RED HAT STORAGE PORTFOLIO OVERVIEW

Andrew Hatfield Practice Lead – and Big Data MILCIS – November 2015 THE STORAGE MISSION To offer a unified, open -defined storage portfolio that delivers a range of data services for next generation workloads thereby accelerating the transition to modern IT infrastructures. THE FUTURE OF STORAGE

Traditional Storage Open, Software-Defined Storage Complex proprietary silos Standardized, unified, open platforms

USER USER USER ADMIN USER e c e r Control Plane (API, GUI) r u a o w S

t f n o e S ADMIN ADMIN ADMIN p

O Gluster +++

Custom GUI Custom GUI Custom GUI e d

r Standard r a Proprietary Software Proprietary Software Proprietary Software a d w n d Computers r a t a S Proprietary Proprietary Proprietary H and Disks Hardware Hardware Hardware WHY BOTHER?

PROPRIETARY Common, off-the-shelf hardware HARDWARE Lower cost, standardized supply chain

SCALE-UP Scale-out architecture ARCHITECTURE Increased operational flexibility

HARDWARE-BASED Software-based intelligence INTELLIGENCE More programmability, agility, and control

CLOSED DEVELOPMENT Open development process PROCESS More flexible, well-integrated technology THE JOURNEY

Open Software-Defined Storage is a fundamental reimagining of how storage infrastructure works.

It provides substantial economic and operational ??? advantages, and it has quickly become ideally suited for a growing number of use cases. ???

Containers

Hyper- Convergence

Analytics Cloud Native Apps Cloud Infrastructure

TODAY EMERGING FUTURE THE RED HAT STORAGE PORTFOLIO THE RED HAT STORAGE PORTFOLIO

Share-nothing, scale-out architecture provides durability

E and adapts to changing demands C E R R U A O W

S Ceph Gluster T

F N management management O E S P Self-managing and self-healing O Ceph Gluster features reduce operational overhead data services data services

Standards-based interfaces and full APIs ease integration with applications and systems E D R R A A W D D N R A T A Supported by the S H experts at Red Hat OVERVIEW: RED HAT CEPH STORAGE

Powerful distributed storage for the cloud and beyond

Built from the ground up as a next-generation storage system, based on years of research and suitable for powering infrastructure platforms

Highly tunable, extensible, and configurable, with policy-based control and no single point of failure TARGET USE CASES Cloud Infrastructure Offers mature interfaces for block and object ● VM Storage with OpenStack Cinder, storage for the enterprise Glance & Nova ● Object storage for tenant apps Rich Media and Archival ● S3-compatible object storage Customer Highlight: Cisco Cisco uses Red Hat Ceph Storage to deliver storage for next-generation cloud services OVERVIEW: RED HAT GLUSTER STORAGE

Nimble file storage for petabyte-scale workloads

Purpose-built as a scale-out file store with a straightforward architecture suitable for public, private, and hybrid cloud

Simple to install and configure, with a minimal hardware footprint TARGET USE CASES Analytics Offers mature NFS, SMB and HDFS interfaces ● Machine analytics with Splunk for enterprise use ● Big data analytics with Hadoop

Enterprise File Sharing ● Media Streaming Customer Highlight: Intuit ● Active Archives Intuit uses Red Hat Gluster Storage to provide Enterprise Virtualization flexible, cost-effective storage for their industry- leading financial offerings. Rich Media & Archival GROWING INNOVATION COMMUNITIES

78 AUTHORS/mo

1500 COMMITS/mo ● Contributions from Intel, SanDisk, SUSE,and DTAG.

● Presenting Ceph Days in cities around the world and quarterly virtual Ceph Developer Summit events. 258 POSTERS/mo

41 AUTHORS/mo

● Over 11M downloads in the last 12 months 259 COMMITS/mo

● Increased development velocity, authorship, and discussion has resulted in rapid feature expansion. 166 POSTERS/mo PARTNER SOLUTIONS

All-flash arrays, optimized for Ceph Systems designed with storage in mind Accelerating software-defined storage

SanDisk sells the InfiniFlash storage arrays, Supermicro's Red Hat Ceph Storage Through silicon innovation and software designed for use with Red Hat Ceph Storage. optimized solutions offer durable, software- optimization, Intel pushes the envelope on Optimizations contributed by SanDisk deliver defined, scale-out storage platforms in open, software-defined storage. A key high performance which allow Ceph 1U/2U/4U form factors and are designed to contributor, Intel recently donated significant customers to service new workloads. maximize performance, density, and capacity hardware to the Ceph project.

