With virtualization and cloud computing revolutionizing the data center, it's time that the network has its own revolution. Join the Network Infrastructure channel on all the hottest topics for network and storage professionals such as software-defined networking, WAN optimization and more to maintain performance and service in your infrastructure

Composable disaggregated infrastructures provide a promising solution to addressing the provisioning and computational efficiency limitations, as well as hardware and operating costs, of integrated, siloed, systems. But how do we solve these problems in an open, standards-based way? 

DMTF, SNIA, the OFA, and the CXL Consortium are working together to provide elements of the overall solution, with Redfish and Swordfish manageability providing the standards-based interface. OFA is developing an Open Fabric Management Framework (OFMF) designed for configuring fabric interconnects and managing composable disaggregated resources in dynamic HPC infrastructures using client-friendly abstractions.

In this webinar, attendees will understand how use cases for scaling management of storage and fabrics and beyond are addressed in these architectures, and the applicability to additional technologies.

Casting the Net: Scaling Management of Storage and Fabrics

Data centers continue to expand their environmental footprints, currently consuming 2% of the developed world’s electricity. Experts predict this number could rise to 13% by 2030. This webinar will cover energy-efficiency in data centers and ways to rein in costs and improve sustainability. This includes delivering more power efficiency per capacity, revolutionizing cooling to reduce heat, increasing system processing to enhance performance, and infrastructure consolidation to reduce the physical and carbon footprint.
 
Join this webcast and you’ll hear our panel of experts discuss:

• Defining Sustainability  
• Why Does Sustainability Matter for IT? 
• Sustainability for Storage & Networking 
• The Importance of Measurement and KPIs
• Sustainability vs. Efficiency 
• Best practices - Now vs. Future  
• Bringing your IT, Facilities and Sustainability Organizations Together

Sustainability in the Data Center Ecosystem

The SODA Foundation, in partnership with Linux Foundation Research, has recently published its Data and Storage Trends 2022 Report, “Data and Storage Strategies in the Era of the Data-Driven Enterprise.” The findings from this global study provide a comprehensive look at the intersection of cloud computing, data and storage management, the configuration of environments that end-user organizations are gravitating to, and priorities of selected capabilities over the next several years. 

SNIA is pleased to host SODA members who led this important research for a live discussion and in-depth look at key trends driving data and storage, including:

• The top 12 trends in data and storage
• Data security challenges facing container deployments
• Approaches to public cloud deployment
• Challenges for storage observability
• Focus on hybrid and multi-cloud deployments
• Top use cases for cloud storage services
• The impact of open source and data and storage

Top 12 Trends in Data and Cloud Storage

Cybercriminals have always been about data – stealing data, compromising data, holding data hostage. Businesses continue to respond with malware detection on laptops and networks to protect data and prevent breaches, so why should storage be left out?  Storage houses what the bad actors are targeting - your data.  Is there anything we can do from within the storage layer to further enhance defense in depth?  
 
Enter "Cyberstorage", a term coined by Gartner, which is defined as doing threat detection and response in storage software or hardware. A parallel, related trend in the security industry is eXtended Detection and Response (XDR) which shifts some of the threat detection from centralized security monitoring tools (SIEMs) down into each domain (e.g., endpoint, network) for faster detection and automated response.  Factor in the growing impact of ransomware and all these forces are driving the need to find creative, new ways to detect malware, including from inside the storage domain.   
 
In this session we'll discuss:
• Cyberstorage and XDR – what are these emerging trends?
• Threat detection and response methods through a storage lens
• Possible approaches for detection when used in conjunction with security tooling
• Why silos between security and storage need to be addressed for successful threat detection

Cyberstorage and XDR: Threat Detection through a Storage Lens

Industry analysts predict Deep Learning will account for the majority of cloud workloads. Additionally, training of Deep Learning models will represent the majority of server applications in the next few years. Among Deep Learning workloads, foundation models -- a new class of AI models that are trained on broad data (typically via self-supervision) using billions of parameters – are expected to consume the majority of the infrastructure.
 
