the Ethernet Alliance has provided good direction as to where Ethernet fits today and tomorrow.

Ok, nuff said (for now)

Cheers
Gs

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

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2023 Server StorageIO(R) and UnlimitedIO All Rights Reserved

Server StorageIO February 2016 Update Newsletter

Volume 16, Issue II

Hello and welcome to the February 2016 Server StorageIO update newsletter.

Even with an extra day during the month of February, there was a lot going on in a short amount of time. This included industry activity from servers to storage and I/O networking, hardware, software, services, mergers and acquisitions for cloud, virtual, containers and legacy environments. Check out the sampling of some of the various industry activities below.

Meanwhile, its now time for March Madness which also means metrics that matter and getting ready for World Backup Data on March 31st. Speaking of World Backup Day, check out the StorageIO events and activities page for a webinar on March 31st involving data protection as part of smart backups.

While your focus for March may be around brackets and other related themes, check out the Carnegie Mellon University (CMU) white paper listed below that looks at NAND flash SSD failures at Facebook. Some of the takeaways involve the importance of cooling and thermal management for flash, as well as wear management and role of flash translation layer firmware along with controllers.

Also see the links to the Google White Paper on their request to the industry for a new type of Hard Disk Drive (HDD) to store capacity data while SSD’s handle the IOP’s. The take away is that while Google uses a lot of flash SSD for high performance, low latency workloads, they also need to have a lot of high-capacity bulk storage that is more affordable on a cost per capacity basis. Google also makes several proposals and suggestions to the industry on what should and can be done on a go forward basis.

Backblaze also has a new report out on their 2015 HDD reliability and failure analysis which makes for an interesting read. One of the take away’s is that while there are newer, larger capacity 6TB and 8TB drives, Backblaze is leveraging the lower cost per capacity of 4TB drives that are also available in volume quantity.

Enjoy this edition of the Server StorageIO update newsletter and watch for new tips, articles, StorageIO lab report reviews, blog posts, videos and podcast’s along with in the news commentary appearing soon.

Cheers GS

In This Issue

  • StorageIOblog posts
  • Industry Activity Trends
  • New and Old Vendor Update
  • Events and Webinars
  • StorageIOblog Posts

    Recent and popular Server StorageIOblog posts include:

    • EMC DSSD D5 Rack Scale Direct Attached Shared SSD All Flash Array Part I
      and Part II – EMC DSSD D5 Direct Attached Shared AFA
      EMC announced the general availability of their DSSD D5 Shared Direct Attached SSD (DAS) flash storage system (e.g. All Flash Array or AFA) which is a rack-scale solution. If you recall, EMC acquired DSSD back in 2014 which you can read more about here. EMC announced four configurations that include 36TB, 72TB and 144TB raw flash SSD capacity with support for up to 48 dual-ported host client servers.
    • Various Hardware (SAS, SATA, NVM, M2) and Software (VHD) Defined Odd’s and Ends
      Ever need to add another GbE port to a small server, workstation or perhaps Intel NUC, however no PCIe slots are available? How about attaching a M2 form factor flash SSD card to a server or device that does not have an M2 port, or, for mirroring two M2 cards together with a RAID adapter? Looking for tool to convert a Windows system to a Virtual Hard Disk (VHD) while it is running? The following are a collection of odd’s and end’s devices and tools for hardware and software defining your environment.
    • Software Defined Storage Virtual Hard Disk (VHD) Algorithms + Data Structures
      For those who are into, or simply like to talk about software defined storage (SDS), API’s, Windows, Virtual Hard Disks (VHD) or VHDX, or Hyper-V among other related themes, have you ever actually looked at the specification for VHDX? If not, here is the link to the open specification that Microsoft published (this one dates back to 2012).
    • Big Files and Lots of Little File Processing and Benchmarking with Vdbench
      Need to test a server, storage I/O networking, hardware, software, services, cloud, virtual, physical or other environment that is either doing some form of file processing, or, that you simply want to have some extra workload running in the background for what ever reason?

    View other recent as well as past blog posts here

    Server Storage I/O Industry Activity Trends (Cloud, Virtual, Physical)

    StorageIO news (image licensed for use from Shutterstock by StorageIO)

    Some new Products Technology Services Announcements (PTSA) include:

  • Tegile – IntelliFlash HD Now Available To Enterprises Worldwide
  • Via Forbes – Competitors and Cash Bleed Put Pressure on Pure Storage
  • Via HealthCareBusiness – Philips and Amazon team up on cloud-based health record storage
  • Via Zacks – IBM Advances Hybrid Cloud Object Based Storage
  • DataONstorage expands Microsoft Hyper Converged Infrastructure platforms
  • Via ITBusinessEdge – Nimble updates All Flash Array (AFA) storage
  • Carnegie Mellon University – A Large-Scale Study of Flash Memory Failures
  • Cisco Buys Cliqr Cloud Orchestration
  • Backblaze – 2015 Hard Drive Reliability Reports and Analysis
  • Via BusinessCloudNews – Verizon Closing Down Its Public Cloud
  • Via BusinessInsider – US Government Approves Dell and EMC Deal
  • EMC and VMware announce new VCE VxRAIL Converged Solutions
  • EMC announces new IBM zSeries Mainframe enhancements for VMAX
  • EMC announces new DSSD D5 AFA and VMAX AFA enhancements
  • HPE announces enhancements to StoreEasy 1650 storage
  • Seagate now shipping worlds slimmest and fastest 2TB mobile HDD
  • Via VMblog – Oracle Scoops Up Ravello to Boosts Its Public Cloud Offerings
  • Via Investors – SSD and Chinese Investments in Western Digital
  • ATTO announces 32G (e.g. Gen 6) Fibre Channel adapters
  • Google to disk vendors: Make hard drives like this, even if they lose more data
  • Google Disk for Data Centers White Paper (PDF Here)
  • View other recent news and industry trends here

    Vendors you may not have heard of

    Various vendors (and service providers) you may not know or heard about recently.

