Tag: all-flash

Posted on

How to Achieve Flexible Data Protection Availability with All Flash Storage Solutions

Achieve Flexible Data Protection Availability with All Flash Solutions

server storage I/O data infrastructure trends

Updated 1/21/2018

How to Achieve Flexible flash data protection and Availability with All-Flash Storage Solutions

Interactive webinar discussion (not death by power point or Ui Gui product demo ;) pertaining flash data protection )
Tuesday January 30 2018 11AM PT / 2PM ET
Via Redmond Magazine (Free with registration)

Everything is not the same across different organizations, environments, application workloads and the data infrastructures that support them. Fast application and workloads need fast protection, restoration, and resumption as well as fast flash storage. This applies across legacy, software-defined, virtual, container, cloud, hybrid, converged and HCI among other environments.

SDDC Data Infrastructure Data Protection

Join me along with representatives from Pure Storage along with Veeam for this interactive discussion as we explore how to boost the performance, availability, capacity, and economics (PACE) of your applications along with the data infrastructures that support them.

  • How all-flash storage enables faster protection and restoration of fast applications
  • Why data protection and availability should not be an afterthought
  • Ways to leverage your data protection storage to drive business change
  • How to simplify and reduce complexity to boost productivity while lowering costs
  • Why workload aggregation consolidation should not cause aggravation

Register for the live event or catch the replay here.

Where to learn more

Learn more about data protection, SSD, flash, data infrastructure and related topics via the following links:

SDDC Data Infrastructure

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

Software Defined Data Infrastructure Essentials Book SDDC

What this all means and wrap-up

Fast applications need fast and resilient data infrastructures that include server, storage, I/O networking along with data protection. Likewise performance depends on availability along with durability, likewise, availability and accessibility depend on performance, they go hand in hand. Join me and others from Pure Storage as well as Veeam for this conversational discussion about How to Achieve Flexible Data Protection and Availability with All-Flash Storage Solutions.

Ok, nuff said, for now.

Gs

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

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

Posted on

VMware vSAN 6.6 hyper-converged (HCI) software defined data infrastructure

server storage I/O trends

VMware vSAN 6.6 hyper-converged (HCI) software defined data infrastructure

In case you missed it, VMware announced vSAN v6.6 hyper-converged infrastructure (HCI) software defined data infrastructure solution. This is the first of a five-part series about VMware vSAN V6.6. Part II (just the speeds feeds please) is located here, part III (reducing cost and complexity) located here, part IV (scaling ROBO and data centers today) found here, as well as part V here (VMware vSAN evolution, where to learn more and summary).

VMware vSAN 6.6
Image via VMware

For those who are not aware, vSAN is a VMware virtual Storage Area Network (e.g. vSAN) that is software-defined, part of being a software-defined data infrastructure (SDDI) and software-defined data center (SDDC). Besides being software-defined vSAN is HCI combining compute (server), I/O networking, storage (space and I/O) along with hypervisors, management, and other tools.

Software-defined data infrastructure

Excuse Me, What is vSAN and who is if for

Some might find it odd having to explain what vSAN is, on the other hand, not everybody is dialed into the VMware world ecosystem, so let’s give them some help, for everybody else, and feel free to jump ahead.

For those not familiar, VMware vSAN is an HCI software-defined storage solution that converges compute (hypervisors and server) with storage space capacity and I/O performance along with networking. Being HCI means that with vSAN as you scale compute, storage space capacity and I/O performance also increases in an aggregated fashion. Likewise, increase storage space capacity and server I/O performance you also get more compute capabilities (along with memory).

For VMware-centric environments looking to go CI or HCI, vSAN offers compelling value proposition leveraging known VMware tools and staff skills (knowledge, experience, tradecraft). Another benefit of vSAN is the ability to select your hardware platform from different vendors, a trend that other CI/HCI vendors have started to offer as well.

CI and HCI data infrastructure

Keep in mind that fast applications need a fast server, I/O and storage, as well as server storage I/O needs CPU along with memory to generate I/O operations (IOPs) or move data. What this all means is that HCI solutions such as VMware vSAN combine or converge the server compute, hypervisors, storage file system, storage devices, I/O and networking along with other functionality into an easy to deploy (and management) turnkey solution.

Learn more about CI and HCI along with who some other vendors are as well as considerations at www.storageio.com/converge. Also, visit VMware sites to find out more about vSphere ESXi hypervisors, vSAN, NSX (Software Defined Networking), vCenter, vRealize along with other tools for enabling SDDC and SDDI.

Give Me the Quick Elevator Pitch Summary

VMware has enhanced vSAN with version 6.6 (V6.6) enabling new functionality, supporting new hardware platforms along with partners, while reducing costs, improving scalability and resiliency for SDDC and SDDI environments. This includes from small medium business (SMB) to mid-market to small medium enterprise (SME) as well as workgroup, departmental along with Remote Office Branch Office (ROBO).

Being a HCI solution, management functions of the server, storage, I/O, networking, hypervisor, hardware, and software are converged to improve management productivity. Also, vSAN integrated with VMware vSphere among other tools enable modern, robust data infrastructure that serves, protect, preserve, secure and stores data along with their associated applications.

Where to Learn More

The following are additional resources to learn more about vSAN and related technologies.

What this all means

Overall a good set of enhancements as vSAN continues its evolution looking back just a few years ago, to where it is today and will be in the future. If you have not looked at vSAN recently, take some time beyond reading this piece to learn some more.

Continue reading more about VMware vSAN 6.6 in part II (just the speeds feeds please) is located here, part III (reducing cost and complexity) located here, part IV (scaling ROBO and data centers today) located here, as well as part V here (VMware vSAN evolution, where to learn more and summary).

Ok, nuff said (for now…).

Cheers
Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert (and vSAN). Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Watch for the spring 2017 release of his new book “Software-Defined Data Infrastructure Essentials” (CRC Press).