This webcast will discuss how Deep Learning models are gaining prominence in various industries, and provide examples of the benefits of AI adoption. We’ll enumerate considerations for selection of Deep Learning infrastructure in on-premises and cloud datacenters. Our presentation will include an assessment of various solution approaches, and identify challenges faced by enterprises in their adoption of AI and Deep Learning technologies. We’ll answer questions like:
·       What benefits are enterprises enjoying from innovations in AI, Machine Learning, and Deep Learning?
·       How should cost, performance, and flexibility be traded off when designing deep learning infrastructure?
·       How are cloud native AI software stacks such as Kubernetes being leveraged by organizations to reduce complexity with rapidly evolving software stacks (TensorFlow, PyTorch, etc.)?
·       What are the challenges in operationalizing Deep Learning infrastructure?
·       How can Deep Learning solutions scale?
·       Besides cost, time-to-train, data storage capacity and data bandwidth, what else should be considered when selecting a Deep Learning infrastructure?

Training Deep Learning Models in the Cloud

Machine learning (ML) is the study and development of algorithms that improves with use of data. As it deals with the training data, the machine algorithm changes and grows. Most ML models begin with “training data” which the machine processes and begins to “understand” statistically. 
Machine learning models are resource intensive. To anticipate, validate, and recalibrate millions of times, they demand a significant amount of processing power. Training an ML model might slow down your machine and hog local resources. 
The proposed solution is to containerize ML with NVMe over Fibre Channel (FC-NVMe) by putting your ML models in a container. In this webcast, we will highlight the benefits of containerizing ML models with FC-NVMe, discussing: 

• Containers are lightweight software packages that run-in isolation on the host computing environment. Containers are predictable, repetitive, and immutable. This ensures that no unexpected issues occur while moving them to a new system or between environments. A cluster of containers can be created with a configuration suited for machine learning requirements. Containers are also easy to coordinate (or “orchestrate”). 

• Artificial Intelligence (AI) at scale sets the standard for storage infrastructure in terms of capacity and performance, making it one of the most crucial factors for containers.

• FC-NVMe is an extension of the NVMe network protocol to Fibre Channel delivering faster and more efficient connectivity between storage and servers and providing the highest throughput and fastest response times. 

• The combination of FC-NVMe with an NVMe SSD solution with containerized ML allows orchestration to scale data-intensive workloads and increase data mining speed.

Benefits of FC-NVMe for Containerized ML Models

A new class of cloud and datacenter infrastructure is emerging into the marketplace. This new infrastructure element, often referred to as Data Processing Unit (DPU), Infrastructure Processing Unit (IPU) or xPU as a general term, takes the form of a server hosted PCIe add-in card or on-board chip(s), containing one or more ASIC’s or FPGA's, usually anchored around a single powerful SoC device. 

The OPI project has been created to foster the emergence of an open and creative software ecosystem for DPU/IPU based cloud infrastructure. The project intends to delineate what a DPU/IPU is, to loosely define a framework(s) and architecture for a DPU/IPU-based software stack(s) applicable to any vendors hardware solution, to allow the creation of a rich open- source application ecosystem, to integrate with existing open-source projects aligned to the same vision such as the Linux kernel, IPDK.io, DPDK and SPDK to create new APIs for interaction with and between the elements of the DPU/IPU ecosystem:
• the DPU/IPU hardware 
• DPU/IPU hosted applications 
• the host node 
• remote provisioning software 
• remote orchestration software

Learning Objectives: 
• OPI introduction 
• OPI workstream definitions and status 
• How you too can contribute to OPI

An Introduction to the OPI (Open Programmable Infrastructure) Project

Have you ever wondered how intelligent Industry 4.0 factories or smart cities of the future will process massive amounts of sensor and machine data? What you may not expect is a digital twin will most likely play a role. A digital twin is a virtual representation of an object, system or process that spans its lifecycle, is updated from real-time data, and uses simulation, machine learning and reasoning to help decision-making. Digital twins can be used to help answer what-if AI-analytics questions, yield insights on business objectives and make recommendations on how to control or improve outcomes.