    StorageIO news (image licensed for use from Shutterstock by StorageIO)

    • SkySync – Enterprise File Sync and Share
    • SANblaze – Storage protocol emulation tools
    • OpenIT – DCIM and Data Infrastructure Management Tools
    • Infinit.sh – Decentralized Software Based File Storage Platform
    • Alluxio –
      Open Source Software Defined Storage Abstraction Layer
    • Genie9
      Backup and Data Protection Tools
    • E8 Storage – Software Defined Stealth Storage Startup

    Check out more vendors you may know, have heard of, or that are perhaps new on the Server StorageIO Industry Links page here (over 1,000 entries and growing).

     

    StorageIO Webinars and Industry Events

    EMCworld (Las Vegas) May 2-4, 2016

    Interop (Las Vegas) May 4-6 2016

    NAB (Las Vegas) April 19-20, 2016

    March 31, 2016 Webinar (1PM ET) – Smart Backup and World Backup Day

    February 25, 2016 Webinar (11AM PT) – Migrating to Hyper-V including from Vmware

    February 24, 2016 Webinar (11AM ET) – How To Become a Data Protection Hero

    February 23, 2016 Webinar (11AM PT) – Rethinking Data Protection

    January 19, 2016 Webinar (9AM PT) – Solve Virtualization Performance Issues Like a Pro

    See more webinars and other activities on the Server StorageIO Events page here.

    Server StorageIO Industry Resources and Links

    Check out these useful links and pages:

    storageio.com/links,
    objectstoragecenter.com, storageioblog.com/data-protection-diaries-main/,
    thenvmeplace.com, thessdplace.com and storageio.com/performance among others.

    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

    Part II – EMC DSSD D5 Direct Attached Shared AFA

    Part II – EMC DSSD D5 Direct Attached Shared AFA

    server storage I/O trends

    This is the second post in a two-part series on the EMC DSSD D5 announcement, you can read part one here.

    Lets take a closer look at how EMC DSSD D5 works, its hardware and software components, how it compares and other considerations.

    How Does DSSD D5 Work

    Up to 48 Linux servers attach via dual port PCIe Gen 3 x8 cards that are stateless. Stateless simply means they do not have any flash or are not being used as storage cards, rather, they are essentially just an NVMe adapter card. With the first release block, HDFS file along with object and APIs are available for Linux systems. These drivers enabling the shared NVMe storage to be accessed by applications using different streamlined server and storage I/O driver software stacks to cut latency. DSSD D5 is meant to be a rack scale solutions so distance is measured as inside a rack (e.g. a couple of meters).

    The 5U tall DSSD D5 supports 48 servers via a pair of I/O Modules (IOM) each with 48 ports that in turn attach to the data plane and on to the Flash Modules (FM). Also attached to the data plane are a pair of controllers that are active / active for performing management tasks, however they do not sit in the data path. This means that host client directly access the FMs without having to go through a controller which is the case in traditional storage systems and AFAs. The controllers only get involved when there is some setup, configuration or other management activities, otherwise they get out-of-the-way, kind of like how management should function. There when you need them to help, then get out-of-the-way so productive work can be done.

    EMC DSSD shared ssd das
    Pardon the following hand drawn sketches, you can see some nice pretty diagrams, videos and other content via the EMC Pulse Blog as well as elsewhere.

    Note that the host client servers take on the responsibility for managing and coordinating data consistency meaning data can be shared between servers assuming applicable software is used for implementing integrity. This means that clustering and other software that can support shared storage are able to support low latency high performance read and write activity the DSSD D5 as opposed to relying on the underlying storage system for handling the shared storage coordination such as in a NAS. Another note is that the DSSD D5 is optimized for concurrent multi-threaded and asynchronous I/O operations along with atomic writes for data integrity that enable the multiple cores in today’s faster processors to be more effectively leveraged.

    The data plane is a mesh or switch or expander based back plane enabling any of the north bound (host client-server) 96 (2 x 48) PCIe Gen 3 x4 ports to reach the up to 36 (or as few as 18) FMs that are also dual pathed. Note that the host client-server PCIe dual port cards are Gen 3 x8 while the DSSD D5 ports are Gen 3 x4. Simple math should tell you that if are going to have 2 x PCIe Gen 3 x4 ports running at full speed, you want to have a Gen 3 x8 connection inside the server to get full performance.

    Think of the data plane similar to how a SAS expander works in an enclosure or a SAS switch, the difference being it is PCIe and not SAS or other protocol. Note that even though the terms mesh, fabric, switch, network are used, these are NOT attached to traditional LAN, SAN, NAS or other networks. Instead, this is a private “networked back plane” between the server and storage devices (e.g. FM).

    EMC DSSD D5 details

    The dual controllers (e.g. control plane) over see the flash management including garbage collection among other tasks, as well as storage is thin provisioned.

    Dual Controllers (active/active) are connected to each other (e.g. control plane) as well as to the data path, however, do not sit in the data path. Thus this is a fast path control path approach meaning the controllers can get involved to do management functions when needed, and get out-of-the-way of work when not needed. The controllers are hot-swap and add global management functions including setting up, tearing down host client/server I/O paths, mappings and affinities. Controllers also support the management of CUBIC RAID data protection functions performed by the Flash Modules (FM).

    Other functions the controllers implement leveraging their CPUs and DRAM include flash translation layer (FTL) functions normally handled by SSD cards, drives or other devices. These FTL functions include wear-leveling for durability, garbage collection, voltage power management among other tasks. The result is that the flash modules are able to spend more time and their resources handling I/O operations vs. handling management tasks vs. traditional off the shelf SSD drives, cards or devices.

