Designing elastic storage architectures leveraging distributed NVMe. Your network becomes your storage!

Similar documents
SOFTWARE-DEFINED BLOCK STORAGE FOR HYPERSCALE APPLICATIONS

MicroTerabyte - NVMesh - Oracle RAC Reference Architecture

Oracle Exadata: Strategy and Roadmap

Next-Generation NVMe-Native Parallel Filesystem for Accelerating HPC Workloads

VMware Virtual SAN Technology

Annual Update on Flash Memory for Non-Technologists

Lenovo - Excelero NVMesh Reference Architecture

Evolution of Rack Scale Architecture Storage

Was ist dran an einer spezialisierten Data Warehousing platform?

Delivering High-Throughput SAN with Brocade Gen 6 Fibre Channel. Friedrich Hartmann SE Manager DACH & BeNeLux

New Approach to Unstructured Data

Top 5 Reasons to Consider

NVMe Direct. Next-Generation Offload Technology. White Paper

VEXATA FOR ORACLE. Digital Business Demands Performance and Scale. Solution Brief

NVMe over Fabrics. High Performance SSDs networked over Ethernet. Rob Davis Vice President Storage Technology, Mellanox

Hitachi Virtual Storage Platform Family: Virtualize and Consolidate Storage Management

SoftFlash: Programmable Storage in Future Data Centers Jae Do Researcher, Microsoft Research

Chelsio Communications. Meeting Today s Datacenter Challenges. Produced by Tabor Custom Publishing in conjunction with: CUSTOM PUBLISHING

DataON and Intel Select Hyper-Converged Infrastructure (HCI) Maximizes IOPS Performance for Windows Server Software-Defined Storage

Implementing SQL Server 2016 with Microsoft Storage Spaces Direct on Dell EMC PowerEdge R730xd

DDN. DDN Updates. DataDirect Neworks Japan, Inc Nobu Hashizume. DDN Storage 2018 DDN Storage 1

DDN. DDN Updates. Data DirectNeworks Japan, Inc Shuichi Ihara. DDN Storage 2017 DDN Storage

Dell EMC Isilon All-Flash

FlashGrid Software Enables Converged and Hyper-Converged Appliances for Oracle* RAC

Optimizing the Data Center with an End to End Solutions Approach

Composable Infrastructure for Public Cloud Service Providers

MODERNISE WITH ALL-FLASH. Intel Inside. Powerful Data Centre Outside.

Oracle Database Exadata Cloud Service Exadata Performance, Cloud Simplicity DATABASE CLOUD SERVICE

Storage Designed to Support an Oracle Database. White Paper

Flash In the Data Center

Red Hat Ceph Storage and Samsung NVMe SSDs for intensive workloads

From Rack Scale to Network Scale: NVMe Over Fabrics Enables Exabyte Applica>ons. Zivan Ori, CEO & Co-founder, E8 Storage

Key Technology Trends, Marketplace Drivers, & AFA Rankings Jerome M. Wendt President & Founder Ken Clipperton Lead Analyst, Storage

RIDESHARING YOUR CLOUD DATA CENTER Realize Better Resource Utilization with NVMe-oF

The Datacentered Future Greg Huff CTO, LSI Corporation

By John Kim, Chair SNIA Ethernet Storage Forum. Several technology changes are collectively driving the need for faster networking speeds.

Leveraging the power of Flash to Enable IT as a Service

NVMe over Universal RDMA Fabrics

Interface Trends for the Enterprise I/O Highway

WHITE PAPER QUANTUM S XCELLIS SCALE-OUT NAS. Industry-leading IP Performance for 4K, 8K and Beyond

HPE Synergy HPE SimpliVity 380

Hewlett Packard Enterprise HPE GEN10 PERSISTENT MEMORY PERFORMANCE THROUGH PERSISTENCE

RIDESHARING YOUR CLOUD DATA CENTER Realize Better Resource Utilization with NVMe-oF

Scaling Internet TV Content Delivery ALEX GUTARIN DIRECTOR OF ENGINEERING, NETFLIX

DELL EMC VXRACK FLEX FOR HIGH PERFORMANCE DATABASES AND APPLICATIONS, MULTI-HYPERVISOR AND TWO-LAYER ENVIRONMENTS

Dell EMC All-Flash solutions are powered by Intel Xeon processors. Learn more at DellEMC.com/All-Flash

G2M Research Fall 2017 NVMe Market Sizing Webinar

Fast and Easy Persistent Storage for Docker* Containers with Storidge and Intel

vsan Mixed Workloads First Published On: Last Updated On:

Cisco HyperFlex HX220c M4 and HX220c M4 All Flash Nodes

IME (Infinite Memory Engine) Extreme Application Acceleration & Highly Efficient I/O Provisioning

Expand In-Memory Capacity at a Fraction of the Cost of DRAM: AMD EPYCTM and Ultrastar

Nutanix Tech Note. Virtualizing Microsoft Applications on Web-Scale Infrastructure

Pocket: Elastic Ephemeral Storage for Serverless Analytics

Pivot3 Acuity with Microsoft SQL Server Reference Architecture

What s New in VMware vsphere 4.1 Performance. VMware vsphere 4.1

Mellanox InfiniBand Solutions Accelerate Oracle s Data Center and Cloud Solutions

Modern hyperconverged infrastructure. Karel Rudišar Systems Engineer, Vmware Inc.

Toward a Memory-centric Architecture

HP visoko-performantna OLTP rješenja

Evaluation Report: HP StoreFabric SN1000E 16Gb Fibre Channel HBA

Lenovo Database Configuration for Microsoft SQL Server TB

Virtualized SQL Server Performance and Scaling on Dell EMC XC Series Web-Scale Hyper-converged Appliances Powered by Nutanix Software

SUPERMICRO, VEXATA AND INTEL ENABLING NEW LEVELS PERFORMANCE AND EFFICIENCY FOR REAL-TIME DATA ANALYTICS FOR SQL DATA WAREHOUSE DEPLOYMENTS

INTEL NEXT GENERATION TECHNOLOGY - POWERING NEW PERFORMANCE LEVELS

Software Defined Storage at the Speed of Flash. PRESENTATION TITLE GOES HERE Carlos Carrero Rajagopal Vaideeswaran Symantec

Leveraging Software-Defined Storage to Meet Today and Tomorrow s Infrastructure Demands

ACCELERATE YOUR ANALYTICS GAME WITH ORACLE SOLUTIONS ON PURE STORAGE

NVMFS: A New File System Designed Specifically to Take Advantage of Nonvolatile Memory

NVMe Over Fabrics (NVMe-oF)

HPE Strategy for VMware Cloud Foundation

Taking Hyper-converged Infrastructure to a New Level of Performance, Efficiency and TCO

Oracle Exadata Statement of Direction NOVEMBER 2017

QLogic/Lenovo 16Gb Gen 5 Fibre Channel for Database and Business Analytics

Architecting For Availability, Performance & Networking With ScaleIO

Next Generation Data Center : Future Trends and Technologies

The Data-Protection Playbook for All-flash Storage KEY CONSIDERATIONS FOR FLASH-OPTIMIZED DATA PROTECTION

Highly Scalable, Non-RDMA NVMe Fabric. Bob Hansen,, VP System Architecture

Lenovo Database Configuration

NetApp AFF A300 Gen 6 Fibre Channel

Create a Flexible, Scalable High-Performance Storage Cluster with WekaIO Matrix

Copyright 2012 EMC Corporation. All rights reserved.

IaaS Vendor Comparison

TITLE. the IT Landscape

SurFS Product Description

Maximizing Fraud Prevention Through Disruptive Architectures Delivering speed at scale.

Solid State Storage is Everywhere Where Does it Work Best?

Designing Next Generation FS for NVMe and NVMe-oF

NVM Express Awakening a New Storage and Networking Titan Shaun Walsh G2M Research

Isilon: Raising The Bar On Performance & Archive Use Cases. John Har Solutions Product Manager Unstructured Data Storage Team

Paperspace. Architecture Overview. 20 Jay St. Suite 312 Brooklyn, NY Technical Whitepaper

STORAGE NETWORKING TECHNOLOGY STEPS UP TO PERFORMANCE CHALLENGES

Flash Storage with 24G SAS Leads the Way in Crunching Big Data

Opportunities from our Compute, Network, and Storage Inflection Points

Virtual WAN Optimization Controllers

The PowerEdge M830 blade server

FAST SQL SERVER BACKUP AND RESTORE

Copyright 2012, Oracle and/or its affiliates. All rights reserved.

Data Movement & Tiering with DMF 7

Optimizing Tier-1 Enterprise Storage for Solid State Memory

Transcription:

Designing elastic storage architectures leveraging distributed NVMe Your network becomes your storage!