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

Posted on

VMware vSAN V6.6 Part II (just the speeds feeds features please)

server storage I/O trends

VMware vSAN v6.6 Part II (just the speeds feeds features please)

In case you missed it, VMware announced vSAN v6.6 hyper-converged infrastructure (HCI) software defined data infrastructure solution. This is the second of a five-part series about VMware vSAN V6.6. View Part I here, part III (reducing cost and complexity) located here, part IV (scaling ROBO and data centers today) found here, as well as part V here (VMware vSAN evolution, where to learn more and summary).

VMware vSAN 6.6
Image via VMware

For those who are not aware, vSAN is a VMware virtual Storage Area Network (e.g. vSAN) that is software-defined, part of being a software-defined data infrastructure (SDDI) and software-defined data center (SDDC). Besides being software-defined vSAN is HCI combining compute (server), I/O networking, storage (space and I/O) along with hypervisors, management, and other tools.

Just the Speeds and Feeds Please

For those who just want to see the list of what’s new with vSAN V6.6, here you go:

  • Native encryption for data-at-rest
  • Compliance certifications
  • Resilient management independent of vCenter
  • Degraded Disk Handling v2.0 (DDHv2)
  • Smart repairs and enhanced rebalancing
  • Intelligent rebuilds using partial repairs
  • Certified file service & data protection solutions
  • Stretched clusters with local failure protection
  • Site affinity for stretched clusters
  • 1-click witness change for Stretched Cluster
  • vSAN Management Pack for vRealize
  • Enhanced vSAN SDK and PowerCLI
  • Simple networking with Unicast
  • vSAN Cloud Analytics with real-time support notification and recommendations
  • vSAN ConfigAssist with 1-click hardware lifecycle management
  • Extended vSAN Health Services
  • vSAN Easy Install with 1-click fixes
  • Up to 50% greater IOPS for all-flash with optimized checksum and dedupe
  • Support for new next-gen workloads
  • vSAN for Photon in Photon Platform 1.1
  • Day 0 support for latest flash technologies
  • Expanded caching tier choice
  • Docker Volume Driver 1.1

What’s New and Value Proposition of vSAN 6.6

Let’s take a closer look beyond the bullet list of what’s new with vSAN 6.6, as well as perspectives of those features to address different needs. The VMware vSAN proposition is to evolve and enable modernizing data infrastructures with HCI powered by vSphere along with vSAN.

Three main themes or characteristics (and benefits) of vSAN 6.6 include addressing (or enabling):

  • Reducing risk while scaling
  • Reducing cost and complexity
  • Scaling for today and tomorrow

VMware vSAN 6.6 summary
Image via VMware

Reducing risk while scaling

Reducing (or removing) risk while evolving your data infrastructure with HCI including flexibility of choosing among five support hardware vendors along with native security. This includes native security, availability and resiliency enhancements (including intelligent rebuilds) without sacrificing storage efficiency (capacity) or effectiveness (performance productivity), management and choice.

VMware vSAN DaRE
Image via VMware

Dat level Data at Rest Encryption (DaRE) of all vSAN dat objects that are enabled at a cluster level. The new functionality supports hybrid along with all flash SSD as well as stretched clusters. The VMware vSAN DaRE implementation is an alternative to using self-encrypting drives (SEDs) reducing cost, complexity and management activity. All vSAN features including data footprint reduction (DFR) features such as compression and deduplication are supported. For security, vSAN DaRE integrations with compliance key management technologies including those from SafeNet, Hytrust, Thales and Vormetric among others.

VMware vSAN management
Image via VMware

ESXi HTML 5 based host client, along with CLI via ESXCLI for administering vSAN clusters as an alternative in case your vCenter server(s) are offline. Management capabilities include monitoring of critical health and status details along with configuration changes.

VMware vSAN health management
Image via VMware

Health monitoring enhancements include handling of degraded vSAN devices with intelligence proactively detecting impending device failures. As part of the functionality, if a replica of the failing (or possible soon to fail) device exists, vSAN can take action to maintain data availability.

Where to Learn More

The following are additional resources to find out more about vSAN and related technologies.

What this all means

With each new release, vSAN is increasing its feature, functionality, resiliency and extensiveness associated with traditional storage and non-CI or HCI solutions. Continue reading more about VMware vSAN 6.6 in Part I here, part III (reducing cost and complexity) located here, part IV (scaling ROBO and data centers today) found here, as well as part V here (VMware vSAN evolution, where to learn more and summary).

Ok, nuff said (for now…).

Cheers
Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert (and vSAN). Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Watch for the Spring 2017 release of his new book “Software-Defined Data Infrastructure Essentials” (CRC Press).

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

Posted on

VMware vSAN V6.6 Part III (reducing costs complexity)

server storage I/O trends

VMware vSAN V6.6 Part III (Reducing costs complexity)

In case you missed it, VMware announced vSAN v6.6 hyper-converged infrastructure (HCI) software defined data infrastructure solution. This is the third of a five-part series about VMware vSAN V6.6. View Part I here, Part II (just the speeds feeds please) is located here, part IV (scaling ROBO and data centers today) found here, as well as part V here (VMware vSAN evolution, where to learn more and summary).

VMware vSAN 6.6
Image via VMware

For those who are not aware, vSAN is a VMware virtual Storage Area Network (e.g. vSAN) that is software-defined, part of being a software-defined data infrastructure (SDDI) and software-defined data center (SDDC). Besides being software-defined vSAN is HCI combining compute (server), I/O networking, storage (space and I/O) along with hypervisors, management, and other tools.

