Knowledge Center
Throughout the year, DNSF Member companies share their expert knowledge by providing educational webinars through the SNIA BrightTALK channel. Check out some of our recent webinars and see why viewers say:
Awesome presentation. Probably the most clearly comprehensible yet comprehensive webinar I've attended in some time. Great job you guys!
Speakers took special care to be vendor and technology neutral which I greatly appreciate.
Excellent balance of industry dynamics and details of the protocol
On Demand Webinars
Addressing the Hidden Costs of AI
The latest buzz around generative artificial intelligence (AI) ignores the massive costs to run and power the technology. Without any guard rails in place, what are the impacts of AI on sustainability and costs across our technology resources? This webinar will offer insights on the potentially hidden technical and infrastructure costs associated with generative AI, best practices and potential solutions to be considered.
Everything You Wanted to Know About Throughput, IOPs, and Latency But Were Too Proud to Ask
Any discussion about storage systems is incomplete without the mention of Throughput, IOPs, and Latency. But what exactly do these terms mean and why are they important?
Collectively, these three terms are often referred to as storage performance metrics. Performance can be defined as the effectiveness of a storage system to address I/O needs of an application or workload. Different application workloads have different I/O patterns, and with that arises different bottlenecks, so there is no “one-size fits all” in storage systems. These storage performance metrics help with storage solution design and selection based on application/workload demands.
Accelerating Generative AI: Options for Conquering Dataflow Bottlenecks
Workloads using generative artificial intelligence trained on large language models are frequently throttled by insufficient resources (e.g., memory, storage, compute, or network dataflow bottlenecks). If not identified and addressed, these dataflow bottlenecks can constrain Gen AI application performance well below optimal levels.
Given the compelling uses across natural language processing (NLP), video analytics, document resource development, image processing, image generation, and text generation, being able to run these workloads efficiently has become critical to many IT and industry segments. The resources that contribute to generative AI performance and efficiency include CPUs, DPUs, GPUs, FPGAs, plus memory and storage controllers. Join this webinar to hear a panel a broad of industry veterans who discuss the topic of accelerating Gen AI.
NVMe/TCP: Performance, Deployment and Automation
NVMe/TCP has gained a lot of attention due to its great performance characteristics and relatively low cost. Since then, the NVMe/TCP protocol has been enhanced to add features such as Discovery Automation, Authentication and Secure Channels that make it more suitable for use in enterprise environments. As customers evaluate their options and consider adopting NVMe/TCP for use in their environment, many find they need a bit more information before deciding how to move forward.
Why Web 3.0 is Important to Enterprise Storage
Explore the exciting and rapidly evolving world of decentralized storage and how it is bridging the gap between Web 2.0 and Web 3.0
- Why is enterprise decentralized storage important?
- What are the benefits, the demand, and why now?
- How will on-premises to cloud to decentralized storage evolve?
- What are the use cases of decentralized storage?
- Who are the members and Working Groups of the Decentralized Storage Alliance?
Sustainability in a Data Center Ecosystem
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. 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
An Introduction to the OPI (Open Programmable Interfrastructure) Project
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. At this live webinar, experts actively leading this initiative provide an introduction to the OPI project, discuss OPI workstream definitions and status, and explain how you can get involved.
What's in a Name? Memory Semantics and Data Movement with CXL and SDXI
The SNIA Smart Data Accelerator Interface (SDXI) Technical Work Group (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.
Adjacently, Compute Express Link™ (CXL™) is an industry-supported Cache-Coherent Interconnect for Processors, Memory Expansion, and Accelerators, increasingly used to complement CPUs in support of emerging applications such as AI and ML. In this webinar, we will:
- Introduce SDXI and CXL
- Discuss data movement needs in a CXL ecosystem
- Cover SDXI advantages in a CXL interconnect
You've Been Framed! xPU, GPU and Computational Storage Programming Frameworks
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 webinar provides 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 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
xPU Deployment and Solutions Deep Dive
- When to deploy
- Where to deploy
- How to deploy
Storage Life on the Edge: Accelerated Performance Strategies
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. In this presentation, SNIA experts 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
xPU Accelerator Offload Functions
As covered in our first webinar “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.
