Hi [[ session.user.profile.firstName ]]

Introduction to Incast, Head of Line Blocking, and Congestion Management

For a long time, the architecture and best practices of storage networks have been relatively well-understood. Recently, however, advanced capabilities have been added to storage that could have broader impacts on networks than we think.

The three main storage network transports - Fibre Channel, Ethernet, and InfiniBand – all have mechanisms to handle increased traffic, but they are not all affected or implemented the same way. For instance, placing a protocol such as NVMe over Fabrics can mean very different things when looking at one networking method in comparison to another.

Unfortunately, many network administrators may not understand how different storage solutions place burdens upon their networks. As more storage traffic traverses the network, customers face the risk of congestion leading to higher-than-expected latencies and lower-than expected throughput. Watch this webinar to learn:

•Typical storage traffic patterns
•What is Incast, what is head of line blocking, what is congestion, what is a slow drain, and when do these become problems on a network?
•How Ethernet, Fibre Channel, InfiniBand handle these effects
•The proper role of buffers in handling storage network traffic
•Potential new ways to handle increasing storage traffic loads on the network

After you watch the webcast, check out the Q&A blog http://bit.ly/323kyNj
Recorded Jun 18 2019 61 mins
Your place is confirmed,
we'll send you email reminders
Presented by
Sathish Gnanasekaran, Broadcom; John Kim, Mellanox; J Metz, Cisco; Tim Lustig, Mellanox
Presentation preview: Introduction to Incast, Head of Line Blocking, and Congestion Management

Network with like-minded attendees

  • [[ session.user.profile.displayName ]]
    Add a photo
    • [[ session.user.profile.displayName ]]
    • [[ session.user.profile.jobTitle ]]
    • [[ session.user.profile.companyName ]]
    • [[ userProfileTemplateHelper.getLocation(session.user.profile) ]]
  • [[ card.displayName ]]
    • [[ card.displayName ]]
    • [[ card.jobTitle ]]
    • [[ card.companyName ]]
    • [[ userProfileTemplateHelper.getLocation(card) ]]
  • Channel
  • Channel profile
  • QUIC – Will it Replace TCP/IP? Apr 2 2020 5:00 pm UTC 75 mins
    Lars Eggert, NetApp; Christine McMonigal, Intel; Alex McDonald, NetApp
    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 webcast 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
  • Fibre Channel SAN Workloads Feb 12 2020 6:00 pm UTC 75 mins
    Barry Maskas, HPE; Nishant Lodha, Marvell; Mark Jones, Broadcom
    Fibre Channel (FC) SAN workloads are not difficult, but there are several people who do not understand how the workloads line up to appropriate storage protocol and their characteristics. Different workloads have different “Fingerprints,” so to speak. Since FC SANs are block, they work very well with applications that have a lot of transactional data, a lot of random read/write loads, and are particularly good for virtual machine file systems.

    This webinar will discuss:
    •I/O fingerprints: I/O block sizes & IOPS requirements for various “FC SAN applications”
    •An overview of application access patterns, guided by best practices and experience
    •How FC fulfills these IOPS requirements and how CPU BW is as important as IOPS

    We will briefly investigate application sensitivity to latency, and show how protocol can affect performance.
  • The Truth About Owning Your Data Center Jan 22 2020 10:00 pm UTC 60 mins
    Bala Kalavala, Chief Architect
    With the cloud transformation taking mainstream traditional data center based technology solutions seems to have impact of disruption and aiming to find new balance in continued existence. Most organizations still have firm believe having own data center is a good thing as long as advances in the areas of power, cooling, communication, hardware and software are adopted with operations based on AI.

    Continuing to manage existing Data Centers, Hybrid Cloud has become the reality of most IT organizations, enabling appropriate design and architecture plays critical role in success of adopting to owning data center in the modern world.

