Tag: u.2

Posted on

Intel Micron 3D XPoint Evolving

Intel Micron 3D XPoint Evolving

Intel Micron 3D XPoint Evolving

Intel Micron 3D XPoint Evolving

Generations of memory
Major memory classes or categories timeline (Image via Intel and Micron)

Co-Creators of 3D XPoint the next generation of non-volatile memory (NVM) also known as storage class memory (SCM) or Persistent Memory (PMEM) have announced they will complete joint development of second-generation technology, then pursue their separate paths. Intel and Micron jointly announced 3D XPoint three years (July 2015) as a new technology with the first generation of products have appeared in the market or past year or so.

Various industry vs customer adoption deployment timelines
Various Adoption Deployment Timelines for different focus areas

For those in the industry who measure technology on shorter months vs. years adoption and deployment scenarios, or time from press release until new news, some would say 3D XPoint is late, behind schedule, which perhaps it is based on some timelines. On the other hand, IT customers tend to be on a different timeline that may seem like glacial speed to industry focused rapid change. IMHO 3D XPoint is about on the right timeline based on IT customer deployment which may very well accelerate for broader usage with the second generation based products.

3D XPoint based Intel Optane
Top Intel 750 NVMe PCIe AiC SSD, bottom Intel Optane NVMe 900P U.2 SSD with Ableconn carrier

While the focus is easily around Intel and Micron going separate ways, keep in mind that there is the second generation of 3D XPoint in the works. Some might consider the second generation of 3D XPoint as the first real production and volume technology with the first being just that, the first generation. An example of a first generation 3D XPoint based product are the Intel Optane NVMe devices such as the one show above, and discussed in this StorageIO Lab test drive post here.

NVMe and NVM along with SCM as well as PMEM better together

Where to learn more

Learn more about Intel, Micron, NVM, NVMe, 3D XPoint, SCM, PMEM and data infrastructures related topics via the following links:

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

Software Defined Data Infrastructure Essentials Book SDDC

What this all means

Some may see the announcement of Intel and Micron pursuing separate paths as a negative while others as a positive. While completing the second-generation development together, both can leverage what they have done while seeking different, presumably divergent or expand paths forward.

A concern could be if Intel and Micron merely go their separate ways yet focus on the same market areas. A benefit could be if Intel and Micron pursue different market focus areas with some overlap while expanding to broader opportunities.

The latter scenario could be useful for moving the technology forward by giving it new and different opportunities. For example, some that favor Intel along with its ecosystem would prefer whatever Intel does next. Likewise, those that favor Micron and their ecosystem may influence the direction Micron goes.

Does this mean Micron and Intel are all done collaborating? Tough to say.

However, they still share a fabrication facility (fab) imFLASH in Lehi Utah.

Overall, I think this is a good move for both Intel and Micron once they get the second generation of 3D XPoint developed and into production for customer deployments. With Intel Micron 3D XPoint Evolving, lets see what’s next.

Ok, nuff said, for now.

Cheers Gs

Greg Schulz – Microsoft MVP Cloud and Data Center Management, VMware vExpert 2010-2018. Author of Software Defined Data Infrastructure Essentials (CRC Press), as well as Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press), Resilient Storage Networks (Elsevier) and twitter @storageio. Courteous comments are welcome for consideration. First published on https://storageioblog.com any reproduction in whole, in part, with changes to content, without source attribution under title or without permission is forbidden.

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

Posted on

Use Intel Optane NVMe U.2 SFF 8639 SSD drive in PCIe slot

Use NVMe U.2 SFF 8639 disk drive form factor SSD in PCIe slot

server storage I/O data infrastructure trends

Need to install or use an Intel Optane NVMe 900P or other Nonvolatile Memory (NVM) Express NVMe based U.2 SFF 8639 disk drive form factor Solid State Device (SSD) into PCIe a slot?

For example, I needed to connect an Intel Optane NVMe 900P U.2 SFF 8639 drive form factor SSD into one of my servers using an available PCIe slot.

The solution I used was an carrier adapter card such as those from Ableconn (PEXU2-132 NVMe 2.5-inch U.2 [SFF-8639] via Amazon.com among other global venues.

xxxx
Top Intel 750 NVMe PCIe AiC SSD, bottom Intel Optane NVMe 900P U.2 SSD with Ableconn carrier

The above image shows top an Intel 750 NVMe PCIe Add in Card (AiC) SSD and on the bottom an Intel Optane NVMe 900P 280GB U.2 (SFF 8639) drive form factor SSD mounted on an Ableconn carrier adapter.

NVMe server storage I/O sddc

NVMe Tradecraft Refresher

NVMe is the protocol that is implemented with different topologies including local via PCIe using U.2 aka SFF-8639 (aka disk drive form factor), M.2 aka Next Generation Form Factor (NGFF) also known as "gum stick", along with PCIe Add in Card (AiC). NVMe accessed devices can be installed in laptops, ultra books, workstations, servers and storage systems using the various form factors. U.2 drives are also refereed to by some as PCIe drives in that the NVMe command set protocol is implemented using PCIe x4 physical connection to the devices. Jump ahead if you want to skip over the NVMe primer refresh material to learn more about U.2 8639 devices.

data infrastructure nvme u.2 8639 ssd
Various SSD device form factors and interfaces

In addition to form factor, NVMe devices can be direct attached and dedicated, rack and shared, as well as accessed via networks also known as fabrics such as NVMe over Fabrics.

NVMeoF FC-NVMe NVMe fabric SDDC
The many facets of NVMe as a front-end, back-end, direct attach and fabric

Context is important with NVMe in that fabric can mean NVMe over Fibre Channel (FC-NVMe) where the NVMe command set protocol is used in place of SCSI Fibre Channel Protocol (e.g. SCSI_FCP) aka FCP or what many simply know and refer to as Fibre Channel. NVMe over Fabric can also mean NVMe command set implemented over an RDMA over Converged Ethernet (RoCE) based network.

NVM and NVMe accessed flash SCM SSD storage

Another point of context is not to confuse Nonvolatile Memory (NVM) which are the storage or memory media and NVMe which is the interface for accessing storage (e.g. similar to SAS, SATA and others). As a refresher, NVM or the media are the various persistent memories (PM) including NVRAM, NAND Flash, 3D XPoint along with other storage class memories (SCM) used in SSD (in various packaging).

Learn more about 3D XPoint with the following resources:

Learn more (or refresh) your NVMe server storage I/O knowledge, experience tradecraft skill set with this post here. View this piece here looking at NVM vs. NVMe and how one is the media where data is stored, while the other is an access protocol (e.g. NVMe). Also visit www.thenvmeplace.com to view additional NVMe tips, tools, technologies, and related resources.

NVMe U.2 SFF-8639 aka 8639 SSD

On quick glance, an NVMe U.2 SFF-8639 SSD may look like a SAS small form factor (SFF) 2.5" HDD or SSD. Also, keep in mind that HDD and SSD with SAS interface have a small tab to prevent inserting them into a SATA port. As a reminder, SATA devices can plug into SAS ports, however not the other way around which is what the key tab function does (prevents accidental insertion of SAS into SATA). Looking at the left-hand side of the following image you will see an NVMe SFF 8639 aka U.2 backplane connector which looks similar to a SAS port.

Note that depending on how implemented including its internal controller, flash translation layer (FTL), firmware and other considerations, an NVMe U.2 or 8639 x4 SSD should have similar performance to a comparable NVMe x4 PCIe AiC (e.g. card) device. By comparable device, I mean the same type of NVM media (e.g. flash or 3D XPoint), FTL and controller. Likewise generally an PCIe x8 should be faster than an x4, however more PCIe lanes does not mean more performance, its what’s inside and how those lanes are actually used that matter.