Our relationship includes: Customer can expect to see: Intel development efforts have included:

● Engineering and product collaboration ● Reference architectures, validated for ● SSD and performance optimizations

● Community thought leadership performance, density, and capacity ● CephFS development

● Whitepapers and datasheets that support Red Hat Storage solutions RED HAT STORAGE TARGET WORKLOADS DIFFERENT KINDS OF STORAGE

CAPACITY PERFORMANCE

Object OpenStack

N storage E G - T Sync and DBaaS X

E share Hyper- N convergence

Analytics

VMWare

Enterprise

L file sharing A N O I T I D A R T FOCUSED SET OF USE CASES

Big Data analytics with Hadoop ANALYTICS Machine data analytics with Splunk

CLOUD Virtual machine storage with OpenStack

INFRASTRUCTURE Object storage for tenant applications

RICH MEDIA Cost-effective storage for rich media streaming AND ARCHIVAL Active archives

SYNC AND SHARE File sync and share with ownCloud

ENTERPRISE Storage for conventional VIRTUALIZATION virtualization with RHEV BIG DATA ANALYTICS

HADOOP MAP REDUCE FRAMEWORK

In-place Hadoop analytics in a POSIX compatible environment

Hadoop Distributed Red Hat Gluster Storage Cluster

FEATURES BENEFITS

● Allows the Hortonworks Data Platform 2.1 to be ● Flexible, unified enterprise big data repository deployed on Red Hat Gluster Storage ● Better analytics (Hadoop and non-Hadoop) ● Hadoop tools can operate on data in-place ● Familiar POSIX-compatible file system and tools ● Access to the Hadoop ecosystem of tools ● Start small, scale as big data needs grow ● Access to non-Hadoop analytics tools ● Multi-volume support (HDFS is single-volume) ● Consistent operating model: Hadoop can run directly ● Unified management (Hortonworks HDP Ambari on Red Hat Gluster Storage nodes and Red Hat Gluster Storage) MACHINE DATA ANALYTICS

Hot/warm data optimized for performance

High-performance, scale-out, online 10s of TB on Splunk server DAS cold storage for Splunk Enterprise Cold optimized for cost, capacity and elasticity

Red Hat Storage Server on commodity x86 servers

FEATURES BENEFITS

● Multiple ingest options using NFS & FUSE ● Run high speed indexing and search on ● Expand storage pools without incurring downtime Splunk’s cold data store ● ● Support for both clustered and non-clustered Pay as you grow economics for Splunk cold data configurations ● Reduce ingestion time for data with standard protocols ● “Always online”, fast, disk-based storage pools provide constant access to historical data VIRTUAL MACHINE STORAGE

OPENSTACK

Glance Nova Keystone API Swift API Cinder API API API The most widely deployed 1 technology for OpenStack storage CEPH OBJECT GATEWAY CEPH BLOCK DEVICE (RGW) (RBD)

CEPH STORAGE CLUSTER (RADOS)

FEATURES BENEFITS

● Full integration with Nova, Cinder and Glance ● Provides both volume storage and ● Single storage for images and ephemeral and object storage for tenant applications persistent volumes ● Reduces provisioning time for new virtual machines ● Copy-on-write provisioning ● No data transfer of images between storage and ● Swift-compatible object storage gateway compute nodes required ● ● Full integration with Red Hat Enterprise Unified installation experience with Red Hat OpenStack Platform Enterprise Linux OpenStack Platform

1 http://superuser.openstack.org/articles/openstack-users-share-how-their-deployments-stack-up STORAGE FOR TENANT APPLICATIONS

OPENSTACK

APP APP APP APP Unstructured data storage for S3 API S3 API S3 API S3 API distributed, cloud-native CEPH OBJECT GATEWAY CEPH OBJECT GATEWAY applications (RGW) (RGW)

RED HAT CEPH STORAGE CLUSTER

FEATURES BENEFITS

● Compatibility with S3 and Swift APIs ● Supports broad ecosystem of tools and ● Fully-configurable replicated or erasure coded applications built for the S3 API storage backends ● Provides a modern hot/warm/cold storage ● Cache tiering pools topology that offers cost-efficient performance ● ● Multi-site failover Advanced durability at optimal price RICH MEDIA