    Key takeaways:
    - Data Center Innovations
    - Best practices
    - Top service providers
    - Hybrid Governance

    Join to learn, new methods, models and tools are needed which help to put the Data Center Strategy into action improving functionality and performance!
  • The Next Generation Lossless Network in the Data Center Recorded: Jan 21 2020 57 mins
    Paul Congdon, PhD, CTO of Tallac Networks
    Modern data centers are tasked with delivering intelligent multi-media responses to real-time human interactions. Massive amounts of data are being churned and sifted by highly parallel applications, such as Online Data Intensive Services (OLDI) and Artificial Intelligence (AI), which historically required specialized High-Performance Computing (HPC) infrastructure.

    New advancements in high-speed distributed solid-state storage, coupled with remote direct memory access (RDMA) and new networking technologies to better manage congestion, are allowing these parallel environments to run atop more generalized next generation Cloud infrastructure. Generalized cloud infrastructure is also being deployed in the telecommunication operator’s central office.

    The key to advancing cloud infrastructure to the next level is the elimination of loss in the network; not just packet loss, but throughput loss and latency loss.

    There simply should be no loss in the data center network. Congestion is the primary source of loss and in the network, congestion leads to dramatic performance degradation. This presentation summaries work from the IEEE 802 Network Enhancements for the Next Decade Industry Connections Activity (Nendica).

    The Nendica report describes the need for new technologies to combat loss in the data center network and introduces promising potential solutions.
  • Beyond the Edge: The New Application-Specific Network Recorded: Jan 21 2020 29 mins
    Rob Anderson, Head of Product Marketing & Greg Shields, Datacenter Specialist, NetFoundry
    2019 will be the year of application explosion and extension of the datacenter’s edge as we know it. This massively distributed application environment is being fueled by digital transformation projects in hybrid networking, multi-cloud and IIoT.

    Do you have an architecture in place to support and future-proof your network in this new application-centric world?

    Join this webinar to learn how to develop a strategy that is agile, reliable and secure and by design.

    Industry experts will discuss:

    - How this new edge-to-cloud landscape will change your network’s architecture

    - Game-changing technology advances including Microsoft Azure & AWS Outpost

    - How traditional networks must evolve to support the modern digital enterprise

    - Why you need to pay attention to a Zero Trust security approach

    - Real-world examples of network typologies for the cloud era

    If you are involved in the digital transformation of your datacenter’s edge, this is a must-see educational webinar.
  • Where Does SPDK Fit in the NVMe-oF Landscape? Recorded: Jan 9 2020 61 mins
    Jim Harris, Intel; Ben Walker, Intel, Tim Lustig, Mellanox
    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, discussing:

    •Overview of the SPDK project
    •Key NVMe-oF use cases for SPDK
    •Examples of NVMe-oF use cases not suited for SPDK
    •NVMe-oF Target Architecture and Design
    •NVMe-oF Host Architecture and Design
    •Performance data

    After you watch the webcast, check out the Q&A blog at http://bit.ly/SPDKQA
  • Understanding Fibre Channel Scaling Recorded: Nov 6 2019 60 mins
    Mark Rogov, Dell EMC; Brandon Hoff, Broadcom; J Metz, Cisco
    One of Fibre Channel’s greatest strengths is its ability to scale to thousands and thousands of nodes, while providing predictable performance. So, when we say that Fibre Channel has unmatched scalability, what does that actually mean? And how does it work?

    We often hear about “designed from the ground up,” but in this case it’s actually true. From each individual link, to the overall domain architecture, each step along the way is intended to be approached in a scalable fashion.

    In this webinar, we’ll be breaking down the pieces of the puzzle that help give Fibre Channel its robustness when you’re working at fabrics even greater than 10,000 nodes. We’ll be talking about:

    •What a deterministic storage network is
    •Fabric management principles
    •Negotiated credit transfers (buffer-to-buffer credits)
    •Network Engineering/Design Principles
    •Oversubscription and Fan-In Ratios
    •Topologies that help scale
    •Domains and Fabric limits
    •Consistency of performance at scale

    Along the way, we’ll be talking about some of the ways that Fibre Channel differs from other popular storage networks as they approach large-scale environments, and how it handles issues that arise in such cases.