Reducing cost and complexity

Reducing your total cost of ownership (TCO) including lower capital expenditures (CapEx) and operating (OPEX). VMware is claiming CapEx and OpEx reduced TCO of 50%. Keep in mind that solutions such as vSAN also can help drive return on investment (ROI) as well as return on innovation (the other ROI) via improved productivity, effectiveness, as well as efficiencies (savings). Another aspect of addressing TCO and ROI includes flexibility leveraging stretched clusters to address HA, BR, BC and DR Availability needs cost effectively. These enhancements include efficiency (and effectiveness e.g. productivity) at scale, proactive cloud analytics, and intelligent operations.

VMware vSAN stretch cluster
Image via VMware

Low cost (or cost-effective) Local, Remote Resiliency and Data Protection with Stretched Clusters across sites. Upon a site failure, vSAN maintains availability is leveraging surviving site redundancy. For performance and productivity effectiveness, I/O traffic is kept local where possible and practical, reducing cross-site network workload. Bear in mind that the best I/O is the one you do not have to do, the second is the one with the least impact.

This means if you can address I/Os as close to the application as possible (e.g. locality of reference), that is a better I/O. On the other hand, when data is not local, then the best I/O is the one involving a local or remote site with least overhead impact to applications, as well as server storage I/O (including networks) resources. Also keep in mind that with vSAN you can fine tune availability, resiliency and data protection to meet various needs by adjusting fault tolerant mode (FTM) to address a different number of failures to tolerate.

server storage I/O locality of reference

Network and cloud friendly Unicast Communication enhancements. To improve performance, availability, and capacity (CPU demand reduction) multicast communications are no longer used making for easier, simplified single site and stretched cluster configurations. When vSAN clusters upgrade to V6.6 unicast is enabled.

VMware vSAN unicast
Image via VMware

Gaining insight, awareness, adding intelligence to avoid flying blind, introducing vSAN Cloud Analytics and Proactive Guidance. Part of a VMware customer, experience improvement program, leverages cloud-based health checks for easy online known issue detection along with relevant knowledge bases pieces as well as other support notices. Whether you choose to refer to this feature as advanced analytics, artificial intelligence (AI), proactive rules enabled management problem isolation, solving resolution I will leave that up to you.

VMware vSAN cloud analytics
Image via VMware

Part of the new tools analytics capabilities and prescriptive problem resolution (hmm, some might call that AI or advanced analytics, just saying), health check issues are identified, notifications along with suggested remediation. Another feature is the ability to leverage continuous proactive updates for advance remediation vs. waiting for subsequent vSAN releases. Net result and benefit are reducing time, the complexity of troubleshooting converged data infrastructure issues spanning servers, storage, I/O networking, hardware, software, cloud, and configuration. In other words, enable you more time to be productive vs. finding and fixing problems leveraging informed awareness for smart decision-making.

Where to Learn More

The following are additional resources to find out more about vSAN and related technologies.

What this all means

Continue reading more about VMware vSAN 6.6 in part I here, part II (just the speeds feeds please) located here, part IV (scaling ROBO and data centers today) found here, as well as part V here (VMware vSAN evolution, where to learn more and summary).

Ok, nuff said (for now…).

Cheers
Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert (and vSAN). Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Watch for the spring 2017 release of his new book “Software-Defined Data Infrastructure Essentials” (CRC Press).

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

Posted on

VMware vSAN V6.6 Part IV (HCI scaling ROBO and data centers today)

server storage I/O trends

VMware vSAN V6.6 Part IV (HCI scaling ROBO and data centers today)

In case you missed it, VMware announced vSAN v6.6 hyper-converged infrastructure (HCI) software defined data infrastructure solution. This is the fourth of a five-part series about VMware vSAN V6.6. View Part I here, Part II (just the speeds feeds please) is located here, part III (reducing cost and complexity) located here, as well as part V here (VMware vSAN evolution, where to learn more and summary).

VMware vSAN 6.6
Image via VMware

For those who are not aware, vSAN is a VMware virtual Storage Area Network (e.g. vSAN) that is software-defined, part of being a software-defined data infrastructure (SDDI) and software-defined data center (SDDC). Besides being software-defined vSAN is HCI combining compute (server), I/O networking, storage (space and I/O) along with hypervisors, management, and other tools.

Scaling HCI for ROBO and data centers today and for tomorrow

Scaling with stability for today and tomorrow. This includes addressing your applications Performance, Availability, Capacity and Economics (PACE) workload requirements today and for the future. By scaling with stability means boosting performance, availability (data protection, security, resiliency, durable, FTT), effective capacity without one of those attributes compromising another.

VMware vSAN data center scaling
Image via VMware

Scaling today for tomorrow also means adapting to today’s needs while also flexible to evolve with new application workloads, hardware as well as a cloud (public, private, hybrid, inter and intra-cloud). As part of continued performance improvements, enhancements to optimize for higher performance flash SSD including NVMe based devices.

VMware vSAN cloud analytics
Image via VMware

Part of scaling with stability means enhancing performance (as well as productivity) or the effectiveness of a solution. Keep in mind that efficiency is often associated with storage (or server or network) space capacity savings or reductions. In that context then effectiveness means performance and productivity or how much work can be done with least overhead impact. With vSAN, V6.6 performance enhancements include reduced checksum overhead, enhanced compression, and deduplication, along with destaging optimizations.

Other enhancements that help collectively contribute to vSAN performance improvements include VMware object handling (not to be confused with cloud or object storage S3 or Swift objects) as well as faster iSCSI for vSAN. Also improved are more accurate refined cache sizing guidelines. Keep in mind that a little bit of NAND flash SSD or SCM in the right place can have a significant benefit, while a lot of flash cache costs much cash.

Part of enabling and leveraging new technology today includes support for larger capacity 1.6TB flash SSD drives for cache, as well as lower read latency with 3D XPoint and NVMe drives such as those from Intel among others. Refer to the VMware vSAN HCL for current supported devices which continue evolve along with the partner ecosystem. Future proofing is also enabled where you can grow from today to tomorrow as new storage class memories (SCM) among other flash SSD as well as NVMe enhanced storage among other technologies are introduced into the market as well as VMware vSAN HCL.

