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

Shared or Distributed HDFS – What’s Right for Me?

If you’re running Hadoop for big data analytics this webinar is for you!

Currently, there are two competing architectures for how to implement Hadoop Distributed File System (HDFS). The original HDFS approach utilizes storage co-located with the compute servers, but that can often present challenges of wasted compute and/or storage when you scale. An emerging alternative relies on dedicated storage resources shared by the compute cluster, providing a cost-effective and reliable solution.

Join Engineering Fellow and Chief Data Scientist Janet George, as she compares and contrasts these two approaches and provides definitive quantities guidelines to planners and architects to help identify the best solutions for your Big Data and analytic needs.

Between these two methods, we’ll compare and contrast:
-Data Reliability and Bit Loss
-High Availability
-Cost of Capacity

We look forward to you joining us!
Recorded Jul 21 2016 40 mins
Your place is confirmed,
we'll send you email reminders
Presented by
Janet George, Chief Data Scientist, Engineering Fellow, SanDisk
Presentation preview: Shared or Distributed HDFS – What’s Right for Me?

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
  • How to Develop a Data Strategy for Analytics May 29 2019 5:00 pm UTC 60 mins
    Erik Ottem, Senior Director, Data Center Systems
    It’s hard work to uncover real business results through analytics. It is common that you spend much more time curating the data than improving your algorithms. When diving into analytics for business value, you have to roll up your sleeves and prepare to put in the work. A data strategy for analytics may include finding real data sets from many sources that can be used in training your machine as quickly and effectively as possible, but one thing is imperative, the scalability and manageability of data is critical to the success of your analytics project.

    In this webinar you’ll learn:
    - Why an analytics strategy is paramount in driving business results

    - Questions you should ask before building a strategy for analytics

    - How to identify the different data needs for typical analytic workloads

    - How to identify the high performance and large volume data needs, and the appropriate data infrastructure for each

    -How to implement an effective management approach to keep your analytic workloads happy
  • How to leverage NVMe-based storage in existing FC SAN and iSCSI Environments May 15 2019 5:00 pm UTC 45 mins
    Rajeev Sharma, Senior Product Manager, Data Center Systems
    Businesses across the globe are grappling with how to not only capture and preserve their data, but more importantly, how to transfer the data into actionable insights. After all, data is the currency of the modern economy, and the speed by which an organization can unlock the possibilities of its data is paramount to its success. As a result, many organizations are turning to NVMe – a protocol that is disrupting all-flash array architectures – to provide higher performance and improve their data’s time-to-value. But, transitioning an infrastructure to NVMe may bring up questions, specifically how this will impact existing FC SAN and iSCSI environments.

    In this webinar, you will learn:

    Why organizations are considering NVMe, and benefits of NVMe-based storage arrays
    How to address the challenges of transitioning to NVMe-based storage
    How to leverage NVMe-based solutions in existing FC and iSCSI storage environments
    How to effectively consolidate storage silos without any trade-offs in performance and latency
    How Western Digital’s IntelliFlash N-Series enables high performance at low latency for the most demanding workloads, your mission critical applications
  • NVMe-oF 101 - Understanding NVMe-oF and How it Drives Business Value May 1 2019 5:00 pm UTC 60 mins
    Dave Montgomery, Director, Storage Platforms Marketing, Western Digital
    Every IT shop is trying to balance two different objectives: 1) increase capacity; 2) deliver the requisite performance against a variety of workloads. Indiscriminately spending money that doesn’t align capacity and storage performance with the workloads’ needs, is wasteful. However, connecting storage capacity and performance across the network with workloads is an easy way to allocate storage resources cost effectively, as needed.

    To address today’s dynamic data requirements, we must consider that end users need a next-generation infrastructure that aligns storage resources with workloads without jeopardizing performance, capacity, or incurring unwarranted expense. Non-Volatile Memory Express over Fabrics (NVMe-oF) is a storage protocol that aims to simplify the interconnection of computer memory, storage, and networking, while improving performance of the storage infrastructure and related applications, to meet IT departments’ objectives and drive business value.

    In this webinar, you will learn:
    • What is NVMe-oF
    • The business value of NVMe-oF
    • The role that NVMe-oF will play in transforming data centers of the future
  • Performance, Reliability, Flexibility and Low Cost: All in One Storage Solution? Recorded: Apr 18 2019 45 mins
    Esther Spanjer, Director of Business Development EMEIA
    Software Defined Storage is a growing trend in the datacenter, as IT managers are moving away from traditional Tier-1 OEM solutions in an effort to increase flexibility and reduce cost. But putting together a SDS solution, based on various hardware and software components can be challenging. Enter the pre-tested reference architectures from Western Digital and DataCore, that take on storage solutions of Tier-1 OEM vendors by providing equally high performance and world class reliability. But at a much more cost-attractive price point and with much greater flexibility in its tiering capability.

