SlideShare a Scribd company logo
Managing ScaleIO
as Software on Mesos
David vonThenen
{code} by Dell EMC
http://dvonthenen.com
@dvonthenen
© Copyright 2017 Dell Inc.2
Open source at Dell EMC
– Contribute to meaningful OSS projects
– Create new thought leading OSS applications
– Drive awareness of OSS opportunities with Dell EMC
product teams
– Participate in relevant community engagement projects
– Act in the interest of building a community
{code} by Dell EMC is a group of passionate open
source engineers and advocates working to build a
community around software-based infrastructure.
Platinum Sponsor
© Copyright 2017 Dell Inc.3
Agenda
• What is Mesos?
• What is ScaleIO?
• Using ScaleIO on Mesos
• Easier way? Yes, ScaleIO Framework!
• Demo
Mesos
What is it?
© Copyright 2017 Dell Inc.5
What is Mesos?
• From a resource perspective, it’s a cluster manager
• From an application perspective, it’s a scheduler
• Is a Container Scheduler
• Mesos Universal Containerizer
– Docker
– rkt (CoreOS)
– Mesos Containerizer
• Fair and efficient workload placement
• Adheres to a set of constraints
© Copyright 2017 Dell Inc.6
Components of Mesos
• Zookeeper
– Provides leader election through quorum
– Enable distributed coordination (cluster state)
• Master
– Control plane
– Enables fine-grained resource sharing (CPU,
memory, disk)
– Manages Mesos Framework
• Agent
– Compute. Where the task will run.
© Copyright 2017 Dell Inc.7
Where can I run Mesos?
© Copyright 2017 Dell Inc.8
Mesos will run on…
© Copyright 2017 Dell Inc.9
Mesos Framework
• Ability to schedule tasks based on Application needs
• Framework implements two components:
– Scheduler – Accepts/Denies Resources
– Executor – Container + Application
• Multiple Frameworks run within the Mesos cluster
• Dogfooding – Marathon is a Framework
– Marathon is a basic “default” Framework
© Copyright 2017 Dell Inc.10
Frameworks / Offer-Accept
© Copyright 2017 Dell Inc.11
Generic Application
+
More
© Copyright 2017 Dell Inc.12
Specialized Frameworks
© Copyright 2017 Dell Inc.13
Framework = Custom Scheduling
• Ability to customize the scheduling of your particular application
– Customization in the form of:
– Run-time?
– Availability?
– Fault Tolerance?
– Hardware Acceleration?
– Location?
ScaleIO
What is it?
© Copyright 2017 Dell Inc.15
What is ScaleIO?
Three ways to consume
– Build your own - Software-only
– Pre-validated - ScaleIO Ready Node
– Turnkey with Networking – VxRack FLEX
• Platform Agnostic
• Media agnostic
Software-Defined; Distributed; Data Center Scale; Shared Block Storage
SSDHDD NVMePCIe
© Copyright 2017 Dell Inc.16
Why ScaleIO?
Lightweight
• Extremely lightweight
• Leaves plenty of
resources for services
• StorageReview’s ScaleIO Performance Testing
“We saw exemplary performance in both
configurations. The most impressive feat
though was how well ScaleIO in HCI did,
demonstrating how little impact the
storage overhead has on the platform.”
© Copyright 2017 Dell Inc.17
Why ScaleIO?
Grow as you need
• Add (or remove) nodes
and storage devices on
the fly – granular
• Cost savings without
need to overprovision
© Copyright 2017 Dell Inc.18
Why ScaleIO?
Infrastructure
Agnostic
• Hardware agnostic
• Supports any major OS
or a combination within
the same system
• Community contributed
drivers, features, and
additional functionality
SSDHDD NVMePCIe
© Copyright 2017 Dell Inc.19
Why ScaleIO?
Scalability &
Performance
• Managed as a single
service rather than silos
• ScaleIO automatically
balances resources for
performance and
utilization
• Result = Predictable
performance at scale
© Copyright 2017 Dell Inc.20
Why ScaleIO?
Automation
• Easily automatable
• Robust CLI and
complete REST API
allows easy scripting
via configuration
management or
orchestration tools
© Copyright 2017 Dell Inc.21
Why ScaleIO?
Manageability
• Minutes to discover and
deploy
• Standard x86 servers
and Ethernet makes
operations a breeze
• Virtual IPs and auto-
failover for MDM cluster
© Copyright 2017 Dell Inc.22
Why ScaleIO?
Availability &
Resiliency
• Built-in data protection
• Distributed
Mesh Mirror
• Extremely fast rebuild
times for resiliency
© Copyright 2017 Dell Inc.23
Go for a test drive!
• Try ScaleIO as a free download!
• https://www.emc.com/products-solutions/trial-software-download/scaleio.htm
ScaleIO on Mesos
