Data Storage Innovation Conference 2016 Abstracts
Break Out Sessions and Agenda Tracks Include:
Note: This agenda is a work in progress. Check back for updates on additional sessions as well as the agenda schedule.
Big Data Essentials For IT Professionals
Sujee Maniyam, Founder/Big Data Principal, Elephant Scale
Big Data is a ‘buzz’ word. There are lots of systems and software that claim to be doing Big Data. How do you separate noise from facts?
In this talk we aim to give you a comprehensive coverage of modern Big Data landscape. We will talk about various components , open source projects that make up Big Data ‘barn’. The talk will cover a few Big Data use cases and recommended designs for those use cases.
Developers / Managers / Architects / Directors
Beginner / Intermediate
Scalable and Smart Storage Class Memory Layer for Big Data
Robert Geiger, Chief Architect and VP Engineering, Ampool Inc.
Today, if events change the decision model, we wait until the next batch model build for new insights. By extending fast “time-to-decisions” into the world of Big Data Analytics to get fast “time-to-insights”, apps will get what used to be batch insights in near real time. Enabling this is technology such as smart in-memory data storage, new storage class memory, and products designed to do one or more parts of an analysis pipeline very well. In this talk we describe how Ampool is building on Apache Geode to allow Big Data analysis solutions to work together with a scalable smart storage class memory layer to allow fast and complex end to end pipelines to be built- closing the loop and providing dramatically lower time to critical insights.
- Explain what SCM means in Big Data, its importance and why it matters
- Explain the Big Data analysis loop & system properties needed at each phase
- Review Big Data requirements for storage class memory
- Demonstrate an in memory big data pipeline Provide benchmark numbers
“Direct-to-Cloud” Technology Innovations that Open Up the Cloud for Big Data App
Jay Migliaccio, Director of Cloud Platforms & Services, Aspera, an IBM company
Moving big data in and out of the cloud has presented an insurmountable challenge for organizations looking to leverage the cloud for big data applications. Typical file transfer acceleration "gateways" upload data to cloud object storage in two phases, which introduces significant delays, limits the size of the data that can be transferred, and increases local storage costs, and machine compute time and costs. This session will describe direct-to-cloud capabilities that achieve maximum end-to-end transfer speeds and scale out of storage through direct integration with the underlying object storage interfaces, enabling transferred data to be written directly to object storage and available immediately when the transfer completes. It will explore how organizations across different industries are using direct-to-cloud technology for applications that require the movement of gigabytes, terabytes or petabytes of data in, out and across the cloud.
- An understanding of the root causes of technical bottlenecks associated with using cloud-based serv
- Methods to overcome these technical bottlenecks and speed up cloud-based big data workflows
- Insight into how organizations across different industries have successfully deployed cloud-based
Solving the Framework-Storage Gap in Big Data
Haoyuan Li, Founder and CEO, Alluxio
As datasets continue to grow, storage has increasingly become the critical bottleneck for enterprises leveraging Big Data frameworks like Spark, MapReduce, Flink, etc. The frameworks themselves are driving much of the exciting innovation in Big Data, but the complexity of the underlying storage systems is slowing the pace that data assets can be leveraged by these frameworks. Traditional storage architectures are inadequate for distributed computing and the size of today’s datasets.
In this talk, Haoyuan Li, co-creator of Tachyon (and a founding committer of Spark) and CEO of Tachyon Nexus will explain how the next wave of innovation in storage will be driven by separating the functional layer from the persistent storage layer, and how memory-centric architecture through Tachyon is making this possible. Li will describe the future of distributed file storage and highlight how Tachyon supports specific use cases.
Li will share the vision of the Tachyon project, highlight exciting new capabilities, and give a preview at upcoming new features. The project is one of the fastest growing big data open source projects. It is deployed at many companies, including Alibaba, Baidu and Barclays. Tachyon manages hundreds of machines in some of the production deployments and brings orders of magnitude improvement. In addition, Tachyon has attracted more than 200 contributors from over 50 institutions, including Alibaba, Redhat, Baidu, Intel, and IBM.
Birds of a Feather
Privacy Versus (In)security: Who Should Win and Why Between Apple and the FBI?
The FBI publicly demanded that Apple help the FBI unlock a dead terrorist’s cell phone by providing a special proprietary “back door”. Apple refused, noting that such a tool would invariably escape into the wild and jeopardize the security and privacy of the entire cell phone community: consumer and business. An anonymous 3rd party broke the impasse by providing such a backdoor. But, the issue remains: privacy/security controls versus selected data recovery demands. What is your opinion? Come to this BoF and help us find a win/win solution.
Open Source Storage and Datacenter
Michael Dexter, iXsystems Inc; Christopher R. Hertel, Samba Team; Jordan Hubbard, CTO, iXsystems Inc; Ronald Pagani, Jr, Open Technology Partners, LLC
At this Birds of a Feather session, we’ll discuss how open source is enabling new storage and datacenter architectures. All are welcome who have an interest in open source, scale-up and scale-out storage, hyperconvergence and exploring open solutions for the datacenter.
- How is open source solving your datacenter challenges?
- What is working? What is not?
- What would you like to see?
- Which project(s) are you most excited about?
Compute, Bandwidth and Storage Implications for Next Generation Entertainment Applications
Yahya H. Mirza, CEO/CTO, Aclectic Systems
Today there is a great excitement in increasing the immersion of virtual reality productions using real-time computer generated content, offline rendered content, captured content, and their combinations. Camera vendors are striving to rapidly enable film makers to capture more immersive reality. Headset vendors are working to allow viewers to experience a greater sense of presence to actually experience the virtual environments in a life-like manner. Consequently, these emerging forms of entertainment are expanding across multiple dimensions, integrating data from multiple cameras to create 360 degree and 360 degree stereoscopic video. The resulting separate frames are stitched together to form a 360 degree by 180 degree view from a single point in space. More cameras lead to synthesized 3D stereoscopic view from a single point in all directions. This situation is further complicated by the emerging promise of Light Field cameras that dramatically increase the compute, storage and bandwidth requirements over conventional feature films and interactive 3D game applications.
This BOF will start with a short presentation that overviews the various emerging entertainment forms and their implications. Next, a single visual effects shot will be dissected to illustrate the technical issues involved. Finally, a group discussion will be facilitated to discuss how emerging storage technologies will impact these emerging entertainment forms.
Advanced Data Reduction Concepts
Ronald Pagani Jr., Principal Consultant, Open Technology Partners LLC; SNIA Data Protection and Capacity Optimization Committee
Since arriving over a decade ago, the adoption of data deduplication has become widespread throughout the storage and data protection communities. This tutorial assumes a basic understanding of deduplication and covers topics that attendees will find helpful in understanding today’s expanded use of this technology. Topics will include trends in vendor deduplication design and practical use cases, e.g., primary storage, data protection, replication, etc., and will also cover other data reduction technologies, e.g., compression, etc.
- Have a clear understanding of current data reduction design trends.
- Have the ability to discern between various deduplication design approaches and strengths.
- Recognize new potential use cases for data reduction technologies in various storage environments.
How to Reduce Data Capacity in Object Storage: Dedup and More
Dong In Shin, CTO, G-Cube Inc.
There are growing interest on object storage as a backup and version storage for their massive data on primary storage due to its intuitive interfaces and relatively low cost of ownership. However, object storage in its early stage now does not consider capacity optimization very well (especially on its open source implementation like Openstack Swift and Ceph). This presentation introduces data reduction techniques from the viewpoint of object storage; we will cover deduplication, compression, and more interesting techniques for capacity optimization on object storage.
- Object storage data layout
- Data backup using object storage
- Capacity optimization techniques for object storage
Jim Thompson, Senior Systems Engineer, Avere System
When it comes to cloud computing, the ability to turn massive amounts of compute cores on and off on-demand can be very attractive to IT departments, who need to manage peaks and valleys in user activity. With cloud bursting, the majority of the data can stay on premises while tapping into compute from public cloud providers, reducing risk and minimizing need to move large files.
Hear from Jim Thompson, Senior Systems Engineer at Avere Systems, on the IT and business benefits that cloud bursting provides, including increased compute capacity, lower IT investment, financial agility, and, ultimately, faster time to market.
- Define cloud bursting and its use cases within the enterprise
- Outline specific benefits offered by cloud bursting
- Learn about case studies with actual companies using cloud bursting
Plotting Your Data Exit Before Entering the Private Cloud
Fredrik Forslund, Director of Cloud and Data Center Erasure Solutions, Blancco Technology Group
According to the Ponemon Institute, 30 percent of business information is stored in the cloud. Like any relationship, both sides are wide-eyed about the limitless possibilities, attentive and full of promise. What promises, you might ask? Higher IT control, centralized management and delivery efficiencies are just a few.
But not all relationships last forever. Maybe a cloud storage provider isn’t meeting up to its pre-defined expectations, or they’ve decided to change the terms and conditions of their agreement. Perhaps they’ve had repeated outages. Or it might be as simple as coming to the end of the service agreement or contract. Whatever the reason might be, one of the biggest mistakes a company can make is not plotting out every single step of their exit plan well before entering the cloud. This could triple the likelihood of losing customer trust, loyalty and long-term business. And when you factor in the hefty legal fines and repercussions, it’s the kind of damage that’s nearly impossible to bounce back from.