NVMe U.2 8639 2.5" 1.8" SSD driveNVMe U.2 8639 2.5 1.8 SSD drive slot pin
NVMe U.2 SFF 8639 Drive (Software Defined Data Infrastructure Essentials CRC Press)

With U.2 devices the key tab that prevents SAS drives from inserting into a SATA port is where four pins that support PCIe x4 are located. What this all means is that a U.2 8639 port or socket can accept an NVMe, SAS or SATA device depending on how the port is configured. Note that the U.2 8639 port is either connected to a SAS controller for SAS and SATA devices or a PCIe port, riser or adapter.

On the left of the above figure is a view towards the backplane of a storage enclosure in a server that supports SAS, SATA, and NVMe (e.g. 8639). On the right of the above figure is the connector end of an 8639 NVM SSD showing addition pin connectors compared to a SAS or SATA device. Those extra pins give PCIe x4 connectivity to the NVMe devices. The 8639 drive connectors enable a device such as an NVM, or NAND flash SSD to share a common physical storage enclosure with SAS and SATA devices, including optional dual-pathing.

More PCIe lanes may not mean faster performance, verify if those lanes (e.g. x4 x8 x16 etc) are present just for mechanical (e.g. physical) as well as electrical (they are also usable) and actually being used. Also, note that some PCIe storage devices or adapters might be for example an x8 for supporting two channels or devices each at x4. Likewise, some devices might be x16 yet only support four x4 devices.

NVMe U.2 SFF 8639 PCIe Drive SSD FAQ

Some common questions pertaining NVMe U.2 aka SFF 8639 interface and form factor based SSD include:

Why use U.2 type devices?

Compatibility with what’s available for server storage I/O slots in a server, appliance, storage enclosure. Ability to mix and match SAS, SATA and NVMe with some caveats in the same enclosure. Support higher density storage configurations maximizing available PCIe slots and enclosure density.

Is PCIe x4 with NVMe U.2 devices fast enough?

While not as fast as a PCIe AiC that fully supports x8 or x16 or higher, an x4 U.2 NVMe accessed SSD should be plenty fast for many applications. If you need more performance, then go with a faster AiC card.

Why not go with all PCIe AiC?

If you need the speed, simplicity, have available PCIe card slots, then put as many of those in your systems or appliances as possible. Otoh, some servers or appliances are PCIe slot constrained so U.2 devices can be used to increase the number of devices attached to a PCIe backplane while also supporting SAS, SATA based SSD or HDDs.

Why not use M.2 devices?

If your system or appliances supports NVMe M.2 those are good options. Some systems even support a combination of M.2 for local boot, staging, logs, work and other storage space while PCIe AiC are for performance along with U.2 devices.

Why not use NVMeoF?

Good question, why not, that is, if your shared storage system supports NVMeoF or FC-NVMe go ahead and use that, however, you might also need some local NVMe devices. Likewise, if yours is a software-defined storage platform that needs local storage, then NVMe U.2, M.2 and AiC or custom cards are an option. On the other hand, a shared fabric NVMe based solution may support a mixed pool of SAS, SATA along with NVMe U.2, M.2, AiC or custom cards as its back-end storage resources.

When not to use U.2?

If your system, appliance or enclosure does not support U.2 and you do not have a need for it. Or, if you need more performance such as from an x8 or x16 based AiC, or you need shared storage. Granted a shared storage system may have U.2 based SSD drives as back-end storage among other options.

How does the U.2 backplane connector attach to PCIe?

Via enclosures backplane, there is either a direct hardwire connection to the PCIe backplane, or, via a connector cable to a riser card or similar mechanism.

Does NVMe replace SAS, SATA or Fibre Channel as an interface?

The NVMe command set is an alternative to the traditional SCSI command set used in SAS and Fibre Channel. That means it can replace, or co-exist depending on your needs and preferences for access various storage devices.

Who supports U.2 devices?

Dell has supported U.2 aka PCIe drives in some of their servers for many years, as has Intel and many others. Likewise, U.2 8639 SSD drives including 3D Xpoint and NAND flash-based are available from Intel among others.

Can you have AiC, U.2 and M.2 devices in the same system?

If your server or appliance or storage system support them then yes. Likewise, there are M.2 to PCIe AiC, M.2 to SATA along with other adapters available for your servers, workstations or software-defined storage system platform.

NVMe U.2 carrier to PCIe adapter

The following images show examples of mounting an Intel Optane NVMe 900P accessed U.2 8639 SSD on an Ableconn PCIe AiC carrier. Once U.2 SSD is mounted, the Ableconn adapter inserts into an available PCIe slot similar to other AiC devices. From a server or storage appliances software perspective, the Ableconn is a pass-through device so your normal device drivers are used, for example VMware vSphere ESXi 6.5 recognizes the Intel Optane device, similar with Windows and other operating systems.

intel optane 900p u.2 8639 nvme drive bottom view
Intel Optane NVMe 900P U.2 SSD and Ableconn PCIe AiC carrier

The above image shows the Ableconn adapter carrier card along with NVMe U.2 8639 pins on the Intel Optane NVMe 900P.

intel optane 900p u.2 8639 nvme drive end view
Views of Intel Optane NVMe 900P U.2 8639 and Ableconn carrier connectors

The above image shows an edge view of the NVMe U.2 SFF 8639 Intel Optane NVMe 900P SSD along with those on the Ableconn adapter carrier. The following images show an Intel Optane NVMe 900P SSD installed in a PCIe AiC slot using an Ableconn carrier, along with how VMware vSphere ESXi 6.5 sees the device using plug and play NVMe device drivers.

NVMe U.2 8639 installed in PCIe AiC Slot
Intel Optane NVMe 900P U.2 SSD installed in PCIe AiC Slot

NVMe U.2 8639 and VMware vSphere ESXi
How VMware vSphere ESXi 6.5 sees NVMe U.2 device

Intel NVMe Optane NVMe 3D XPoint based and other SSDs

Here are some Amazon.com links to various Intel Optane NVMe 3D XPoint based SSDs in different packaging form factors:

Here are some Amazon.com links to various Intel and other vendor NAND flash based NVMe accessed SSDs including U.2, M.2 and AiC form factors:

Note in addition to carriers to adapt U.2 8639 devices to PCIe AiC form factor and interfaces, there are also M.2 NGFF to PCIe AiC among others. An example is the Ableconn M.2 NGFF PCIe SSD to PCI Express 3.0 x4 Host Adapter Card.

In addition to Amazon.com, Newegg.com, Ebay and many other venues carry NVMe related technologies.
The Intel Optane NVMe 900P are newer, however the Intel 750 Series along with other Intel NAND Flash based SSDs are still good price performers and as well as provide value. I have accumulated several Intel 750 NVMe devices over past few years as they are great price performers. Check out this related post Get in the NVMe SSD game (if you are not already).

Where To Learn More

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

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

Software Defined Data Infrastructure Essentials Book SDDC

What This All Means

NVMe accessed storage is in your future, however there are various questions to address including exploring your options for type of devices, form factors, configurations among other topics. Some NVMe accessed storage is direct attached and dedicated in laptops, ultrabooks, workstations and servers including PCIe AiC, M.2 and U.2 SSDs, while others are shared networked aka fabric based. NVMe over fabric (e.g. NVMeoF) includes RDMA over converged Ethernet (RoCE) as well as NVMe over Fibre Channel (e.g. FC-NVMe). Networked fabric accessed NVMe access of pooled shared storage systems and appliances can also include internal NVMe attached devices (e.g. as part of back-end storage) as well as other SSDs (e.g. SAS, SATA).