In the second webinar in this series we take a deeper dive into the accelerator offload functions of the xPU. We discuss what problems the xPUs are coming to solve, where in the system they live, and the functions they implement, focusing on:
- Network Offloads
- Security Offloads
- Compute Offloads
- Storage Offloads
SmartNICs to xPUs: Why the Use of Accelerators is Accelerating
As applications continue to increase in complexity and users demand more from their workloads, there is a trend to again 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. How are these different than GPU, TPU, CPU? xPUs accelerate and offload functions including math, networking, storage, cryptography, security, and management. This webcast covers key topics about, and clarify questions surrounding, xPUs.
Storage Life on the Edge: Security Challenges
The complex and changeable structure of edge computing, together with its network connections, massive real-time data, challenging operating environment, distributed edge cloud collaboration, and other characteristics, create a multitude of security challenges. This panel of experts explores these challenges and wade into the debate as to whether existing security practices and standards are adequate for this emerging area of computing. Join us for a discussion that covers:
- Understanding the key security issues associated with edge computing
- Identify potentially relevant standards and industry guidance (e.g., IoT security)
- Offer awareness of new security initiatives focused on edge computing
Storage Life on the Edge: Managing Edge Use Cases
This second webcast in the Storage Life on the Edge series, provides an overview of edge to cloud use cases where storage and compute resources need to be deployed in practical topologies that deliver the very best in application performance. From data analytics and AI inference to emerging IoT edge applications, our panelists will provide a cornucopia of use cases across these categories along with specific, real-world examples.
Storage Life on the Edge: Managing Data from the Edge to the Cloud and Back
Cloud to Edge infrastructures are rapidly growing. It is expected that by 2025, up to 75% of all data generated will be created at the edge. However, Edge is a tricky word and you’ll get a different definition depending on who you ask. The physical edge could be in a factory, retail store, hospital, car, plane, cell tower level, or on your mobile device. The network edge could be a top-of-rack switch, server running host-based networking, or 5G base station.
The Edge means putting servers, storage, and other devices outside the core data center and closer to both the data sources and the users of that data—both edge sources and edge users could be people or machines.
At our first webcast in this series, “Storage Life on the Edge: Managing Data from the Edge to the Cloud and Back” you‘ll learn:
- Data and compute pressure points: aggregation, near & far Edge
- Supporting IoT data
- Analytics and AI considerations
- Understanding data lifecycle to generate insights
- Governance, security & privacy overview
- Managing multiple Edge sites in a unified way
Revving Up Storage for Automotive
The automotive industry is effectively transforming the vehicle into a data center on wheels. Connectedness, autonomous driving, and media & entertainment bring in more and more storage onboard and into the networked data centers. But all the storage in (and for) a car is not created equal. There are 10s if not 100s of different processors on the car. Some are attached to storage and some are not. Each application demands different characteristics from the storage device. Let’s explore all of this in an informational journey with the industry experts from both the storage and automotive worlds.
Object Storage: Trends, Use Cases
Storing objects has become commonplace. Object storage provides bulk and undifferentiated storage for unstructured data like photos, video & audio, DNA sequences, files, backups, and it can even protect against ransomware. Object access is also simplified because there are no built-in hierarchies or filesystems of objects, and no devices to manage that look like disks. So, what’s new? Object storage has traditionally been accomplished in the software stack and is now being accomplished directly on the media. In this presentation, we highlight how this is happening and discuss:
- Object storage characteristics
- The differences and similarities between object and key value storage
- Security options unique to object storage including ransomware mitigation
- Why use object storage: Use cases and applications
- Object storage and containers: Why Kubernetes’ COSI (Container Object Storage Interface)?
NVMe-oF: Discovery Automation for NVMe IP-based SANs
NVMe IP-based SANs (including TCP, RoCE, iWARP) have the potential to provide significant benefits in application environments ranging from the Edge to the Data Center. However, before we can fully unlock NVMe IP-based SAN’s potential, we first need to overcome the NVMe over Fabrics (NVMe-oF™) discovery problem. This discovery problem, specific to IP based fabrics, can result in the need for Host administrators to explicitly configure each Host to access each of the NVM subsystems in their environment. In addition, any time an NVM Subsystem interface is added or removed, the Host administrator may need to explicitly update the configuration of impacted hosts. This process does not scale when more than a few Host and NVM subsystem interfaces are in use. Also, due to the de-centralized nature of this process, it also adds complexity when trying to use NVMe IP-based SANs in environments that require a high-degrees of automation.
For these and other reasons, several companies have been collaborating on innovations that simplify and automate the discovery process used with NVMe IP-based SANs.