In this session, leading IT, cloud infrastructure and tech experts from Blancco Technology Group and other firms will outline the step-by-step process of developing a written exit plan for data stored in the cloud and how to plot their data exit plan against key regulatory criteria so that they can best minimize the likelihood of data being accessed or stolen by cyber thieves.
- Learn how to create an exit plan for storing data in the private cloud.
- Learn how to plot data exit plan against regulatory standards.
- Learn value/benefits of removing data safely.
Storage in Combined Service/Product Data Infrastructures
Craig Dunwoody, CTO, GraphStream Incorporated
It is increasingly common to combine as-a-service and as-a-product consumption models for elements of an organization's data infrastructure, including applications; development platforms; databases; and networking, processing, and storage resources. Some refer to this as "hybrid" architecture.
Using technical (not marketing) language, and without naming specific vendors or products, this presentation covers some improved storage capabilities becoming available in service and product offerings, and some scenarios for integrating these kinds of offerings with other data infrastructure services and products.
- Considerations for Choosing Storage Services and or Products for Specific Use Cases
- Evolving economics of service and product consumption models for storage resources
- Reducing cost and operational complexity by consolidating storage capabilities into a smaller number of platforms
Dealing with the “Other” Latency: What the Cloud Portends for IT Infrastructure
Lazarus Vekiarides, CTO and Co-founder, ClearSky Data
As flash storage becomes mainstream, storage pros are frequently bombarded by vendors and the press about the importance of latency when considering the performance of storage systems.
Simultaneously, the public cloud has emerged as a remote computing resource that is disrupting the way businesses use IT. In a world of geographically dispersed islands of compute, however, the latency problem takes on a different complexion: System designers need to consider the impact of physical distance and the speed of light more carefully than the latency of storage media.
In this discussion, we will cover some of the implications of latency on the performance of distributed systems and, in particular storage systems, in the context of the public cloud. We’ll detail:
- The performance limitations that latency can create
- Tools and infrastructure that can be used to mitigate these effects
- A reference architecture that can minimize this problem holistically
- The performance limitations that latency can create
- Tools and infrastructure that can be used to mitigate these effects
- A reference architecture that can minimize this problem holistically
Why Analytics on Cloud Storage?
Padmavathy Madhusudhanan, Principal Consultant, Wipro Technologies
Radhakrishna Singuru, Principal Architect, Wipro Technologies
Cloud platforms that provide a scalable, virtualized infrastructure are becoming ubiquitous. As the underlying storage can meet extreme demands of scalability in this platform, running storage analytics applications in cloud is gaining momentum. Gartner estimates 85% of Fortune 500 companies do not reap the full benefit of their data analytics, causing them to loose potential opportunities. Different Cloud providers do supply various metrics but they seem to be not uniform and inadequate sometimes. This mandates for a Cloud Storage analytics solution that follows a scientific process of transforming storage data metrics into insight for making better decisions.
- Key areas where Cloud storage analytics help ex. capacity planning
- Challenges in cloud based storage analytics (no uniform metrics across providers etc)
- Benefits of Cloud based Storage analytics: Data Isolation
Introduction to OpenStack Cinder
Sean McGinnis, Sr. Principal Software Engineer, Dell
Cinder is the block storage management service for OpenStack. Cinder allows provisioning iSCSI, fibre channel, and remote storage services to attach to your cloud instances. LVM, Ceph, and other external storage devices can be managed and consumed through the use of configurable backend storage drivers.
Led by a core member of Cinder, this session will provide an introduction to the block storage services in OpenStack as well as give an overview of the Cinder project itself.
Whether you are looking for more information on how to use block storage in OpenStack, are looking to get involved in an open source project, or are just curious about how storage fits into the cloud, this session will provide a starting point to get going.
- Cloud storage management
- Open source storage management
Deploying and Optimizing for Cloud Storage Systems using Swift Simulator
Gen Xu, Software Engineer, Intel
With the rise of cloud systems, IT spending on storage system is increasing. In order to minimize costs, architects must optimize system capacities and characteristics. Current capacity planning is mostly based on trial and errors as well as rough resource estimations. With increasing hardware diversity and software stack complexity this approach is not efficient enough. To meet both Storage capacity and SLA/SLOs requirements needs kind of trade-off.
If you are planning to deploy a storage cluster, growth is what you should be concerned with and prepared for. So how exactly can you architect a storage system, without breaking the bank, while sustaining a sufficient capacity and performance across the scaling spectrum?
The session is designed to present a novel simulation approach which shows flexibility and high accuracy to be used for cluster capacity planning, performance evaluation and optimization before system provisioning. We will focus specifically on storage capacity planning and provide criteria for getting the best price-performance configuration by setting Memory, SSD and Magnetic Disk ratio. We will also highlight performance optimization ability via evaluating different OS parameters (e.g. log flush and write barrier), software configurations (e.g. proxy and object worker numbers) and hardware setups (e.g. CPU, cluster size, the ratio of proxy server to storage server, network topology selection CLOS vs. Fat Tree).
- Design challenges of a cloud storage deployment
- Storage system modeling technology for OpenStack-Swift
- Use Case study: plan and optimize a storage cluster to meet capacity and performance requirements.
Swift Use Cases with SwiftStack
John Dickinson, Director of Technology, SwiftStack
Swift is a highly available, distributed, scalable, eventually consistent object/blob store available as open source. It is designed to handle non-relational (that is, not just simple row-column data) or unstructured data at large scale with high availability and durability. For example, it can be used to store files, videos, documents, analytics results, Web content, drawings, voice recordings, images, maps, musical scores, pictures, or multimedia. Organizations can use Swift to store large amounts of data efficiently, safely, and cheaply. It scales horizontally without any single point of failure. It offers a single multi-tenant storage system for all applications, the ability to use low-cost industry-standard servers and drives, and a rich ecosystem of tools and libraries. It can serve the needs of any service provider or enterprise working in a cloud environment, regardless of whether the installation is using other OpenStack components. Use cases illustrate the wide applicability of Swift.
Imminent Challenges for the Cloud Storage Industry and the Solution
Mark Carlson, Principal Engineer, Industry Standards, Toshiba
Udayan Singh, Head, SPE-Storage, Platform and Manageability, Tata Consultancy Services
The storage industry is being transformed by the adoption of Cloud Storage. Challenges that were overlooked during the initial stages of cloud storage industry growth are now becoming core issues of today and the future. In this session we discuss the major challenges that corporations will face to avail themselves of the best of services from multiple cloud providers; or to move from one cloud provider to another in a seamless manner.
The SNIA CDMI standard addresses these challenges by offering interoperability between clouds storage. SNIA and Tata Consultancy Services (TCS) have partnered to create a SNIA CDMI Conformance Test Program to help cloud storage companies achieve conformance to CDMI and ensure interoperability between clouds. The TCS CDMI Conformance Assurance Solution (CAS) provides cloud storage product testing and detailed reports for conformance to the CDMI specification.
As interoperability becomes critical, end user companies should include the CDMI standard in their RFPs and demand conformance to CDMI from vendors.
- Understand the critical challenges that the cloud storage industry is facing
- Solution to address the identified challenges
- Benefits of CDMI conformance testing
- Benefits for end user companies
Beyond the Cloud: Space-based Data Storage
Scott Sobhani, Co-founder & CEO, Cloud Constellation Corporation
As cloud and storage projections continue to rise, the number of organizations moving to the Cloud is escalating and it is clear cloud storage is here to stay. However, is it secure? Data is the lifeblood for government entities, countries, cloud service providers and enterprises alike and losing or exposing that data can have disastrous results. There are new concepts for data storage on the horizon that will deliver secure solutions for storing and moving sensitive data around the world. In this session, attendees will learn about new best practices to bypass the Internet.
- Understanding the next phase of cloud storage
- New architectural designs for reliable, redundant off-world storage
- By-passing cross-jurisdictional restrictions to avoid violating privacy regulations
- Understanding how a mother/daughter satellite configuration allows users to circumvent leaky networks
- Isolating data from the Internet and leased lines
Efficient and Agile Persistent Storage for Containers
Carlos Carrero, Sr. Principal Technical Product Manager, Veritas
Chad Ryan Thibodeau, Product Manager, Veritas
Containers are called to the next big wave in application delivery, offering better resource utilization, agility and performance than traditional virtualization techniques. Once enterprises start running databases and applications with persistent storage needs, a new challenge appears with this new paradigm. This session will discuss how Veritas uses Software Defined Storage solutions to provide efficient and agile persistent storage for containers, offering enterprise capabilities like resilience, snapshots, I/O acceleration and Disaster Recovery. A reference architecture using commodity servers and server side storage will be presented. Finally, future challenges around quality of service, manageability and visibility will be covered in this session.
- Understand how start working with containers today in a hyper-converged infrastructure
- Use Software Defined Storage to fulfil persistent storage needs
- Get a vision on futures on persistent storage for containers
5 Ways to Convince Your CEO It’s Time for a Storage Refresh
David Siles, CTO, DataGravity
Storage has historically stayed in its “box.” Any developments in the industry were contained to limited dimensions such as costs, feeds or speeds. But in today’s digital world, it’s not enough to just deliver data – all parts of your infrastructure must be able to answer ever-present data security questions, extract valuable insights, identify sensitive information and help protect critical data from incoming threats.