    The FMs insert from the front and come in two sizes of 2TB and 4TB of raw NAND capacity. What’s different about the FMs vs. some other vendors approach is that these are not your traditional PCIe flash cards, instead they are custom cards with a proprietary ASIC and raw nand dies. DRAM is used in the FM as a buffer to hold data for write optimization as well as enhance wear-leveling to increase flash endurance.

    The result is up to thousands of nand dies spread over up to 36 FMs however more important, more performance being derived out of those resources. The increased performance comes from DSSD implementing its own flash translation layer, garbage collection, power voltage management among other techniques to derive more useful work per watt of energy consumed.

    EMC DSSD performance claims:

    • 100 microsecond latency for small IOs
    • 100GB bandwidth for large IOs
    • 10 Million small IO IOPs
    • Up to 144TB raw capacity

    How Does It Compare To Other AFA and SSD solutions

    There will be many apples to oranges comparisons as is often the case with new technologies or at least until others arrive in the market.

    Some general comparisons that may be apples to oranges as opposed to apples to apples include:

    • Shared and dense fast nand flash (eMLC) SSD storage
    • disaggregated flash SSD storage from server while enabling high performance, low latency
    • Eliminate pools or ponds of dedicated SSD storage capacity and performance
    • Not a SAN yet more than server-side flash or flash SSD JBOD
    • Underlying Flash Translation Layer (FTL) is disaggregated from SSD devices
    • Optimized hardware and software data path
    • Requires special server-side stateless adapter for accessing shared storage

    Some other comparisons include:

    • Hybrid and AFA shared via some server storage I/O network (good sharing, feature rich, resilient, slower performance and higher latency due to hardware, network and server I/O software stacks). For example EMC VMAX, VNX, XtremIO among others.
    • Server attached flash SSD aka server SAN (flash SSD creates islands of technology, lower resource sharing, data shuffling between servers, limited or no data services, management complexity). For example PCIe flash SSD state full (persistent) cards where data is stored or used as a cache along with associated management tools and drivers.
    • DSSD D5 is a rack-scale hybrid approach combing direct attached shared flash with lower latency, higher performance vs. traditional AFA or hybrid storage array, better resource usage, sharing, management and performance vs. traditional dedicated server flash. Compliment server-side data infrastructure and applications scale-out software. Server applications can reach NVMe storage via user spacing with block, hdfs, Flood and other APIs.

    Using EMC DSSD D5 in possible hybrid ways

    What Happened to Server PCIe cards and Server SANs

    If you recall a few years ago the industry rage was flash SSD PCIe server cards from vendors such as EMC, FusionIO (now part of SANdisk), Intel (still Intel), LSI (now part of Seagate), Micron (still Micron) and STEC (now part of Western Digital) among others. Server side flash SSD PCIe cards are still popular particular with newer NVMe controller based models that use the NVMe protocol stack instead of AHC/SATA or others.

    However as is often the case, things evolve and while there is still a place for server-side state full PCIe flash cards either for data or as cache, there is also the need to combine and simplify management, as well as streamline the software I/O stacks which is where EMC DSSD D5 comes into play. It enables consolidation of server-side SSD cards into a shared 5U chassis enabling up to 48 dual pathed servers access to the flash pools while using streamlined server software stacks and drivers that leverage NVMe over PCIe.

    Where to learn more

    Continue reading with the following links about NVMe, flash SSD and EMC DSSD.

  • Part one of this series here and part two here.
  • Performance Redefined! Introducing DSSD D5 Rack-Scale Flash Solution (EMC Pulse Blog)
  • EMC Unveils DSSD D5: A Quantum Leap In Flash Storage (EMC Press Release)
  • EMC Declares 2016 The “Year of All-Flash” For Primary Storage (EMC Press Release)
  • EMC DSSD D5 Rack-Scale Flash (EMC PDF Overview)
  • EMC DSSD and Cloudera Evolve Hadoop (EMC White Paper Overview)
  • Software Aspects of The EMC DSSD D5 Rack-Scale Flash Storage Platform (EMC PDF White Paper)
  • EMC DSSD D5 (EMC PDF Architecture and Product Specification)
  • EMC VFCache respinning SSD and intelligent caching (Part II)
  • EMC To Acquire DSSD, Inc., Extends Flash Storage Leadership
  • Part II: XtremIO, XtremSW and XtremSF EMC flash ssd portfolio redefined
  • XtremIO, XtremSW and XtremSF EMC flash ssd portfolio redefined
  • Learn more about flash SSD here and NVMe here at thenvmeplace.com
  • What this all means

    EMC with DSSD D5 now has another solution to offer clients, granted their challenge as it has been over the past couple of decades now will be to educate and compensate their sales force and partners on what technology solution to put for different needs.

    On one hand, life could be simpler for EMC if they only had one platform solution that would then be the answer to every problem, something that some other vendors and startups face. Likewise, if all you have is one solution, then while you can try to make that solution fit different environments, or, get the environment to adapt to the solution, having options is a good thing if those options can remove complexity along with cost while boosting productivity.

    I would like to see support for other operating systems such as Windows, particular with the future Windows 2016 based Nano, as well as hypervisors including VMware, Hyper-V among others. On the other hand I also would like to see a Sharp Aquous Quattron 80" 1080p 240Hz 3D TV on my wall to watch HD videos from my DJI Phantom Drone. For now focusing on Linux makes sense, however, would be nice to see some more platforms supported.

    Keep an eye on the NVMe space as we are seeing NVMe solutions appearing inside servers, storage system, external dedicated and shared, as well as some other emerging things including NVMe over Fabric. Learn more about EMC DSSD D5 here.