    Please join us on November 6th at 10:00 am PT/1:00 pm ET for another educational webinar on Fibre Channel!
  • CCS [Ep.6]: Next-Generation Cybersecurity - Policy Process and Organization Recorded: Oct 31 2019 59 mins
    Johna Till Johnson, CEO and Founder, Nemertes Research
    Cloud and Cybersecurity Series [Ep.6]: Next-Generation Cybersecurity: Policy Process and Organization

    Resources are finite. So deploying them wisely is what differentiates successful cybersecurity organizations from those that are less successful. Find out how these successful cybersecurity organizations are structured, what policies they have in place, and what strategies they do—and don’t—follow to protect their enterprise organizations.
  • CCS [Ep.5]: Application Security Meets Multicloud Recorded: Oct 23 2019 50 mins
    John Burke, CIO and Principal Research Analyst, Nemertes Research
    Cloud and Cybersecurity Series [Ep.5]: Application Security Meets Multicloud

    Enterprises are developing and buying applications to run everywhere: across multiple clouds, multiple data centers, desktops, mobile devices, and IoT devices. In a multicloud environment, IT needs to take a multipronged approach to securing applications.

    We'll how organizations approach securing their applications for the multicloud, ranging from changes in the development process to the embrace of security technologies including IAMaaS, microservice authentication, and enterprise secure cloud access and policy enforcement (ESCAPE).

    This webinar presents data from Nemertes' in-depth research study of 335 organizations in 11 countries across a range of vertical industries.
  • What Software Defined Storage Means for Storage Networking Recorded: Oct 22 2019 62 mins
    Ted Vojnovich, Lenovo; Fred Bower, Lenovo; Tim Lustig, Mellanox
    Software defined storage, or SDS, is growing in popularity in both cloud and enterprise accounts. But what makes it different from traditional storage arrays? Does it really save money? Is it more complicated to support? Is it more scalable or higher-performing? And does it have different networking requirements than traditional storage appliances?

    Watch this SNIA webcast to learn:
    •How software-defined storage differs from integrated storage appliances
    •Whether SDS supports block, file, object, or all three types of storage access
    •Potential issues or pitfalls with deploying SDS
    •How SDS affects storage networking
    •Scale-up vs. scale-out vs. hyperconverged vs. cloud

    After you watch the webcast, check out the Q&A blog http://bit.ly/SDS-Q-A
  • Understanding Storage Security and Threats Recorded: Oct 8 2019 51 mins
    Pierre Mouallem, Lenovo; John Kim, Mellanox; J Metz, Cisco; Steve Vanderlinden, Lenovo
    What does it mean to be protected and safe? You need the right people and the right technology. This presentation is going to go into the broad introduction of security principles in general. This will include some of the main aspects of security, including defining the terms that you must know, if you hope to have a good grasp of what makes something secure or not. We’ll be talking about the scope of security, including threats, vulnerabilities, and attacks – and what that means in real storage terms. In this live webcast we will cover:

    •Protecting the data (Keeping “the bad” out)
    •Threat landscape, Bad actors/hackers
    •Attack vectors, attack surfaces, vulnerabilities
    •Physical security issues
    •Layers of protection (encryption – last line of defense)
    •Remediation after a breach/incident

    After you watch the webcast, check out the Q&A blog: http://bit.ly/2JQ1s5L
  • CCS [Ep.4]: Next-Generation Cybersecurity - Technology Foundations Recorded: Oct 1 2019 53 mins
    Johna Till Johnson, CEO and Founder, Nemertes Research
    Cloud and Cybersecurity Series [Ep.4] Next-Generation Cybersecurity - Technology Foundations

    The bad news? Threats evolve. Bad actors continue to improve their games.
    The good news? Cybersecurity technology is also evolving and improving. This webinar drills down into the emerging technologies that successful cybersecurity organizations are deploying to protect their firms. Find out what works, what's a waste of resources--and how to deploy the technologies that work.
  • CCS [Ep. 3]: Succeeding in the Multicloud Recorded: Sep 24 2019 39 mins
    John Burke, CIO and Principal Research Analyst, Nemertes Research
    Cloud and Cybersecurity Series [Ep.3]: Succeeding in the Multicloud

    With most IT work being done in the cloud, what does it mean to be successful and what are the characteristics of highly successful cloud enterprises?