Let’s deploy it!
© Copyright 2017 Dell Inc.25
Install Components
• Hefty installation manual… but the components are:
• MDM cluster
– MDM rpm/deb
– LIA rpm/deb
– Gateway rpm/deb
• ScaleIO Data Server
– SDS rpm/deb
• ScaleIO Data Client
– SDC rpm/deb
• What about doing this on 100s or 1000s of nodes?
© Copyright 2017 Dell Inc.26
Example Deployment
• 3 Rack Hyper-converged Deployment
• MDM Cluster
– 3 MDM nodes
– Install packages: 3 x MDM, 3 x LIA, and 3 x Gateway
• 41 x 3 racks = 123 servers
– Install packages: 123 x SDS, 123 x SDC
• 255 packages to install!!
© Copyright 2017 Dell Inc.27
Well… DevOps
• DevOps isn’t the magic bullet…
• Resources on-premise and in the cloud
• Different operating systems
• Same operating systems, different versions
• Understand operation details of applications
• Interfaces change with software versions
• Hardware isn’t the same
© Copyright 2017 Dell Inc.28
Monitoring?
• What about maintenance?
• Who is going to monitor this thing?
• Still need to know when things go south!
Easier way?
Yes, the ScaleIO Framework
© Copyright 2017 Dell Inc.30
Easier way?
© Copyright 2017 Dell Inc.31
ScaleIO Framework
• Idea! Let’s create a Software-based Storage Framework
• ScaleIO + Mesos Framework = Awesome Sauce!
• First release in Sept 2016. Now on version 0.3.1
• https://github.com/codedellemc/scaleio-framework
© Copyright 2017 Dell Inc.32
What the Framework provides…
• Framework installs and configures ScaleIO on all
Mesos Agent (compute) nodes
• Stand up ScaleIO without knowing operational details
• Monitor the storage platform
• Persistent storage native to the container scheduling
platform
• Globally accessible storage!
• What storage array? Reduce complexity
• Deploy Anywhere!
© Copyright 2017 Dell Inc.33
Why do we care?
• Many container workloads are long running
• Most applications have state: user data,
configuration, and etc
• Top 7 of 12 Apps in Docker Hub are
persistent applications!
© Copyright 2017 Dell Inc.34
Death of a Container
• Where does my data go?
• Turned to the compute node’s local disk
to store data
• What happens on a node failure?
• Production applications require high
availability
• External Storage
/etc /var
/bin /opt
/data
© Copyright 2017 Dell Inc.35
What this means for your Apps…
• No data loss on infrastructure failures
• Highly Available containers and Apps!
• Insulates changes with:
– Container scheduler (APIs, etc)
– Storage platform (workflows, APIs, etc)
• Production ready!
© Copyright 2017 Dell Inc.36
Schedulers + SDS = ???
© Copyright 2017 Dell Inc.37
Manages the Storage Enablement
• ScaleIO Framework installs and configures software that enables Mesos containers to provision
and use ScaleIO volumes!
• REX-Ray
– Vendor agnostic storage orchestration engine
– AWS, Azure, Ceph, DigitalOcean, GCE, ScaleIO, VirtualBox, and more
– Home: https://rexray.codedellemc.com
– GitHub: https://github.com/codedellemc/rexray
• mesos-module-dvdi
– Provides hooks for Mesos Agent nodes to manage external storage
– Contributed back to Apache Mesos
– GitHub: https://github.com/codedellemc/mesos-module-dvdi
Demo
Let’s see it!
© Copyright 2017 Dell Inc.39
Manage the Storage Enablement
• Mesos Configuration
– 3 Mesos Master nodes (Management)
– 3 Mesos Agent nodes (Compute)
• ScaleIO Cluster (Scale-out storage)
– Will install on top of 3 Mesos Agent nodes
– 180 GB local disks on each node to make up this Storage Pool
• ScaleIO Framework
– GitHub: https://github.com/codedellemc/scaleio-framework
• Persistent External Storage
– Using REX-Ray
› GitHub: https://github.com/emccode/rexray
– Using mesos-module-dvdi
› GitHub: https://github.com/emccode/mesos-module-dvdi
© Copyright 2017 Dell Inc.40
The Moving Parts
Scheduler
Mesos Cluster
Mesos
Agent
App
Mesos
Agent
App
Offer
Offer
Take our projects for a spin at the {code} Labs
http://github.com/codedellemc/labs
© Copyright 2017 Dell Inc.42
codedellemc.com
community.codedellemc.com
@codeDellEMC
blog.codedellemc.com
{code} by Dell EMC is a group of
passionate open source engineers and
advocates working to build a community
around software-based infrastructure.
rexray.codedellemc.com
github.com/codedellemc/labs
HOL01 Use REX-Ray & ScaleIO w/ Docker, Mesos and Kubernetes
David vonThenen
@dvonthenen
http://dvonthenen.com
Managing ScaleIO as Software on Mesos