    Join Esther Spanjer and Manfred Berger from Western Digital’s Business Development team and Michel Portelli, Senior Director EMEA Marketing at DataCore Software for this webinar, in which you will learn more about:

    1. DataCore SDS Software Solution
    2. Western Digital hardware JBOD and server platforms
    3. Western Digital and Datacore’s joint storage solutions to take on the SDS market
  • DNAFabric - How Tableau Empowers Data-Driven Decisions on Media Assets (Part 2) Recorded: Apr 17 2019 25 mins
    Erik Weaver, Global Director, M&E Market Development, Western Digital; Tridib Chakravarty, CEO, StorageDNA
    In part-two of our DNAFabric series, we will dig deeper into how abstraction, combined with Tableau, enables a new generation of data insights. To empower decision-makers to derive actionable insights from large data sets, we will highlight the power of laying a foundation that supports next-generation artificial intelligence and machine learning applications to both see and understand data.
  • NVMe All-Flash Arrays:How to Make the Right Decision for your Enterprise Storage Recorded: Apr 10 2019 26 mins
    David Ridgeway, Senior Manager of Product Marketing. Data Center Systems @ Western Digital
    Accelerating time to insights is the new currency and lifeline for your business. To tap into these insights, today's businesses need an advanced storage option that delivers performance, simplicity, and economics. Success requires you to take advantage of the latest high-performance storage constructs – flash memory, NVMe standards, and fast data storage – to eliminate bottlenecks, management complexity, and the high cost of traditional storage solutions.

    In this webinar you will learn how NVMe enables higher performance all-flash arrays (AFAs) with the requisite enterprise-class management and high efficiency for cost-effective on-premises storage. Even if you’re considering your first AFA, this webinar will provide the information you need when deploying next-generation NVMe AFA solutions:

    -Learn about the benefits that NVMe AFAs bring to enterprise, such as fast data acceleration and accelerating multi-site disaster recovery
    -Five key features to look for in next-generation AFAs
    -Find out how CIOs are using NVMe All-Flash storage to support mission-critical applications
    -Discover, with support from the Forrester Total Economic Impact Study, how flash storage helps consolidate multiple tiers of storage to save on power, cooling, and rack space at a lower total cost
  • How NVMe is Reshaping the Enterprise Storage Landscape Recorded: Apr 3 2019 28 mins
    Erik Ottem, Senior Director, Data Center Systems
    Traditional data infrastructures can’t keep up with the rapid growth of low latency semiconductor storage and multi-core processors. Today’s system design requires a multi-lane data infrastructure to keep up with today’s high-performance servers supporting hundreds, if not thousands, of virtual workloads. Join us to see how enterprise storage is evolving – from a slow two-lane country road powered by SAS and SATA to a fast 12-lane divided highway driven by NVMe – to deliver the infrastructure your business needs to stay relevant.
  • HDD Technology, a Look Under the Hood Recorded: Mar 28 2019 31 mins
    Esther Spanjer, Enterprise Business Development Director; Cagatay Kilic, Business Development Manager
    Join Cagatay Kilic and Esther Spanjer from the EMEAI Business Development team, for this webinar if you are interested in understanding more about HDD technology features and how they are implemented in the Western Digital Enterprise Grade HDD product line. Cagatay will discuss topics such as PRM vs SMR vs XMR recording, micro-actuator vs dual-actuator , HAMR vs MAMR and why Western Digital fills its high capacity drives with Helium. Additionally, Esther will share with you Western Digital’s view on the HDD Market and the co-existence of HDD and SSDs in the datacenter. For those of you that want to know of what’s going on “under the hood” in an Enterprise Grade HDD will come away with knowledge on the following:

    1. HDD technology features
    2. Market trends for HDDs in the datacenter
    3. Western Digital’s enterprise grade HDD offering
  • DNAFabric –The Power of Abstraction for Hybrid Media Workflows (Part 1) Recorded: Mar 27 2019 25 mins
    Erik Weaver, Global Director, M&E Market Development, Western Digital, Tridib Chakravarty, CEO, StorageDNA
    In Part 1 of this two-part series on DNAFabric, we will explore how and why legacy storage infrastructures must shift to address today’s digital content demands in media & entertainment. We’ll start the discussion by exploring what abstraction means and why it is an important consideration in asset identification, resource allocation, collaboration, and the creation of indelible metadata in a hybrid world. In Part 2 of our DNAFabric series, we’ll dig deeper into how abstraction, combined with Tableau, allows a new generation of data insights.
  • Western Digital and 451 Research: Strategies for Managing Unstructured Data Recorded: Mar 20 2019 59 mins
    Erik Ottem, Senior Director, Western Digital; Stephen Hill, Senior Analyst, 451 Research
    Data protection has always been one of the top priorities of IT; but the very nature of business data has been quietly changing behind the scenes. Today, unstructured data in the form of documents, images and other types of media files are making up the lion’s share of new data growth, and traditional storage and backup models are unable to provide the information and visibility needed to protect, manage and realize the full potential of the growing mountain of unstructured business data.
  • IntelliFlash, NVMe, and the Storage Landscape Recorded: Mar 13 2019 22 mins
    Scott Lowe, CEO of ActualTech Media and Narayan Venkat, VP of Data Center Systems at Western Digital
    Join ActualTech Media CEO, Scott Lowe and Narayan Venkat, VP of Data Center Systems at Western Digital as they discuss IntelliFlash, NVMe and the current overall storage landscape.