As you go through your next technology refresh, what benefits should your storage deliver to your business, and by which dimensions should you measure them? In this session, DataGravity Chief Technology Officer David Siles will address the new standards for aligning your storage platform with your data’s needs, and share tips for highlighting the consequences of outdated storage to your CEO. Your company’s critical data wasn’t created to live and die in a system that can’t maximize its value or protect it from risks.
- Contextualize storage and IT from a C-level business perspective
- Identify the storage strategy that best fits your data and company
- Incorporate data security considerations to discover and protect sensitive data
- Empower employees w/ increased productivity & collaboration, & ID insights that improve bottom line
The Role of Tape Technology in Managing the Exponential Growth of Cold Data
Osamu Shimizu, Research Engineer, FUJIFILM Corporation
The increasing need for data storage capacity due to enormous amounts of newly created data year after year is an endless story. However, budgets for data storage are not nearly increasing at the same rate as data capacity growth, while retaining the data still remains very important. In consequence, having an inexpensive but reliable storage solution is paramount for this situation. Fortunately, most data generated is "cold data", which is rarely accessed but still needs to be retained for quite a long period of time. Tape storage, which has a long proven history with applications in various industries, is suitable for retaining such cold data because of its low TCO (total cost of ownership), advanced performance, high reliability and promising future outlook compared to other candidate technologies for cold storage (e.g. HDD, Optical Discs).
In this presentation, we will go through the reasons why tape storage is suitable for retaining cold data and will present the latest tape technologies and future outlook.
- What is cold data?
- Tape's advantages in cold storage
- Latest tape storage technologies
- Future outlook of tape storage
Embrace Hyper-scale Storage Architecture to Drastically Increase Reliability and Lower Costs
Sudhakar Mungamoori, Vice President, Customer Success and Sales Engineering, Formation Data Systems
The tightly coupled architecture used by the vast majority of enterprises today is archaic and a new approach is needed to manage the explosion of data in a world of shrinking IT budgets. Enter: hyper-scale IT architecture.
Sudhakar Mungamoori will explain why a modern, software-driven and loosely coupled architecture is required for hyper-scale IT. He will highlight how this innovative architecture approach mitigates complexity, improves agility and reliability through on demand IT resources and reduces costs by as much as 10X.
Mungamoori will highlight how enterprises can learn from companies like Google and Facebook who built their own loosely coupled IT architectures to capitalize on its advantages. He will discuss use cases and best practices for IT departments that cannot similarly build their own, but are strategically looking to adopt loosely coupled architectures in order to remain competitive without blowing their budget in the face of today’s data deluge.
- Why tightly coupled storage array architectures don’t meet the scale, performance or economic requirements of today’s enterprise, not to mention the future.
- How distributed, hyper-scale software architectures provide increased scale, availability and resilience across many different workload profiles.
- Challenges IT departments deploying hyper-scale solutions face, and best practices for how they can overcome these issues
- How to migrate application workloads from legacy storage arrays to software-defined architectures using tiering and quality of service for guaranteed performance delivery.
- How de-duplication, journaling and space efficient snapshots provide superior data protection with granular recovery across distributed nodes to minimize data loss and storage consumption.
Intro to Data Protection-Backup to Tape, Disk & Beyond
Tom Sas, Worldwide Product Marketing Manager, Hewlett Packard Enterprise
Extending the enterprise backup paradigm with disk-based technologies allow users to significantly shrink or eliminate the backup time window. This tutorial focuses on various methodologies that can deliver efficient and cost effective solutions. This includes approaches to storage pooling inside of modern backup applications, using disk and file systems within these pools, as well as how and when to utilize Continuous Data Protection, deduplication and virtual tape libraries (VTL), as well as the cloud.
- Understand backup and restore technology including tape, disk, snapshots, deduplication, virtual tape, replication technologies and the cloud.
- Compare and contrast backup and restore alternatives to achieve data protection and data recovery.
- Identify and define backup and restore operations and terms.
Trends in Backup and Restoration Technologies
Jason Iehl, Manager - Systems Engineering, Netapp
Many disk technologies, both old and new, are being used to augment tried and true backup and data protection methodologies to deliver better information and application restoration performance; These technologies work in parallel with the existing backup paradigm. This session will discuss many of these technologies in detail; Important considerations of data protection include performance, scale, regulatory compliance, recovery objectives and cost; Technologies include contemporary backup, disk based backups, snapshots, continuous data protection and capacity optimized storage, as well as cloud services. This tutorial will cover how these technologies interoperate, as well as best practices recommendations for deployment in today's heterogeneous data centers.
- Understand backup and restore technology including tape, disk, snapshots, deduplication, virtual tape, replication technologies and the cloud.
- Compare and contrast backup and restore alternatives to achieve data protection and data recovery.
- Identify and define backup and restore operations and terms.
Protecting Data in a Big Data World
David A. Chapa, CTO and Managing Partner, Elovate
Data growth is in an explosive state, and these "Big Data" repositories need to be protected. In addition, new regulations are mandating longer data retention, and the job of protecting these ever-growing data repositories is becoming even more daunting. This presentation will outline the challenges, methodologies, and best practices to protect the massive scale "Big Data" repositories.
- Understand the unique challenges of managing and protecting "Big Data" repositories.
- Understand the various technologies available for protecting "Big Data" repositories.
- Understand various data protection considerations and best practices for "Big Data" repositories the, for various environments, including Disaster Recovery/Replication, Capacity Optimization, etc.
Privacy vs Data Protection: The Impact of EU Data Protection Legislation
Thomas Rivera, Sr. Technical Associate, HDS
After reviewing the diverging data protection legislation in the EU member states, the European Commission (EC) decided that this situation would impede the free flow of data within the EU zone. The EC response was to undertake an effort to "harmonize" the data protection regulations and it started the process by proposing a new data protection framework. This proposal includes some significant changes like defining a data breach to include data destruction, adding the right to be forgotten, adopting the U.S. practice of breach notifications, and many other new elements. Another major change is a shift from a directive to a rule, which means the protections are the same for all 27 countries and includes significant financial penalties for infractions. This tutorial explores the new EU data protection legislation and highlights the elements that could have significant impacts on data handling practices.
- Highlight the major changes to the previous data protection directive.
- Review the differences between “Directives” versus “Regulations”, as it pertains to the EU legislation.
- Learn the nature of the Reforms as well as the specific proposed changes – in both the directives and the regulations.
Maximizing Storage Density While Conserving Valuable Rack Real Estate
Chaz Stevens, Director of Marketing, Aberdeen LLC
Aberdeen delivers extreme computing power with our ultra-dense, extreme performance storage devices, packing over 3/4 Petabyte into only 4U of rack space. While consuming just 4U of rack space, Aberdeen’s ultra-dense storage devices suit a wide range of capacity hungry applications, including big data analytics or massive block or object storage
Aberdeen custom configures your server or storage products to your exact specifications. The ease of our online configurator lets you choose the storage device to fit precisely what you want. Exploring the features of Aberdeen’s NAS line, including our N49 4U 78 Bay, Ultra Dense, High Performance 12Gb/s SAS, storage device.
Identifying Performance Bottlenecks with Real-World Applications and Flash-Based Storage
Dennis Martin, President, Demartek
Where are today’s storage performance bottlenecks, how do you find them and how does adding flash storage affect them? Demartek will report the results (IOPS, throughput and latency) of vendor-neutral performance tests run on database and virtualization workloads typical of those found in today’s data centers. The tests cover both hybrid and all-flash solutions from several manufacturers and using a variety of form factors and interfaces. You will come away with reasonable estimates of what to expect in practice, observe how different workloads affect storage system performance and notice the difference in performance results depending on where the measurements were taken. Technologies discussed include server-side flash, hybrid storage arrays, all-flash arrays and various interfaces including NVMe.
- Learn how real-world workloads perform on different types of flash storage
- Learn how different application workloads affect latency
- Learn about some of the interfaces used for flash storage
High Availability for Centralized NVMe
Zivan Ori, CEO and Co-founder, E8 Storage
Using NVMe drives in a centralized manner introduces the need for high availability. Without it, a simple failure in the NVMe enclosure will result in loss of access to a big group of disks. Loss of a single NVMe disk will impact all hosts mapped to this disk. We will review the state of the industry in approaching these problems, the challenges in performing HA and RAID at the speeds and latency of NVMe, and introduce new products in this space.
Panel: Shingled Magnetic Recording (SMR) – Data Management Techniques Examined
Moderator: Tom Coughlin, President, Coughlin Associates
Panelists: Jorge Campello, Global Director of Systems and Solutions, Western Digital; Mark Carlson, Principal Engineer, Industry Standards, Toshiba, Chair, SNIA Technical Council; Josh Bingaman, Firmware Engineering Manager, Seagate Technology
The unyielding growth of digital data continues to drive demand for higher capacity, lower-cost storage. With the advent of Shingled Magnetic Recording (SMR), which overlaps HDD tracks to provide a 25 percent capacity increase versus conventional magnetic recording technology, storage vendors are able to offer extraordinary drive capacities within existing physical footprints. That said, IT decision makers and storage system architects need to be cognizant of the different data management techniques that come with SMR technology, namely Drive Managed, Host Managed and Host Aware. This panel session will offer an enterprise HDD market overview from prominent storage analyst Tom Coughlin as well as presentations on SMR data management methods from leading SMR HDD manufacturers (Seagate, Toshiba and Western Digital).