More Related Content

What's hot

Large Scale Cassandra Made Better in Containers - Chris Duchesne and Aaron Sp...
Large Scale Cassandra Made Better in Containers - Chris Duchesne and Aaron Sp...Large Scale Cassandra Made Better in Containers - Chris Duchesne and Aaron Sp...
Large Scale Cassandra Made Better in Containers - Chris Duchesne and Aaron Sp...
{code} by Dell EMC
 
{code} and containers
{code} and containers{code} and containers
{code} and containers
{code} by Dell EMC
 
Kubernetes and ScaleIO demo - Clinton Kitson - Dell EMC World 2017
Kubernetes and ScaleIO demo - Clinton Kitson - Dell EMC World 2017Kubernetes and ScaleIO demo - Clinton Kitson - Dell EMC World 2017
Kubernetes and ScaleIO demo - Clinton Kitson - Dell EMC World 2017
{code} by Dell EMC
 
Deep Dive on Container Storage Architectures - Clinton Kitson and Chris Duche...
Deep Dive on Container Storage Architectures - Clinton Kitson and Chris Duche...Deep Dive on Container Storage Architectures - Clinton Kitson and Chris Duche...
Deep Dive on Container Storage Architectures - Clinton Kitson and Chris Duche...
{code} by Dell EMC
 
Docker for Private Clouds with RackHD - Justin Kenney and Aaron Spiegel - Del...
Docker for Private Clouds with RackHD - Justin Kenney and Aaron Spiegel - Del...Docker for Private Clouds with RackHD - Justin Kenney and Aaron Spiegel - Del...
Docker for Private Clouds with RackHD - Justin Kenney and Aaron Spiegel - Del...
{code} by Dell EMC
 
Storage Integrations for Container Orchestrators
Storage Integrations for Container OrchestratorsStorage Integrations for Container Orchestrators
Storage Integrations for Container Orchestrators
{code} by Dell EMC
 
Data Analytics Using Container Persistence Through SMACK - Manny Rodriguez-Pe...
Data Analytics Using Container Persistence Through SMACK - Manny Rodriguez-Pe...Data Analytics Using Container Persistence Through SMACK - Manny Rodriguez-Pe...
Data Analytics Using Container Persistence Through SMACK - Manny Rodriguez-Pe...
{code} by Dell EMC
 
Containers and their Ecosystem: An Introduction to Containers - Kendrick Cole...
Containers and their Ecosystem: An Introduction to Containers - Kendrick Cole...Containers and their Ecosystem: An Introduction to Containers - Kendrick Cole...
Containers and their Ecosystem: An Introduction to Containers - Kendrick Cole...
{code} by Dell EMC
 
Deep-Dive on Container Networking Architectures - Frans van Rooyen - Dell EMC...
Deep-Dive on Container Networking Architectures - Frans van Rooyen - Dell EMC...Deep-Dive on Container Networking Architectures - Frans van Rooyen - Dell EMC...
Deep-Dive on Container Networking Architectures - Frans van Rooyen - Dell EMC...
{code} by Dell EMC
 
Cloudy with a Chance of Databases
Cloudy with a Chance of DatabasesCloudy with a Chance of Databases
Cloudy with a Chance of Databases
Kellyn Pot'Vin-Gorman
 
DevOps and DBA- Delphix
DevOps and DBA-  DelphixDevOps and DBA-  Delphix
DevOps and DBA- Delphix
Kellyn Pot'Vin-Gorman
 
Oracle Open World 2017 Delphix and DBVisit
Oracle Open World 2017 Delphix and DBVisitOracle Open World 2017 Delphix and DBVisit
Oracle Open World 2017 Delphix and DBVisit
Kellyn Pot'Vin-Gorman
 
Containers and microservices for realists
Containers and microservices for realistsContainers and microservices for realists
Containers and microservices for realists
Karthik Gaekwad
 
DevOps and Decoys How to Build a Successful Microsoft DevOps Including the Data
DevOps and Decoys  How to Build a Successful Microsoft DevOps Including the DataDevOps and Decoys  How to Build a Successful Microsoft DevOps Including the Data
DevOps and Decoys How to Build a Successful Microsoft DevOps Including the Data
Kellyn Pot'Vin-Gorman
 
Database Migrations to the Cloud
Database Migrations to the CloudDatabase Migrations to the Cloud
Database Migrations to the Cloud
Kellyn Pot'Vin-Gorman
 
Farming Dinosaurs
Farming DinosaursFarming Dinosaurs
Farming Dinosaurs
Kellyn Pot'Vin-Gorman
 
The Cloud Talk
The Cloud TalkThe Cloud Talk
The Cloud Talk
Kellyn Pot'Vin-Gorman
 
Cloud Presentation and OpenStack case studies -- Harvard University
Cloud Presentation and OpenStack case studies -- Harvard UniversityCloud Presentation and OpenStack case studies -- Harvard University
Cloud Presentation and OpenStack case studies -- Harvard University
Barton George
 
Considering Bare Metal
Considering Bare MetalConsidering Bare Metal
Considering Bare Metal
Satish Hemachandran
 
Machine learning services with SQL Server 2017
Machine learning services with SQL Server 2017Machine learning services with SQL Server 2017
Machine learning services with SQL Server 2017
Mark Tabladillo
 

What's hot (20)

Large Scale Cassandra Made Better in Containers - Chris Duchesne and Aaron Sp...
Large Scale Cassandra Made Better in Containers - Chris Duchesne and Aaron Sp...Large Scale Cassandra Made Better in Containers - Chris Duchesne and Aaron Sp...
Large Scale Cassandra Made Better in Containers - Chris Duchesne and Aaron Sp...
 