    Ok, nuff said (for now)

    Cheers
    Gs

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

    All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2023 Server StorageIO(R) and UnlimitedIO All Rights Reserved

    EMC DSSD D5 Rack Scale Direct Attached Shared SSD All Flash Array Part I

    EMC DSSD D5 Rack Scale Direct Attached Shared SSD All Flash Array Part I

    server storage I/O trends

    This is the first post in a two-part series pertaining to the EMC DSSD D5 announcement, you can read part two here.

    EMC announced today the general availability of their DSSD D5 Shared Direct Attached SSD (DAS) flash storage system (e.g. All Flash Array or AFA) which is a rack-scale solution. If you recall, EMC acquired DSSD back in 2014 which you can read more about here. EMC announced four configurations that include 36TB, 72TB and 144TB raw flash SSD capacity with support for up to 48 dual-ported host client servers.

    Via EMC Pulse Blog

    What Is DSSD D5

    At a high level EMC DSSD D5 is a PCIe direct attached SSD flash storage solution to enable aggregation of disparate SSD card functionality typically found in separate servers into a shared system without causing aggravation. DSSD D5 helps to alleviate server side I/O bottlenecks or aggravation issues that can be the result of aggregation of workloads or data. Think of DSSD D5 as an shared application server storage I/O accelerator for up to 48 servers to access up to 144TB of raw flash SSD to support various applications that have the need for speed.

    Applications that have the need for speed or that can benefit from less time waiting for results, where time is money, or boosting productivity can enable high profitability computing. This includes legacy as well as emerging applications and workloads spanning little data, big data and big fast structure and unstructured data. From Oracle to SAS to HBASE and Hadoop among others, perhaps even Alluxio.

    Some examples include:

    • Clusters and scale-out grids
    • High Performance COMpute (HPC)
    • Parallel file systems
    • Forecasting and image processing
    • Fraud detection and prevention
    • Research and analytics
    • E-commerce and retail
    • Search and advertising
    • Legacy applications
    • Emerging applications
    • Structured database and key-value repositories
    • Unstructured file systems, HDFS and other data
    • Large undefined work sets
    • From batch stream to real-time
    • Reduces run times from days to hours

    Where to learn more

    Continue reading with the following links about NVMe, flash SSD and EMC DSSD.

  • Part one of this series here and part two here.
  • Performance Redefined! Introducing DSSD D5 Rack-Scale Flash Solution (EMC Pulse Blog)
  • EMC Unveils DSSD D5: A Quantum Leap In Flash Storage (EMC Press Release)
  • EMC Declares 2016 The “Year of All-Flash” For Primary Storage (EMC Press Release)
  • EMC DSSD D5 Rack-Scale Flash (EMC PDF Overview)
  • EMC DSSD and Cloudera Evolve Hadoop (EMC White Paper Overview)
  • Software Aspects of The EMC DSSD D5 Rack-Scale Flash Storage Platform (EMC PDF White Paper)
  • EMC DSSD D5 (EMC PDF Architecture and Product Specification)
  • EMC VFCache respinning SSD and intelligent caching (Part II)
  • EMC To Acquire DSSD, Inc., Extends Flash Storage Leadership
  • Part II: XtremIO, XtremSW and XtremSF EMC flash ssd portfolio redefined
  • XtremIO, XtremSW and XtremSF EMC flash ssd portfolio redefined
  • Learn more about flash SSD here and NVMe here at thenvmeplace.com
  • What this all means

    Today’s legacy, and emerging applications have the need for speed, and where the applications may not need speed, the users as well as Internet of Things (IoT) that depend upon, or feed those applications do need things to move faster. Fast applications need fast software and hardware to get the same amount of work done faster with less wait delays, as well as process larger amounts of structured and unstructured little data, big data and very fast big data.

    Different applications along with the data infrastructures they rely upon including servers, storage, I/O hardware and software need to adapt to various environments, one size, one approach model does not fit all scenarios. What this means is that some applications and data infrastructures will benefit from shared direct attached SSD storage such as rack scale solutions using EMC DSSD D5. Meanwhile other applications will benefit from AFA or hybrid storage systems along with other approaches used in various ways.

    Continue reading part two of this series here including how EMC DSSD D5 works and more perspectives.

    Ok, nuff said (for now)

    Cheers
    Gs

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

    All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2023 Server StorageIO(R) and UnlimitedIO All Rights Reserved

    Server StorageIO January 2016 Update Newsletter

    Volume 16, Issue I – beginning of Year (BoY) Edition

    Hello and welcome to the January 2016 Server StorageIO update newsletter.

    Is it just me, or did January disappear in a flash like data stored in non-persistent volatile DRAM memory when the power is turned off? It seems like just the other day that it was the first day of the new year and now we are about to welcome in February. Needless to say, like many of you I have been busy with various projects, many of which are behind the scenes, some of which will start appearing publicly sooner while others later.

    In terms of what have I been working on, it includes the usual of performance, availability, capacity and economics (e.g. PACE) related to servers, storage, I/O networks, hardware, software, cloud, virtual and containers. This includes NVM as well as NVMe based SSD’s, HDD’s, cache and tiering technologies, as well as data protection among other things with Hyper-V, VMware as well as various cloud services.

    Enjoy this edition of the Server StorageIO update newsletter and watch for new tips, articles, StorageIO lab report reviews, blog posts, videos and podcast’s along with in the news commentary appearing soon.

    Cheers GS

    In This Issue

  • Feature Topic
  • Industry Trends News
  • Commentary in the news
  • Tips and Articles
  • StorageIOblog posts
  • Videos and Podcasts
  • Events and Webinars
  • Recommended Reading List
  • Industry Activity Trends
  • Server StorageIO Lab reports
  • New and Old Vendor Update
  • Resources and Links
  • Feature Topic – Microsoft Nano, Server 2016 TP4 and VMware

    This months feature topic is virtual servers and software defined storage including those from VMware and Microsoft. Back in November I mentioned the 2016 Technical Preview 4 (e.g. TP4) along with Storage Spaces Direct and Nano. As a reminder you can download your free trial copy of Windows Server 2016 TP4 from this Microsoft site here.