- Enterprise HDD market update
- Brief introduction of Shingled Magnetic Recording (SMR)
- Deep dive into SMR data management techniques (Drive Managed, Host Managed and Host Aware
Windows Interoperability Workshop
Christopher Hertel, Software Developer, Sr. Program Manager, Dell/Compellent
Windows and POSIX are different, and bridging the gap between the two—particularly with Network File Systems—can be a daunting endeavor ...and annoying, too. This tutorial will provide an overview of the SMB3 network file protocol (the heart and soul of Windows Interoperability) and describe some of the unique and powerful features that SMB3 provides. We will also point out and discuss some of the other protocols and services that are integrated with SMB3 (such as PeerDist), and show how the different pieces are stapled together and made to fly. The tutorial will also cover the general structure of Microsoft's protocol documentation, the best available cartography for those lost in the Interoperability Jungle. Some simple code examples will be used sparingly as examples, wherever it may seem clever and useful to do so.
- Become familiar with the Windows Interoperability Ecosystem
- Better understand Microsoft's Specifications
- Identify Windows-specific semantic details
Object Drives: Simplifying the Storage Stack
Mark Carlson, Principal Engineer, Industry Standards, Toshiba
A number of scale out storage solutions, as part of open source and other projects, are architected to scale out by incrementally adding and removing storage nodes. Example projects include:
Swift (OpenStack object storage)
The typical storage node architecture includes inexpensive enclosures with IP networking, CPU, Memory and Direct Attached Storage (DAS). While inexpensive to deploy, these solutions become harder to manage over time. Power and space requirements of Data Centers are difficult to meet with this type of solution. Object Drives further partition these object systems allowing storage to scale up and down by single drive increments.
- What are object drives?
- What value do they provide?
- Where are they best deployed?
Massively Scalable File Storage
Philippe Nicolas, Advisor, OpenIO
Internet changed the world and continues to revolutionize how people are connected, exchange data and do business. This radical change is one of the causes of the rapid explosion of data volume that required a new data storage approach and design. One of the common elements is that unstructured data rules the IT world. How famous Internet services we all use every day can support and scale with thousands of new users and hundreds of TB added daily and continue to deliver an enterprise-class SLA ? What are various technologies behind a Cloud Storage service to support hundreds of millions users? This tutorial covers technologies introduced by famous papers about Google File System and BigTable, Amazon Dynamo or Apache Hadoop. In addition, Parallel, Scale-out, Distributed and P2P approaches with open source and proprietary ones are illustrated as well. This tutorial adds also some key features essential at large scale to help understand and differentiate industry vendors and open source offerings.
- Understand technology directions for large scale storage deployments
- Be able to compare technologies
- Learn from big internet companies about their storage choices and approaches
The Tip of the Iceberg: The Coming Era of Open Source Enterprise Storage
Michael Dexter, Senior Analyst, iXsystems, Inc
Joy's Law, named after Sun Microsystems' founder, is proving painfully true: “The best people work for someone else” and the explosive growth of open source now dictates that you are always out numbered by skilled developers you could never obtain or afford. This is not however a bad thing. Collaboration always beats competition when building community infrastructure and the OpenZFS project is taking Sun's next generation file system to unforeseen and unimaginable levels. OpenZFS-powered projects like FreeNAS have inverted the conversation from "I wish I could have this enterprise technology at home" to "Why aren't we using this at work?"
- Learn about Open Source and the OpenZFS file system
- Understand the advantages that OpenZFS provide to systems of all sizes
- Survey the OpenZFS community, developers and vendors
- Explore SDS and Platform-Defined OpenZFS solutions
Ceph For The Enterprise
David Byte, Senior Technology Strategist, SUSE
Few, if any, enterprise organizations will be willing to consume an upstream version of Ceph. This session will cover general guidelines for implementing Ceph for the enterprise and cover available reference architectures from SUSE.
- Understanding design choices for Ceph
- General sizing guidelines
- Using ceph in a traditional environment
- Managing ceph in the enterprise
High Performance Storage for Science Workloads
Ulrich Fuchs, IT Service Manager, CERN
The unique challenges in the field of nuclear high energy physics are already pushing the limits of storage solutions today, however, the projects planned for the next ten years call for storage capacities, performance and access patterns that exceed the limits of many of today's solutions.
This talk will present the limitations in network and storage and explain the architecture chosen for tomorrow's storage implementations in this field. Tests of various file systems (Lustre, NFS, Block Object storage, GPFS ..) have been performed and the results of performance measurements for different hardware solutions and access patterns will be presented.
- Shared file system and storage performance requirements in science workloads
- Setup and results of performance measurements of different file systems: the LUSTRE FS, GPFS
- Technology differences between several file systems and storage solutions
MarFS: A Scalable Near-POSIX File System over Cloud Objects
Gary Grider, HPC Division Leader, Los Alamos National Laboratory
Many computing sites need long-term retention of mostly cold data often “data lakes”. The main function of this storage tier is capacity but non trivial bandwidth/access requirements exist. For many years, tape was the best economic solution. Data sets have grown larger more quickly than tape bandwidth improvements and access demands have increased. Disk can be more economically for this storage tier. The Cloud Community has moved towards erasure based object stores to gain scalability and durability using commodity hardware. The Object Interface works for new applications but legacy applications utilize POSIX for their interface. MarFS is a Near-POSIX File System using cloud storage for data and many POSIX file systems for metadata. MarFS will scale the POSIX namespace metadata to trillions of files and billions of files in a single directory while storing the data in efficient massively parallel ways in industry standard erasure protected cloud style object stores.
- Storage tiering in future HPC and large scale computing environments
- Economic drivers for implementing data lakes/tiered storage
- HPC specific requirements for data lakes - multi way scaling
- Overview of existing solution space
- How the MarFS solution works and for what types of situations
High Performance NAS, New design for New IT Challenges
Pierre Evenou, CEO, Rozo Systems
Philippe Nicolas, Advisor, Rozo Systems
Rozo Systems develops a new generation of Scale-Out NAS with a radical new design to deliver a new level of performance. RozoFS is a high scalable, high performance and high resilient file storage product, fully hardware agnostic, that relies on an unique patented Erasure Coding technology developed at University of Nantes in France. This new philosophy in file serving extends what is capable and available today on the market with super fast and seamless data protection techniques. Thus RozoFS is the perfect companion for high demanding environments such HPC, Life Sciences, Media and Entertainment, Oil and Gas.
- Learn new Scale-Out NAS design
- Learn new Erasure Coding technology
- Understand Use cases challenges solved by RozoFS
Storage Systems Can Now Get ENERGY STAR Labels and Why You Should Care
Dennis Martin, President, Demartek
We all know about ENERGY STAR labels on refrigerators and other household appliances. In an effort to drive energy efficiency in data centers, storage systems can now get ENERGY STAR labels through the EPA announced its ENERGY STAR Data Center Storage program. This program uses the taxonomies and test methods described in the SNIA Emerald Power Efficiency Measurement specification, which is part of the SNIA Green Storage Initiative. In this session, Dennis Martin, President of Demartek, the first SNIA Emerald Recognized Tester company, will discuss the similarities and differences in power supplies used in computers you build yourself and in data center storage equipment, 80PLUS ratings, and why it is more efficient to run your storage systems at 230v or 240v rather than 115v or 120v. Dennis will share his experiences running the EPA ENERGY STAR Data Center Storage tests for storage systems and why vendors want to get approved.
- Learn about power supply efficiencies
- Learn about running datacenter equipment at 230 volts vs. 115 volts
- Learn about the SNIA Emerald Power Efficiency Measurement
- Learn about the EPA ENERGY STAR Data Center Storage program
Power-Efficient Data Storage
Brian Zahnstecher, Principal, PowerRox
Everyone wants to save energy in one form or another and energy efficiency is right at the top of lists of data center owner/architect pain points and key concerns. As worldwide data grows at an exponential rate, data storage solutions are creating an ever-increasing footprint for power in the data center. Understanding the key factors of power utilization for storage solutions is critical to optimizing that power footprint whether it be for purposes of system design or application in a data center or elsewhere. This talk will provide a high-level overview of storage technologies and compare/contrast them from a power perspective. More importantly, it will identify the best and simplest opportunities for reducing overall energy usage. Electrical engineering and/or power technical knowledge is not required as this is targeted for both technologists and facilities/business decision-makers.
- Where are the "low-hanging fruit" opportunities for power savings in data storage?
- What drives peak vs. average power draw in data storage?