General wrap-up (for now) NVMe U.2 8639 and related tips include:

  • Verify the performance of the device vs. how many PCIe lanes exist
  • Update any applicable BIOS/UEFI, device drivers and other software
  • Check the form factor and interface needed (e.g. U.2, M.2 / NGFF, AiC) for a given scenario
  • Look carefully at the NVMe devices being ordered for proper form factor and interface
  • With M.2 verify that it is an NVMe enabled device vs. SATA

Learn more about NVMe at www.thenvmeplace.com including how to use Intel Optane NVMe 900P U.2 SFF 8639 disk drive form factor SSDs in PCIe slots as well as for fabric among other scenarios.

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

HPE Announces AMD Powered Gen 10 ProLiant DL385 For Software Defined Workloads

HPE Announces AMD Powered Gen 10 ProLiant DL385 For Software Defined Workloads

server storage I/O data infrastructure trends

By Greg Schulz – www.storageioblog.com November 20, 2017

HPE Announced today a new AMD EPYC 7000 Powered Gen 10 ProLiant DL385 for Software Defined Workloads including server virtualization, software-defined data center (SDDC), software-defined data infrastructure (SDDI), software-defined storage among others. These new servers are part of a broader Gen10 HPE portfolio of ProLiant DL systems.

HPE AMD EPYC Gen10 DL385
24 Small Form Factor Drive front view DL385 Gen 10 Via HPE

The value proposition being promoted by HPE of these new AMD powered Gen 10 DL385 servers besides supporting software-defined, SDDI, SDDC, and related workloads are security, density and lower price than others. HPE is claiming with the new AMD EPYC system on a chip (SoC) processor powered Gen 10 DL385 that it is offering up to 50 percent lower cost per virtual machine (VM) than traditional server solutions.

About HPE AMD Powered Gen 10 DL385

HPE AMD EPYC 7000 Gen 10 DL385 features:

  • 2U (height) form factor
  • HPE OneView and iLO management
  • Flexible HPE finance options
  • Data Infrastructure Security
  • AMD EPYC 7000 System on Chip (SoC) processors
  • NVMe storage (Embedded M.2 and U.2/8639 Small Form Factor (SFF) e.g. drive form factor)
  • Address server I/O and memory bottlenecks

These new HPE servers are positioned for:

  • Software Defined, Server Virtualization
  • Virtual Desktop Infrastructure (VDI) workspaces
  • HPC, Cloud and other general high-density workloads
  • General Data Infrastructure workloads that benefit from memory-centric or GPUs

Different AMD Powered DL385 ProLiant Gen 10 Packaging Options

Common across AMD EPYC 7000 powered Gen 10 DL385 servers are 2U high form factor, iLO management software and interfaces, flexible LAN on Motherboard (LOM) options, MicroSD (optional dual MicroSD), NVMe (embedded M.2 and SFF U.2) server storage I/O interface and drives, health and status LEDs, GPU support, single or dual socket processors.

HPE AMD EPYC Gen10 DL385 Look Inside
HPE DL385 Gen10 Inside View Via HPE

HPE AMD EPYC Gen10 DL385 Rear View
HPE DL385 Gen10 Rear View Via HPE

Other up to three storage drive bays, support for Large Form Factor (LFF) and Small Form Factor (SFF) devices (HDD and SSD) including SFF NVMe (e.g., U.2) SSD. Up to 4 x Gbe NICs, PCIe riser for GPU (optional second riser requires the second processor). Other features and options include HPE SmartArray (RAID), up to 6 cooling fans, internal and external USB 3. Optional universal media bay that can also add a front display, optional Optical Disc Drive (ODD), optional 2 x U.2 NVMe SFF SSD. Note media bay occupies one of three storage drive bays.

HPE AMD EPYC Gen10 DL385 Form Factor
HPE DL385 Form Factor Via HPE

Up to 3 x Drive Bays
Up to 12 LFF drives (2 per bay)
Up to 24 SFF drives ( 3 x 8 drive bays, 6 SFF + 2 NVMe U.2 or 8 x NVMe)

AMD EPYC 7000 Series

The AMD EPYC 7000 series is available in the single and dual socket. View additional AMD EPYC speeds and feeds in this data sheet (PDF), along with AMD server benchmarks here.

HPE AMD EPYC Specifications
HPE DL385 Gen 10 AMD EPYC Specifications Via HPE

AMD EPYC 7000 General Features

  • Single and dual socket
  • Up to 32 cores, 64 threads per socket
  • Up to 16 DDR4 DIMMS over eight channels per socket (e.g., up to 2TB RAM)
  • Up to 128 PCIe Gen 3 lanes (e.g. combination of x4, x8, x16 etc)
  • Future 128GB DIMM support

AMD EPYC 7000 Security Features

  • Secure processor and secure boot for malware rootkit protection
  • System memory encryption (SME)
  • Secure Encrypted Virtualization (SEV) hypervisors and guest virtual machine memory protection
  • Secure move (e.g., encrypted) between enabled servers

Where To Learn More

Learn more about Data Infrastructure and related server technology, trends, tools, techniques, tradecraft and tips with the following links.

  • AMD EPYC 7000 System on Chip (SoC) processors
  • Gen10 HPE portfolio and ProLiant DL systems.
  • Various Data Infrastructure related news commentary, events, tips and articles
  • Data Center and Data Infrastructure industry links
  • Data Infrastructure server storage I/O network Recommended Reading List Book Shelf
  • Software Defined Data Infrastructure Essentials (CRC 2017) Book

    • What This All Means

    With the flexible options including HDD, SSD as well as NVMe accessible SSDs, large memory capacity along with computing cores, these new solutions provide good data infrastructure server density (e.g., CPU, memory, I/O, storage) per cubic foot or meter per cost.

    I look forward to trying one of these systems out for software-defined scenarios including virtualization, software-defined storage (SDS) among others workload scenarios. Overall the HPE announcement of the new AMD EPYC 7000 Powered Gen 10 ProLiant DL385 looks to be a good option for many environments.

    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

    NVMe Wont Replace Flash By Itself They Complement Each Other

    NVMe Wont Replace Flash By Itself They Complement Each Other

    server storage I/O data infrastructure trends

    Updated 2/2/2018

    NVMe Wont Replace Flash By Itself They Complement Each Other

    >various NVM flash and SSD devices
    Various Solid State Devices (SSD) including NVMe, SAS, SATA, USB, M.2

    There has been some recent industry marketing buzz generated by a startup to get some attention by claiming via a study sponsored by including the startup that Non-Volatile Memory (NVM) Express (NVMe) will replace flash storage. Granted, many IT customers as well as vendors are still confused by NVMe thinking it is a storage medium as opposed to an interface used for accessing fast storage devices such as nand flash among other solid state devices (SSDs). Part of that confusion can be tied to common SSD based devices rely on NVM that are persistent memory retaining data when powered off (unlike the memory in your computer).

    NVMe is an access interface and protocol

    Instead of saying NVMe will mean the demise of flash, what should or could be said however some might be scared to say it is that other interfaces and protocols such as SAS (Serial Attached SCSI), AHCI/SATA, mSATA, Fibre Channel SCSI Protocol aka FCP aka simply Fibre Channel (FC), iSCSI and others are what can be replaced by NVMe. NVMe is simply the path or roadway along with traffic rules for getting from point a (such as a server) to point b (some storage device or medium e.g. flash SSD). The storage medium is where data is stored such as magnetic for Hard Disk Drive (HDD) or tape, nand flash, 3D XPoint, Optane among others.

    NVMe and NVM better together

    NVMe and NVM including flash are better together

    The simple quick get to the point is that NVMe (e.g. Non Volatile Memory aka NVM Express [NVMe]) is an interface protocol (like SAS/SATA/iSCSI among others) used for communicating with various nonvolatile memory (NVM) and solid state device (SSDs). NVMe is how data gets moved between a computer or other system and the NVM persistent memory such as nand flash, 3D XPoint, Spintorque or other storage class memories (SCM).