{code} and containers
{code} and containers{code} and containers
{code} and containers
 
Kubernetes and ScaleIO demo - Clinton Kitson - Dell EMC World 2017
Kubernetes and ScaleIO demo - Clinton Kitson - Dell EMC World 2017Kubernetes and ScaleIO demo - Clinton Kitson - Dell EMC World 2017
Kubernetes and ScaleIO demo - Clinton Kitson - Dell EMC World 2017
 
Deep Dive on Container Storage Architectures - Clinton Kitson and Chris Duche...
Deep Dive on Container Storage Architectures - Clinton Kitson and Chris Duche...Deep Dive on Container Storage Architectures - Clinton Kitson and Chris Duche...
Deep Dive on Container Storage Architectures - Clinton Kitson and Chris Duche...
 
Docker for Private Clouds with RackHD - Justin Kenney and Aaron Spiegel - Del...
Docker for Private Clouds with RackHD - Justin Kenney and Aaron Spiegel - Del...Docker for Private Clouds with RackHD - Justin Kenney and Aaron Spiegel - Del...
Docker for Private Clouds with RackHD - Justin Kenney and Aaron Spiegel - Del...
 
Storage Integrations for Container Orchestrators
Storage Integrations for Container OrchestratorsStorage Integrations for Container Orchestrators
Storage Integrations for Container Orchestrators
 
Data Analytics Using Container Persistence Through SMACK - Manny Rodriguez-Pe...
Data Analytics Using Container Persistence Through SMACK - Manny Rodriguez-Pe...Data Analytics Using Container Persistence Through SMACK - Manny Rodriguez-Pe...
Data Analytics Using Container Persistence Through SMACK - Manny Rodriguez-Pe...
 
Containers and their Ecosystem: An Introduction to Containers - Kendrick Cole...
Containers and their Ecosystem: An Introduction to Containers - Kendrick Cole...Containers and their Ecosystem: An Introduction to Containers - Kendrick Cole...
Containers and their Ecosystem: An Introduction to Containers - Kendrick Cole...
 
Deep-Dive on Container Networking Architectures - Frans van Rooyen - Dell EMC...
Deep-Dive on Container Networking Architectures - Frans van Rooyen - Dell EMC...Deep-Dive on Container Networking Architectures - Frans van Rooyen - Dell EMC...
Deep-Dive on Container Networking Architectures - Frans van Rooyen - Dell EMC...
 
Cloudy with a Chance of Databases
Cloudy with a Chance of DatabasesCloudy with a Chance of Databases
Cloudy with a Chance of Databases
 
DevOps and DBA- Delphix
DevOps and DBA-  DelphixDevOps and DBA-  Delphix
DevOps and DBA- Delphix
 
Oracle Open World 2017 Delphix and DBVisit
Oracle Open World 2017 Delphix and DBVisitOracle Open World 2017 Delphix and DBVisit
Oracle Open World 2017 Delphix and DBVisit
 
Containers and microservices for realists
Containers and microservices for realistsContainers and microservices for realists
Containers and microservices for realists
 
DevOps and Decoys How to Build a Successful Microsoft DevOps Including the Data
DevOps and Decoys  How to Build a Successful Microsoft DevOps Including the DataDevOps and Decoys  How to Build a Successful Microsoft DevOps Including the Data
DevOps and Decoys How to Build a Successful Microsoft DevOps Including the Data
 
Database Migrations to the Cloud
Database Migrations to the CloudDatabase Migrations to the Cloud
Database Migrations to the Cloud
 
Farming Dinosaurs
Farming DinosaursFarming Dinosaurs
Farming Dinosaurs
 
The Cloud Talk
The Cloud TalkThe Cloud Talk
The Cloud Talk
 
Cloud Presentation and OpenStack case studies -- Harvard University
Cloud Presentation and OpenStack case studies -- Harvard UniversityCloud Presentation and OpenStack case studies -- Harvard University
Cloud Presentation and OpenStack case studies -- Harvard University
 
Considering Bare Metal
Considering Bare MetalConsidering Bare Metal
Considering Bare Metal
 
Machine learning services with SQL Server 2017
Machine learning services with SQL Server 2017Machine learning services with SQL Server 2017
Machine learning services with SQL Server 2017
 