    Three good Microsoft Blog posts about storage spaces to check out include:

    • Storage Spaces Direct in Technical Preview 4 (here)
    • Hardware options for evaluating Storage Spaces Direct in Technical Preview 4 (here)
    • Storage Spaces Direct – Under the hood with the Software Storage Bus (here)

    As for Microsoft Nano, for those not familiar, it’s not a new tablet or mobile device, instead, it is a very light weight streamlined version of the Windows Server 2016 server. How streamlined? Much more so then the earlier Windows Server versions that simply disabled the GUI and desktop interfaces. Nano is smaller from a memory and disk storage space perspective meaning it uses less RAM, boots faster, has fewer moving parts (e.g. software modules) to break (or need patching).

    Specifically Nano removes 32 bit support and anything related to the desktop and GUI interfaces as well as removing the console interface. That’s right, no console or virtual console to log into, Wow is gone, access is via Powershell or Windows Management Interface tools from remote systems. How small is it? I have a Nano instance built on a VHDX that is under a GB in size, granted, its only for testing. The goal of Nano is to have a very light weight streamlined version of Windows Server that can run hundreds (or more) VMs in a small memory footprint, not to mention supports lots of containers. Nano is part of WIndows TP4, learn more about Nano here in this Microsoft post including how to get started using it.

    Speaking of VMware, if you have not received an invite yet to their Digital Enterprise February 6, 2016 announcement event, click here to register.

    StorageIOblog Posts

    Recent and popular Server StorageIOblog posts include:

    View other recent as well as past blog posts here

    Server Storage I/O Industry Activity Trends (Cloud, Virtual, Physical)

    StorageIO news (image licensed for use from Shutterstock by StorageIO)

    Some new Products Technology Services Announcements (PTSA) include:

    • EMC announced Elastic Cloud Storage (ECS) V2.2. A main theme of V2.2 is that besides being the 3rd generation of EMC object storage (dating back to Centera, then Atmos), is that ECS is also where the functionality of Centera, Atmos and other functionality converge. ECS provides object storage access along with HDFS (Hadoop and Hortonworks certified) and traditional NFS file access.

      Object storage access includes Amazon S3, OpenStack Swift, ATMOS and CAS (Centera). In addition to the access, added Centera functionality for regulatory compliance has been folded into the ECS software stack. For example, ECS is now compatible with SEC 17 a-4(f) and CFTC 1.3(b)-(c) regulations protecting data from being overwritten or erased for a specified retention period. Other enhancements besides scalability, resiliency and ease of use include meta data and search capabilities. You can download and try ECS for non-production workloads with no capacity or functionality limitations from EMC here.

    View other recent news and industry trends here

    StorageIO Commentary in the news

    StorageIO news (image licensed for use from Shutterstock by StorageIO)
    Recent Server StorageIO commentary and industry trends perspectives about news, activities tips, and announcements. In case you missed them from last month:

    • TheFibreChannel.com: Industry Analyst Interview: Greg Schulz, StorageIO
    • EnterpriseStorageForum: Comments Handling Virtual Storage Challenges
    • PowerMore (Dell): Q&A: When to implement ultra-dense storage

    View more Server, Storage and I/O hardware as well as software trends comments here

    Vendors you may not have heard of

    Various vendors (and service providers) you may not know or heard about recently.

    • Datrium – DVX and NetShelf server software defined flash storage and converged infrastructure
    • DataDynamics – StorageX is the software solution for enabling intelligent data migration, including from NetApp OnTap 7 to Clustered OnTap, as well as to and from EMC among other NAS file serving solutions.
    • Paxata – Little and Big Data management solutions

    Check out more vendors you may know, have heard of, or that are perhaps new on the Server StorageIO Industry Links page here (over 1,000 entries and growing).

    StorageIO Tips and Articles

    Recent Server StorageIO articles appearing in different venues include:

    • InfoStor:  Data Protection Gaps, Some Good, Some Not So Good

    And in case you missed them from last month

    • IronMountain:  5 Noteworthy Data Privacy Trends From 2015
    • Virtual Blocks (VMware Blogs):  Part III EVO:RAIL – When And Where To Use It?
    • InfoStor:  Object Storage Is In Your Future
    • InfoStor:  Water, Data and Storage Analogy

    Check out these resources and links technology, techniques, trends as well as tools. View more tips and articles here

    StorageIO Videos and Podcasts

    StorageIO podcasts are also available via and at StorageIO.tv

    StorageIO Webinars and Industry Events

    EMCworld (Las Vegas) May 2-4, 2016

    Interop (Las Vegas) May 4-6 2016

    NAB (Las Vegas) April 19-20, 2016

    TBA – March 31, 2016

    Redmond Magazine Gridstore (How to Migrate from VMware to Hyper-V) February 25, 2016 Webinar (11AM PT)

    TBA – February 23, 2016

    Redmond Magazine and Dell Foglight – Manage and Solve Virtualization Performance Issues Like a Pro (Webinar 9AM PT) – January 19, 2016

    See more webinars and other activities on the Server StorageIO Events page here.

    From StorageIO Labs

    Research, Reviews and Reports

    Quick Look: What’s the Best Enterprise HDD for a Content Server?
    Which enterprise HDD for content servers

    Insight for Effective Server Storage I/O decision-making
    This StorageIO® Industry Trends Perspectives Solution Brief and Lab Review (compliments of Seagate and Servers Direct) looks at the Servers Direct (www.serversdirect.com) converged Content Solution platforms with Seagate (www.seagate.com) Enterprise Hard Disk Drive (HDDs).