VMware vSAN and data center class applications
Image via VMware

Traditional CI and in particular many HCI solutions have been optimized or focused on smaller application workloads including VDI resulting in the perception that HCI, in general, is only for smaller environments, or larger environment non-mission critical workloads. With vSAN V6.6 VMware is addressing and enabling larger environment mission critical applications including Intersystem Cache medical health management software among others. Other application workload extensions including support for higher performance demanding Hadoop big data analytics, a well as extending virtual desktop infrastructure (VDI) workspace with XenDesktop/XenApp, along with Photon 1.1 container support.

What about VMware vSAN 6.6. Packaging and License Options

As part of vSAN 6.6 VMware several solution bundle packaged options for the data center as well as smaller ROBO environment. Contact your VMware representative or partner to learn more about specific details.

VMware vSAN cloud analytics
Image via VMware

VMware vSAN cloud analytics
Image via VMware

Where to Learn More

The following are additional resources to find out more about vSAN and related technologies.

What this all means

Continue reading more about VMware vSAN 6.6 in part I here, part II (just the speeds feeds please) is located here, part III (reducing cost and complexity) located here as well as part V here (VMware vSAN evolution, where to learn more and summary).

Ok, nuff said (for now…).

Cheers
Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert (and vSAN). Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Watch for the Spring 2017 release of his new book “Software-Defined Data Infrastructure Essentials” (CRC Press).

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

Posted on

VMware vSAN V6.6 Part V (vSAN evolution and summary)

server storage I/O trends

VMware vSAN V6.6 Part V (vSAN evolution and summary)

In case you missed it, VMware announced vSAN v6.6 hyper-converged infrastructure (HCI) software defined data infrastructure solution. This is the fifth of a five-part series about VMware vSAN V6.6. View Part I here, Part II (just the speeds feeds please) is located here, part III (reducing cost and complexity) found here, part IV (scaling ROBO and data centers today) located here.

VMware vSAN 6.6
Image via VMware

For those who are not aware, vSAN is a VMware virtual Storage Area Network (e.g. vSAN) that is software-defined, part of being a software-defined data infrastructure (SDDI) and software-defined data center (SDDC). Besides being software-defined vSAN is HCI combining compute (server), I/O networking, storage (space and I/O) along with hypervisors, management, and other tools.

How has vSAN (formerly referred to as VSAN) Evolved

A quick recap of the VMware vSAN progression which first appeared as part of vSphere 5.5. (e.g. vSAN 5.5 can be thought of 1.0 in some ways) consists of several releases. Since vSAN is tightly integrated with VMware vSphere along with associated management tools, there is a correlation between enhancements to the underlying hypervisor, and added vSAN functionality. Keep in mind sometimes by seeing where something has been, helps to view where going.

Previous vSAN enhancements include:

  • 5.5 Hybrid (mixed HDD and flash)
  • 6.2 (2016) All flash (e.g. AFA) versions included data footprint reduction (DFR) technologies such as compression and dedupe along with performance Quality of Service (QoS) enhancements.
  • 6.5 Cross Cloud functionality including the announcement of container support, cloud-native apps, as well as upcoming vSphere, vSAN, NSX and other VMware software-defined data center (SDDC) and software-defined data infrastructure (SDDI) technology running natively on AWS (not on EC2) cloud infrastructure.
  • 6.6 Modern data infrastructure flexibility, scalability, resiliency, extensibility including performance, availability, capacity and economics (PACE).

V5.5

  • Distributed RAID
  • Per-VM SPBM
  • Set and change FTT via policy
  • In-kernel hyper-convergence engine
  • RVC and Observer

V6.0

  • All-flash architecture
  • Perf improvements (4xIOPS)
  • 64-node support
  • High-density storage blades
  • Fault domain awareness
  • Scalable snapshots and clones
  • Disk enclosure management

V6.1

  • Windows Failover Clustering
  • Oracle RAC support
  • HW checksum and encryption
  • 2-node ROBO mode
  • UltraDIMM and NVMe support
  • Stretch clusters
  • 5 min RPO (vSphere Rep)
  • SMP-FT support
  • Health Check, vROps, Log Insight

V6.2

  • IPv6 support
  • Software checksum
  • Nearline dedupe and compression on all-flash
  • Erasure coding on all-flash
  • QoS IOPS limits
  • Performance monitoring service

V6.5

  • iSCSI
  • 2-Node direct connect
  • PowerCLI
  • Public APIs and SDK
  • 512e support
  • All-Flash to all editions

Where to Learn More

The following are additional resources to find out more about vSAN and related technologies.

What this all means, wrap up and summary

VMware continues to extend the software-defined data center (SDDC) and Software-Defined Data Infrastructure (SDDI) ecosystem with vSAN to address the needs from smaller SMB and ROBO environments to larger SME and enterprise workloads. To me a theme with V6.6 is expanding resiliency, scalability with stability to expand vSAN upmarket as well as into new workloads similar to how vSphere has evolved.

With each new release, vSAN is increasing its feature, functionality, resiliency and extensiveness associated with traditional storage and non-CI or HCI solutions. Overall a good set of enhancements as vSAN continues its evolution looking back just a few years ago, to where it is today and will be in the future. If you have not looked at vSAN recently, take some time beyond reading this piece to learn some more.

Ok, nuff said (for now…).

Cheers
Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert (and vSAN). Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Watch for the Spring 2017 release of his new book “Software-Defined Data Infrastructure Essentials” (CRC Press).

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

Posted on

Cisco Next Gen 32Gb Fibre Channel NVMe SAN Updates

server storage I/O trends

Cisco Next Gen 32Gb Fibre Channel and NVMe SAN Updates

Cisco announced today next generation MDS storage area networking (SAN) Fibre Channel (FC) switches with 32Gb, along with NVMe over FC support.