    We'll dig into the what it means to be successful in the cloud and what successful organizations do more of (and less of) than their less successful peers. We'll look across technologies adopted, organizational and operational practices, and vendors embraced.

    This webinar presents the highlights of Nemertes' in-depth research study of 335 organizations in 11 countries across a range of vertical industries. Later episodes will discuss security topics as well as focusing in on application development and security.
  • CCS [Ep.2]: Mastering Multicloud - Architectures, Organizations, Building Blocks Recorded: Sep 12 2019 57 mins
    John Burke, CIO and Principal Research Analyst, Nemertes Research
    Cloud and Cybersecurity Series [Ep. 2]: Mastering Multicloud - Architectures, Organizations, Building Blocks

    In 2019 the balance tipped, and for the first time the majority of enterprise IT workloads are running in the cloud, not in a data center.

    Enterprise IT staff need to stop thinking of cloud solutions as islands of function and special cases and begin to think of pulling it all together into a cohesive multicloud. We'll lay out the major categories of tools and systems and how they fit together, and at the organizational structures and operational practices needed to support multicloud operations.

    This webinar presents the highlights of Nemertes' in-depth research study of 335 organizations in 11 countries across a range of vertical industries. Later episodes will discuss cloud organizations and operational practices, and success metrics and best practices for cloud organizations.
  • 2019 Global State of the WAN - Panel Discussion Recorded: Sep 10 2019 60 mins
    Our Global Networking Leaders
    Enterprise networking needs are shifting--cloud models and new applications are driving digital transformation, according to this newly released State of the WAN Report.

    To better understand networking and application performance challenges, priorities, and plans, Aryaka conducts an annual State of the WAN survey administrated to almost 800 global IT and network practitioners. In this report they discovered that almost 50% have over 100 applications, and because of this increasing complexity, IT professionals are having a hard time provisioning, optimizing, and securing their Cloud and WAN deployments.

    Join us for this panel discussion as we reveal findings from the third annual global survey and insights into the State of the WAN in 2019, including:

    • The biggest challenges companies are facing with their WAN
    • Features IT professionals are looking for in an SD-WAN solution
    • Top Applications driving WAN transformation
    • Insights into N.America, Europe and APAC trends

    We will also be hosting a panel at 14:00 GMT for our European folks. Please visit,
    https://www.brighttalk.com/webcast/17572/365909?utm_source=AryakaEMEA
  • 2019 Global State of the WAN - Panel Discussion Recorded: Sep 10 2019 60 mins
    Our Global Networking Leaders
    Enterprise networking needs are shifting--cloud models and new applications are driving digital transformation, according to this newly released State of the WAN Report.

    To better understand networking and application performance challenges, priorities, and plans, Aryaka conducts an annual State of the WAN survey administrated to almost 800 global IT and network practitioners. In this report they discovered that almost 50% have over 100 applications, and because of this increasing complexity, IT professionals are having a hard time provisioning, optimizing, and securing their Cloud and WAN deployments.

    Join us for this panel discussion as we reveal findings from the third annual global survey and insights into the State of the WAN in 2019, including:

    • The biggest challenges companies are facing with their WAN
    • Features IT professionals are looking for in an SD-WAN solution
    • Top Applications driving WAN transformation
    • Insights into N.America, Europe and APAC trends

    And so much more...
  • CCS[Ep1]: Next-Generation Cybersecurity - Success Metrics, Best Practices & More Recorded: Sep 5 2019 59 mins
    Johna Till Johnson, CEO & Founder, Nemertes Research
    Cloud & Cybersecurity Series [Ep.1]: Success Metrics, Best Practices & More

    What does it take for enterprise cybersecurity teams to "up their games" to the next level of cybersecurity? What does it mean to be a "successful" cybersecurity organization, and what technologies and practices does it take to become one?

    This webinar presents the highlights of Nemertes' in-depth research study of 335 organizations in 11 countries across a range of vertical industries.