- What are the key characteristics (or figures of merit) for power that differentiate storage solution
New Fresh Storage Approach for New IT Challenges
Laurent Denel, CEO, OpenIO
Philippe Nicolas, Advisor, OpenIO
With a design started in 2006, OpenIO is a new flavor among the dynamic object storage market segment. Beyond Ceph and OpenStack Swift, OpenIO is the last coming player in that space. The product relies on an open source core object storage software with several object APIs, file sharing protocols and applications extensions. The inventors of the solution took a radical new approach to address large scale environment challenges. Among them, the product avoids any rebalance like consistent hashing based systems always trigger. The impact is immediate as new machines contribute immediately without any extra tasks that impact the platform service. OpenIO also introduces the Conscience, an intelligent data placement service, that optimizes the location of the data based on various criteria such nodes workload, storage space… OpenIO is fully hardware agnostic, running on commodity x86 servers promoting a total independence.
- Understand object storage design
- Learn the limitation of classic approaches
- Investigate new method to build an design very large scale storage system
Are You Ready to Deploy In-memory Computing Applications?
Shaun Walsh, Managing Partner, G2M Communications
Businesses are extracting value from more data, more sources and at increasingly real-time rates. Spark and HANA are just the beginning. This presentation details existing and emerging solutions for in-memory computing solutions that address this market trend and the disruptions that happen when combining big-data (Petabyes) with in-memory/real-time requirements. We will also be providing use cases and survey results from users who have implemented in memory computing applications, It provides an overview and trade-offs of key solutions (Hadoop/Spark, Tachyon, Hana, NoSQL-in-memory, etc) and related infrastructure (DRAM, Nand, 3D-crosspoint, NV-DIMMs, high-speed networking) and the disruption to infrastructure design and operations when "tiered-memory" replaces "tiered storage". And it also includes real customer data on how they are addressing and planning for this transition with this architectural framework in mind. Audience will leave with a framework to evaluate and plan for their adoption of in-memory computing.
- Learn what is takes to evaluate, plan and implement in-memory computing applications
Machine Learning Based Prescriptive Analytics for Data Center Networks
Hariharan Krishnaswamy, Principal Engineer, Dell
In modern data center with thousands of servers, thousands of switches and storage devices, and millions of cables, failures could arise anywhere in compute, network or storage layer. The infrastructures provides multiple sources of huge volumes of data - time series data of events, alarms, statistics, IPC, system-wide data structures, traces and logs. Interestingly, data is gathered in different formats and at different rates by different subsystems. In this heterogeneous data representation, the ability to blend and ingest the data to discover hidden correlations and patterns is important. Robust data architecture and machine learning techniques are required to predict impending functional or performance issues and to propose desired actions that can mitigate an unwanted situation before it happens. This presentation will outline the challenges and address machine learning based solutions to understand long term trends, provide assessment of risk of failures, and suggest appropriate actions.
- Challenges of data center environment
- Machine Learning
Hyperconverged Infrastructures – What They Can Do and Where They’re Going
Eric Slack, Sr. Analyst, Evaluator Group
Hyperconverged infrastructures combine compute, storage and networking components into a modular, scale-out platform that typically includes a hypervisor and some comprehensive management software. The technology is usually sold as self-contained appliance modules running on industry-standard server hardware with internal HDDs and SSDs. This capacity is abstracted and pooled into a shared resource for VMs running on each module or ‘node’ in the cluster.
Hyperconverged infrastructures are sold as stand-alone appliances or as software that companies or integrators can use to build their own compute environments for private or hybrid clouds, special project infrastructures or department/remote office IT systems.
- Understand what hyperconvergence is – and is not
- Understand the capabilities this technology can bring
- Tour of current hyperconverged products
- Discussion of where this technology is going
Bringing the Benefits of Hyperconvergence to Secondary Storage
Nick Howell, Tech Evangelist, Cohesity
As much as Primary Storage has evolved over the last decade, including virtualization, cloud, and moving into hyperconverged platforms, Secondary Storage has not received the same treatment. Unfortunately, primary storage only accounts for approximately 20% of the average datacenter's storage footprint. A large bulk of data is kept in secondary systems for things like data protection, test/dev, & analytics.
What if there was one platform that brought all of these together under one banner? A single distributed file system running on commodity hardware, and designed from the ground-up with scale-out and shared-nothing architecture as a priority.
In this session, we will go over the trouble areas plaguing today's datacenter, identifying silos and bottlenecks found in most enterprise architectures, and show you how Cohesity is providing a way for you to consolidate all of these different workflows and stacks into a single distributed scale-out "as-you-grow" platform.
- Data Protection
- File Shares
- In-Place Analytics
Selecting Workloads for Hyperconverged vs Hyperscale Software-Defined Storage
Eric Carter, Senior Director of Marketing, Hedvig
Debate is rising in the industry over the best method for deploying infrastructure in private and public cloud datacenters. The predictable performance, packaging, and capacity increments of hyperconverged systems have made it the latest model to gain traction. Hyperscale is also gaining momentum as a preferred architecture due to its independent scaling capabilities. Now, businesses are asking, which is the best deployment for software-defined storage? The answer: it depends.
Attendees will learn which deployment is suitable for their workload types – ranging from general purpose server virtualization and VDI to big data and non-virtualized applications. Attendees from companies looking to modernize their IT infrastructure with a goal of being more agile and “cloud-like” will gain insight into whether hyperscale, hyperconverged, or a mixture of both systems provides the right solution to support their storage needs.
- How to distinguish hyperconverged from hyperscale and the advantages of each
- How software-defined storage is deployed in each architecture
- How organizations get started with software-defined storage
Hyperconverged Infrastructure – Use Cases and Buyer’s Guide
Ibrahim Rahmani, Director of Product and Solutions Marketing, DataCore
The interest in hyper-converged infrastructure has increased dramatically in the last few years. But there is a lot of confusion in the market. Which use cases are best suited for hyper-converged? What should a buyer look for when evaluating different hyper-converged products? How to manage hyper-converged in your infrastructure? How does Software-defined Storage (SDS) fit into all of this?
- Best use cases for hyper-converged infrastructure
- Most important criteria for selecting the right solution
- Fastest way to incorporate hyper-converged into your infrastructure
- Easiest way to manage hyper-converged
Scale-out Searchable Storage for the Cloud Age
Tony Barbagallo, VP Product, Caringo
Everyone and everything is creating data—lots of data—faster than at any time in history. But how do you gain actionable insight from this data when you have millions—or even billions—of files? And how do you keep up with the relentless flow of data from different sources, while providing access to this information across different applications? With today’s constantly increasing capacities and file counts, it’s impossible to quickly move or import data into different tools that promise to solve these issues. Learn how to solve these issues with Swarm 8, searchable storage for the cloud age.
Stress-free Backup Storage
Bob Pothier, Senior Systems Engineer, Exagrid
If the time you spend managing backups could be better spent on other more important IT initiatives, learn how ExaGrid’s disk backup with data deduplication appliances solve the problems that have plagued backup storage since the very beginning of IT as well as the newer problems caused by virtualization and explosive data growth. ExaGrid’s unique landing zone and scale-out architecture provide the fastest backups, restores, and offsite tape copies as well as VM boots in seconds to minutes versus hours with other solutions. ExaGrid keeps the backup window fixed in length even as data grows at a reduced cost up front and over time.
Digital Transformation: Are You Ready?
Kelvin Chowe, Systems Engineer, Tegile
As organizations look to support digital transformation in the datacenter, they’ll need to discover new ways to support new solutions like Cloud and Analytics. The traditional disk-based storage they're depending on is not keeping up. Flash is transforming datacenter infrastructure performance, capacity and cost to address these challenges. Join Chris Tsilipounidakis from Tegile as he examines the ways of transforming to an all-flash datacenter to support various, mixed application workloads in an ever-changing ecosystem.
Is This 'The ONE'?
David Byte, Sr. Technology Strategist, SUSE
Bringing open source software defined storage home to your data center is a bit like bringing your significant other home to meet the family. Does it have the qualities that are important? Is it going to dump your data? The best way to ensure success is to pick the right one. SUSE Enterprise Storage is THE one, come hear all the reasons why.
Introduction to Compuverde – Software Defined Storage
Stefan Bernbo, Founder, Compuverde
This session will discuss the benefits and features of Compuverde, a scale-out software defined storage solution.
KEY NOTE SPEAKERS AND GENERAL SESSIONS
Storage Implications of Cognitive Computing
Balint Fleischer, Chief Research Officer, Huawei
Jian Li, Research Program Director, Huawei Technologies
In the era of data explosion in Cloud-Mobile convergence and Internet of Things, traditional architectures and storage systems will not be sufficient to support the transition of enterprises to cognitive analytics. The ever increasing data rates and the demand to reduce time to insights will require an integrated approach to data ingest, processing and storage to reduce end-to-end latency, much higher throughput, much better resource utilization, simplified manageability, and considerably lower energy usage to handle highly diversified analytics. Yet next-generation storage systems must also be smart about data content and application context in order to further improve application performance and user experience. A new software-defined storage system architecture offers the ability to tackle such challenges. It features seamless end-to-end data service of scalable performance, intelligent manageability, high energy efficiency, and enhanced user experience.