Cisco Fibre Channel (FC) Directors (Left) and Switches (Right)

Highlights of the Cisco announcement include:

  • MDS 9700 48 port 32Gbps FC switching module
  • High density 768 port 32Gbps FC directors
  • NVMe over FC for attaching fast flash SSD devices (current MDS 9700, 9396S, 9250i and 9148S)
  • Integrated analytics engine for management insight awareness
  • Multiple concurrent protocols including NVMe, SCSI (e.g. SCSI_FCP aka FCP) and FCoE

Where to Learn More

The following are additional resources to learn more.

What this all means, wrap up and summary

Fibre Channel remains relevant for many environments and it makes sense that Cisco known for Ethernet along with IP networking enhance their offerings. By having 32Gb Fibre Channel, along with adding NVMe over Fabric provides existing (and new) Cisco customers to support their legacy (e.g. FC) and emerging (NVMe) workloads as well as devices. For those environments that still need some mix of Fibre Channel, as well as NVMe over fabric this is a good announcement. Keep an eye and ear open for which storage vendors jump on the NVMe over Fabric bandwagon now that Cisco as well as Brocade have made switch support announcements.

Ok, nuff said (for now…).

Cheers
Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert (and vSAN). Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Watch for the spring 2017 release of his new book “Software-Defined Data Infrastructure Essentials” (CRC Press).

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

Posted on

HPE Continues Buying Into Server Storage I/O Data Infrastructures

Storage I/O Data Infrastructures trends
Updated 1/16/2018

HPE expanded its Storage I/O Data Infrastructures portfolio buying into server storage I/O data infrastructure technologies announcing an all cash (e.g. no stock) acquisition of Nimble Storage (NMBL). The cash acquisition for a little over $1B USD amounts to $12.50 USD per Nimble share, double what it had traded at. As a refresh, or overview, Nimble is an all flash shared storage system leverage NAND flash solid storage device (SSD) performance. Note that Nimble also partners with Cisco and Lenovo platforms that compete with HPE servers for converged systems.

Earlier this year (keep in mind its only mid-March) HPE also announced acquisition of server storage Hyper-Converged Infrastructure (HCI) vendor Simplivity (about $650M USD cash). In another investment this year HPE joined other investors as part of scale out and software defined storage startups Hedvig latest funding round (more on that later). These acquisitions are in addition to smaller ones such as last years buying of SGI, not to mention various divestitures.

Data Infrastructures

What Are Server Storage I/O Data Infrastructures Resources

Data Infrastructures exists to support business, cloud and information technology (IT) among other applications that transform data into information or services. The fundamental role of data infrastructures is to give a platform environment for applications and data that is resilient, flexible, scalable, agile, efficient as well as cost-effective.

Technologies that make up data infrastructures include hardware, software, cloud or managed services, servers, storage, I/O and networking along with people, processes, policies along with various tools spanning legacy, software-defined virtual, containers and cloud.

HPE and Server Storage Acquisitions

HPE and its predecessor HP (e.g. before the split that resulted in HPE) was familiar with expanding its data infrastructure portfolio spanning servers, storage, I/O networking, hardware, software and services. These range from Compaq who acquired DEC which gave them the StorageWorks brand and product line up (e.g. recall EVA and its predecessors), Lefthand, 3PAR, IBRIX, Polyserve, Autonomy, EDS and others that I’m guessing some at HPE (along with customers and partners) might not want to remember.

In addition to their own in-house including via technology acquisition, HPE also partners for its entry-level and volume low-end MSA (Modular Storage Array) series with DotHill who was acquired by Seagate a year or so ago. In addition to the MSA, other HPE OEMs for storage include Hitachi Ltd. (e.g. parent of Hitachi Data Systems aka HDS) reselling their high-end enterprise class storage system as the XP7, as well as various other partner arrangements.

Keep in mind that HPE has a large server business from low to high-end, spanning towers to dense blades to dual, quad and cluster in box (CiB) configurations with various processor architectures. Some of these servers are used as platforms for not only HPE, also other vendors software defined storage, as well as tin wrapped software solutions, appliances and systems. HPE is also one of a handful of partners working with Microsoft to bring the software defined private (and hybrid) Azure Stack cloud stack as an appliance to market.

HPE acquisitions Dejavu or Something New?

For some people there may be a sense of Dejavu of what HPE and its predecessors have previously acquired, developed, sold and supported into the market over years (and decades in some cases). What will be interesting to see is how the 3PAR (StoreServ) and Lefthand based (StoreVirtual) as well as ConvergedSystem 250-HC product lines are realigned to make way for Nimble and Simplivity.

Likewise what will HPE do with MSA at the low-end, continue to leverage it for low-end and high-volume basic storage similar to Dell with the Netapp/Engenio powered MD series? Or will HPE try to move the Nimble down market and displace the MDS? What about in the mid-market, will Nimble be unleashed to replace StoreVirtual (e.g. Lefthand), or will they fence it in (e.g. being restricted to certain scenarios?
Will the Nimble solution be allowed to move up market into the low-end of where 3PAR has been positioned, perhaps even higher up given its all flash capabilities. Or, will there be a 3PAR everywhere approach?

Then there is Simplivity as the solution is effectively software running on an HPE server (or with other partners Cisco and Lenovo) along with a PCIe offload card (with Simplivity data services acceleration). Note that Simplivity leverages PCIe offload cards for some of their functionality, this too is familiar ground for HPE given its ASIC use by 3PAR.

Simplivity has the potential to disrupt some low to mid-range, perhaps even larger opportunities that are looking to go to a converged infrastructure (CI) or HCI deployment as part of their data infrastructure needs. One can speculate that Simplivity after repackaging will be positioned along current HPE CI and HCI solutions.

This will be interesting to watch to see if the HPE server and storage groups can converge not only from a technology point, also sales, marketing, service, and support perspective. With the Simplivity solution, HPE has an opportunity to move the industry thinking or perception that HCI is only for small environments defined by what some products can do.