    In other words, the only thing NVMe will, should, might or could kill off would be the use of some other interface such as SAS, SATA/AHCI, Fibre Channel, iSCSI along with propritary driver or protocols. On the other hand, given the extensibility of NVMe and how it can be used in different configurations including as part of fabrics, it is an enabler for various NVMs also known as persistent memories, SCMs, SSDs including those based on NAND flash as well as emerging 3D XPoint (or Intel version) among others.

    Where To Learn More

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

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

    Software Defined Data Infrastructure Essentials Book SDDC

    What This All Means

    Context matters for example, NVM as the medium compared to NVMe as the interface and access protocols. With context in mind you can compare like or similar apples to apples such as nand flash, MRAM, NVRAM, 3D XPoint, Optane among other persistent memories also known as storage class memories, NVMs and SSDs. Likewise with context in mind NVMe can be compared to other interfaces and protocols such as SAS, SATA, PCIe, mSATA, Fibre Channel among others. The following puts all of this into context including various packaging options, interfaces and access protocols, functionality and media.

    NVMe is the access for NVM flash
    Putting IT all together

    Will NVMe kill off flash? IMHO no not by itself, however NVMe combined with some other form of NVM, SCM, persistent memory as a storage medium may eventually combine as an alternative to NVMe and flash (or SAS/SATA and flash). However, for now at least for many applications, NVMe is in your future (along with flash among other storage mediums), the questions include when, where, why, how, with what among other questions (and answers). NVMe wont replace flash by itself (at least yet) as they complement each other.

    Keep in mind, if NVMe is the answer, what are the questions.

    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

    If NVMe is the answer, what are the questions?

    If NVMe is the answer, what are the questions?

    If NVMe is the answer, then what are the various questions that should be asked?

    Some common questions that NVMe is the answer to include what is the difference between NVM and NVMe?

    Is NVMe only for servers, does NVMe require fabrics and what benefit is NVMe beyond more IOPs.

    Lets take a look at some of these common NVMe conversations and other questions.

    Main Features and Benefits of NVMe

    Some of the main feature and benefits of NVMe among others include:

      • 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

    NVM and Media memory matters

    Whats the differences between NVM and NVMe? Non-Volatile Memory (NVM) which as its name implies is persistent electronic memory medium where data is stored. Today you commonly know about NVMs as NAND flash Solid State Devices (SSD), along with NVRAM among others emerging storage class memories (SCM).

    Emerging SCM such as 3D XPoint among other mediums (or media if you prefer) have the premises of boosting both read and write performance beyond traditional NAND flash, closer to DRAM, while having durability also closer to DRAM. For now let’s set the media and mediums aside and get back to how they or will be accessed as well as used.

    server storage I/O NVMe fundamentals

    Server and Storage I/O Media access matters

    NVM Express (e.g. NVMe) is a standard industry protocol for accessing NVM media (SSD and flash devices, storage system, appliances). If NVMe is the answer, then depending on your point of view, NVMe can be (or is) a replacement (today or in the future) for AHCI/SATA, Serial Attached SCSI (SAS). What this means is that NVMe can coexist or replace other block SCSI protocol implementations (e.g. Fibre Channel FCP aka FCP, iSCSI, SRP) as well as NBD (among others).

    Similar to the SCSI command set that is implemented on different networks (e.g. iSCSI (IP), FCP (Fibre Channel), SRP (InfiniBand), SAS) NVMe as a protocol is now implemented using PCIe with form factors of add-in cards (AiC), M.2 (e.g. gum sticks aka next-gen form factor or NGFF) as well as U.2 aka 8639 drive form factors. There are also the emerging NVMe over Fabrics variants including FC-NVMe (e.g. NVMe protocol over Fibre Channel) which is an alternative to SCSI_FCP (e.g. SCSI on Fibre Channel). An example of a PCIe AiC that I have include the Intel 750 400GB NVMe (among others). You should be able to find the Intel among other NVMe devices from your prefered vendor as well as different venues including Amazon.com.

    NVM, flash and NVMe SSD
    Left PCIe AiC x4 NVMe SSD, lower center M.2 NGFF, right SAS and SATA SSD

    The following image shows an NVMe U.2 (e.g. 8639) drive form factor device that from a distance looks like a SAS device and connector. However looking closer some extra pins or connectors that present a PCIe Gen 3 x4 (4 PCIe lanes) connection from the server or enclosure backplane to the devices. These U.2 devices plug into 8639 slots (right) that look like a SAS slot that can also accommodate SATA. Remember, SATA can plug into SAS, however not the other way around.

    NVMe U.2 8639 driveNVMe 8639 slot
    Left NVMe U.2 drive showing PCIe x4 connectors, right, NVMe U.2 8639 connector

    What NVMe U.2 means is that the 8639 slots can be used for 12Gbps SAS, 6Gbps SATA or x4 PCIe-based NVMe. Those devices in turn attach to their respective controllers (or adapters) and device driver software protocol stack. Several servers have U.2 or 8639 drive slots either in 2.5” or 1.8” form factors, sometimes these are also called or known as “blue” drives (or slots). The color coding simply helps to keep track of what slots can be used for different things.

    Navigating your various NVMe options

    If NVMe is the answer, then some device and component options are as follows.

    NVMe device components and options include:

      • Enclosures and connector port slots
      • Adapters and controllers
      • U.2, PCIe AIC and M.2 devices
      • Shared storage system or appliances
      • PCIe and NVMe switches

    If NVMe is the answer, what to use when, where and why?

    Why use an U.2 or 8639 slot when you could use PCIe AiC? Simple, your server or storage system may be PCIe slot constrained, yet have more available U.2 slots. There are U.2 drives from various vendors including Intel and Micro, as well as servers from Dell, Intel and Lenovo among many others.

    Why and when would you use an NVMe M.2 device? As a local read/write cache, or perhaps a boot and system device on servers or appliances that have M.2 slots. Many servers and smaller workstations including Intel NUC support M.2. Likewise, there are M.2 devices from many different vendors including Micron, Samsung among others.

    Where and why would you use NVMe PCIe AiC? Whenever you can and if you have enough PCIe slots of the proper form factor, mechanical and electrical (e.g. x1, x4, x8, x16) to support a particular card.

    Can you mix and match different types of NVMe devices on the same server or appliance? As long as the physical server and its software (BIOS/UEFI, operating system, hypervisors, drivers) support it yes. Most server and appliance vendors support PCIe NVMe AiCs, however, pay attention to if they are x4, x8 both mechanical as well as electrical. Also, verify operating system and hypervisor device driver support. PCIe NVMe AiCs are available from Dell, Intel, Micron and many other vendors.

    Networking with your Server and NVMe Storage

    Keep in mind that context is important when discussing NVMe as there are devices for attaching as the back-end to servers, storage systems or appliances, as well as for front-end attachment (e.g. for attaching storage systems to servers). NVMe devices can also be internal to a server or storage system and appliance, or, accessible over a network. Think of NVMe as an upper-level command set protocol like SCSI that gets implemented on different networks (e.g. iSCSI, FCP, SRP).

    How can NVMe use PCIe as a transport to use devices that are outside of a server? Different vendors have PCIe adapter cards that support longer distances (few meters) to attach to devices. For example, Dell EMC DSSD has a special dual port (two x4 ports) that are PCIe x8 cards for attachment to the DSSD shared SSD devices.

    Note that there are also PCIe switches similar to SAS and InfiniBand among other switches. However just because these are switches, does not mean they are your regular off the shelf network type switch that your networking folks will know what to do with (or want to manage).

    The following example shows a shared storage system or appliance being accessed by servers using traditional block, NAS file or object protocols. In this example, the storage system or appliance has implemented NVMe devices (PCIe AiC, M.2, U.2) as part of their back-end storage. The back-end storage might be all NVMe, or a mix of NVMe, SAS or SATA SSD and perhaps some high-capacity HDD.

