Name: NVM Express Over Fabrics -- A Panel Discussion
Start: 2016-10-20T17:00:00Z
End: 2016-10-20T17:00:57.000Z
Location: BrightTALK
Rating: 3.8

NVM Express® is an open collection of standards and information to fully expose the benefits of non-volatile memory in all types of computing environments from mobile to data center. NVMe™ is designed from the ground up to deliver high bandwidth and low latency storage access for current and future NVMe technologies.

While a host has been able to address NVMe device memory using Controller Memory Buffer (CMB) and Persistent Memory Region (PMR), this memory has never been addressable by NVMe commands. NVM Express recently introduced the Subsystem Local Memory IO Command Set (SLM), which allowed NVMe device memory to be addressable by NVMe commands; however, this memory could not be addressed by the host using host memory addresses. 
A new technical proposal is being developed by NVM Express that would allow SLM to be assigned to a host memory address range. This presentation will describe the architecture of this new NVMe feature and discuss the benefits and use cases that host addressable SLM enables.

Host Addressing of NVMe Subsystem Local Memory

For more than a decade, the University of New Hampshire InterOperability Laboratory (UNH-IOL) and the NVM Express organization have worked together to advance an open ecosystem for NVM Express technology. This collaboration centers on developing and refining a robust compliance and interoperability testing program to ensure NVMe devices operate reliably across diverse platforms, drivers and hardware configurations.
 
In this webinar, attendees will gain valuable insights into the NVMe compliance and interoperability testing program, including how it helps vendors validate their products and accelerate time to market. Representatives from UNH-IOL will explain the scope of testing services available to NVM Express members, while speakers from member companies Marvell and Xinnor will share their perspectives on the importance of testing. The session will conclude with a live Q&A, allowing attendees to ask technical and logistical questions about the testing process and how to get involved.

NVM Express Compliance & Interoperability Testing: UNH-IOL Guidelines and Marvell & Xinnor Use Cases

Today’s customers expect data centers to remain fully operational, online and reliable with minimal downtime, while efficiently maintaining vast amounts of data. The NVMe® Management Interface (NVMe-MI™) Specification simplifies the process of managing NVMe storage devices by enabling the ability to easily discover, monitor, configure and update NVMe devices. To continually advance NVMe-MI technology efficiency, NVM Express has introduced the NVMe-MI 2.0 Specification, which includes the NVMe High Availability, Asynchronous Event Notification and I3C features, as well as additional important enhancements. 

This webinar will explore the new features included in the NVMe-MI 2.0 Specification to simplify event notification processes and monitor drive health and state changes across NVMe storage devices. The presenters will demonstrate various use cases including how multiple Baseboard Management Consoles (BMCs) can manage a dual-port NVMe storage device via 2-Wire bus. Additionally, they will demonstrate how BMCs can subscribe to receive asynchronous event notifications from NVMe storage devices to avoid costly polling. Attendees will learn how NVMe storage devices ensure enhanced reliability and efficiency on the out-of-band management interfaces for their enterprise and hyperscale data center architectures.

Scaling Up Data Center Management with the NVMe-MI™ 2.0 Specification

Cloud, enterprise and IoT spaces are currently processing an unprecedented amount of data to meet the ever-evolving demands of the storage industry. The demand is leading to increased network bandwidth usage, host memory and CPU utilization and system performance bottlenecks. The NVM Express® (NVMe®) Computational Storage feature addresses these performance issues and enables a standardized mechanism for vendors to include streamlined computational features across their architectures.

In this webinar, presenters from IBM and Solidigm will share real world use cases about how their companies are currently leveraging Computational Storage. Solidigm will discuss how it is using Computational Storage to free up cycles from the host, improve network bandwidth and maintain data integrity. IBM will share how it is leveraging Computational Storage to create a set of algorithms that detect ransomware issues.

NVMe Computational Storage: From Addressing Ransomware to Improving Bandwidth

The NVMe® over Fabrics (NVMe-oF™) specifications define a network architecture that supports data transfers over a range of storage networking fabrics. By using NVMe systems with NVMe-oF technology, data centers can readily establish high-performance storage networks with high throughput and low latency. 