Similar to Managing ScaleIO as Software on Mesos

ContainerCon EU 2016 - Software-Defined Storage and Container Schedulers
ContainerCon EU 2016 - Software-Defined Storage and Container SchedulersContainerCon EU 2016 - Software-Defined Storage and Container Schedulers
ContainerCon EU 2016 - Software-Defined Storage and Container Schedulers
David vonThenen
 
Virtualization and Containers
Virtualization and ContainersVirtualization and Containers
Virtualization and Containers
Kellyn Pot'Vin-Gorman
 
Webinar: End-to-End CI/CD with GitLab and DC/OS
Webinar: End-to-End CI/CD with GitLab and DC/OSWebinar: End-to-End CI/CD with GitLab and DC/OS
Webinar: End-to-End CI/CD with GitLab and DC/OS
Mesosphere Inc.
 
DevOps for the DBA- Jax Style!
DevOps for the DBA-  Jax Style!DevOps for the DBA-  Jax Style!
DevOps for the DBA- Jax Style!
Kellyn Pot'Vin-Gorman
 
HBaseCon2017 Splice Machine as a Service: Multi-tenant HBase using DCOS (Meso...
HBaseCon2017 Splice Machine as a Service: Multi-tenant HBase using DCOS (Meso...HBaseCon2017 Splice Machine as a Service: Multi-tenant HBase using DCOS (Meso...
HBaseCon2017 Splice Machine as a Service: Multi-tenant HBase using DCOS (Meso...
HBaseCon
 
Real World Modern Development Use Cases with RackHD and Adobe
Real World Modern Development Use Cases with RackHD and AdobeReal World Modern Development Use Cases with RackHD and Adobe
Real World Modern Development Use Cases with RackHD and Adobe
Timothy Gelter
 
Implementing DevOps – How it came to the fore, its key elements and example d...
Implementing DevOps – How it came to the fore, its key elements and example d...Implementing DevOps – How it came to the fore, its key elements and example d...
Implementing DevOps – How it came to the fore, its key elements and example d...
Barton George
 
New DevOps for the DBA
New DevOps for the DBANew DevOps for the DBA
New DevOps for the DBA
Kellyn Pot'Vin-Gorman
 
{code} and Containers - Open Source Infrastructure within Dell Technologies
{code} and Containers - Open Source Infrastructure within Dell Technologies{code} and Containers - Open Source Infrastructure within Dell Technologies
{code} and Containers - Open Source Infrastructure within Dell Technologies
The {code} Team
 
DevOps and the DBA
DevOps and the DBADevOps and the DBA
DevOps and the DBA
Kellyn Pot'Vin-Gorman
 
The Fastest Way to Redis on Pivotal Cloud Foundry
The Fastest Way to Redis on Pivotal Cloud FoundryThe Fastest Way to Redis on Pivotal Cloud Foundry
The Fastest Way to Redis on Pivotal Cloud Foundry
VMware Tanzu
 
Docker vs. Kubernetes vs. Serverless
Docker vs. Kubernetes vs. ServerlessDocker vs. Kubernetes vs. Serverless
Docker vs. Kubernetes vs. Serverless
LogicworksNY
 
How Container Schedulers and Software-based Storage will Change the Cloud
How Container Schedulers and Software-based Storage will Change the CloudHow Container Schedulers and Software-based Storage will Change the Cloud
How Container Schedulers and Software-based Storage will Change the Cloud
David vonThenen
 
Screw DevOps, Let's Talk DataOps
Screw DevOps, Let's Talk DataOpsScrew DevOps, Let's Talk DataOps
Screw DevOps, Let's Talk DataOps
Kellyn Pot'Vin-Gorman
 
Data platforms 2017
Data platforms 2017Data platforms 2017
Data platforms 2017
Kellyn Pot'Vin-Gorman
 
Oracle - Continuous Delivery NYC meetup, June 07, 2018
Oracle - Continuous Delivery NYC meetup, June 07, 2018Oracle - Continuous Delivery NYC meetup, June 07, 2018
Oracle - Continuous Delivery NYC meetup, June 07, 2018
Oracle Developers
 
Introduction to Apache Mesos and DC/OS
Introduction to Apache Mesos and DC/OSIntroduction to Apache Mesos and DC/OS
Introduction to Apache Mesos and DC/OS
Steve Wong
 
The world of Docker and Kubernetes
The world of Docker and Kubernetes The world of Docker and Kubernetes
The world of Docker and Kubernetes
vty
 
Sviluppare velocemente applicazioni sicure con SUSE CaaS Platform e SUSE Manager
Sviluppare velocemente applicazioni sicure con SUSE CaaS Platform e SUSE ManagerSviluppare velocemente applicazioni sicure con SUSE CaaS Platform e SUSE Manager
Sviluppare velocemente applicazioni sicure con SUSE CaaS Platform e SUSE Manager
SUSE Italy
 