This webinar will introduce digital twin usage in edge IoT applications, highlighting what is available today, what to expect in the next couple of years, and what the future holds.  We will provide examples of how digital twin methods help capture virtual representation of real-world entities and processes, discussing: 

• What is driving the edge IoT need 
• Data analytics problems solved by digital twins
• How digital twins are being used today, tomorrow and beyond
• Use cases: adaptive agile factories, massive data generation across industries, and system of systems processes
• Why this is a technology and trend that is here to stay

Journey to the Center of Massive Data: Digital Twins

Using software to perform memory copies has been the gold standard for applications performing memory-to-memory data movement or system memory operations. With new accelerators and memory types enriching the system architecture, accelerator-assisted memory data movement and transformation need standardization.

SNIA's Smart Data Accelerator Interface (SDXI) Technical Work Group (TWG) is at the forefront of standardizing this. The SDXI TWG is designing an industry-open standard for a memory-to-memory data movement and acceleration interface that is – Extensible, Forward-compatible, and Independent of I/O interconnect technology. A candidate for the v1.0 SNIA SDXI standard is now in review.

Adjacently, Compute Express Link™ (CXL™) is an industry-supported Cache-Coherent Interconnect for Processors, Memory Expansion, and Accelerators. CXL is designed to be an industry-open standard interface for high-speed communications, as accelerators are increasingly used to complement CPUs in support of emerging applications such as Artificial Intelligence and Machine Learning.

In this webcast, we will: 
• Introduce SDXI and CXL 
• Discuss data movement needs in a CXL ecosystem  
• Cover SDXI advantages in a CXL interconnect

What’s in a Name? Memory Semantics and Data Movement with CXL™ and SDXI

The race to the cloud over the past two decades has been fast and furious. The ease and flexibility of turning on services when you want them, turning them off when you don’t, is an enticing prospect for developers as well as application deployment teams, but it has not been without its challenges. Many cite expanding costs, data sovereignty, or security as reasons for repatriation of workloads, but what about other factors, such as data gravity, latency, and extending workloads to the edge?

Kubernetes platforms offer a unique cloud-like experience — all the flexibility, elasticity, and ease of use — with the added benefit of a common user experience regardless of where it is deployed — on premises, in a private or public cloud, even at the edge. It also allows organizations to run different workloads on different underlying platforms by abstracting the system layer, creating a seamless hybrid and multicloud strategy. We even see more and more service providers offering Containers-as-a-Service regardless of where the physical infrastructure resides.

Our panel of experts will debate these issues, discussing:
• So how are all these trends coming together?
• Is cloud repatriation really a thing? 
• How are traditional hardware vendors reinventing themselves to compete? 
• Where does the data live? 
• How is the data accessed? 
• What workloads are emerging?

Kubernetes Trials & Tribulations: Cloud, Data Center, Edge

At the 2022 Open Compute Global Summit, OEMs, cloud service providers, hyperscale data center, and SSD vendors showcased products and their vision for how the family of EDSFF form factors solves real data challenges. In this webcast, SNIA SSD SIG co-chairs Cameron Brett of KIOXIA and Jonmichael Hands of Chia Network explain how having a flexible and scalable family of form factors allows for optimization for different use cases, different media types on SSDs, scalable performance, and improved data center TCO. They'll highlight the latest SNIA specifications that support these form factors, provide an overview of platforms that are EDSFF-enabled, and discuss the future for new product and application introductions.

EDSFF - Taking Center Stage in the Data Center

With the emergence of GPUs, xPUs (DPU, IPU, FAC, NAPU, etc) and computational storage devices for host offload and accelerated processing, a panoramic wild west of frameworks are emerging, consolidating and vying for the preferred programming software stack that best integrates the application layer with these underlying processing units. 
 
This webcast will provide an overview of programming frameworks that support (1) GPUs (CUDA, SYCL, OpenCL, oneAPI), (2) xPUs (DASH, DOCA, OPI, IPDK), and (3) Computational Storage (SNIA computational storage API, NVMe TP4091 and FPGA programming shells). 