    I was given the opportunity to do some hands-on testing running different application workloads with a 2U content solution platform along with various Seagate Enterprise 2.5” HDDs handle different application workloads. This includes Seagate’s Enterprise Performance HDDs with the enhanced caching feature.

    Read more in this Server StorageIO industry Trends Perspective white paper and lab review.

    Looking for NVM including SSD information? Visit the Server StorageIO www.thessdplace.com and www.thenvmeplace.com micro sites. View other StorageIO lab review and test drive reports here.

    Server StorageIO Recommended Reading List

    The following are various recommended reading including books, blogs and videos. If you have not done so recently, also check out the Intel Recommended Reading List (here) where you will also find a couple of mine as well as books from others. For this months recommended reading, it’s a blog site. If you have not visited Duncan Eppings (@DuncanYB) Yellow-Bricks site, you should, particular if you are interested in virtualization, high availability and related topical themes.

    Seven Databases in Seven Weeks guide to no SQL via Amazon.com

    Granted Duncan being a member of the VMware CTO office covers a lot of VMware related themes, however being the author of several books, he also covers non VMware related topics. Duncan recently did a really good and simple post about rebuilding a failed disk in a VMware VSAN vs. in a legacy RAID or erasure code based storage solution.

    One of the things that struck me as being important with what Duncan wrote about is avoiding apples to oranges comparisons. What I mean by this is that it is easy to compare traditional parity based or mirror type solutions that chunk or shard data on KByte basis spread over disks, vs. data that is chunk or sharded on GByte (or larger) basis over multiple servers and their disks. Anyway, check out Duncan’s site and recent post by clicking here.

    Server StorageIO Industry Resources and Links

    Check out these useful links and pages:

    storageio.com/links
    objectstoragecenter.com
    storageioblog.com/data-protection-diaries-main/
    storageperformance.us
    thenvmeplace
    thessdplace.com
    storageio.com/performance.com
    storageio.com/raid
    storageio.com/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

    RIP Windows SIS (Single Instance Storage), or at least in Server 2016

    RIP Windows SIS, or at least in Server 2016

    server storage I/O trends

    I received as a Microsoft MVP a partner communication today from Microsoft of a heads up as well as pass on to others that Single Instance Storage (SIS) has been removed from Windows Server 2016 (Read the Microsoft Announcement here, or below). Windows SIS is part of Microsoft’s portfolio of tools and technology for implementing Data Footprint Reduction (DFR).

    Granted Windows Server 2016 has not been released yet, however you can download and try out the latest release such as Technical Preview 4 (TP4), get the bits from Microsoft here. Learn more about some of the server and storage I/O enhancements in TP4 including storage spaces direct here.

    Partner Communication from Microsoft

    Partner Communication
    Please relay or forward this notification to ISVs and hardware partners that have used Single Instance Storage (SIS) or implemented the SIS backup API.

    Single Instance Storage (SIS) has been removed from Windows Server 2016
    Summary:   Single Instance Storage (SIS), a file system filter driver used for NTFS file deduplication, has been removed from Windows Server. In Dec 2015, the SIS feature has been completely removed from Windows Server and Windows Storage Server editions.  SIS was officially deprecated in Windows Server 2012 R2 in this announcement and will be removed from future Windows Server Technical Preview releases.

    Call to action:
    Storage vendors that have any application dependencies on legacy SIS functions or SIS backup and restore APIs should verify that their applications behave as expected on Windows Server 2016 and Windows Storage Server 2016. Windows Server 2012 included Microsoft’s next generation of deduplication technology that uses variable-sized chunking and hashing and offers far superior deduplication rates. Users and backup vendors have already moved to support the latest Microsoft deduplication technology and should continue to do so.

    Background:
    SIS was developed and used in Windows Server since 2000, when it was part of Remote Installation Services. SIS became a general purpose file system filter driver in Windows Storage Server 2003 and the SIS groveler (the deduplication engine) was included in Windows Storage Server. In Windows Storage Server 2008, the SIS legacy read/write filter driver was upgraded to a mini-filter and it shipped in Windows Server 2008, Windows Server 2012 and Windows Server 2012 R2 editions. Creating SIS-controlled volumes could only occur on Windows Storage Server, however, all editions of Windows Server could read and write to volumes that were under SIS control and could restore and backup volumes that had SIS applied.

    Volumes using SIS that are restored or plugged into Windows Server 2016 will only be able to read data that was not deduplicated. Prior to migrating or restoring a volume, users must remove SIS from the volume by copying it to another location or removing SIS using SISadmin commands.

    The SIS components and features:

    • SIS Groveler. The SIS Groveler searched for files that were identical on the NTFS file system volume. It then reported those files to the SIS filter driver.
    • SIS Storage Filter. The SIS Storage Filter was a file system filter that managed duplicate copies of files on logical volumes. This filter copied one instance of the duplicate file into the Common Store. The duplicate copies were replaced with a link to the Common Store to improve disk space utilization.
    • SIS Link. SIS links were pointers within the file system, maintaining both application and user experience (including attributes such as file size and directory path) while I/O was transparently redirected to the actual duplicate file located within the SIS Common Store.
    • SIS Common Store. The SIS Common Store served as the repository for each file identified as having duplicates. Each SIS-maintained volume contained one SIS Common Store, which contained all of the merged duplicate files that exist on that volume.
    • SIS Administrative Interface. The SIS Administrative Interface gave network administrators easy access to all SIS controls to simplify management.
    • SIS Backup API. The SIS Backup API (Sisbkup.dll) helped OEMs create SIS-aware backup and restoration solutions.