Using MySQL Containers
Using MySQL ContainersUsing MySQL Containers
Using MySQL Containers
Matt Lord
 

Similar to Managing ScaleIO as Software on Mesos (20)

ContainerCon EU 2016 - Software-Defined Storage and Container Schedulers
ContainerCon EU 2016 - Software-Defined Storage and Container SchedulersContainerCon EU 2016 - Software-Defined Storage and Container Schedulers
ContainerCon EU 2016 - Software-Defined Storage and Container Schedulers
 
Virtualization and Containers
Virtualization and ContainersVirtualization and Containers
Virtualization and Containers
 
Webinar: End-to-End CI/CD with GitLab and DC/OS
Webinar: End-to-End CI/CD with GitLab and DC/OSWebinar: End-to-End CI/CD with GitLab and DC/OS
Webinar: End-to-End CI/CD with GitLab and DC/OS
 
DevOps for the DBA- Jax Style!
DevOps for the DBA-  Jax Style!DevOps for the DBA-  Jax Style!
DevOps for the DBA- Jax Style!
 
HBaseCon2017 Splice Machine as a Service: Multi-tenant HBase using DCOS (Meso...
HBaseCon2017 Splice Machine as a Service: Multi-tenant HBase using DCOS (Meso...HBaseCon2017 Splice Machine as a Service: Multi-tenant HBase using DCOS (Meso...
HBaseCon2017 Splice Machine as a Service: Multi-tenant HBase using DCOS (Meso...
 
Real World Modern Development Use Cases with RackHD and Adobe
Real World Modern Development Use Cases with RackHD and AdobeReal World Modern Development Use Cases with RackHD and Adobe
Real World Modern Development Use Cases with RackHD and Adobe
 
Implementing DevOps – How it came to the fore, its key elements and example d...
Implementing DevOps – How it came to the fore, its key elements and example d...Implementing DevOps – How it came to the fore, its key elements and example d...
Implementing DevOps – How it came to the fore, its key elements and example d...
 
New DevOps for the DBA
New DevOps for the DBANew DevOps for the DBA
New DevOps for the DBA
 
{code} and Containers - Open Source Infrastructure within Dell Technologies
{code} and Containers - Open Source Infrastructure within Dell Technologies{code} and Containers - Open Source Infrastructure within Dell Technologies
{code} and Containers - Open Source Infrastructure within Dell Technologies
 
DevOps and the DBA
DevOps and the DBADevOps and the DBA
DevOps and the DBA
 
The Fastest Way to Redis on Pivotal Cloud Foundry
The Fastest Way to Redis on Pivotal Cloud FoundryThe Fastest Way to Redis on Pivotal Cloud Foundry
The Fastest Way to Redis on Pivotal Cloud Foundry
 
Docker vs. Kubernetes vs. Serverless
Docker vs. Kubernetes vs. ServerlessDocker vs. Kubernetes vs. Serverless
Docker vs. Kubernetes vs. Serverless
 
How Container Schedulers and Software-based Storage will Change the Cloud
How Container Schedulers and Software-based Storage will Change the CloudHow Container Schedulers and Software-based Storage will Change the Cloud
How Container Schedulers and Software-based Storage will Change the Cloud
 
Screw DevOps, Let's Talk DataOps
Screw DevOps, Let's Talk DataOpsScrew DevOps, Let's Talk DataOps
Screw DevOps, Let's Talk DataOps
 
Data platforms 2017
Data platforms 2017Data platforms 2017
Data platforms 2017
 
Oracle - Continuous Delivery NYC meetup, June 07, 2018
Oracle - Continuous Delivery NYC meetup, June 07, 2018Oracle - Continuous Delivery NYC meetup, June 07, 2018
Oracle - Continuous Delivery NYC meetup, June 07, 2018
 
Introduction to Apache Mesos and DC/OS
Introduction to Apache Mesos and DC/OSIntroduction to Apache Mesos and DC/OS
Introduction to Apache Mesos and DC/OS
 
The world of Docker and Kubernetes
The world of Docker and Kubernetes The world of Docker and Kubernetes
The world of Docker and Kubernetes
 
Sviluppare velocemente applicazioni sicure con SUSE CaaS Platform e SUSE Manager
Sviluppare velocemente applicazioni sicure con SUSE CaaS Platform e SUSE ManagerSviluppare velocemente applicazioni sicure con SUSE CaaS Platform e SUSE Manager
Sviluppare velocemente applicazioni sicure con SUSE CaaS Platform e SUSE Manager
 
Using MySQL Containers
Using MySQL ContainersUsing MySQL Containers
Using MySQL Containers
 

Recently uploaded

Letter and Document Automation for Bonterra Impact Management (fka Social Sol...
Letter and Document Automation for Bonterra Impact Management (fka Social Sol...Letter and Document Automation for Bonterra Impact Management (fka Social Sol...
Letter and Document Automation for Bonterra Impact Management (fka Social Sol...
Jeffrey Haguewood
 