Your hosts from Excelero 2 Yaniv Romem CTO & Co-founder Josh Goldenhar Vice President Product Management

FINALISTS 3 Excelero s NVMesh Named 2017 Product of the Year in Software- Defined Storage by Storage Magazine and SearchStorage

Elastic Storage Trends & Enablers 4 Modern, scale-out applications require Elastic storage to optimize for performance, scale, cost NVMe SSD performance and density are evolving rapidly but capabilities are underutilized Server SAN enables maximum utilization of high-performance flash over the network

Excelero Delivers Future-Proof Block Storage 5 What? NVMesh Server SAN is high-performance, software-defined block storage. It pools NVMe drives on standard servers; utilizing NVMf or RDDA to add SAN functionality such as: Centralized management and provisioning GUI and RESTful interfaces Logical Volumes Data Protection and Multi-pathing Drive and Host failure recovery Multi-attach LUNs for clustered file systems

What is NVMesh server SAN? 6 NVMesh allows unmodified applications to utilize pooled NVMe storage devices across a network at local speeds and latencies. Distributed NVMe storage resources are pooled with the ability to create arbitrary, dynamic block volumes that can be utilized by any host running the NVMesh block client.

NVMesh Software Hierarchy 7 NVMesh software-defined storage separates the data plane, control plane and management plane.

NVMesh Software Components 8

Unique Client-side Architecture 9

NVMe Deployment Challenges 10 Local Storage in Application Server Storage is Centralized NVMesh Target Module NVMesh Target Module Intelligent Client Block Driver Intelligent Client Block Driver Storage is unified into one pool NVMesh Target Module & Intelligent Client Block Driver run on all nodes NVMesh bypasses server CPU Linearly scalable Storage is unified into one pool NVMesh Target Module runs on storage nodes Intelligent Client Block Driver runs on server nodes Applications get performance of local storage

What Makes NVMesh Unique? Server SAN Elastic NVMe Zero-CPU 100% SDS, leveraging standard servers and next generation storage & networking components Pools NVMe storage across a network at local speeds and latencies Enables 100% converged infrastructure Virtual Array Deployed as a virtual, distributed non-volatile array and supports both converged and disaggregated architectures Client-side, distributed Architecture Enables NVMe sharing that scales performance linearly at near 100% efficiency 11

NVMesh & Intel NVMe

Test Environment 13

Test Results 14

Test Results 15

Industries & Applications

Web Monsters: Hyperscale Web & Cloud 17 Hyperscale Use Cases Artificial Intelligence Operational Analytics Databases Containers and Orchestration Real-time Analytics Intrusion Detection

High-Performance For Databases 18 Industries: Hyperscale Web & Cloud, Enterprise NVMesh eliminates traditional SAN bottlenecks by leveraging low-latency, highperformance NVMe for the server to storage system attachment. NVMesh is optimized for both transactional I/O activity along with low latency, as well as for large bandwidth data transfers. As existing servers and storage can do more work instance, the licensing cost per transaction is reduced drastically.

Customer Success Case Studies

Customer Success Customer Success Any-K Storage 4K streaming @ 60fps to 50+ workstations concurrently Use Case Any-K production & post-production Streaming, editing and reel presentation to simultaneously active workstations Problem 4K & 8K video is changing requirements for storage performance and capacity Workstations need high BW & low latency performance for streaming, editing and reel presentation Customers need future-proof solutions that will support 10k Solution With just 6 standard servers powered by 3D NAND, NVMesh enabled 4K streaming @ 60fps to 50+ workstations concurrently The solution gives twice the performance of competing solutions at 50% of the cost and requires a much lower data center footprint

Customer Success Customer Success Pooling NVMe Within GPFS NSDs enables new Science use cases Use Case 80 pooled NVMe devices give 250GB/s of throughput and 20M random 4k IOPS Large-scale modeling, simulation, analysis and visualization Visualizes supercomputer simulation data on 100s of compute nodes Problem Finish check pointing faster and start running the job. Achieve performance of 250GB/Sec at the lowest price Solution NVMesh by Excelero enables SciNet to create a petabyte-scale unified pool of high-performance flash distributed retaining the speeds and latencies of directly-attached media

Customer Success Customer Success High throughput & low latency for Oracle databases Use Case Running Oracle faster than Oracle does Cluster performance is a key priority for large Oracle environments, especially for customers with tables that size up to billions rows and serve thousands of users driving analytics against that data Problem Traditional AFA storage solutions give latencies of slightly less than 1 millisecond; customers often get thousands of queries a day and some of these can take over an hour to run. Solution NVMesh offers latencies of single digit microseconds. This significantly speeds up database scans and queries Running Oracle database on NVMesh enables customers to reduce the number of licenses needed for their clusters.

Questions? 23

Thank you!