    In this webcast you will learn:

    -Why All-Flash right now?
    -The advantages or NVMe and when and why you might need it
    -The economic value of IntelliFlash and the “silicon to system” Western Digital architecture

    If you are interested in learning more about IntelliFlash, industry knowledge on the current state of NVMe or hearing more about our perspectives on NVMe make sure to check out the resources in the attachments.
  • Smart Cities and Surveillance: Next-Gen Storage Security Recorded: Mar 6 2019 44 mins
    Brian Mallari, Director Surveillance Marketing
    The security video market continues to see tremendous growth, driven by heightened concerns over terrorism, broader availability of more advanced imaging technology, and potential leverage of security cameras for improving operational efficiencies.

    Hear how smart security video not only assists security personnel in maintaining public safety but can also be used to ultimately improve infrastructure, driving in part the emergence and growth of smart cities.

    The so-called smart security edge requires innovative, dynamic storage technology to deliver the performance, capacity and endurance needed for real-time artificial intelligence and video analytics. Please join us as we discuss the broadest portfolio of edge-to-core storage solutions for smart security video, only from Western Digital.
  • The Changing Requirements for Automotive NAND Flash Storage Recorded: Feb 28 2019 38 mins
    Russell Ruben, Director, Automotive Marketing
    NAND flash storage is moving from infotainment to many key applications as the automotive industries drives to autonomous vehicles. As the applications change, so does the usage from single storage systems to domain, shared storage. With these additional use cases come additional challenges and requirements for NAND flash.
  • Composable Infrastructure - An Evolutionary Tale Recorded: Jan 31 2019 42 mins
    Esther Spanjer, Director of Business Development EMEIA
    Datacenter storage infrastructure has come a long way since the days of bare metal and one application per server. Once we found a way to share data across the network in the form of NAS and SAN, the industry has worked on many different fronts to improve CPU utilization, performance and cost and reduce complexity and maintenance. Virtualization, converged and hyper-converged technologies, all added incremental improvements in managing datacenter storage. But modern datacenter managers still deal with problems such as SKU growth, stranded capacity and the need to be flexible enough to adapt to unpredictable growth. The right solution for this is Composable Infrastructure, the ability to disaggregate HW resources and compose them through software.

    Join us for a LIVE webinar where we will discuss the historical evolution of datacenter storage infrastructure and explain how we will move towards Composable Infrastructure in the future.

    Main topics will include:
    1. The evolution from bare metal deployments to current modern infrastructure of scale-out, converged/hyperconverged architectures
    2. What is Composable Infrastructure and what are its benefits?
    3. Western Digital’s offering for Composable Infrastructure
  • Western Digital ActiveScale™ Hadoop Use Case Recorded: Jan 30 2019 18 mins
    Mike McWhorter, Senior Technologist, DCS Field Applications Engineering
    Mike McWhorter, Senior Technologist, reviews how Western Digital IT leverages the new S3A feature in Hadoop to create a second tier of seamless storage for analytics. Hadoop S3A allows you to connect your Hadoop cluster to any on-premises or hybrid S3™-compliant object store -- achieving massive scale at substantially lower overall cost.
  • Top Reasons for Considering NVMe Recorded: Jan 24 2019 32 mins
    Clay Ryder, Data Center Systems Marketing
    Is the latent value of your vast data resources being fully leveraged for your maximum success? Odds are, it’s probably not. Ironically, the growth and commercial success you are experiencing due to your data infrastructure, may grind it to a halt, unable to support the burgeoning info glut. “But, how can this be?” you may ask. The answer is simple, your digital business deserves better storage.