Unstructured image, video, and audio content Massively-scalable, flexible, and cost-effective storage for image, video, and audio content Red Hat Gluster Red Hat Ceph Storage Cluster Storage Cluster

FEATURES BENEFITS

● Provides massive and linear in on- ● Support for multi-petabyte storage clusters on premise or cloud environments commodity hardware ● Offers robust data protection with an optimal ● Erasure coding and for capacity- blend of price & performance optimized or performance-optimized pools ● Standard protocols allow access to broadcast ● Support for standard file & object protocols content anywhere, on any device ● Snapshots and replication capabilities for high ● Cost-effective, high performance storage for availability and disaster recovery on-demand rich media content ACTIVE ARCHIVES

Unstructured Unstructured Volume file data object data backups , capacity-optimized archival storage on commodity hardware Red Hat Gluster Red Hat Ceph Storage Cluster Storage Cluster

FEATURES BENEFITS

● Cache tiering to enable "temperature"- ● Store data based on its access frequency based storage ● Store data on premise or in a public or hybrid cloud ● Erasure coding to support archive and ● Achieve durability while reducing raw capacity cold storage use cases requirements and limiting cost ● Support for industry-standard file and ● Deploy on industry-standard hardware object access protocols FILE SYNC AND SHARE

Web Mobile Desktop browser application OS Powerful, software-defined, scale- out, on-premise storage for file sync and share with ownCloud OWNCLOUD ENTERPRISE EDITION

RED HAT GLUSTER STORAGE

FEATURES BENEFITS

● Secure file sync and share with enterprise-grade ● Secure collaboration with consumer-grade auditing and accounting ease of use ● Combined solution of Red Hat Gluster Storage, ● Lower risk by storing data on-premise ownCloud, HP ProLiant SL4550 Gen 8 servers ● Conform to corporate data security and ● Deployed on-premise, managed by internal IT compliance polices ● Access sync and share data from mobile devices, ● Lower total cost of ownership with standard, desktop systems, web browsers high-density servers and open source ENTERPRISE VIRTUALIZATION

Scalable, reliable storage for Red Hat Enterprise Virtualization

FEATURES BENEFITS

● Reliably store virtual machine images in a ● Reduce operational complexities by distributed Red Hat Gluster Storage volume eliminating dependency on complex and ● Manage storage through the RHEV-M console expensive SAN infrastructures ● ● Deploy on standard hardware of choice Deploy efficiently on less expensive, easier to provision, standard hardware ● Seamlessly grow and shrink storage ● infrastructure when demand changes Achieve centralized visibility and control of server and storage infrastructure

22 The Journey to Software-Defined Storage INTERNAL ONLY RED HAT STORAGE FUTURE WORKLOADS USE CASES: TODAY AND FUTURE

CURRENT USE CASES TARGET USE CASES

Big Data analytics Big Data analytics ● Storage plug-in for ● Persistent back-end for Hortonworks Data Platform Spark ANALYTICS Machine data analytics Machine data analytics ● Online cold storage for ● Storage for ELK, Solr IT operations data with Splunk USE CASES: TODAY AND FUTURE

CURRENT USE CASES TARGET USE CASES

Virtual machine storage Database storage ● Volume, ephemeral, and ● Storage for databases image storage with Cinder, with Trove OPENSTACK Nova, and Glance Object storage for Storage back-end for Manila tenant applications ● Shared file system-as-a- ● Swift-compatible storage service for tenants for cloud applications USE CASES: TODAY AND FUTURE

CURRENT USE CASES TARGET USE CASES

Rich media streaming ● Cost-effective storage for RICH MEDIA rich media streaming

AND ARCHIVAL Active archives Compliant archives ● Scalable, cost-effective ● Cost-effective online storage storage for compliance and for active archives regulatory needs USE CASES: TODAY AND FUTURE

CURRENT USE CASES TARGET USE CASES

ENTERPRISE Enterprise sync and share Enterprise sync and share ● Storage for Dropbox-style ● Storage for shared folders SYNC AND SHARE shared folders (file backend) (object backend) USE CASES: TODAY AND FUTURE

CURRENT USE CASES TARGET USE CASES

Conventional ENTERPRISE virtualization storage Hyper-converged ● Integrated storage for Red Hat architectures Enterprise Virtualization ● Hyper-converged VIRTUALIZATION (with separate compute and architectures storage clusters)