What I mean by this is that HPE with its enterprise and SMB along with SME and cloud managed service provider experience as well as servers can bring hyper-scale out (and up) converged to the market. In other words, start addressing the concern I hear from larger organizations that most CI or HCI solutions (or packaging) are just for smaller environments. HPE has the servers, they have the storage from MSAs to other modules and core data infrastructure building blocks along with the robustness of the Simplivity software to enable hyper-scale out CI.

What about bulk, object, scale-out storage

HPE has a robust tape business, yes I know tape is dead, however tell that to the customers who keep buying products providing revenue along with margin to HPE (and others). Likewise HPE has VTLs as well as other solutions for addressing bulk data (e.g. big data, backups, protection copies, archives, high volume, and large quantity, what goes on tape or object). For example HPE has the StoreOnce solution.

However where is the HPE object storage story?

Otoh, does HPE its own object storage software, simply partner with others? HPE can continue to provide servers along with underlying storage for other vendors bulk, cloud and object storage systems, and where needed, meet in the channel among other arrangements.

On the other hand, this is where similar to Polyserve and Ibrix among others in the past have come into play, with HPE via its pathfinder (investment group) joining others in putting some money into Hedvig. HPE gets access to Hedvig for their scale out storage that can be used for bulk as well as other deployments including CI, HCI and CIB (e.g. something to sell HPE servers and storage with).

HPE can continue to partner with other software providers and software-defined storage stacks. Keep in mind that Milan Shetti (CTO, Data Center Infrastructure Group HPE) is no stranger to these waters given his past at Ibrix among others.

What About Hedvig

Time to get back to Hedvig which is a storage startup whose software can run on various server storage platforms, as well as in different topologies. Different topologies include in a CI or HCI, Cloud, as well as scale out with various access including block, file and object. In addition to block, file and object access, Hedvig has interesting management tools, data services, along with support for VMware, Docker, and OpenStack among others.

Recently Hedvig landed another $21.5M USD in funding bringing their total to about $52M USD. HPE via its investment arm, joins other investors (note HPE was part of the $21.5M, that was not the amount they invested) including Vertex, Atlantic Bridge, Redpoint, edbi and true ventures.

What does this mean for HPE and Hedvig among others? Tough to say however easy to imagine how Hedvig could be leveraged as a partner using HPE servers, as well as for HPE to have an addition to their bulk, scale-out, cloud and object storage portfolio.

Where to Learn More

View more material on HPE, data infrastructure and related topics with the following links.

  • Cloud and Object storage are in your future, what are some questions?
  • PCIe Server Storage I/O Network Fundamentals
  • If NVMe is the answer, what are the questions?
  • Fixing the Microsoft Windows 10 1709 post upgrade restart loop
  • Data Infrastructure server storage I/O network Recommended Reading
  • Introducing Windows Subsystem for Linux WSL Overview
  • IT transformation Serverless Life Beyond DevOps with New York Times CTO Nick Rockwell Podcast
  • HPE Announces AMD Powered Gen 10 ProLiant DL385 For Software Defined Workloads
  • AWS Announces New S3 Cloud Storage Security Encryption Features
  • NVM Non Volatile Memory Express NVMe Place
  • Data Infrastructure Primer and Overview (Its Whats Inside The Data Center)
  • January 2017 Server StorageIO Update Newsletter
  • September and October 2016 Server StorageIO Update Newsletter
  • HP Buys one of the seven networking dwarfs and gets a bargain
  • Did HP respond to EMC and Cisco VCE with Microsoft Hyper-V bundle?
  • Give HP storage some love and short strokin
  • While HP and Dell make counter bids, exclusive interview with 3PAR CEO David Scott
  • Data Protection Fundamental Topics Tools Techniques Technologies Tips
  • Hewlett-Packard beats Dell, pays $2.35 billion for 3PAR
  • HP Moonshot 1500 software defined capable compute servers
  • What Does Converged (CI) and Hyper converged (HCI) Mean to Storage I/O?
  • What’s a data infrastructure?
  • Ensure your data infrastructure remains available and resilient
  • Object Storage Center, The SSD place and The NVMe place

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

    Software Defined Data Infrastructure Essentials Book SDDC

    What this all means

    Generally speaking I think this is a good series of moves for HPE (and their customers) as long as they can execute in all dimensions.

    Let’s see how they execute, and by this, I mean more than simply executing or terminating staff from recently acquired or earlier acquisitions. How will HPE craft go to the market message that leverages the portfolio to compete and hold or take share from other vendors, vs. cannibalize across its own lines (e.g. revenue prevention)? With that strategy and message, how will HPE assure existing customers will be taken care, be given a definite upgrade and migration path vs. giving them a reason to go elsewhere.

    Hopefully HPE unleashes the full potential of Simplivity and Nimble along with 3PAR, XP7 where needed, along with MSA at low-end (or as part of volume scale-out with servers for software defined), to mention sever portfolio. For now, this tells me that HPE is still interested in maintaining, expanding their data infrastructure business vs. simply retrenching selling off assets. Thus this looks like HPE is interested in continuing to invest in data infrastructure technologies including buying into server, storage I/O network, hardware, software solutions, while not simply clinging to what they already have, or previously bought.

    Everything is not the same in data centers and across data infrastructure, so why have a one size fits all approach for organization as large, diverse as HPE.

    Congratulations and best wishes to the folks at Hedvig, Nimble, Simplivity.

    Now, lets see how this all plays out.

    Ok, nuff said, for now.

    Gs

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

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

    Posted on

    EMC is now Dell EMC, part of Dell Technologies and other server storage Updates

    EMC is now Dell EMC and other server storage Updates

    server storage I/O trends

    In case you missed it or did not hear, EMC is now Dell EMC and is future ready (one of their new tag lines).