Join David Black and Claudio DeSanti to learn how NVM Express has expanded the NVMe-oF specifications to include vital security features to protect against cyberattacks and enable data centers to establish efficient and secure storage area networks. Attendees will receive an overview of the NVMe-oF security mechanisms and learn about recently standardized security advancements, including improvements to in-band authentication and Transport Layer Security (TLS) usage requirements.

Advancing Data Center Security  with NVMe-oF™ Technology

The NVM Express® (NVMe®) specification and implementations have come a long way since 2013, when the NVM Express organization and UNH-IOL partnered to form the official NVM Express technology compliance program. As the specifications have evolved over the past decade, compliance and interoperability testing has become more complicated as new features and testing requirements have been added for features such as Flexible Data Placement (FDP), Cross Namespace Copy and the upcoming Computational Storage Command Set. 

In this webinar, we will discuss the current status of NVMe compliance testing, included the testing requirements for the newest features like Performance Characteristics Reporting Feature, Dispersed Namespaces and more. Finally, we will discuss future testing and how companies can become “test ready” for the upcoming Zoned Name Space (ZNS) over Fabrics and FDP features.

NVMe® Compliance Program: Preparing to Test New Features

Our industry needs a standardized, multi-vendor solution to boot computer systems from OS images stored on NVMe devices across a network. This is critical for large deployments. The newly published NVM Express® Boot Specification and ecosystem partnership with UEFI and ACPI enables this by leveraging the NVMe-oF standard. 

This talk is a dive into the details of the new specification and the design of an open-source prototype for booting over NVMe/TCP transport using a UEFI implementation.

Booting Your OS Across the NVMe-oF™ Transport – NVMe® Boot Specification

Using a Centralized Discovery Controller (CDC) with NVMe® over Fabrics (NVMe-oF™) on IP-based fabrics, such as NVMe/TCP and NVMe/RDMA, enables overcoming discovery challenges and has the potential to provide significant benefits in application environments, ranging from the edge to the data center. Leveraging automated discovery, each host and subsystem of an NVMe IP-based SAN automatically discovers the CDC, which aggregates discovery information and connectivity constraints for all hosts and subsystems. By simplifying and automating the discovery process and enabling administrative configuration of connectivity constraints with NVMe fabric zoning in NVMe IP-based SANs, data center environments can experience reduced overhead with a more centralized system. Discovery automation and NVMe fabric zoning provide a clean evolution of existing host discovery by utilizing existing functionality in a more efficient way.

Join us for a webinar featuring technology experts from Dell and HPE covering the collaborative efforts toward creating Discovery Automation enhancements. The presenters will review the Discovery Automation roadmap, discuss recent enhancements and the new zoning. Finally, the presenters will review use cases and how the zoning has been made available for new use types.

Discovery Automation Enhancement: Enabling NVMe Over IP-Based Fabrics Systems

The NVMe 2.0 specifications, released in 2021, were refactored to enable faster and simpler development of NVMe solutions. As we enter a new era in hyperscale and enterprise computing, the NVM Express Technical Work Group worked to optimize the suite of NVMe specifications to support emerging use cases for diverse market segments. 

In this NVM Express hosted webinar, contributors of the NVMe 2.0 specifications will provide a comprehensive overview of the refactoring effort, critical specification features, and new command sets such as Zoned Namespace and Key Value. Webinar attendees will learn why these changes were made, how they will affect the NVMe device environment and how the new features will impact NVMe SSD development and performance.

About the Presenters:
Peter Onufryk, Intel Fellow, Intel
Nick Adams, Principal Software Engineer, Intel
Matias Bjørling, Director, Western Digital
Bill Martin, SSD I/O Standards, Samsung

NVMe 2.0 Specifications: Fast, Simple and Optimized for the Future of Storage

Join industry NVMe technology experts from NVIDIA and Cisco as they discuss the origins of the NVMe standard and its adaption to a multi-transport technology with the development of the NVMe over Fabrics (NVMe-oF) specification, and where it fits as a transport technology in today's data centers. Participants of this webcast will also learn about deployment use cases of NVMe-oF technology, including backend storage access, Storage Area Network (SAN), Composable Infrastructure, storage acceleration with GPUs, and Hyperconverged Infrastructure (HCI). Lastly, a summary of the various security and management features will be introduced. 

Register to reserve your spot today!