    We separated the best from the rest, and took an in-depth look into what made the most successful organizations that way. Participants will come away with best practices, tools, technologies, and organizational structures that contribute to success. Most importantly, they'll learn how to measure cybersecurity success--and their progress towards it.
  • Fibre Channel and Security Recorded: Aug 27 2019 60 mins
    Nishant Lodha, Marvell; Brandon Hoff, Broadcom; J Metz, Cisco
    Fibre Channel has long been known to be a very secure protocol for storage. Even so, there is no such thing as a “perfectly secure” technology, and for that reason it’s important to constantly update and protect against threats.

    The sheer variety of environments in which Fibre Channel fabrics are deployed makes it very difficult to simply rely only on physical security. In fact, it’s possible to access different storage systems by different users, even when spanned over several sites. Fibre Channel enables security services to specifically address these concerns, and prevent misconfigurations or access to data by non-authorized people and machines.

    This webcast is going to dive deep into the guts of security aspects of Fibre Channel, looking closely at the protocols used to implement security in a Fibre Channel fabric. In particular, we’re going to look at:

    •The definitions of the protocols to authenticate Fibre Channel devices
    •What are the different classes of threats, and what are the mechanisms to protect against them
    •What are session keys and how to set them up
    •How Fibre Channel negotiates these parameters to insure frame-by-frame integrity and confidentiality
    •How Fibre Channel establishes and distributes policies across a fabric

    Please join us to learn more about the technical considerations that Fibre Channel brings to the table to secure and protect your data and information.
  • Previewing the Storage Developer Conference EMEA in 2020 Recorded: Aug 13 2019 29 mins
    Alex McDonald, Vice-Chair SNIA EMEA, and Office of the CTO, NetApp; Paul Talbut, General Manager, SNIA EMEA
    The SNIA EMEA Storage Developer Conference (SDC) will return to Tel Aviv in early February 2020.

    SDC EMEA is organised by SNIA, the non-profit industry association responsible for data storage standards and education, and the conference is designed to provide an open and independent platform for technical education and knowledge sharing amongst the local storage development community.

    SDC is built by developers – for developers.

    This session will offer a preview of what is planned for the 2020 agenda ahead of the call for presentations and will also give potential sponsors the information they need to be able to budget for their participation in the event. If you have attended previously as a delegate, this is a great opportunity to learn more about how you can raise your profile as a speaker or get your company involved as a sponsor. There will be time allocated during the webcast to ask questions about the options available. Companies who have significant storage development teams will learn why this conference is valuable to the local technical community and why they should be directly engaged.
  • Kubernetes in the Cloud (Part 2) Recorded: Jul 17 2019 60 mins
    Michelle Tidwell, Program Director, IBM; Tom Clark, Distinguished Engineer, IBM; Matt Levan, Storage Solutions Architect, IBM
    As enterprises move to a hybrid multi-cloud world, they are faced with many challenges. Decisions surrounding what technologies to use is one, but they are also seeing a transformation in traditional IT roles. The storage admins are asked to be more cloud savvy while new roles of cloud admins are emerging to handle the complexities of deploying simple and efficient clouds. Meanwhile, both these roles are asked to ensure a self-service environment is architected so that application developers can get resources needed to develop cutting edge apps not in weeks, days or hours, but in minutes.

    In part one of this three part series, we covered the high level aspects of Kubernetes. This presentation will discuss key capabilities IT vendors are creating based on open source technologies such as Docker and Kubernetes to build self-service infrastructure to support hybrid multi-cloud deployments.We’ll cover:

    •Persistent storage and how to specify it
    •Ensuring application portability between Private and Public Clouds
    •Building a self-service infrastructure (Helm, Operators)
    •Selecting Block, File, Object (Traditional Storage, SDS)

    After you watch the webcast, check out the Q&A blog here: http://bit.ly/2M3IVpm
Updating the network infrastructure for the 21st century
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

Embed in website or blog

Successfully added emails: 0
Remove all
  • Title: Introduction to Incast, Head of Line Blocking, and Congestion Management
  • Live at: Jun 18 2019 5:00 pm
  • Presented by: Sathish Gnanasekaran, Broadcom; John Kim, Mellanox; J Metz, Cisco; Tim Lustig, Mellanox
  • From:
Your email has been sent.
or close