    In this webinar we’ll explore the top reasons you should considering deploying NVMe-based storage in your enterprise. You’ll learn how NVMe can not only shift the current data bottleneck, but eliminate it all together while laying the groundwork for a future of highly-decentralized high-performance storage. More importantly, we’ll look beyond the speeds and feeds to envision how NVMe can act as a change agent to drive innovation and success in your business. Discover how NVMe can unlock the latent value of your data by delivering data to your fingertips while changing the fundamental economics of your storage and retrieval of data forever.
  • Western Digital IntelliFlash Operating Environment Recorded: Jan 22 2019 15 mins
    Harrison Waller - Sr. Manager Technical Marketing, Western Digital
    Get an overview of the IntelliFlash user interface and visualize simple workflows for storage administration. Explore the various features and widgets, plus gain insights into storage performance and capacity management on an Western Digital IntelliFlash storage array.
  • Western Digital’s Composable Infrastructure Vision Recorded: Jan 15 2019 33 mins
    Dave Montgomery, Director, Storage Platforms Marketing
    The ‘general-purpose’ architectures that have served so well in the past are reaching their limits of scalability, performance and efficiency, typically using a uniform ratio of resources to address all compute processing, storage and network bandwidth requirements. As a result, the ‘one size fits all’ approach is no longer effective for data-intensive workloads. What is required for today’s data-centric architectures that address such diverse applications as big data, fast data, data analytics, artificial intelligence (AI) and machine learning (ML), are capabilities that enable more control over the blend of resources that each application needs so that optimized levels of processing, storage and network bandwidth can be scaled independent of one another, enabling both flexibility and composability.

    Composable Disaggregated Infrastructures (CDIs) are becoming a popular solution – delivering greatly improved TCO and addressing the inflexible nature of many current IT architectures. With a total market CAGR of 58.2% (forecasted from 2017 to 2022), CDIs treat physical compute, storage and network fabric resources as services and use an API to create a virtual application environment that provides whatever resources the application needs in real-time to meet workload demands.

    This webinar will cover the current economic pain-points of today’s IT infrastructures and introduce Western Digital’s OpenFlex™ line of composable infrastructure, fabric-attached storage products.
  • In-Memory Computing at Scale – The Next Computing Frontier Recorded: Dec 13 2018 37 mins
    Esther Spanjer, Director of Business Development EMEIA
    The heavy demands of safe city initiatives, IoT workloads, and other time-sensitive data sets are hitting memory constraints at scale. New datacenter architectures become more and more memory-centric to address the pursuit of greater data processing at lower latency. But IT managers are confronted with cost of high capacity DIMM modules, limited amount of DIMM slots available within the server and low CPU utilization.

    In this webinar, Esther Spanjer, Director of Business Development EMEAI will discuss the technical constraints of memory-intensive applications, and how they can be solved by Western Digital’s newly announced Ultrastar DC ME200 Memory Extension Drive. You will learn more about:

    1. Market trends and challenges for memory-intensive applications
    2. Technical implementation of the Ultrastar DC ME200 inside a server, enabling up to 24TiB of byte-addressable memory in a 1U server
    3. Real test data on applications, such as Memcached, Redis, MySQL and SAP Hana
  • Persistent Memory’s Role in Storage Solutions Recorded: Nov 28 2018 49 mins
    Clay Ryder, Data Center Systems Marketing
    Persistent Memory such as Non-volatile DIMMs (NVDIMMs) is finding its way into enterprise storage solutions that were formerly the domain of HDDs and SSDs. The promise of running your applications and workloads at the speed of memory, but at a lower cost and with better durability is certainly alluring. But does this mean that persistent memory will replace ubiquitous HDD and SSD solutions? Will it be right for you? And how will it impact the rest of the storage market?

    Join us for a Video Meetup where we’ll walk you through an introduction to persistent memory, and how to think about incorporating it into your storage infrastructure either now or in the future. We’ll be talking with an IT pro from the Spiceworks Community as well as an expert from Western Digital.

    What we'll discuss:
    -What is persistent memory and how is it different from SSDs and HDDs?
    - How persistent memory works and how it could fit into storage solutions
    - How your data can travel between varying tiers of storage performance Comparison of cost and performance with traditional storage solutions
    - Determining whether the investment is worth it and making the business case
Trends and best-practices for data at scale
Western Digital Corporation is an industry-leading provider of storage technologies and solutions that enable people to create, leverage, experience and preserve data. The company addresses ever-changing market needs by providing a full portfolio of compelling, high-quality storage solutions with customer-focused innovation, high efficiency, flexibility and speed. Our products are marketed under the HGST, SanDisk and WD brands to OEMs, distributors, resellers, cloud infrastructure providers and consumers.

Embed in website or blog

Successfully added emails: 0
Remove all
  • Title: Shared or Distributed HDFS – What’s Right for Me?
  • Live at: Jul 21 2016 5:00 pm
  • Presented by: Janet George, Chief Data Scientist, Engineering Fellow, SanDisk
  • From:
Your email has been sent.
or close