Next-generation Interconnects: The Critical Importance of Connectors and Cables
There is an impressive array of data center infrastructure components designed to address expanding requirements for higher-bandwidth and lower-power. This includes defining new terminology and addressing the next-generation copper and optics solutions required to deliver high signal integrity, lower-latency, and lower insertion loss to achieve maximum efficiency, speed, and density.
Storage for AI Applications
Artificial intelligence (AI) is a technology which encompasses a broad range of use cases, largely divided into training and inference. In this webcast, we look at what types of storage are typically needed for different aspects of AI, including different types of access (local vs. networked, block vs. file vs. object) and different performance requirements. And we will discuss how different AI implementations balance the use of on-premises vs. cloud storage.
SAN Overview - How Fibre Channel Hosts and Targets Really Communicate
Each SAN transport has its own way to initialize and transfer data. So how do initiators (hosts) and targets (storage arrays) communicate in Fibre Channel (FC) Storage Area Networks (SANs)? Find out in this webcast where Fibre Channel experts will answer:
- How do FC links activate?
- Is FC routable?
- What kind of flow control is present in FC?
- How do initiators find targets and set up their communication?
- Finally, how does actual data get transferred since that is the ultimate goal?
This session will introduce these concepts to demystify the FC SAN for the network professional.
Storage Technologies & Practices Ripe for Refresh: Part 2
In our second installment of our Storage Technologies & Practices Ripe for Refresh, we will cover older HDD device interfaces and file systems. Advice will be given on how to replace these in production environments as well as why these changes are recommended. Also, we will be covering protocols that you should consider removing from your networks, either older versions of protocols where only newer versions should be used, or protocols that have been supplanted by superior options and should be discontinued entirely.
Finally, we will look at physical networking interfaces and cabling that are popular today but face an uncertain future as networking speeds grow ever faster.
Security of Data on NVMe-oF, The Armored Truck Way
With ever increasing threat vectors both inside and outside the data center, a compromised customer dataset can quickly result in a torrent of lost business data, eroded trust, significant penalties, and potential lawsuits. Vulnerabilities exist at every point when scaling out NVMe, which require data to be secured every time it leaves a server or the storage media, not only when leaving the data center. NVMe over Fabrics is poised to be the one of the most dominant transports of the future and securing and validating the vast amounts of data that would traverse this fabric is not just prudent, but paramount.
Join the webcast to hear industry experts discuss current and future strategies to secure and protect your mission critical data. You will learn:
- Industry trends and regulations around data security
- Potential threats and vulnerabilities
- Existing security mechanisms and best practices
- How to secure NVMe in flight and at rest
- Ecosystem and market dynamics
- Upcoming standards
Great Storage Debate: Hyperconverged vs. Disaggregated vs. Centralized
In the ongoing evolution of the datacenter, a popular debate involves how storage is allocated and managed. There are three competing visions about how storage should be done; those are Hyperconverged Infrastructure (HCI), Disaggregated Storage, and Centralized Storage.
IT architects, storage vendors, and industry analysts argue constantly over which is the best approach and even the exact definition of each. Isn’t Hyperconverged constrained? Is Disaggregated designed only for large cloud service providers? Is Centralized storage only for legacy applications?
NVMe-oF: Looking Beyond Performance Hero Numbers
When it comes to performance of NVMe over Fabrics (NVMe-oF) one should look beyond test results that demonstrate NVMe-oF’s dramatic reduction in latency. There are other, more important, questions that should be asked in order to understand the fabric’s real-world benefits. This webcast will attempt to answer questions beyond “it depends.”
Gain insights from an industry wide panel of NVMe and fabric technology experts as they discuss the thought process you can use to determine pros and cons of a fabric for your environment, including:
- Use cases driving fabric choices
- NVMe transports and their strengths
- Industry dynamics driving adoption
- Considerations for scale, security, and efficiency
Storage Technologies & Practices Ripe for Refresh
So much of what we discuss within SNIA is the latest emerging technologies in storage. While it’s good to know about what technology is coming, it’s also important to understand the technologies that should be sunsetted.
In this webcast, you’ll learn about storage technologies and practices in your data center that are ready for refresh or possibly retirement. Find out why some long-standing technologies and practices should be re-evaluated. We’ll discuss:
- Obsolete hardware, protocols, interfaces and other aspects of storage
- Why certain technologies are no longer in general use
- Technologies on their way out and why
- Drivers for change
- Justifications for obsoleting proven technologies
- Trade-offs risks: new faster/better vs. proven/working tech
Not Again! Data Deduplication for Storage Systems
Organizations inevitably store multiple copies of the same data. Users and applications store the same files over and over, intentionally or inadvertently. Developers, testers and analysts keep many similar copies of the same data. And backup programs copy the same or similar files daily, often to multiple locations or storage devices. It’s not unusual to end up with some data replicated thousands of times. So how do we stop the duplication madness? Watch this webcast where we discuss how to reduce the number of copies of data that get stored, mirrored, and backed up.