    What this means is that EMC is no longer a publicly traded company instead now being privately held under the Dell Technologies umbrella. In case you did not know or had forgotten, one of the principal owners of Dell Technologies is Michael Dell aka the founder of Dell Computers which itself went private a few years ago. The Dell Server division which sells direct as well as via channels and OEMs is now part of the Dell EMC division (e.g. they sell Servers, Storage, I/O and Networking hardware, software and services).

    Dell EMC Storage Portfolio
    Dell EMC Storage Portfolio – Via emc.com

    Other related news and activities include:

    • Dell EMC sells Content Division (e.g. Documentum (bought in 2003), InfoArchive and LEAP) to OpenText for $1.62B USD
    • Dell is selling its Sonicwall and software division (e.g. what was a mix of Quest and other non-EMC related software) to a Private Equity group. The new company to be called Quest has ironically as one of its investors, activist PE firm Elliott Management. You might recall Elliott Management was the activist investor pushing for more value out of EMC for shareholders.
    • Expands Data Protection Portfolio For VMware Environments
    • Hybrid Cloud Platform Enhancements
    • XtremIO New Features and Management for Virtualized Environments
    • Combines DSSD and PowerEdge Servers for SAS (Software) Analytics
    • ScaleIO Ready Node Offers All-Flash Software-Defined
    • Expands Microsoft Support across Cloud and Converged Infrastructure
    • With approximately 140,000 employees worldwide post merger Dell EMC has announce some expected layoffs.

    Dell EMC Enahncements made today

    • Announced a new entry-level VMAX (200F) with very small physical footprint, affordable starter system price and flexibility to scale as you need to grow. Also announced were SRDF third site enhancements as well as VPLEX updates.
    • Data Domain enhancements including OS 6.0, flash and tiering across private, public and hybrid cloud
    • Unity mid-range storage (e.g. the successor to VNX) enhanced with all-flash and UnityOE software updates that include in-line compression along with cloud tiering. All-flash Unity models using 15.36TB SAS Flash SSD drives (3D NAND) can support up to 384TB in a 2U rack. Cloud tiering includes support for Virtustream, AWS and Microsoft Azure.

    Dell EMC VMAX storage family
    Dell EMC VMAX family and new 200F – Via emc.com

    Note that in-line compression on Unity and VMAX systems is available on all-flash based systems, while tiering is available on both all-flash as well as hybrid systems.

    Where To Learn More

    Dell Updates Storage Center Operating System 7 (SCOS 7)
    EMC DSSD D5 Rack Scale Direct Attached Shared SSD All Flash Array Part I
    Part II – EMC DSSD D5 Direct Attached Shared AFA
    EMCworld 2016 Getting Started on Dell EMC announcements
    EMCworld 2016 EMC Hybrid and Converged Clouds Your Way
    Dell-EMC: The Storage Ramifications
    VMware Targets Synergies in Dell-EMC Deal 
    Dell to Buy EMC for $67B; Sharpen Focus on Large Enterprises and High-End Computing
    Dell SAN strategy examined after move to go private
    EMC VxRack Neutrino Nodes launched for OpenStack cloud storage
    EMC Under Pressure To Spin Off VMware
    EMC Bridges Cloud, On-Premise Storage With TwinStrata Buy
    Top Ten Takeaways from EMC World
    When to implement ultra-dense server storage
    EMCworld 2015 How Do You Want Your Storage Wrapped?
    EMCworld 2015 How Do You Want Your Storage Wrapped?

    What This All Means

    For those that think (or wish) that now that EMC has gone private (e.g. granted under Dell ownership) that they have gone away and no longer relevant, time will tell what happens long term. However while they (EMC, now Dell EMC) are no longer a publicly held company, they are still very much in the public spotlight addressing legacy, current as well as emerging IT data infrastructure and software-defined data center, software defined storage and related topics spanning cloud, virtual, container among others.

    What this all means is that Dell EMC is following through with providing different types of data infrastructure along with associated server, storage and I/O solutions as well as associated software defined storage management and data protection tools to meet various needs. How do you want your storage wrapped? Do you want it software defined such as a ScaleIO, ECS (object), DataDomain (data protection), VIPR, or Unity among other virtual storage appliances (VSAs), or tin-wrapped as a physical storage system or appliance?

    With the VMAX 200F, Dell EMC is showing that they can scale-down the VMAX. Dell EMC is also showing they can scale VMAX up and out while making it affordable and physically practical for smaller environments who want, need or are required to have traditional enterprise class storage in a small footprint (price, physical space) with enterprise resiliency.

    Dell EMC Storage Portfolio
    Dell EMC Storage Portfolio – Via emc.com

    A question that comes up is what happens with the various competing Dell and EMC (pre-merger) storage product lines. If you look closely at the storage line up photo above, you will notice the Dell SC (e.g. Compellent) is shown along with all of the EMC solutions. This should or could prompt the question of what about the PS series (e.g. EqualLogic) or some MD. So far the answer I have received is that they remain available for sale which you can confirm via the Dell website. However, what will the future bring to those or others is still TBD.

    Needless to say there is more to see and hear coming out of Dell EMC in the weeks and months ahead, that is unless as some predict (or wishful thinking) they go away which I don’t see happening anytime soon. Oh, FWIW, Dell and EMC have been Server StorageIO clients direct and indirect via 3rd parties in the past (that’s a disclosure btw).

    Ok, nuff said, for now…

    Cheers
    Gs

    Greg Schulz – Microsoft MVP and VMware vSAN vExpert, 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

    Posted on

    Get in the NVMe SSD game (if you are not already) with Intel 750 among others

    Get in the NVMe SSD game (if you are not already)

    server storage I/O trends

    Updated 2/2/2018

    Get in the NVMe SSD game. If you are or have talked the Non Volatile Memory (NVM) and NVM Express (NVMe) flash SSD talk, however have not yet done the walk, there are some good opportunities to do so. One example how to start walking the talk is get something like the Intel 750 400GB NVMe PCIe Add in Card (AiC) which you should be able to find on different venues including Amazon for $400 USD or less (recently saw the 400GB version for about $309 USD delivered). Of course the question might then be what to do with a NVMe device when you get it which besides running your applications on it, you can find some benchmark and workload generator tools, scripts and examples here.