We will discuss strengths and challenges and market adoption across these programming frameworks as we untangle the alphabet soup of new frameworks that include:
• AI/ML: OpenCL, CUDA, SYCL, oneAPI 
• xPU: DOCA, OPI, DASH, IPDK 
• Core data path frameworks: SPDK, DPDK 
• Computational Storage: SNIA Standard 0.8 (in public review), TP4091

You’ve Been Framed! xPU, GPU & Computational Storage Programming Frameworks

Wide-spread adoption of Kubernetes over the last several years has been remarkable and Kubernetes is now recognized as the most popular orchestration tool for containerized workloads. As applications and workflows in Kubernetes continue to evolve, so must the platform and storage.  

So, where are we today, and where are we going? Find out in this “15 Minutes in the Cloud” session, where we’ll discuss: 
 
• Persistence - From ephemeral to persistent - what has putting persistence in the mix done to applications? 
• Business Continuity - What’s needed for business continuity, backup & recovery and DR? 
• Deployment - Kubernetes delivered as a service, in the cloud, on-premises, data center and edge. How is that different in each case?   
• Performance/Scalability – How do you scale and still ensure performance?
• Trends – What are the business drivers and what does the future hold?

15 Minutes in the Cloud: Kubernetes is Evolving, Are You?

Our 1st and 2nd webcasts in this xPU series explained what xPUs are, how they work, and what they can do. In this 3rd webcast, we will dive deeper into next steps for xPU deployment and solutions, discussing:
When to deploy
• Pros and cons of dedicated accelerator chips versus running everything on the CPU
• xPU use cases across hybrid, multi-cloud and edge environments 
• Cost and power considerations
Where to deploy
• Deployment operating models: Edge, Core Data Center, CoLo, Public Cloud
• System location: In the server, with the storage, on the network, or in all those locations?
How to deploy
• Mapping workloads to hyperconverged and disaggregated infrastructure 
• Integrating xPUs into workload flows 
• Applying offload and acceleration elements within an optimized solution

xPU Deployment and Solutions Deep Dive

Organizations are adopting containers at an increasingly rapid rate. In fact, there are few organizations that haven’t implemented containers in their environment today. DevOps expect a flexible, seamless development, deployment and orchestration experience. With platform agnostic capabilities and a stateless container design, Kubernetes streamlines these processes – and with the contribution of persistent, cloud native storage, stateful information becomes reality along with advanced storage capabilities including features such as snapshots, rollbacks, etc.

Storage implications for Kubernetes will be the topic of this live webcast where storage experts from the Storage Networking Industry Association (SNIA) and Kubernetes experts from the Cloud Native Computing Foundation (CNCF) will discuss: 

• Key storage attributes of cloud native storage for Kubernetes
• How do we use cloud native storage in Kubernetes environments?  
• Workloads and real-world use cases

This webcast will help you better understand and address storage and persistent data challenges in a Kubernetes environment.
After you watch the presentation, check out the Q&A blog https://bit.ly/KubernetesEverywhereQA

Kubernetes is Everywhere – What About Cloud Native Storage?

Edge is the new frontier of compute and data in today’s world, driven by the explosive growth of mobile devices, work from home, digital video, smart cities, and connected cars. An increasing percentage of data is generated and processed at the edge of the network. With this trend comes the need for faster computing, access to storage, and movement of data at the edge as well as between the edge and the data center. Attend this SNIA Networking Storage Forum webcast on June 15, 2022 where we will discuss: 

• The increasing need to do more at the edge across compute, storage and networking
• The rise of intelligent edge locations
• Different solutions that provide faster processing or data movement at the edge
• How computational storage can speed up data processing and transmission at the edge
• Security considerations for edge processing 
 
We look forward to having you join us to cover all this and more. We promise to keep you on the edge of your virtual seat!