Achieving a Software Defined Cognitive Infrastructure for Oceans of Data
Michelle Tidwell, SNIA Board Member, IBM Systems Storage, Business Line Manager, Software Defined Storage
We've heard it said that data is the new natural resource. In today's extremely dynamic, fast growing and interconnected world, businesses need more agile IT infrastructure to handle larger, faster, and growing variant types of Oceans of Data. The rise of cloud and hybrid cloud infrastructures, the common practice of server virtualization for efficiency and flexibility requires storage infrastructure that is equally flexible, to deliver, manage and protect data with superior performance to keep businesses operational through any data disruption or disaster. The IBM System Storage session will examine the IBM technologies that will help address the challenges and pain-points that IT professionals are experiencing to deliver dynamic insights for businesses and governments worldwide. Included in the IBM session are examples of how clients today are deploying Flash, Object and Software Defined Storage to rapidly and effectively deliver monetization of data.
Enterprise Architectures – the Pace Accelerates
Camberley Bates, Managing Director and Senior Analyst, The Evaluator Group
Since the 90’s the storage architectures of SAN and NAS, have been well understood and deployed with the focus on efficiency. With cloud-like applications, the massive scale of data and analystics, the introduction of solid state and HPC type applications hitting the data center, the architectures are changing, rapidly. It is a time of incredible change and opportunity for business and the IT staff that supports the change. Welcome to the new world of Enterprise Data Storage.
A DNA-based Archival Storage System
Luis Henrique Ceze, University of Washington
Demand for data storage is growing exponentially, but the capacity of existing storage media is not keeping up. Using DNA to archive data is an attractive possibility because it is extremely dense, with a raw limit of 1 exabyte/mm3 (10^9 GB/mm3), and long-lasting, with observed half-life of over 500 years.
This work presents an architecture for a DNA-based archival storage system. It is structured as a key-value store, and leverages common biochemical techniques to provide random access. We also propose a new encoding scheme that offers controllable redundancy, trading off reliability for density. We demonstrate feasibility, random access, and robustness of the proposed encoding with wet lab experiments. Finally, we highlight trends in biotechnology that indicate the impending practicality of DNA storage.
Preparing Applications for Persistent Memory
Doug Voigt, Distinguished Technologist, Hewlett Packard Enterprise
New persistent memory technologies promise to revolutionize the way applications store data. Many aspects of application data access will need to be revisited in order to get full advantage of these technologies. The journey will involve several new types of libraries and ultimately programming language changes. In this session we will use the concepts of the SNIA NVM Programming Model to explore the emerging landscape of persistent memory related software from an application evolution point of view.
- Learn how applications can navigate the transitions created by persistent memory
- Learn about additional software and services that can help
Today’s Big Changes Are Just The Tip of the Iceberg
Jim Handy, General Director, Objective Analysis
Computer architecture is undergoing cataclysmic change. New flash tiers have been added to storage, and SSD caching has brought DAS back into servers. Storage Class Memory looms on the horizon, and with it come new storage protocols, new DIMM formats, and even new processor instructions. Meanwhile new chip technologies are phasing in, like 3D NAND flash and 3D XPoint Memory, new storage formats are being proposed including the Open-Channel SSD and Storage Intelligence, and all-flash storage is rapidly migrating into those applications that are not moving into the cloud. The future promises to bring us computing functions embedded within the memory array, learning systems permeating all aspects of computing, and adoption of architectures that are very different from today’s standard Von Neuman machines. In this presentation we will examine these technical changes and reflect on ways to avoid designing systems and software that limit our ability to migrate from today’s technologies to those of tomorrow.
Panel: Cloud Computing and Storage, Will Enterprises be All-in and When?
Moderator: Mark Carlson, Principal Engineer, Industry Standards, Toshiba
Panelists: Scott Sobhani, Cloud Constellation; Fredrik Forslund, Blancco Technology Group; Craig Dunwoody, GraphStream; Laz Vekiarides, ClearSky Data; Padmavathy Madhusudhanan, Wipro
Cloud Computing and Storage/Data is maturing but where are Enterprises in the adoption of the cloud? Are they increasingly adopting public cloud? Are they setting up their own private clouds? How successful are they in doing so?
This panel will discuss the issues these customers are facing and how various products, services and data management techniques are addressing those issues.
Panel: Solid State Storage, Persistent Memory - Harvesting the Wheat from the Chaff
Moderator: Wayne M. Adams, SNIA Chairman Emeritus
Panelists: Jim Handy, General Director, Objective Analysis; Peter Murray, Principal System Engineer, Virtual Instruments; Doug Voigt, Distinguished Technologist, Hewlett Packard Enterprise; Mat Young, VP Marketing, Netlist
Panel will discuss the trends of solid state storage, all flash arrays, and persistent memory. Panel will touch on topics including application development to leverage unique solid state storage and persistent memory features, considerations for workloads and performance, and data replication/protection. Industry specifications and work such as SNIA Performance Test Suite (PTS) and Non-Volatile Memory(NVM) will be positioned.
SAS: Today’s Fast and Flexible Storage Fabric
Rick Kutcipal, President, SCSI Trade Association; Product Planning and Architecture, Broadcom Limited
For storage professionals seeking fast, flexible and reliable data access, Serial Attached SCSI (SAS) is the proven platform for innovation. With a robust roadmap, SAS provides superior enterprise-class system performance, connectivity and scalability. This presentation will discuss why SCSI continues to be the backbone of enterprise storage deployments and how it continues to rapidly evolve by adding new features, capabilities, and performance enhancements. It will include an up-to-the-minute recap of the latest additions to the SAS standard and roadmaps, the status of 12Gb/s SAS deployment, advanced connectivity solutions, MultiLink SAS™, and 24Gb/s SAS development. Presenters will also provide updates on new SCSI features such as Storage Intelligence and Zoned Block Commands (ZBC) for shingled magnetic recording.
- Gain insight on how SAS continues to be the primary building block for advanced storage solutions.
- Hear the latest updates on the market adoption of 12Gb/s SAS and why it is significant.
- See high performance use case examples in a real-world environment such as distributed databases.
- See examples of how SAS is a potent connectivity solution especially when coupled with SAS switching solutions. These innovative SAS configurations become a vehicle for low cost storage expansion.
Under the Hood with NVMe over Fabrics
J Metz, R&D Engineer, SNIA ESF
Non-Volatile Memory Express (NVMe) has piqued the interest of many people in the storage world. Using a robust, efficient, and highly flexible transportation protocol for SSDs, Flash, and future Non-Volatile Memory storage devices, the NVM Express group is working on extending these advantages over a networked Fabric. We will explore not only what NVMe over Fabrics is, but also specifically pay attention to how it works.
- Key terms and concepts
- Architectural components
- Differences between NVMe-based fabrics and SCSI-based fabrics
- Practical examples of NVMe over fabrics solutions
- Important future considerations
Intro to Encryption and Key Management: Why, What and Where?
Eric Hibbard, CTO-Security and Privacy, HDS
This Tutorial will explore the fundamental concepts of implementing secure enterprise storage using current technologies, and will focus on the implementation of a practical secure storage system. The high level requirements that drive the implementation of secure storage for the enterprise, including legal issues, key management, current available technologies, as well as fiscal considerations will be explored. There will also be implementation examples that will illustrate how these requirements are applied to actual system implementations.
- Understand the legal issues that drive encryption requirements.
- Compare and contrast the various encryption implementation schemes.
- Understand the various means by which key management can be accomplished, as well as the common key management issues and implementation guidelines.
Multi-Vendor Key Management with KMIP
Tim Hudson, CTO & Technical Director, Cryptsoft Pty Ltd
Practical experience from implementing the OASIS Key Management Interoperability Protocol (KMIP) and from deploying and interoperability testing multiple vendor implementations of KMIP form the bulk of the material covered. Guidance will be provided that covers the key issues to require that your vendors address and how to distinguish between simple vendor tick-box approaches to standard conformance and actual interoperable solutions.
- In-depth knowledge of the core of the OASIS KMIP
- Awareness of requirements for practical interoperability
- Guidance on the importance of conformance testing
Implementing Stored-Data Encryption
Michael Willett, VP Marketing, Drive Trust Alliance
Data security is top of mind for most businesses trying to respond to the constant barrage of news highlighting data theft, security breaches, and the resulting punitive costs. Combined with litigation risks, compliance issues and pending legislation, companies face a myriad of technologies and products that all claim to protect data-at-rest on storage devices. What is the right approach to encrypting stored data?
The Trusted Computing Group, with the active participation of the drive industry, has standardized on the technology for self-encrypting drives (SED): the encryption is implemented directly in the drive hardware and electronics. Mature SED products are now available from all the major drive companies, both HDD (rotating media) and SSD (solid state) and both laptops and data center. SEDs provide a low-cost, transparent, performance-optimized solution for stored-data encryption. SEDs do not protect data in transit, upstream of the storage system.
For overall data protection, a layered encryption approach is advised. Sensitive data (eg, as identified by specific regulations: HIPAA, PCI DSS) may require encryption outside and upstream from storage, such as in selected applications or associated with database manipulations.
This tutorial will examine a ‘pyramid’ approach to encryption: selected, sensitive data encrypted at the higher logical levels, with full data encryption for all stored data provided by SEDs.
- The mechanics of SEDs, as well as application and database-level encryption
- The pros and cons of each encryption subsystem
- The overall design of a layered encryption approach
Self-Encrypting Storage for Consumers
Robert Thibadeau, CEO, Drive Trust Alliance
The emerging industry standard for stored-data encryption is Self-Encrypting Drive (SED), defined in Trusted Computing Group (TCG) specifications and now provided by all the drive manufacturers. SEDs are now 100% deployed in data center storage and all client drives are SED-enabled. But, adoption of SEDs in the consumer space is not yet 100%.