    NVMe ssd storage
    Various NVM flash SSD including NVMe devices

    Sure there are newer, more expensive, higher capacity cards, some are general availability (GA) while others are on early preview or evaluation basis.

    However a good value, cost-effective way to get into the NVMe game, or expand your footprint are devices such as the Intel 750.

    I have some of these cards and they have been great for use with various workloads. The Intel 750 cards are plug and play in various systems including my TS140s among larger robust servers running Windows Server (2012 R2, 2016 TP5), Ubuntu (various) and VMware ESXi (various).

    There are in the box drivers for these Intel 750 cards, however to get a little more performance recommend visiting the Intel site, get the SSD tools, update the firmware on the cards if needed, as well as try the Intel vs. native drivers.

    There are many vendors with NVMe PCIe cards, as well as U.2/SFF 8639 drives and M.2 mini-cards including Intel, Micron, Seagate, WD among many others

    Where To Learn More

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

    Software Defined Data Infrastructure Essentials Book SDDC

    What This All Means

    Time to get in the NVMe game if you have not already done so moving from talking the talk to walking the talk. With cost of early generation NVMe devices such as the Intel 750 among others there are great opportunities to get started. On the other hand if you are already using NVMe, there are some good opportunities to add extra NVMe based SSD to other servers or systems.

    Speaking of NVMe talk, join me and others on a panel (Session 303) moderated by Dr. Jay Metz (@drjmetz) August 11th at Flash Memory Summit where we will discuss NVMe including NVMe over fabric networks (e.g. moving beyond the PCIe bus). Also keep in mind, with NVMe the question is not if, rather when, where, why, how with what and how to coexist and leverage existing technologies, hardware, software and people skill sets.

    Ok, nuff said, for now.

    Gs

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

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

    Posted on

    Intel Micron 3D XPoint server storage NVM SCM PM SSD

    3D XPoint server storage class memory SCM


    Storage I/O trends

    Updated 1/31/2018

    Intel Micron 3D XPoint server storage NVM SCM PM SSD.

    This is the second of a three-part series on the recent Intel and Micron 3D XPoint server storage memory announcement. Read Part I here and Part III here.

    Is this 3D XPoint marketing, manufacturing or material technology?

    You can’t have a successful manufactured material technology without some marketing, likewise marketing without some manufactured material would be manufactured marketing. In the case of 3D XPoint and its announcement launch, their real technology shown, granted it was only wafer and dies as opposed to an actual DDR4 DIMM or PCIe Add In Card (AIC) or drive form factor Solid State Device (SSD) product. On the other hand, on a relative comparison basis, even though there is marketing collateral available to learn more from, this was far from a over the big-top made for TV or web circus event, which can be a good thing.


    Wafer unveiled containing 3D XPoint 128 Gb dies

    Who will get access to 3D XPoint?

    Initially 3D XPoint production capacity supply will be for the two companies to offer early samples to their customers later this year with general production slated for 2016 meaning early real customer deployed products starting sometime in 2016.

    Is it NAND or NOT?

    3D XPoint is not NAND flash, it is also not NVRAM or DRAM, it’s a new class of NVM that can be used for server class main memory with persistency, or as persistent data storage among other uses (cell phones, automobiles, appliances and other electronics). In addition, 3D XPoint is more durable with a longer useful life for writing and storing data vs. NAND flash.

    Why is 3D XPoint important?

    As mentioned during the Intel and Micron announcement, there have only been seven major memory technologies introduced since the transistor back in 1947, granted there have been many variations along with generational enhancements of those. Thus 3D XPoint is being positioned by Intel and Micron as the eighth memory class joining its predecessors many of which continue to be used today in various roles.


    Major memory classes or categories timeline

    In addition to the above memory classes or categories timeline, the following shows in more detail various memory categories (click on the image below to get access to the Intel interactive infographic).

    Intel History of Memory Infographic
    Via: https://intelsalestraining.com/memory timeline/ (Click on image to view)

    What capacity size is 3D XPoint?

    Initially the 3D XPoint technology is available in a 2 layer 128 bit (cell) per die capacity. Keep in mind that there are usually 8 bits to a byte resulting in 16 GByte capacity per chip initially. With density improvements, as well as increased stacking of layers, the number of cells or bits per die (e.g. what makes up a chip) should improve, as well as most implementations will have multiple chips in some type of configuration.

    What will 3D XPoint cost?

    During the 3D XPoint launch webinar Intel and Micron hinted that first pricing will be between current DRAM and NAND flash on a per cell or bit basis, however real pricing and costs will vary depending on how packaged for use. For example if placed on a DDR4 or different type of DIMM or on a PCIe Add In Card (AIC) or as a drive form factor SSD among other options will vary the real price. Likewise as with other memories and storage mediums, as production yields and volumes increase, along with denser designs, the cost per usable cell or bit can be expected to further improve.

    Where to read, watch and learn more

    Storage I/O trends

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

    Software Defined Data Infrastructure Essentials Book SDDC

    What This All Means

    DRAM which has been around for sometime has plenty of life left for many applications as does NAND flash including new 3D NAND, vNAND and other variations. For the next several years, there will be a co-existences between new and old NVM and DRAM among other memory technologies including 3D XPoint. Read more in this series including Part I here and Part III here.

    Disclosure: Micron and Intel have been direct and/or indirect clients in the past via third-parties and partners, also I have bought and use some of their technologies direct and/or in-direct via their partners.

    Ok, nuff said, for now.

    Gs

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

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