    References:
    https://msdn.microsoft.com/en-us/library/windows/desktop/aa362538(v=vs.85).aspx
    https://msdn.microsoft.com/en-us/library/windows/desktop/aa362512(v=vs.85).aspx
    https://msdn.microsoft.com/en-us/library/dexter.functioncatall.sis(v=vs.90).aspx
    https://blogs.technet.com/b/filecab/archive/2012/05/21/introduction-to-data-deduplication-in-windows-server-2012.aspx
    https://blogs.technet.com/b/filecab/archive/2006/02/03/single-instance-store-sis-in-windows-storage-server-r2.aspx

    What this all means

    Like it or not, SIS is being removed from Windows 2016 replaced by the new Microsoft deduplication or data footprint reduction (DFR) technology.

    You have been advised…

    RIP Windows SIS

    Ok, nuff said (for now)

    Cheers
    Gs

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

    All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2023 Server StorageIO(R) and UnlimitedIO All Rights Reserved

    Server StorageIO December 2015 Update Newsletter


    Server and StorageIO Update Newsletter

    Volume 15, Issue XII – End of Year (EOY) Edition

    Hello and welcome to this December 2015 Server StorageIO update newsletter.

    Seasons Greetings and Happy New Years.

    Winter has arrived here in the northern hemisphere and it is also the last day of 2015 e.g. End Of Year or EOY). For some this means relaxing and having fun after a busy year, for others, it’s the last day of the most important quarter of the most important year ever, particular if you are involved in sales or spending.

    This is also that time of year where predictions for 2016 will start streaming out as well as reflections looking back at 2015 appear (more on these in January). Another EOY activity is planning for 2016 as well as getting items ready for roll-out or launch in the new year. Overall 2015 has been a very good year with many things in the works both public facing, as well as several behind the scenes some of which will start to appear throughout 2016.

    Enjoy this abbreviated edition of the Server StorageIO update newsletter and watch for new tips, articles, predictions, StorageIO lab report reviews, blog posts, videos and podcast’s along with in the news commentary appearing soon.

    Thank you for enabling a successful 2015 and wishing you all a prosperous new year in 2016.

    Cheers GS

    In This Issue

  • Tips and Articles
  • Events and Webinars
  • Resources and Links
  • StorageIO Tips and Articles

    Recent Server StorageIO articles appearing in different venues include:

    • IronMountain:  5 Noteworthy Data Privacy Trends From 2015
    • Virtual Blocks (VMware Blogs):  Part III EVO:RAIL – When And Where To Use It?
    • InfoStor:  Object Storage Is In Your Future
    • InfoStor:  Water, Data and Storage Analogy

    Check out these resources and links technology, techniques, trends as well as tools. View more tips and articles here

    StorageIO Webinars and Industry Events

    EMCworld (Las Vegas) May 2-4, 2016

    Interop (Las Vegas) May 4-6 2016

    NAB (Las Vegas) April 19-20, 2016

    Redmond Magazine Gridstore (How to Migrate from VMware to Hyper-V) February 25, 2016 Webinar (11AM PT)

    See more webinars and other activities on the Server StorageIO Events page here.

    Server StorageIO Industry Resources and Links

    Check out these useful links and pages:

    storageio.com/links
    objectstoragecenter.com
    storageioblog.com/data-protection-diaries-main/
    storageperformance.us
    thenvmeplace
    thessdplace.com
    storageio.com/raid
    storageio.com/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

    NVMe Place NVM Non Volatile Memory Express Resources

    Updated 8/31/19
    NVMe place server Storage I/O data infrastructure trends

    Welcome to NVMe place NVM Non Volatile Memory Express Resources. NVMe place is about Non Volatile Memory (NVM) Express (NVMe) with Industry Trends Perspectives, Tips, Tools, Techniques, Technologies, News and other information.

    Disclaimer

    Please note that this NVMe place resources site is independent of the industry trade and promoters group NVM Express, Inc. (e.g. www.nvmexpress.org). NVM Express, Inc. is the sole owner of the NVM Express specifications and trademarks.

    NVM Express Organization
    Image used with permission of NVM Express, Inc.

    Visit the NVM Express industry promoters site here to learn more about their members, news, events, product information, software driver downloads, and other useful NVMe resources content.

     

    The NVMe Place resources and NVM including SCM, PMEM, Flash

    NVMe place includes Non Volatile Memory (NVM) including nand flash, storage class memories (SCM), persistent memories (PM) are storage memory mediums while NVM Express (NVMe) is an interface for accessing NVM. This NVMe resources page is a companion to The SSD Place which has a broader Non Volatile Memory (NVM) focus including flash among other SSD topics. NVMe is a new server storage I/O access method and protocol for fast access to NVM based storage and memory technologies. NVMe is an alternative to existing block based server storage I/O access protocols such as AHCI/SATA and SCSI/SAS devices commonly used for access Hard Disk Drives (HDD) along with SSD among other things.

    Server Storage I/O NVMe PCIe SAS SATA AHCI
    Comparing AHCI/SATA, SCSI/SAS and NVMe all of which can coexist to address different needs.

    Leveraging the standard PCIe hardware interface, NVMe based devices (that have an NVMe controller) can be accessed via various operating systems (and hypervisors such as VMware ESXi) with both in the box drivers or optional third-party device drivers. Devices that support NVMe can be 2.5″ drive format packaged that use a converged 8637/8639 connector (e.g. PCIe x4) coexisting with SAS and SATA devices as well as being add-in card (AIC) PCIe cards supporting x4, x8 and other implementations. Initially, NVMe is being positioned as a back-end to servers (or storage systems) interface for accessing fast flash and other NVM based devices.