Optimizing NVMe over Fabrics Peformance with Different Ethernet Transports: Host Factors
NVMe over Fabrics technology is gaining momentum and getting more traction in data centers, but there are three kinds of Ethernet based NVMe over Fabrics transports: iWARP, RoCEv2 and TCP. How do we optimize NVMe over Fabrics performance with different Ethernet transports?
This discussion won’t tell you which transport is the best. Instead we unfold the performance of each transport and tell you what it would take for each transport to get the best performance, so that you can make the best choice for your transport for NVMe over Fabrics solutions.
Compression: Putting the Squeeze on Storage
Everyone knows data volumes are exploding faster than IT budgets. And customers are increasingly moving to flash storage, which is faster and easier to use than hard drives, but still more expensive. To cope with this conundrum and squeeze more efficiency from storage, storage vendors and customers can turn to data reduction techniques such as compression, deduplication, thin provisioning and snapshots. This webcast will specifically focus on data compression, which can be done at different times, at stages in the storage process, and using different techniques. We’ll discuss:
- Where compression can be done: at the client, on the network, on the storage controller, or within the storage devices
- What types of data should be compressed
- When to compress: real-time compression vs. post-process compression
- Different compression techniques
- How compression affects performance
The Key to Value: Understanding the NVMe Key-Value Standard
The storage industry has many applications that rely on storing data as objects. In fact, it’s the most popular way that unstructured data is accessed.
At the drive level, however, the devil is in the details. Normally, storage devices store information as blocks, not objects. This means that there is some translation that goes on between the data as it is consumed (i.e., objects) and the data that is stored (i.e., blocks).
Naturally, being efficient means that there are performance boosts, and simplicity means that there are fewer things that can go wrong. Moving towards storing key value pairs that get away from the traditional block storage paradigm make it easier and simpler to access objects.This presentation discusses the benefits of Key Value storage, presents the major features of the NVMe-KV Command Set and how it interacts with the NVMe standards. It also covers the SNIA KV-API and open source work that is available to take advantage of Key Value storage.
Everything You Wanted to Know About Storage But Were Too Proud to Ask: Data Reduction
This webcast will specifically focus on the fundamentals of data reduction, which can be performed in different places and at different stages of the data lifecycle. Like most technologies, there are related means to do this, but with enough difference to cause confusion. For that reason, we’re going to be looking at:
- How companies end up with so many copies of the same data
- Difference between deduplication and compression – when should you use one vs. the other?
- Where to reduce data: application-level, networked storage, backups, and during data movement
- When to collapse the copies: real-time vs. post-process deduplication
- Performance considerations
Storage Networking Security Series: Applied Cryptography
The rapid growth in infrastructure to support the real time and continuous collection and sharing of data to make better business decisions has led to an age of unprecedented information access and storage. This proliferation of data sources and of high-density data storage has put volumes of data at one’s fingertips. While the collection of large amounts of data has increased knowledge and efficiencies for businesses, it has also made attacks upon that information—theft, modification, or holding it for ransom--more tempting and easier. Cryptography is often used to protect valuable data.
This webcast presents an overview of applied cryptography techniques for the most popular use cases. We discuss ways of securing data, the factors and trade-offs that must be considered, as well as some of the general risks that need to be mitigated, including:
- Encryption techniques for authenticating users
- Encrypting data—either at rest or in motion
- Using hashes to authenticate/ Information coding and data transfer methodologies
- Cryptography for Blockchain
Storage Networking Security Series: Security & Privacy Regulations
Worldwide, regulations are being promulgated and aggressively enforced with the intention of protecting personal data. These regulatory actions are being taken to help mitigate exploitation of this data by cybercriminals and other opportunistic groups who have turned this into a profitable enterprise. Failure to meet these data protection requirements puts individuals at risk (e.g., identity theft, fraud, etc.), as well as subjecting organizations to significant harm (e.g., legal penalties).