Deploy NVMe Technology Anywhere

The variety of architectures, use-cases and workloads to be managed by Data Center appliances is increasing. It is driving a need for storage and compute disaggregation, while at the same time forcing IT pros to simplify Data Center management and move to hyperconverged infrastructure. However the HCI approach results in siloing of storage that leads to capacity waste and scalability issue. 
This talk is describing how modern smart storage adapters are leveraging NVMe® and NVMe-oF™ technologies to offload servers from heavy storage tasks, and pave the way toward a fully Composable Infrastructure.

Smart Storage Adapters Help Enable NVMe-oF™ Composable Architectures

The Zoned Namespace (ZNS) SSDs is a new NVMe™ Command Set, which exposes a zoned block storage interface between the host and the SSD. This allows more explicit data placement policies from the host, resulting in less over-provisioning, less write amplification and tighter I/O access latencies.

In this talk, we will cover the ZNS command set, the Linux zoned storage ecosystem and the changes to enable ZNS SSDs. We will show how the Linux kernel storage stack enables ZNS, and how new and existing tools and libraries enable one to better utilize and take advantage of the ZNS SSD benefits.

NVMe® Zoned Namespace SSDs & The Zoned Storage Linux Software Ecosystem

NVM Express is dedicated to making the management of NVMe SSDs simple. To achieve this, the organization has built many capabilities into NVMe architecture to enable NVMe SSD management, error reporting and logging capabilities. 

SSD errors could include hardware failure, integrity errors, media errors, temperature issues and more. Tools such as enhance error reporting, logging, management, debugging and telemetry help ensure that a failure of an NVMe SSD does not cause data corruption or loss of data. 

The webcast presenters will provide an overview of how SSDs fail, the various tools used to help predict and prevent errors from happening, as well as how to implement them.

NVMe™ SSD Management, Error Reporting and Logging Capabilities 

The NVMe-oF specification has been described as creating “data center storage disruption” offering performance increases for both applications and the network. With the release of the latest NVMe-oF 1.1 specification in 2019, this technology continues to evolve as more features become available. But what does this mean for the future of data centers? 

In this webcast, participants will receive a summary of the various features added to the new NVMe-oF 1.1 specification, including an overview of multipathing, Asymmetric Namespace Access (ANA) and NVMe/TCP capabilities. Several NVMe technology experts will provide insight into networking considerations, use cases and potential performance challenges that should be understood before the implementation of the NVMe-oF 1.1 specification.

NVMe-oF™ 1.1 Specification: Key Features and Use Cases

The NVM Express™ organization recently announced the release of the NVMe™ 1.4 Base Specification. This webcast will provide an overview and usages for a number of the new features in the NVMe 1.4 Specification including IO Determinism, IO Performance & Endurance Hints, Persistent Event Log, Namespace Write Protect, the Verify Command, and Rebuild Assist. The webcast will also cover how these new features will benefit the cloud, enterprise and client market segments. 

Attendees will also learn how the new features in the NVMe 1.4 specification will be tested for compliance and interoperability. This portion of the webcast will cover testing for features such as IO Determinism, Namespace Write Protect, Persistent Event Log, and Verify Command. Implementers will learn what they need to keep in mind in order to be prepared for NVMe 1.4 testing.

NVMe™ 1.4 Features and Compliance: Everything You Need To Know

The NVMe standard is evolving to support data center deployment of SSDs. Hyperscalers have brought their requirements into NVM Express regarding isolation, predictable latency and write amplification. As a result, new features such as I/O determinism and predictable latency has been added to the upcoming NVMe 1.4 specification to address some of these concerns, and NVMe-oF has added support for TCP as a transport. In this NVM Express, Inc. hosted webinar, Mark Carlson of Toshiba and John Kim of Mellanox will cover the issues and show the new features from multiple data center perspectives.

About the Presenters 
- Mark Carlson is a Principal Engineer at Toshiba Memory and an NVMe Board Member. 
- John Kim is the Director of Storage Marketing at Mellanox.

Powering the Data Center with NVM Express™

NVM Express, Inc., the standards body behind the NVMe™ specification library, recently announced the addition of NVMe™ over TCP (NVMe™/TCP) to the family of NVMe transports. NVMe/TCP defines the mapping of NVMe queues, NVMe™ over Fabrics (NVMe-oF™) capsules and data delivery over the IETF Transport Control Protocol (TCP). 