    NVMe and server storage access
    Servers accessing shared storage with NVMe back-end devices

    NVMe and server storage access via PCIe
    NVMe PCIe attached (via front-end) storage with various back-end devices

    In addition to shared PCIe-attached storage such as Dell EMC DSSD similar to what is shown above, there are also other NVMe options. For example, there are industry initiatives to support the NVMe protocol to use shared storage over fabric networks. There are different fabric networks, they range from RDMA over Converged Ethernet (RoCE) based as well as Fibre Channel NVME (e.g. FC-NVME) among others.

    An option that on the surface may not seem like a natural fit or leverage NVMe to its fullest is simply adding NVMe devices as back-end media to existing arrays and appliances. For example, adding NVMe devices as the back-end to iSCSI, SAS, FC, FCoE or other block-based, NAS file or object systems.

    NVMe and server storage access via shared PCIe
    NVMe over a fabric network (via front-end) with various back-end devices

    A common argument against using legacy storage access of shared NVMe is along the lines of why would you want to put a slow network or controller in front of a fast NVM device? You might not want to do that, or your vendor may tell you many reasons why you don’t want to do it particularly if they do not support it. On the other hand, just like other fast NVM SSD storage on shared systems, it may not be all about 100% full performance. Rather, for some environments, it might be about maximizing connectivity over many interfaces to faster NVM devices for several servers.

    NVMe and server storage I/O performance

    Is NVMe all about boosting the number of IOPS? NVMe can increase the number of IOPS, as well as support more bandwidth. However, it also reduces response time latency as would be expected with an SSD or NVM type of solution. The following image shows an example of not surprisingly an NVMe PCIe AiC x4 SSD outperforming (more IOPs, lower response time) compared to a 6Gb SATA SSD (apples to oranges). Also keep in mind that best benchmark or workload tool is your own application as well as your performance mileage will vary.

    NVMe using less CPU per IOP
    SATA SSD vs. NVMe PCIe AiC SSD IOPS, Latency and CPU per IOP

    The above image shows the lower amount of CPU per IOP given the newer, more streamlined driver and I/O software protocol of NVMe. With NVMe there is less overhead due to the new design, more queues and ability to unlock value not only in SSD also in servers with more sockets, cores and threads.

    What this means is that NVMe and SSD can boost performance for activity (TPS, IOPs, gets, puts, reads, writes). NVMe can also lower response time latency while also enabling higher throughput bandwidth. In other words, you get more work out of your servers CPU (and memory). Granted SSDs have been used for decades to boost server performance and in many cases, delay an upgrade to a newer faster system by getting more work out of them (e.g. SSD marketing 202).

    NVMe maximizing your software license investments

    What may not be so obvious (e.g. SSD marketing 404) is that by getting more work activity done in a given amount of time, you can also stretch your software licenses further. What this means is that you can get more out of your IBM, Microsoft, Oracle, SAP, VMware and other software licenses by increasing their effective productivity. You might already be using virtualization to increase server hardware efficiency and utilization to cut costs. Why not go further and boost productivity to increase your software license (as well as servers) effectiveness by using NVMe and SSDs?

    Note that fast applications need fast software, servers, drivers, I/O protocols and devices.

    Also just because you have NVMe present or PCIe does not mean full performance, similar to how some vendors put SSDs behind their slow controllers and saw, well slow performance. On the other hand vendors who had or have fast controllers (software, firmware, hardware) that were HDD or are even SSD performance constrained can see a performance boost.

    Additional NVMe and related tips

    If you have a Windows server and have not overridden, check your power plan to make sure it is not improperly set to balanced instead of high performance. For example using PowerShell issue the following command:

    PowerCfg -SetActive “381b4222-f694-41f0-9685-ff5bb260df2e”

    Another Windows related tip if you have not done so is enable task manager disk stats by issuing from a command line “diskperf –y”. Then display task manager and performance and see drive performance.

    Need to benchmark, validate, compare or test an NVMe, SSD (or even HDD) device or system, there are various tools and workloads for different scenarios. Likewise those various tools can be configured for different activity to reflect your needs (and application workloads). For example, Microsoft Diskspd, fio.exe, iometer and vdbench sample scripts are shown here (along with results) as a starting point for comparison or validation testing.

    Does M.2. mean you have NVMe? That depends as some systems implement M.2 with SATA, while others support NVMe, read the fine print or ask for clarification.

    Do all NVMe using PCIe run at the same speed? Not necessarily as some might be PCIe x1 or x4 or x8. Likewise some NVMe PCIe cards might be x8 (mechanical and electrical) yet split out into a pair of x4 ports. Also keep in mind that similar to a dual port HDD, NVMe U.2 drives can have two paths to a server, storage system controller or adapter, however both might not be active at the same time. You might also have a fast NVMe device attached to a slow server or storage system or adapter.

    Who to watch and keep an eye on in the NVMe ecosystem? Besides those mentioned above, others to keep an eye on include Broadcom, E8, Enmotus Fuzedrive (micro-tiering software), Excelero, Magnotics, Mellanox, Microsemi (e.g. PMC Sierra), Microsoft (Windows Server 2016 S2D + ReFS + Storage Tiering), NVM Express trade group, Seagate, VMware (Virtual NVMe driver part of vSphere ESXi in addition to previous driver support) and WD/Sandisk among many others.

    Where To Learn More

    Additional related content can be found at:

    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

    NVMe is in your future, that was the answer, however there are the when, where, how, with what among other questions to be addressed. One of the great things IMHO about NVMe is that you can have it your way, where and when you need it, as a replacement or companion to what you have. Granted that will vary based on your preferred vendors as well as what they support today or in the future.

    If NVMe is the answer, Ask your vendor when they will support NVMe as a back-end for their storage systems, as well as a front-end. Also decide when will your servers (hardware, operating systems hypervisors) support NVMe and in what variation. Learn more why NVMe is the answer and related topics at www.thenvmeplace.com

    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

    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)

    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

    Part V – NVMe overview primer (Where to learn more, what this all means)

    This is the fifth in a five-part mini-series providing a NVMe primer overview.

    View Part I, Part II, Part III, Part IV, Part V as well as companion posts and more NVMe primer material at www.thenvmeplace.com.

    There are many different facets of NVMe including protocol that can be deployed on PCIe (AiC, U.2/8639 drives, M.2) for local direct attached, dedicated or shared for front-end or back-end of storage systems. NVMe direct attach is also found in servers and laptops using M.2 NGFF mini cards (e.g. “gum sticks”). In addition to direct attached, dedicated and shared, NVMe is also deployed on fabrics including over Fibre Channel (FC-NVMe) as well as NVMe over Fabrics (NVMeoF) leveraging RDMA based networks (e.g. iWARP, RoCE among others).

    The storage I/O capabilities of flash can now be fed across PCIe faster to enable modern multi-core processors to complete more useful work in less time, resulting in greater application productivity. NVMe has been designed from the ground up with more and deeper queues, supporting a larger number of commands in those queues. This in turn enables the SSD to better optimize command execution for much higher concurrent IOPS. NVMe will coexist along with SAS, SATA and other server storage I/O technologies for some time to come. But NVMe will be at the top-tier of storage as it takes full advantage of the inherent speed and low latency of flash while complementing the potential of multi-core processors that can support the latest applications.

    With NVMe, the capabilities of underlying NVM and storage memories are further realized Devices used include a PCIe x4 NVMe AiC SSD, 12 GbpsSAS SSD and 6 GbpsSATA SSD. These and other improvements with NVMe enable concurrency while reducing latency to remove server storage I/O traffic congestion. The result is that application demanding more concurrent I/O activity along with lower latency will gravitate towards NVMe for access fast storage.