This webcast highlights common privacy principles and themes within key privacy regulations. In addition, the related cybersecurity implications are explored. Lastly, the session will probe a few of the recent regulations/laws to outline interesting challenges due to over and under-specification of data protection requirements (e.g., “reasonable” security), covering:
- How privacy and security is characterized
- Data retention and deletion requirements
- Core data protection requirements of sample privacy regulations from around the globe
- The role that security plays with key privacy regulations
- Data breach implications and consequences
Notable Updates in NVMe-oF 1.1
In the past couple of years since its introduction, NVMe™ over Fabrics (NVMe-oF™) has not been resting on any laurels. Work has been ongoing, and there are several updates that are worth talking about.There is more to a technology than its core standard, of course, and many different groups have been hard at work at improving upon, and fleshing out, many of the capabilities that are related to NVMe-oF. This webcast explores a few of these projects and how they relate to implementing the technology. In particular, we’ll be looking at:
- A summary of new items in NVMe-oF 1.1
- Updates about what is happening in FC-NVMe-2
- How SNIA’s provisioning model helps NVMe-oF Ethernet Bunch of Flash (EBOF) devices
- Managing and provisioning NVMe-oF devices with SNIA Swordfish
Storage Networking Security Series: Key Management
There’s a lot that goes into effective key management. In order to properly use cryptography to protect information, one has to ensure that the associated cryptographic keys themselves are also protected. Careful attention must be paid to how cryptographic keys are generated, distributed, used, stored, replaced and destroyed in order to ensure that the security of cryptographic implementations is not compromised. This webcast introduces the fundamentals of cryptographic key management including key lifecycles, key generation, key distribution, symmetric vs. asymmetric key management, and integrated vs. centralized key management models.
Storage Networking Security Series: Protecting Data-at-Rest
There’s a lot to understand about how to keep your data secure. As this series shows, there are many places along the chain where a weak link can break the entire process. One of the key aspects of keeping data secure – and probably the place where most people think of security – is what happens when the data is “at rest,” or being stored in some sort of stable drive or disk. Watch as we break down the aspects of securing data at rest as part of the overall goal of understanding storage security. In particular, we’ll be looking at:
Storage Networking Security Series: Encryption 101
Encryption has been used through the ages to protect stored secrets, authenticate messages, communicate secretly in broad daylight, and even to check that messages were properly transmitted and received without tamper. Now, it’s often our first go-to tool for making sure that data simply isn’t readable to prying eyes, ears or AI bots. But how does encryption actually work, what makes it tick, and how is it managed? How do we ensure compatibility? How do we protect the keys; i.e., “Who will guard the guards themselves?”
QUIC - Will it Replace TCP/IP?
QUIC is a new UDP-based transport protocol for the Internet, and specifically, the web. Originally designed and deployed by Google, it already makes up 35% of Google's egress traffic, which corresponds to about 7% of all Internet traffic. The strong interest by many other large Internet players in the ongoing IETF standardization of QUIC is likely to lead to an even greater deployment in the near future. This talk will highlight:
- Unique design aspects of QUIC
- Differences to the conventional HTTP/TLS/TCP web stack
- Early performance numbers
- Potential side effects of a broader deployment of QUIC
Ethernet-attached SSDs: Brilliant Idea or Storage Silliness?
Several SSD and networking vendors have recently demonstrated ways to connect SSDs directly to an Ethernet network. They propose that deploying Ethernet SSDs will be more scalable, easier to manage, more performant, and/or lower cost than traditional storage networking solutions that use a storage controller (or hyperconverged node) between the SSDs and the network.
Who would want to attach SSDs directly to the network? Are these vendors brilliant or simply trying to solve a problem that doesn’t exist? What are the different solutions that could benefit from Ethernet SSDs? Which protocols would one use to access them? And how do Ethernet SSDs relate to computational storage?
Object Storage: What, How and Why
There are many types of storage technologies, both in how they are interconnected, consumed and designed. Object storage is no different in that it brings its own set of unique characteristics to the market. In this webcast, you'll learn:
- What object storage is and what it does
- How to use object storage
- Essential characteristics of typical consumption
- Why object storage is important to the future of storage and computing technologies
Where does SPDK fit in the NVMe-oF Landscape?
The Storage Performance Development Kit (SPDK) has gained industry-wide recognition as a framework for building highly performant and efficient storage software with a focus on NVMe. This includes software drivers and libraries for building NVMe-oF host and target solutions. In this presentation, technical leaders from SPDK will provide an overview of the project, NVMe-oF use cases that are best suited for SPDK, and insights into how SPDK achieves its storage networking performance and efficiency.
View All On-Demand Data, Networking & Storage Forum Webcasts