    NVMe as back-end storage
    NVMe as a “back-end” I/O interface for NVM storage media

    NVMe as front-end server storage I/O interface
    NVMe as a “front-end” interface for servers or storage systems/appliances

    NVMe has also been shown to work over low latency, high-speed RDMA based network interfaces including RoCE (RDMA over Converged Ethernet) and InfiniBand (read more here, here and here involving Mangstor, Mellanox and PMC among others). What this means is that like SCSI based SAS which can be both a back-end drive (HDD, SSD, etc) access protocol and interface, NVMe can also being used for back-end can also be used as a front-end of server to storage interface like how Fibre Channel SCSI_Protocol (aka FCP), SCSI based iSCSI, SCSI RDMA Protocol via InfiniBand (among others) are used.

    NVMe features

    Main features of NVMe include among others:

    • Lower latency due to improve drivers and increased queues (and queue sizes)
    • Lower CPU used to handle larger number of I/Os (more CPU available for useful work)
    • Higher I/O activity rates (IOPs) to boost productivity unlock value of fast flash and NVM
    • Bandwidth improvements leveraging various fast PCIe interface and available lanes
    • Dual-pathing of devices like what is available with dual-path SAS devices
    • Unlock the value of more cores per processor socket and software threads (productivity)
    • Various packaging options, deployment scenarios and configuration options
    • Appears as a standard storage device on most operating systems
    • Plug-play with in-box drivers on many popular operating systems and hypervisors

    Shared external PCIe using NVMe
    NVMe and shared PCIe (e.g. shared PCIe flash DAS)

    NVMe related content and links

    The following are some of my tips, articles, blog posts, presentations and other content, along with material from others pertaining to NVMe. Keep in mind that the question should not be if NVMe is in your future, rather when, where, with what, from whom and how much of it will be used as well as how it will be used.

    • How to Prepare for the NVMe Server Storage I/O Wave (Via Micron.com)
    • Why NVMe Should Be in Your Data Center (Via Micron.com)
    • NVMe U2 (8639) vs. M2 interfaces (Via Gamersnexus)
    • Enmotus FuzeDrive MicroTiering (StorageIO Lab Report)
    • EMC DSSD D5 Rack Scale Direct Attached Shared SSD All Flash Array Part I (Via StorageIOBlog)
    • Part II – EMC DSSD D5 Direct Attached Shared AFA (Via StorageIOBlog)
    • NAND, DRAM, SAS/SCSI & SATA/AHCI: Not Dead, Yet! (Via EnterpriseStorageForum)
    • Non Volatile Memory (NVM), NVMe, Flash Memory Summit and SSD updates (Via StorageIOblog)
    • Microsoft and Intel showcase Storage Spaces Direct with NVM Express at IDF ’15 (Via TechNet)
    • MNVM Express solutions (Via SuperMicro)
    • Gaining Server Storage I/O Insight into Microsoft Windows Server 2016 (Via StorageIOblog)
    • PMC-Sierra Scales Storage with PCIe, NVMe (Via EEtimes)
    • RoCE updates among other items (Via InfiniBand Trade Association (IBTA) December Newsletter)
    • NVMe: The Golden Ticket for Faster Flash Storage? (Via EnterpriseStorageForum)
    • What should I consider when using SSD cloud? (Via SearchCloudStorage)
    • MSP CMG, Sept. 2014 Presentation (Flash back to reality – Myths and Realities – Flash and SSD Industry trends perspectives plus benchmarking tips)– PDF
    • Selecting Storage: Start With Requirements (Via NetworkComputing)
    • PMC Announces Flashtec NVMe SSD NVMe2106, NVMe2032 Controllers With LDPC (Via TomsITpro)
    • Exclusive: If Intel and Micron’s “Xpoint” is 3D Phase Change Memory, Boy Did They Patent It (Via Dailytech)
    • Intel & Micron 3D XPoint memory — is it just CBRAM hyped up? Curation of various posts (Via Computerworld)
    • How many IOPS can a HDD, HHDD or SSD do (Part I)?
    • How many IOPS can a HDD, HHDD or SSD do with VMware? (Part II)
    • I/O Performance Issues and Impacts on Time-Sensitive Applications (Via CMG)
    • Via EnterpriseStorageForum: 5 Hot Storage Technologies to Watch
    • Via EnterpriseStorageForum: 10-Year Review of Data Storage

    Non-Volatile Memory (NVM) Express (NVMe) continues to evolve as a technology for enabling and improving server storage I/O for NVM including nand flash SSD storage. NVMe streamline performance enabling more work to be done (e.g. IOPs), data to be moved (bandwidth) at a lower response time using less CPU.

    NVMe and SATA flash SSD performance

    The above figure is a quick look comparing nand flash SSD being accessed via SATA III (6Gbps) on the left and NVMe (x4) on the right. As with any server storage I/O performance comparisons there are many variables and take them with a grain of salt. While IOPs and bandwidth are often discussed, keep in mind that with the new protocol, drivers and device controllers with NVMe that streamline I/O less CPU is needed.

    Additional NVMe Resources

    Also check out the Server StorageIO companion micro sites landing pages including thessdplace.com (SSD focus), data protection diaries (backup, BC/DR/HA and related topics), cloud and object storage, and server storage I/O performance and benchmarking here.

    If you are in to the real bits and bytes details such as at device driver level content check out the Linux NVMe reflector forum. The linux-nvme forum is a good source if you are developer to stay up on what is happening in and around device driver and associated topics.

    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

    Disclaimer

    Disclaimer: Please note that this site is independent of the industry trade and promoters group NVM Express, Inc. (e.g. www.nvmexpress.org). NVM Express, Inc. is the sole owner of the NVM Express specifications and trademarks. Check out the NVM Express industry promoters site here to learn more about their members, news, events, product information, software driver downloads, and other useful NVMe resources content.

    NVM Express Organization
    Image used with permission of NVM Express, Inc.

    Wrap Up

    Watch for updates with more content, links and NVMe resources to be added here soon.

    Ok, nuff said (for now)

    Cheers
    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.