    Like the robust PCIe physical server storage I/O interface it leverages, NVMe provides both flexibility and compatibility. It removes complexity, overhead and latency while allowing far more concurrent I/O work to be accomplished. Those on the cutting edge will embrace NVMe rapidly. Others may prefer a phased approach.

    Some environments will initially focus on NVMe for local server storage I/O performance and capacity available today. Other environments will phase in emerging external NVMe flash-based shared storage systems over time.

    Planning is an essential ingredient for any enterprise. Because NVMe spans servers, storage, I/O hardware and software, those intending to adopt NVMe need to take into account all ramifications. Decisions made today will have a big impact on future data and information infrastructures.

    Key questions should be, how much speed do your applications need now, and how do growth plans affect those requirements? How and where can you maximize your financial return on investment (ROI) when deploying NVMe and how will that success be measured?

    Several vendors are working on, or have already introduced NVMe related technologies or initiatives. Keep an eye on among others including AWS, Broadcom (Avago, Brocade), Cisco (Servers), Dell EMC, Excelero, HPE, Intel (Servers, Drives and Cards), Lenovo, Micron, Microsoft (Azure, Drivers, Operating Systems, Storage Spaces), Mellanox, NetApp, OCZ, Oracle, PMC, Samsung, Seagate, Supermicro, VMware, Western Digital (acquisition of SANdisk and HGST) among others.

    Where To Learn More

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

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

    Software Defined Data Infrastructure Essentials Book SDDC

    What this all means

    NVMe is in your future if not already, so If NVMe is the answer, what are the questions?

    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

    Where, How to use NVMe overview primer

    server storage I/O trends
    Updated 1/12/2018

    This is the fourth in a five-part miniseries providing a primer and overview of NVMe. View companion posts and more material at www.thenvmeplace.com.

    Where and how to use NVMe

    As mentioned and shown in the second post of this series, initially, NVMe is being deployed inside servers as “ back-end,” fast, low latency storage using PCIe Add-In-Cards (AIC) and flash drives. Similar to SAS NVM SSDs and HDDs that support dual-paths, NVMe has a primary path and an alternate path. If one path fails, traffic keeps flowing without causing slowdowns. This feature is an advantage to those already familiar with the dual-path capabilities of SAS, enabling them to design and configure resilient solutions.

    NVMe devices including NVM flash AIC flash will also find their way into storage systems and appliances as back-end storage, co-existing with SAS or SATA devices. Another emerging deployment configuration scenario is shared NVMe direct attached storage (DAS) with multiple server access via PCIe external storage with dual paths for resiliency.

    Even though NVMe is a new protocol, it leverages existing skill sets. Anyone familiar with SAS/SCSI and AHCI/SATA storage devices will need little or no training to carry out and manage NVMe. Since NVMe-enabled storage appears to a host server or storage appliance as an LUN or volume, existing Windows, Linux and other OS or hypervisors tools can be used. On Windows, such as,  other than going to the device manager to see what the device is and what controller it is attached to, it is no different from installing and using any other storage device. The experience on Linux is similar, particularly when using in-the-box drivers that ship with the OS. One minor Linux difference of note is that instead of seeing a /dev/sda device as an example, you might see a device name like /dev/nvme0n1 or /dev/nvme0n1p1 (with a partition).

    Keep in mind that NVMe like SAS can be used as a “back-end” access from servers (or storage systems) to a storage device or system. For example JBOD SSD drives (e.g. 8639), PCIe AiC or M.2 devices. NVMe can also like SAS be used as a “front-end” on storage systems or appliances in place of, or in addition to other access such as GbE based iSCSI, Fibre Channel, FCoE, InfiniBand, NAS or Object.

    What this means is that NVMe can be implemented in a storage system or appliance on both the “front-end” e.g. server or host side as well as on the “back-end” e.g. device or drive side that is like SAS. Another similarity to SAS is that NVMe dual-pathing of devices, permitting system architects to design resiliency into their solutions. When the primary path fails, access to the storage device can be maintained with failover so that fast I/O operations can continue when using SAS and NVMe.

    NVM connectivity options including NVMe
    Various NVM NAND flash SSD devices and their connectivity including NVMe, M2, SATA and 12 Gbps SAS are shown in figure 6.

    Various NVM SSD interfaces including NVMe and M2
    Figure 6 Various NVM flash SSDs (Via StorageIO Labs)

    Left in figure 6 is an NAND flash NVMe PCIe AiC, top center is a USB thumb drive that has been opened up showing an NAND die (chip), middle center is a mSATA card, bottom center is an M.2 card, next on the right is a 2.5” 6 Gbps SATA device, and far fright is a 12 Gbps SAS device. Note that an M.2 card can be either an SATA or NVMe device depending on its internal controller that determines which host or server protocol device driver to use.

    The role of PCIe has evolved over the years as has its performance and packaging form factors. Also, to add in card (AiC) slots, PCIe form factors also include M.2 small form factor that replaces legacy mini-PCIe cards. Another form factor is M.2 (aka Next Generation Form Factor or NGFF) that like other devices, can be an NVMe, or SATA device.

    NGFF also known as 8639 or possibly 8637 (figure 7) can be used to support SATA as well as NVMe depending on the card device installed and host server driver support. There are various M.2 NGFF form factors including 2230, 2242, 2260 and 2280. There are also M.2 to regular physical SATA converter or adapter cards that are available enabling M.2 devices to attach to legacy SAS/SATA RAID adapters or HBAs.

    NVMe 8637 and 8639 interface backplane slotsNVMe 8637 and 8639 interface
    Figure 7 PCIe NVMe 8639 Drive (Via StorageIO Labs)

    On the left of figure 7 is a view towards the backplane of a storage enclosure in a server that supports SAS, SATA, and NVMe (e.g. 8639). On the right of figure 7 is the connector end of an 8639 NVM SSD showing addition pin connectors compared to an SAS or SATA device. Those extra pins give PCIe x4 connectivity to the NVMe devices. The 8639 drive connectors enable a device such as an NVM, or NAND flash SSD to share a common physical storage enclosure with SAS and SATA devices, including optional dual-pathing.

    Where To Learn More

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

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

    Software Defined Data Infrastructure Essentials Book SDDC

    What This All Means

    Be careful judging a device or component by its physical packaging or interface connection about what it is or is not. In figure 6.6 the device has SAS/SATA along with PCIe physical connections, yet it’s what’s inside (e.g. its controller) that determines if it is an SAS, SATA or NVMe enabled device. This also applies to HDDs and PCIe AiC devices, as well as I/O networking cards and adapters that may use common physical connectors, yet implement different protocols. For example, the SFF-8643 HD-Mini SAS internal connector is used for 12 Gbps SAS attachment as well as PCIe to devices such as 8630.

    Depending on the type of device inserted, access can be via NVMe over PCIe x4, SAS (12 Gbps or 6Gb) or SATA. 8639 connector based enclosures have a physical connection with their backplanes to the individual drive connectors, as well as to PCIe, SAS, and SATA cards or connectors on the server motherboard or via PCIe riser slots.

    While PCIe devices including AiC slot based, M.2 or 8639 can have common physical interfaces and lower level signaling, it’s the protocols, controllers, and drivers that determine how they get a software defined and used. Keep in mind that it’s not just the physical connector or interface that determines what a device is or how it is used, it’s also the protocol, command set, and controller and device drivers.

    Continue reading about NVMe with Part V (Where to learn more, what this all means) in this five-part series, or jump to Part I, Part II or Part III.

    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

    NVMe Need for Performance Speed Performance

    server storage I/O trends
    Updated 1/12/2018

    This is the third in a five-part mini-series providing a primer and overview of NVMe. View companion posts and more material at www.thenvmeplace.com.

    How fast is NVMe?