The Drive Trust Alliance (DTA) was formed as a member-driven alliance to promote adoption of SEDs in the consumer space. TCG is a member of DTA, as well as SED makers, SED management vendors, and I.T. organizations. Collectively, we are tackling the obstacles to SED adoption.
The inventor of the SED concept (Dr. Thibadeau), will introduce SEDs, summarize the mature history of SEDs, and highlight some of the DTA initiatives targeted at increasing SED adoption, such as open-source code for management of SEDs, pragmatic education, and particular focus on emerging markets for SEDs, such as IoT (Internet of Things) and the automobile of the future.
For example, the multiple storage systems on futuristic cars will contain information about the car owner, driver(s), and passengers. Such personal information will need strong privacy/security protections and robust erasure when the car is sold or retired. Your car is just one example of embedded consumer-based storage that demands SED-strength protection.
- Appreciate the advantages of self-encryption
- Learn the mission and objectives of the Drive Trust Alliance
- Introduction to the stored-data privacy/security challenges involved in consumer storage
- Highlight the need for self-encryption in IoT, automotive, and other consumer systems
- Observe specific consumer scenarios
Deploying Simple Secure Storage Systems
Chris Allo, Security Engineering Lead, Seagate LLC
This presentation is designed to take a user through the 3 most important basic areas of data storage that require security. These 3 areas can be highly vulnerable areas for customers in smaller to medium sized data storage deployments The goal is to show a simple entry level solution for customers that is several fold cheaper than large protection methods, while meeting acceptable corporate practices if a drive is lost, stolen, misplaced or needs to be re-purposed.
By combining existing methodologies of Key Management and SED (Self Encrypting Data) drive technology we can create a stand-alone secure data storage system.
Keeping the implementation simple provides an easily implementable model for customers and keeps the security model simple yet highly secure.
We currently have a customer we are working with that we can show is an actual example of this type of implementation.
- Smash and Grab security
- Secure drive erasure
- Key Managment principles
Software Defined Storage
Storage on Your Terms: Deep Dive Into Software-Defined Storage Technologies
Michael Letschin, Field CTO, Nexenta Systems, Inc.
Software-Defined Storage (SDS) means different things to different people, with solutions ranging from do it yourself to full-fledged scale up and scale out architectures, the landscape can seem blurry and confusing. This session aims to eliminate the confusion on what all these terms mean by mapping each style of SDS with a corresponding environment. These solutions include the use of virtual server based solutions, containers, bare metal installs and even hyper-converged. Regardless of vertical or company size, from branch offices through the largest enterprise, the right Software-Defined Storage strategy can put you back in control and help you gain unmatched levels of flexibility, scalability, performance, and cost efficiency.
- Learn the different kinds of SDS available
- Determine what SDS solution fits your enterprise need
- Be able to do a cost justification for the future storage in the datacenter
Storage Virtualization in Modern Data Centers
Farid Yavari, VP of Technology, FalconStor
IT is undergoing a radical change. Instant provisioning of resources & complete flexibility of infrastructure is the new standard. The maturity of public cloud offerings is pressuring organizations to become more cost effective. These challenges are the force behind innovation in the DC, driving agility, density & flexibility. The agility & service model of provisioning IT infrastructure has started a wave of virtualization in data centers with software driven management & orchestration. The virtualization of compute through VMs & implementation of (SDN) has solved some of the issues around compute & network flexibility. Storage virtualization enable deployment of commodity hardware, coupled with an intelligent software layer to provide data services. Improving (TCO) through optimization of resource utilization & using lower cost hardware platforms in enterprise solutions plays an integral role in driving efficiency at scale. Deploying an intelligent storage abstraction layer that provides data services & that adapts to various modern workloads is needed to solve the challenges of managing unprecedented data growth today.
How can we remove the complexity & resource drain to enable the enterprise to benefit from storage virtualization while aggregating all data services within a single software-defined platform for storage environments including – physical, virtual, active, inactive, current, legacy – to protect, manage, & leverage business information in the evolving DC?
- Enable organizations to simplify and converge data services, existing resources and infrastructure
- Virtualize storage to enable the efficient movement of data to, from and across storage workloads
- The importance of a unified intelligent abstraction layer in virtual environments
- The importance of being able to virtualize and deliver unified data services
SDS in Practice at Mission Community Hospital
Ibrahim Rahmani, Director of Product and Solutions, DataCore Software
IT in healthcare organizations face many challenges in supporting high-quality medical services. Regulations, the move to electronic records and more sophisticated imaging systems have skyrocketed the amount of data related to patients. In addition, IT has to maintain continuous operations around the clock and deliver the application performance needed by clinicians and staff.
In this session, learn how Mission Community Hospital used Software-defined Storage (SDS) to safeguard patient data, store optimally all medical information and accelerate access to applications involved in patient care.
Among the benefits MCH has seen from SDS are:
- Over 2 years of 24x7x365 operations without any data outages
- 87% reduction in the amount of time to provision additional storage
- Up to 5x performance increase for their PACS systems
- How this customer realized 87% of reduction in the amount of time to provision additional storage
- How this customer achieved 5x performance increase
- How tihs customer saw "Zero" downtime in the last 2 years
Solid State Storage
An Examination of User Workloads for SSDs
Eden Kim, CEO, Calypso Testers
SSD performance depends on the type of workload applied to the storage, i.e. performance depends on the application workload. In this survey, we examine various real world user workloads for both client and enterprise applications. See how different workloads affect SSD performance. See the impact of data reduction, virtualization, encryption and other in-line and SSD based optimizations.
- What are realworld workloads
- What affects workloads
- How do different workloads affect perfromance
Increasing SSD Performance and Lifetime with Multi-stream Technology
Changho Choi, Principal Engineer, Samsung Semiconductor, Inc.
NAND Flash Solid-State Drives(SSDs) are increasingly deployed because of their high IOPS performance and low power consumption. However, one SSD drawback is that, as a SSD continually writes data, valid data can fragment across the NAND flash medium. To reclaim space within data storage blocks containing invalid (obsoleted) data, Garbage Collection activity first relocates valid data to other data blocks and then completely erases the original data blocks. Garbage Collection decreases performance and increases Write Amplification. With multi-stream recently adopted as a T10 SCSI standard, Garbage Collection can be completely eliminated or reduced by storing associated (similar update frequency) data in the same data block. This helps avoid NAND Flash erase block fragmentation for data having the same update frequency. As a result of the decreased write amplification, storage systems exhibit improved read/write performance and longer SSD device lifetimes when exploiting multi-stream methods.
- Multi-stream concepts and operation
- Understanding multi-stream benefits (improved performance and lifetime of SSD)
- Data center application use cases
Storage Class Memory
Planning for Persistent Memory in the Data Center
Sarah Jelinek, Senior SW Engineer, Intel Corp
Persistent memory is a disruptive technology that will require a lot of thought for integration into the data center. What is persistent memory and why does it matter? How will enterprise applications leverage this resource? How will middleware, libraries and run-time application environments change? Sarah will discuss the basics of persistent memory along with how we are making use of persistent memory using load/store access with NVML. Sarah will describe use cases for load/store accessible NVM, some transparent to applications, others non-transparent. And finally, Sarah will discuss where persistent memory is leading us.
- What is persistent memory?
- How will enterprise applications make use of this new technology?
- What future do we envision for persistent memory?
Emerging Non Volatile Memory and Spin Logic
Edward Grochowski, Consultant, Self Employed
Jim Handy, General Director, Objective Analysis
The requirement for high density storage products to meet the expanding amounts of data predicted for this decade and extending well into the next has prompted investigations into alternative technologies which include STT RAM , ReRAM and PCRAM. The cost, reliability and availability of these technologies and their performances continue to encourage product development within the industry. The potential of these NVM products can be thought of as extending far beyond individual devices into massive storage arrays which can be well integrated into new computer architectures. These products exhibit power saving as well as performance characteristics which affect the very nature of computer designs both for memory, logic and storage. This presentation will describe these NV technologies and propose how they may change conventional thinking on how the future could apply these. A bridge between today’s memory and storage products and early NVM applications will be discussed as a demonstration of future projections.
- Spin Logic
Prescriptive Analytics in the NVM Technology
Olga Buchonina, CEO, ProstoLabs
We will discuss the topics of how to use prescriptive analytics approach to provide insights and predict/forecast the behavior of the integrated solutions. How to merge IoT and Enterprise solutions and bring them to the Business Enterprise solutions. The focus will be on the NVM technogy and the Application stack from NVM HW application->Data Collection and Processing-> Business Platform-> Application. We will show how adopting NVM technology allows to increase the revenue stream of the company
- Combining Data Analytics and NVM Technology
- Understanding of the an entire stack which affects data processing
Introduction to Swordfish: Scalable Storage Management
Richelle Ahlvers, Principal Storage Management Architect, Broadcom
The SNIA’s Scalable Storage Management Technical Work Group (SSM TWG) is working to create and publish a new open industry standard specification for storage management called Swordfish. Swordfish defines a customer centric interface for the purpose of managing storage and related data services. Swordfish builds on the DMTF’s Redfish specification’s using RESTful methods and JSON formatting.