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfUnlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Malak Abu Hammad
 
Building Production Ready Search Pipelines with Spark and Milvus
Building Production Ready Search Pipelines with Spark and MilvusBuilding Production Ready Search Pipelines with Spark and Milvus
Building Production Ready Search Pipelines with Spark and Milvus
Zilliz
 
TrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy SurveyTrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy Survey
TrustArc
 
A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024
Intelisync
 
Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024
Jason Packer
 
Main news related to the CCS TSI 2023 (2023/1695)
Main news related to the CCS TSI 2023 (2023/1695)Main news related to the CCS TSI 2023 (2023/1695)
Main news related to the CCS TSI 2023 (2023/1695)
Jakub Marek
 
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with SlackLet's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
shyamraj55
 
Finale of the Year: Apply for Next One!
Finale of the Year: Apply for Next One!Finale of the Year: Apply for Next One!
Finale of the Year: Apply for Next One!
GDSC PJATK
 
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
saastr
 
5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides
DanBrown980551
 
Driving Business Innovation: Latest Generative AI Advancements & Success Story
Driving Business Innovation: Latest Generative AI Advancements & Success StoryDriving Business Innovation: Latest Generative AI Advancements & Success Story
Driving Business Innovation: Latest Generative AI Advancements & Success Story
Safe Software
 
Recommendation System using RAG Architecture
Recommendation System using RAG ArchitectureRecommendation System using RAG Architecture
Recommendation System using RAG Architecture
fredae14
 
Energy Efficient Video Encoding for Cloud and Edge Computing Instances
Energy Efficient Video Encoding for Cloud and Edge Computing InstancesEnergy Efficient Video Encoding for Cloud and Edge Computing Instances
Energy Efficient Video Encoding for Cloud and Edge Computing Instances
Alpen-Adria-Universität
 
Programming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup SlidesProgramming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup Slides
Zilliz
 
Skybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoptionSkybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoption
Tatiana Kojar
 
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
saastr
 
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
alexjohnson7307
 
Generating privacy-protected synthetic data using Secludy and Milvus
Generating privacy-protected synthetic data using Secludy and MilvusGenerating privacy-protected synthetic data using Secludy and Milvus
Generating privacy-protected synthetic data using Secludy and Milvus
Zilliz
 
Nunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdf
Nunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdfNunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdf
Nunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdf
flufftailshop
 

Recently uploaded (20)

Letter and Document Automation for Bonterra Impact Management (fka Social Sol...
Letter and Document Automation for Bonterra Impact Management (fka Social Sol...Letter and Document Automation for Bonterra Impact Management (fka Social Sol...
Letter and Document Automation for Bonterra Impact Management (fka Social Sol...
 
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdfUnlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
Unlock the Future of Search with MongoDB Atlas_ Vector Search Unleashed.pdf
 
Building Production Ready Search Pipelines with Spark and Milvus
Building Production Ready Search Pipelines with Spark and MilvusBuilding Production Ready Search Pipelines with Spark and Milvus
Building Production Ready Search Pipelines with Spark and Milvus
 
TrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy SurveyTrustArc Webinar - 2024 Global Privacy Survey
TrustArc Webinar - 2024 Global Privacy Survey
 
A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024
 
Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024Columbus Data & Analytics Wednesdays - June 2024
Columbus Data & Analytics Wednesdays - June 2024
 
Main news related to the CCS TSI 2023 (2023/1695)
Main news related to the CCS TSI 2023 (2023/1695)Main news related to the CCS TSI 2023 (2023/1695)
Main news related to the CCS TSI 2023 (2023/1695)
 
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with SlackLet's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
Let's Integrate MuleSoft RPA, COMPOSER, APM with AWS IDP along with Slack
 
Finale of the Year: Apply for Next One!
Finale of the Year: Apply for Next One!Finale of the Year: Apply for Next One!
Finale of the Year: Apply for Next One!
 
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
 
5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides
 
Driving Business Innovation: Latest Generative AI Advancements & Success Story
Driving Business Innovation: Latest Generative AI Advancements & Success StoryDriving Business Innovation: Latest Generative AI Advancements & Success Story
Driving Business Innovation: Latest Generative AI Advancements & Success Story
 
Recommendation System using RAG Architecture
Recommendation System using RAG ArchitectureRecommendation System using RAG Architecture
Recommendation System using RAG Architecture
 
Energy Efficient Video Encoding for Cloud and Edge Computing Instances
Energy Efficient Video Encoding for Cloud and Edge Computing InstancesEnergy Efficient Video Encoding for Cloud and Edge Computing Instances
Energy Efficient Video Encoding for Cloud and Edge Computing Instances
 
Programming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup SlidesProgramming Foundation Models with DSPy - Meetup Slides
Programming Foundation Models with DSPy - Meetup Slides
 
Skybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoptionSkybuffer SAM4U tool for SAP license adoption
Skybuffer SAM4U tool for SAP license adoption
 
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
Overcoming the PLG Trap: Lessons from Canva's Head of Sales & Head of EMEA Da...
 