    It depends! Generally speaking NVMe is fast!

    However fast interfaces and protocols also need fast storage devices, adapters, drivers, servers, operating systems and hypervisors as well as applications that drive or benefit from the increased speed.

    A server storage I/O example is in figure 5 where a 6 Gbps SATA NVM flash SSD (left) is shown with an NVMe 8639 (x4) drive that were directly attached to a server. The workload is 8 Kbyte sized random writes with 128 threads (workers) showing results for IOPs (solid bar) along with response time (dotted line). Not surprisingly the NVMe device has a lower response time and a higher number of IOPs. However also note how the amount of CPU time used per IOP is lower on the right with the NVMe drive.

    NVMe storage I/O performance
    Figure 5 6 Gbps SATA NVM flash SSD vs. NVMe flash SSD

    While many people are aware or learning about the IOP and bandwidth improvements as well as the decrease in latency with NVMe, something that gets overlooked is how much less CPU is used. If a server is spending time in wait modes that can result in lost productivity, by finding and removing the barriers more work can be done on a given server, perhaps even delaying a server upgrade.

    In figure 5 notice the lower amount of CPU used per work activity being done (e.g. I/O or IOP) which translates to more effective resource use of your server. What that means is either doing more work with what you have, or potentially delaying a CPU server upgrade, or, using those extra CPU cycles to power software defined storage management stacks including erasure coding or advanced parity RAID, replication and other functions.

    Table 1 shows relative server I/O performance of some NVM flash SSD devices across various workloads. As with any performance, the comparison takes them, and the following with a grain of salt as your speed will vary.

    8KB I/O Size

    1MB I/O size

    NAND flash SSD

    100% Seq. Read

    100% Seq. Write

    100% Ran. Read

    100% Ran. Write

    100% Seq. Read

    100% Seq. Write

    100% Ran. Read

    100% Ran. Write

    NVMe

    IOPs

    41829.19

    33349.36

    112353.6

    28520.82

    1437.26

    889.36

    1336.94

    496.74

    PCIe

    Bandwidth

    326.79

    260.54

    877.76

    222.82

    1437.26

    889.36

    1336.94

    496.74

    AiC

    Resp.

    3.23

    3.90

    1.30

    4.56

    178.11

    287.83

    191.27

    515.17

    CPU / IOP

    0.001571

    0.002003

    0.000689

    0.002342

    0.007793

    0.011244

    0.009798

    0.015098

    12Gb

    IOPs

    34792.91

    34863.42

    29373.5

    27069.56

    427.19

    439.42

    416.68

    385.9

    SAS

    Bandwidth

    271.82

    272.37

    229.48

    211.48

    427.19

    429.42

    416.68

    385.9

    Resp.

    3.76

    3.77

    4.56

    5.71

    599.26

    582.66

    614.22

    663.21

    CPU / IOP

    0.001857

    0.00189

    0.002267

    0.00229

    0.011236

    0.011834

    0.01416

    0.015548

    6Gb

    IOPs

    33861.29

    9228.49

    28677.12

    6974.32

    363.25

    65.58

    356.06

    55.86

    SATA

    Bandwidth

    264.54

    72.1

    224.04

    54.49

    363.25

    65.58

    356.06

    55.86

    Resp.

    4.05

    26.34

    4.67

    35.65

    704.70

    3838.59

    718.81

    4535.63

    CPU / IOP

    0.001899

    0.002546

    0.002298

    0.003269

    0.012113

    0.032022

    0.015166

    0.046545

    Table 1 Relative performance of various protocols and interfaces

    The workload results in table 1 were generated using a vdbench script running on a Windows 2012 R2 based server and are intended to be a relative indicator of different protocol and interfaces; your performance mileage will vary. The results shown below compare the number of IOPs (activity rate) for reads, writes, random and sequential across small 8KB and large 1MB sized I/Os.

    Also shown in table 1 are bandwidth or throughput (e.g. amount of data moved), response time and the amount of CPU used per IOP. Note in table 1 how NVMe can do higher IOPs with a lower CPU per IOP, or, using a similar amount of CPU, do more work at a lower latency. SSD has been used for decades to help reduce CPU bottlenecks or defer server upgrades by removing I/O wait times and reduce CPU consumption (e.g. wait or lost time).

    Can NVMe solutions run faster than those shown above? Absolutely!

    Where To Learn More

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

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

    Software Defined Data Infrastructure Essentials Book SDDC

    What This All Means

    Continue reading about NVMe with Part IV (Where and How to use NVMe) in this five-part series, or jump to Part I, Part II or Part V.

    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

    Different NVMe Configurations

    server storage I/O trends
    Updated 1/12/2018

    This is the second in a five-part mini-series providing a primer and overview of NVMe. View companion posts and more material at www.thenvmeplace.com.

    The many different faces or facets of NVMe configurations

    NVMe can be deployed and used in many ways, the following are some examples to show you its flexibility today as well as where it may be headed in the future. An initial deployment scenario is NVMe devices (e.g. PCIe cards, M2 or 8639 drives) installed as storage in servers or as back-end storage in storage systems. Figure 2 below shows a networked storage system or appliance that uses traditional server storage I/O interfaces and protocols for front-end access, however with back-end storage being all NVMe, or a hybrid of NVMe, SAS and SATA devices.
    NVMe as back-end server storage I/O interface to NVM
    Figure 2 NVMe as back-end server storage I/O interface to NVM storage

    A variation of the above is using NVMe for shared direct attached storage (DAS) such as the EMC DSSD D5. In the following scenario (figure 3), multiple servers in a rack or cabinet configuration have an extended PCIe connection that attached to a shared storage all flash array using NVMe on the front-end. Read more about this approach and EMC DSSD D5 here or click on the image below.

    EMC DSSD D5 NVMe
    Figure 3 Shared DAS All Flash NVM Storage using NVMe (e.g. EMC DSSD D5)

    Next up in figure 4 is a variation of the previous example, except NVMe is implemented over an RDMA (Remote Direct Memory Access) based fabric network using Converged 10GbE/40GbE or InfiniBand in what is known as RoCE (RDMA over Converged Ethernet pronounced Rocky).

    NVMe over Fabric RoCE
    Figure 4 NVMe as a “front-end” interface for servers or storage systems/appliances

    Where To Learn More

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

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

    Software Defined Data Infrastructure Essentials Book SDDC

    What This All Means

    Watch for more topology and configuration options as NVMe along with associated hardware, software and I/O networking tools and technologies emerge over time.

    Continue reading about NVMe with Part III (Need for Performance Speed) in this five-part series, or jump to Part I, Part IV or Part V.

    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

    NVMe overview primer

    server storage I/O trends
    Updated 2/2/2018

    This is the first in a five-part mini-series providing a primer and overview of NVMe. View companion posts and more material at www.thenvmeplace.com.

    What is NVM Express (NVMe)

    Non-Volatile Memory (NVM) includes persistent memory such as NAND flash and other forms Solid State Devices (SSD). NVM express (NVMe) is a new server storage I/P protocol alternative to AHCI/SATA and the SCSI protocol used by Serial Attached SCSI (SAS). Note that the name NVMe is owned and managed by the industry trade group for NVM Express is (www.nvmexpress.org).

    The key question with NVMe is not if, rather when, where, why, how and with what will it appear in your data center or server storage I/O data infrastructure. This is a companion to material that I have on my micro site www.thenvmeplace.com that provides an overview of NVMe, as well as helps to discuss some of the questions about NVMe.

    Main features of NVMe include among others:

    • Lower latency due to improve drivers and increased queues (and queue sizes)
    • Lower CPU used to handler 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

    Why NVMe for Server Storage I/O?
    NVMe has been designed from the ground up for accessing fast storage including flash SSD leveraging PCI Express (PCIe). The benefits include lower latency, improved concurrency, increased performance and the ability to unleash a lot more of the potential of modern multi-core modern processors.