This session will present an overview of Swordfish, including the scope targeted in the initial (V1) release in 2016, as well as the rationale for this effort. This session will also provide the positioning of the specification developed by the SSM TWG vs legacy storage management standards. It will also highlight how Swordfish leverages and extends existing storage management standards (e.g. SMI-S) as well as the base Redfish specification.
- Introduce the audience to emerging standards for storage management
- Provide a clear differentiation between SMI-S and the new standards
- Present a timeline for expected storage functionality to be developed and integrated
Best Practices for Enterprise-Wide Data Protection and Compliance
Kurt Kuckein, Product Manager, DataDirect Networks
Today’s global enterprises are challenged with protecting a growing amount of information living outside of the data center. Secure data sharing and efficient backup throughout an enterprise poses many challenges, from practical capacity and bandwidth considerations to policy and regulatory compliance issues. Rapid data growth and ever-increasing workforce mobility are accelerating these challenges exponentially.
Various software and hardware components in the marketplace claim to solve secure data sharing and endpoint backup protection challenges, but most actually address only a fraction of the problem and require IT teams to source multiple products from multiple vendors without the benefit of joint expertise or support.
This presentation will explore new approaches to enterprise data protection and compliance.
- How to address the massive scalability challenges of data sprawl.
- Why object storage i provide secure cloud collaboration and file sharing across the enterprise.
- How to reduce overall company-wide cost, complexity and risk.
- How to enable secure productivity from personal devices with Anytime, Anywhere, Any Device access
- How to reduce liability and protect data to be compliant with company policies and regulations.
Benefits of 25, 40 and 50GbE Networks for Ceph and Hyperconverged Infrastructure
John Kim, Director, Storage Marketing, Mellanox Technologies
New NICs and switches in 2016 are supporting 25, 50, and 100GbE networking speedsf, in addition to traditional 10Gb and 40Gb Ethernet. Analysts predict 25GbE will be adopted more rapidly than any other Ethernet speed standard. These new Ethernet speeds accelerate performance of software-defined storage including Ceph and various hyperconverged infrastructure solutions. Learn how 25, 40, 50, and 100Gb Ethernet increases the performance and lowers the cost of software-defined storage deployments.
- Understand how 25, 50, and 100GbE network links work
- Learn why 25GbE adoption is projected to be faster than any other Ethernet speed
- See how 25, 40, 50 and 100GbE links accelerate Ceph
- See how 25, 40, and 50GbE links accelerate hyperconverged infrastructure
- Understand how 25, 50 and 100GbE networking lowers the cost of storage deployments
Networking Flash Storage? – Fibre Channel was Always the Answer
Mark Jones, President, FCIA, Director of Technical Marketing and Performance, Broadcom Limited - ECD, Fibre Channel Industry Association
Fibre Channel has been the ubiquitous connection of choice for connecting storage within the datacenter for nearly twenty years. The start of the sixth generation is being celebrated this year by introducing a staggering leap in performance and new features. We will discuss why Fibre Channel holds the enduring popularity it has as well as an in-depth look at the new Gen 6 features and what the future holds. We will discuss how Fibre Channel fits in with key datacenter initiatives such as virtualization, the pervasive adoption of SSD’s/Flash and the movement towards cloud architectures.
- Introduce the audience to the updated Fibre Channel Technology Roadmap. This document serves as a reliable guide for suppliers, manufacturers and distributors of products to plan.
- Specific use cases will be discussed that illustrate how deploying Gen6 Fibre Channel today can accelerate I/O performance hungry applications even in your existing SAN infrastructure.
- Educate attendees on the backward compatibility nature of Fibre Channel with no user intervention required.
Demonstrating NVMe Over Fabrics Performance on Ethernet Fabrics
Rob Davis, VP of Storage Technology, Mellanox Technologies
NVMe Over Fabrics has been a hot topic since late 2014, but both the standard and community drivers have been in development until recently. Both vendors and customers have been exploring what kind of throughput, IOPS and latency may be possible with this new storage protocol. Attend this presentation to see the latest performance numbers showing NVMe running over Ethernet fabrics of different types, and learn how this new protocol leverages RDMA.
- Learn how NVMe Over Fabrics actually performs compared to local NVMe devices
- See how different Ethernet fabrics can support this new storage protocol
- Learn details of how the NVMe Over Fabrics protocol integrates with RDMA
- Understand how using 25, 40, 50, and 100GbE links affects NVMe Over Fabrics performance
Breaking the limitations of captive NVMe storage – 18M IOPs in 2u
Bob Hansen, V.P. Systems Architecture, Apeiron Data Systems
NVMe is quickly replacing SATA and SAS as the native interface of choice for direct attached server storage. This presentation will discuss a new, innovative storage networking solution for the next generation NVM technologies. The talk will provide an overview of a highly scalable, Ethernet based storage networking architecture designed for next generation NVM SSD’s with latencies of < 10 µs. This solution delivers double the performance of in-server SSDs while providing all of the benefits of external, virtualized, shared storage.
- Understand how very high performance NVMe SSDs enable next gen scale out applications
- Understand the limitations of “captive” (in the server) storage solutions
- Review storage networking requirements that support next gen NVM storage technology.
- Understand how a new, world class, Ethernet based, external NVMe storage architecture can deliver
Application Advantages of NVMe over Fabrics – RDMA and Fibre Channel
Brandon Hoff, Director, Product Management, Broadcom
NVMe is being adopted inside the server to unlock the performance of solid state drives as well as newer persistent memory solutions. The next logical step is to leverage the optimized NVMe over fabrics to extend and improve application performance with large amounts of networked storage. NVMe over Fibre Channel (FC-NVMe) and NVMe over RDMA standards are under definition and generating market interest. These new standards bring the performance, built-in congestion management, and ease of use that Fibre Channel brings to Enterprise Datacenters. In this presentation, we will discuss:
- NVMe adoption trends from the disk driver to the storage array
- Key features of high performance networked storage arrays
- NVMe over FC plug-in-play with current FC lossless networks
- Application advantages of leveraging NVMe over Fibre Channel
- Comparison of NVMe over Fibre Channel and NVMe over RDMA
Workload Acquisition for the Enterprise Data Center
Peter Murray, Principal System Engineer, Virtual Instruments
For years, IT architects have sought a way to ensure that an application will operate properly at scale on a particular storage array and network infrastructure. Increasingly, they need to ensure that multiple applications can safely run at peak loading on an All Flash or Hybrid infrastructure. The goal is to optimize the cost of storage deployments and to assure performance scalability once deployed in production.
- How to determine what the I/O data traffic related to an enterprise application looks like from the perspective of the network infrastructure between application servers and storage arrays.
- How the application I/O workload can be modeled to accurately represent the application in production by using storage analytics or vendor performance statistics to generate a synthetic workload model
- How a statistical application model can be used to validate both array and network performance at varying traffic levels and rates to rapidly test “what if” scenarios.
- How multiple application models can be combined to determine appropriate throughput, IOPS, and response time levels on a given array
- How using these models can enable enterprises to cost-effectively test, confidently deploy, configure, maintain and troubleshoot networked storage infrastructure
Delivering Predictable Storage Performance in a Virtualized Environment
Vince LaPaglia, Senior Storage Engineer, Pivot3
Whether you’re considering an all-flash or hybrid storage array, you should expect fast, predictable performance. However, two common obstacles – latency spikes and resource contention –can impact hybrid and all-flash array performance, causing applications to not meet their service levels. Storage Quality of Service (QoS) functionality is now considered a ‘must have’ feature for delivering predictable, consistent performance in flash-based arrays. What’s more, the value of Storage QoS reaches well beyond managing performance; it applies to many types of data services including data protection, security/encryption and data placement.
This presentation will discuss the benefits of QoS in providing consistent performance for mission-critical applications and why it’s important to understand the value and power this emerging capability can offer.
- What Storage QoS is and why it should be considered for both all-flash and hybrid arrays.
- How to consolidate more workloads and guarantee consistent performance for mission-critical apps
- How policy-based QoS can make delivering predictable performance to multiple apps a simple task.
- How QoS managed capabilities such as automated data placement enable customers to meet SLAs
100G iSCSI — A Bright Future for Ethernet Storage
Tom Reu, Consulting Application Engineer, Chelsio
Over the years, iSCSI has not been the choice for storage projects for a variety of reasons. Some consider it slow because of the believe that the only implementations are in software. Some consider it not ready for the enterprise. This talk will discuss enhancements to the iSCSI and networking architecture that will get you thinking differently about iSCSI. In addition, with 100G Ethernet, iSCSI’s future is brighter than ever.
Learn Your Alphabet - SRIOV, NPIV, RoCE, iWARP - to Pump Up Virtual Infrastructure Performance
Dennis Martin, President, Demartek
In an increasingly virtualized server environment, new technologies have emerged that help accelerate the performance of applications within those virtual machines as they connect to external storage or external networks. What do these acronyms mean, where should they be used and what kinds of improvements should be expected? In this session, Dennis Martin explains the concepts involved and shows examples of how these technologies can improve performance of storage and networking in VMware, Hyper-V and even on physical machines.