This webcast will tour the important benefits and features of the new NVMe/TCP specification and dive into the details of this new NVMe transport. Items covered include the wire protocol and optional features such as inline data integrity and transport security. Audience members will gain an technical understanding of the new specification that will help developers seamlessly implement NVMe/TCP in their NVMe-oF solutions.

About the Presenters 

Sagi Grimberg is Chief SW Architect and Co-founder at Lightbits and the lead author of the NVMe/TCP specification.

Peter Onufyrk is a Fellow in the Data Center Solutions business unit at Microsemi, an NVMe Board Member, and NVMe-MI Workgroup Chair.

NVMe™/TCP: What You Need to Know About the Specification

NVM Express® over PCI Express® SSDs is the mainstream solution in the client space because it is low cost and has a smaller form factor than HDDs, while touting high performance and low power usage. Evolving to meet the needs of consumers, NVMe™ implementations touch various markets like gaming, content creation, workstations, mobile, media creation and more. Join Jonmichael Hands of Intel and Cameron Brett of Toshiba for this NVM Express, Inc. hosted webcast to learn more about real-world examples and how NVMe specifications continue to evolve to support client needs.

In this webcast, attendees will learn more about the benefits of selecting NVMe enabled products like Intel SSDs and Toshiba SSDs. The webcast explores the client benefits that have surfaced with the different iterations of the NVMe specifications from NVMe 1.2 to NVMe 1.3 to the upcoming NVMe 1.4. Attendees will receive an in-depth overview of critical NVMe features including easier management of power/thermals, NVMe’s enablement in small form factors like M.2 and BGA, boot partitions and host controlled thermal management and namespace write protection. 

About the Presenters 

Cameron Brett is Director of Marketing, SSD and Storage Solutions, Toshiba Memory America, Inc. and a member of the NVMe Marketing Workgroup.

Jonmichael Hands is a Product Marketing Manager at Intel and the NVMe Marketing Workgroup Co-Chair.

Benefits of NVMe™ SSDs in Client Implementations

NVM Express(R) over Fabrics has the promise of unleashing the potential performance of NVMe(TM) drives in a scalable manner by leveraging the capabilities of mainstream high-performance interconnects.  There are already several fabrics that have taken the lead in proposed deployments, and others that are being considered.  This panel of technologists reviews the benefits of using different fabrics as the platform for this new initiative, and explores how what value they bring to the party for specific applications and workloads.  Is one fabric the clear winner, or does the choice depend upon what the end-user is trying to accomplish?

NVM Express Over Fabrics -- A Panel Discussion

Express

NVMe

InfiniBand

Ethernet

Welcome to the virtualization community on BrightTALK! Whether it affects servers, storage, networks, desktops or other parts of the data center, virtualization provides real benefits by reducing the resources needed for your
infrastructure and creating software-defined data center components. However, it can also complicate your infrastructure. Join this active community to learn best
practices for avoiding virtual machine sprawl and other common virtualization pitfalls as well as how you can make the most of your virtualization environment.

Virtualization

Cloud computing has exploded over the past few years, delivering a previously unimagined level of workplace mobility and flexibility. The cloud computing community on BrightTALK is made up of thousands of engaged professionals learning from the latest cloud computing research and resources. Join the community to expand your cloud computing knowledge and have your questions answered in live sessions with industry experts and vendor representatives.

Cloud Computing

The data center management community focuses on the holistic management and optimization of the data center. From technologies such as virtualization and cloud computing to data center design, colocation, energy efficiency and monitoring, the BrightTALK data center management community provides the most up-to-date and engaging content from industry experts to better your infrastructure and operations. Engage with a community of your peers and industry experts by asking questions, rating presentations and participating in polls during webinars, all while you gain insight that will help you transform your infrastructure into a next generation data center.

Data Center Management

The storage community on BrightTALK is made up of thousands of storage and IT professionals. Find relevant webinars and videos on storage architecture, cloud storage, storage virtualization and more presented by recognized thought leaders. Join the conversation by participating in live webinars and round table discussions.

Storage

As an IT professional, many of the problems you face are multifaceted, complex and don’t lend themselves to simple solutions. The information technology community features useful and free information technology resources. Join to browse thousands of videos and webinars on ITIL best practices, IT security strategy and more presented by leading CTOs, CIOs and other technology experts.

NVM Express Over Fabrics -- A Panel Discussion

Presented by

About this talk

NVM Express