    NVMe Server Storage I/O
    Figure 1 shows common server I/O connectivity including PCIe, SAS, SATA and NVMe.

    NVMe, leveraging PCIe, enables modern applications to reach their full potential. NVMe is one of those rare, generational protocol upgrades that comes around every couple of decades to help unlock the full performance value of servers and storage. NVMe does need new drivers, but once in place, it plugs and plays seamlessly with existing tools, software and user experiences. Likewise many of those drivers are now in the box (e.g. ship with) for popular operating systems and hypervisors.

    While SATA and SAS provided enough bandwidth for HDDs and some SSD uses, more performance is needed. NVMe near-term does not replace SAS or SATA they can and will coexist for years to come enabling different tiers of server storage I/O performance.

    NVMe unlocks the potential of flash-based storage by allowing up to 65,536 (64K) queues each with 64K commands per queue. SATA allowed for only one command queue capable of holding 32 commands per queue and SAS supports a queue with 64K command entries. As a result, the storage IO capabilities of flash can now be fed across PCIe much faster to enable modern multi-core processors to complete more useful work in less time.

    Where To Learn More

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

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

    Software Defined Data Infrastructure Essentials Book SDDC

    What This All Means

    Continue reading about NVMe with Part II (Different NVMe configurations) in this five-part series, or jump to Part III, Part IV or Part V.

    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

    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.

    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.

    Posted on

    3D XPoint nvm pm scm storage class memory

    Part III – 3D XPoint server storage class memory SCM


    Storage I/O trends

    Updated 1/31/2018

    3D XPoint nvm pm scm storage class memory.

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

    What is 3D XPoint and how does it work?

    3D XPoint is a new class or class of memory (view other categories of memory here) that provides performance for reads and writes closer to that of DRAM with about 10x the capacity density. In addition to the speed closer to DRAM vs. the lower NAND flash, 3D XPoint is also non-volatile memory (NVM) like NAND flash, NVRAM and others. What this means is that 3D XPoint can be used as persistent higher density fast server memory (or main memory for other computers and electronics). Besides being fast persistent main memory, 3D XPoint will also be a faster medium for solid state devices (SSD’s) including PCIe Add In Cards (AIC), m2 cards and drive form factor 8637/8639 NVM Express (NVMe) accessed devices that also has better endurance or life span compared to NAND flash.


    3D XPoint architecture and attributes

    The initial die or basic chip building block 3D XPoint implementation is a layer 128 Gbit device which if using 8 bits would yield 16GB raw. Over time increased densities should become available as the bit density improves with more cells and further scaling of the technology, combined with packaging. For example while a current die could hold up to 16 GBytes of data, multiple dies could be packaged together to create a 32GB, 64GB, 128GB etc. or larger actual product. Think about not only where packaged flash based SSD capacities are today, also think in terms of where DDR3 and DDR4 DIMM are at such as 4GB, 8GB, 16GB, 32GB densities.

    The 3D aspect comes from the memory being in a matrix initially being two layers high, with multiple rows and columns that intersect, where those intersections occur is a microscopic material based switch for accessing a particular memory cell. Unlike NAND flash where an individual cell or bit is accessed as part of a larger block or page comprising several thousand bytes at once, 3D XPoint cells or bits can be individually accessed to speed up reads and writes in a more granular fashion. It is this more granular access along with performance that will enable 3D XPoint to be used in lower latency scenarios where DRAM would normally be used.

    Instead of trapping electrons in a cell to create a bit of capacity (e.g. on or off) like NAND flash, 3D XPoint leverages the underlying physical material propertied to store a bit as a phase change enabling use of all cells. In other words, instead of being electron based, it is material based. While Intel and Micron did not specify what the actual chemistry and physical materials that are used in 3D XPoint, they did discuss some of the characteristics. If you want to go deep, check out how the Dailytech makes an interesting educated speculation or thesis on the underlying technology.

    Watch the following video to get a better idea and visually see how 3D XPoint works.



    3D XPoint YouTube Video

    What are these chips, cells, wafers and dies?

    Left many dies on a wafer, right, a closer look at the dies cut from the wafer

    Dies (here and here) are the basic building block of what goes into the chips that in turn are the components used for creating DDR DIMM for main computer memory, as well as for create SD and MicroSD cards, USB thumb drives, PCIe AIC and drive form factor SSD, as well as custom modules on motherboards, or consumption via bare die and wafer level consumption (e.g. where you are doing really custom things at volume, beyond using a soldering iron scale).

    Storage I/O trends

    Has Intel and Micron cornered the NVM and memory market?

    We have heard proclamations, speculation and statements of the demise of DRAM, NAND flash and other volatile and NVM memories for years, if not decades now. Each year there is the usual this will be the year of “x” where “x” can include among others. Resistive RAM aka ReRAM or RRAM aka the memristor that HP earlier announced they were going to bring to market and then earlier this year canceling those plans while Crossbar continues to pursue RRAM. MRAM or Magnetorestive RAM, Phase Change Memory aka CRAM or PCM and PRAM, FRAM aka FeRAM or Ferroelectric RAM among others.

    flash SSD and NVM trends

    Expanding persistent memory and SSD storage markets

    Keep in mind that there are many steps taking time measured in years or decades to go from research and development lab idea to prototype that can then be produced at production volumes in economic yields. As a reference for, there is still plenty of life in both DRAM as well as NAND flash, the later having appeared around 1989.

    Industry vs. Customer Adoption and deployment timeline

    Technology industry adoption precedes customer adoption and deployment

    There is a difference between industry adoption and deployment vs. customer adoption and deployment, they are related, yet separated by time as shown in the above figure. What this means is that there can be several years from the time a new technology is initially introduced and when it becomes generally available. Keep in mind that NAND flash has yet to reach its full market potential despite having made significant inroads the past few years since it was introduced in 1989.

    This begs the question of if 3D XPoint is a variation of phase change, RRAM, MRAM or something else. Over at the Dailytech they lay out a line of thinking (or educated speculation) that 3D XPoint is some derivative or variation of phase change, time will tell about what it really is.

    What’s the difference between 3D NAND flash and 3D XPoint?

    3D NAND is a form of NAND flash NVM, while 3D XPoint is a completely new and different type of NVM (e.g. its not NAND).

    3D NAND is a variation of traditional flash with the difference between vertical stacking vs. horizontal to improve density, also known as vertical NAND or V-NAND. Vertical stacking is like building up to house more tenants or occupants in a dense environment or scaling up, vs scaling-out by using up more space where density is not an issue. Note that magnetic HDD’s shifted to perpendicular (e.g. vertical) recording about ten years ago to break through the super parametric barrier and more recently, magnetic tape has also adopted perpendicular recording. Also keep in mind that 3D XPoint and the earlier announced Intel and Micron 3D NAND flash are two separate classes of memory that both just happen to have 3D in their marketing names.

    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

    First, keep in mind that this is very early in the 3D XPoint technology evolution life-cycle and both DRAM and NAND flash will not be dead at least near term. Keep in mind that NAND flash appeared back in 1989 and only over the past several years has finally hit its mainstream adoption stride with plenty of market upside left. Same with DRAM which has been around for sometime, it too still has plenty of life left for many applications. However other applications that have the need for improved speed over NAND flash, or persistency and density vs. DRAM will be some of the first to leverage new NVM technologies such as 3D XPoint. Thus at least for the next several years, there will be a co-existences between new and old NVM and DRAM among other memory technologies. Bottom line, 3D XPoint is a new class of NVM memory, can be used for persistent main server memory or for persistent fast storage memory. If you have not done so, check out Part I here and Part II here of this three-part series on Intel and Micron 3D XPoint.

    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.