Storage Life on the Edge: Accelerated Performance Strategies

As covered in our first webcast “SmartNICs and xPUs: Why is the Use of Accelerators Accelerating,” we discussed the trend to deploy dedicated accelerator chips to assist or offload the main CPU. These new accelerators (xPUs) have multiple names such as SmartNIC, DPU, IPU, APU, NAPU.  

This second webcast in this series will cover a deeper dive into the accelerator offload functions of the xPU. We’ll discuss what problems the xPUs are coming to solve, where in the system they live, and the functions they implement, focusing on:
Network Offloads  
• Virtual switching and NPU 
• P4 pipelines
• QoS and policy enforcement
• NIC functions
• Gateway functions (tunnel termination, load balancing, etc)
Security  
• Encryption
• Policy enforcement
• Key management and crypto
• Regular expression matching
• Firewall
• Deep Packet Inspection (DPI)
Compute  
• AI calculations, model resolution
• General purpose processing (via local cores)
• Emerging use of P4 for general purpose
Storage  
• Compression and data at rest encryption 
• NVMe-oF offload
• Regular expression matching
• Storage stack offloads

xPU Accelerator Offload Functions

What do you think is a more secure way of securely removing data from a hard drive - putting it through a shredder, or doing an instant secure erase? The answer might surprise you!  Companies go to great lengths to secure their data and prevent confidential information from being made available to others. When a company is done using its ICT equipment, including the storage device, it is important to render the data inaccessible. Sanitization is process or method to render access to target data on storage media infeasible for a given level of effort. SSDs and HDDs have various security features that make this sanitization quick, secure, and verifiable. We will go over the different types of sanitization defined in the new IEEE P2883 Specification for Sanitization of Storage, including “clear”, “purge”, and “Destruct”. We will cover easy ways to perform these methods in mainstream storage interfaces like SATA, SAS, and NVMe. We will cover some recommendations for the verification of sanitization to ensure that devices are meeting stringent requirements.

Selecting the proper form of media sanitization with data sensitivity also needs to be weighed with the consequences of physical destruction. Circular business models are essential for the ICT industry, as a large percentage of energy and carbon emissions come from manufacturing products. Circular business models design waste out, keep materials in use as long as possible, and restore environmental systems in the process. Physical destruction, quite obviously, prevents further use phases for a device. We will cover the purge technique for media sanitization that can be quick, secure, reliable, and verifiable - and most importantly keeps the device in one piece.

Is the Data Really Gone?  A Primer on the Sanitization of Storage Devices

NVMe (Non-Volatile Memory Express) over Fabrics is of tremendous interest among storage vendors, flash manufacturers, and cloud and Web 2.0 customers, Because it offers efficient remote and shared access to a new generation of flash and other non-volatile memory storage, it requires fast, low latency networks, and the first version of the specification is expected to take advantage of RDMA (Remote Direct Memory Access) support in the transport protocol. 

Many customers and vendors are now familiar with the advantages and concepts of NVMe over Fabrics but are not familiar with the specific protocols that support it. This live webcast will explore and compare the Ethernet RDMA protocols and transports that support NVMe over Fabrics and the infrastructure needed to use them. You’ll hear:

•Why NVMe Over Fabrics requires a low-latency network
•How the NVMe protocol is mapped to the network transport  
•How RDMA-capable protocols work
•Comparing available Ethernet RDMA transports: iWARP and RoCE  
•Infrastructure required to support RDMA over Ethernet
•Congestion management methods

How Ethernet RDMA Protocols iWARP and RoCE Support NVMe over Fabrics

RDMA

Ethernet

Storage

iWARP

RoCE

DCBx

Network infrastructure professionals understand that a reliable and secure infrastructure is crucial to enabling business execution. Join the network infrastructure community to interact with thousands of IT professionals. Browse hundreds of on-demand and live webinars and videos to learn about the latest trends in network computing, SDN, WAN optimization and more.

Network Infrastructure

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.

How Ethernet RDMA Protocols iWARP and RoCE Support NVMe over Fabrics

Presented by

About this talk

More from this channel