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
 
Generating privacy-protected synthetic data using Secludy and Milvus
Generating privacy-protected synthetic data using Secludy and MilvusGenerating privacy-protected synthetic data using Secludy and Milvus
Generating privacy-protected synthetic data using Secludy and Milvus
 
Nunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdf
Nunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdfNunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdf
Nunit vs XUnit vs MSTest Differences Between These Unit Testing Frameworks.pdf
 

Managing ScaleIO as Software on Mesos

  • 1. Managing ScaleIO as Software on Mesos David vonThenen {code} by Dell EMC http://dvonthenen.com @dvonthenen
  • 2. © Copyright 2017 Dell Inc.2 Open source at Dell EMC – Contribute to meaningful OSS projects – Create new thought leading OSS applications – Drive awareness of OSS opportunities with Dell EMC product teams – Participate in relevant community engagement projects – Act in the interest of building a community {code} by Dell EMC is a group of passionate open source engineers and advocates working to build a community around software-based infrastructure. Platinum Sponsor
  • 3. © Copyright 2017 Dell Inc.3 Agenda • What is Mesos? • What is ScaleIO? • Using ScaleIO on Mesos • Easier way? Yes, ScaleIO Framework! • Demo
  • 5. © Copyright 2017 Dell Inc.5 What is Mesos? • From a resource perspective, it’s a cluster manager • From an application perspective, it’s a scheduler • Is a Container Scheduler • Mesos Universal Containerizer – Docker – rkt (CoreOS) – Mesos Containerizer • Fair and efficient workload placement • Adheres to a set of constraints
  • 6. © Copyright 2017 Dell Inc.6 Components of Mesos • Zookeeper – Provides leader election through quorum – Enable distributed coordination (cluster state) • Master – Control plane – Enables fine-grained resource sharing (CPU, memory, disk) – Manages Mesos Framework • Agent – Compute. Where the task will run.
  • 7. © Copyright 2017 Dell Inc.7 Where can I run Mesos?
  • 8. © Copyright 2017 Dell Inc.8 Mesos will run on…
  • 9. © Copyright 2017 Dell Inc.9 Mesos Framework • Ability to schedule tasks based on Application needs • Framework implements two components: – Scheduler – Accepts/Denies Resources – Executor – Container + Application • Multiple Frameworks run within the Mesos cluster • Dogfooding – Marathon is a Framework – Marathon is a basic “default” Framework
  • 10. © Copyright 2017 Dell Inc.10 Frameworks / Offer-Accept
  • 11. © Copyright 2017 Dell Inc.11 Generic Application + More
  • 12. © Copyright 2017 Dell Inc.12 Specialized Frameworks
  • 13. © Copyright 2017 Dell Inc.13 Framework = Custom Scheduling • Ability to customize the scheduling of your particular application – Customization in the form of: – Run-time? – Availability? – Fault Tolerance? – Hardware Acceleration? – Location?
  • 15. © Copyright 2017 Dell Inc.15 What is ScaleIO? Three ways to consume – Build your own - Software-only – Pre-validated - ScaleIO Ready Node – Turnkey with Networking – VxRack FLEX • Platform Agnostic • Media agnostic Software-Defined; Distributed; Data Center Scale; Shared Block Storage SSDHDD NVMePCIe
  • 16. © Copyright 2017 Dell Inc.16 Why ScaleIO? Lightweight • Extremely lightweight • Leaves plenty of resources for services • StorageReview’s ScaleIO Performance Testing “We saw exemplary performance in both configurations. The most impressive feat though was how well ScaleIO in HCI did, demonstrating how little impact the storage overhead has on the platform.”
  • 17. © Copyright 2017 Dell Inc.17 Why ScaleIO? Grow as you need • Add (or remove) nodes and storage devices on the fly – granular • Cost savings without need to overprovision
  • 18. © Copyright 2017 Dell Inc.18 Why ScaleIO? Infrastructure Agnostic • Hardware agnostic • Supports any major OS or a combination within the same system • Community contributed drivers, features, and additional functionality SSDHDD NVMePCIe
  • 19. © Copyright 2017 Dell Inc.19 Why ScaleIO? Scalability & Performance • Managed as a single service rather than silos • ScaleIO automatically balances resources for performance and utilization • Result = Predictable performance at scale
  • 20. © Copyright 2017 Dell Inc.20 Why ScaleIO? Automation • Easily automatable • Robust CLI and complete REST API allows easy scripting via configuration management or orchestration tools
  • 21. © Copyright 2017 Dell Inc.21 Why ScaleIO? Manageability • Minutes to discover and deploy • Standard x86 servers and Ethernet makes operations a breeze • Virtual IPs and auto- failover for MDM cluster
  • 22. © Copyright 2017 Dell Inc.22 Why ScaleIO? Availability & Resiliency • Built-in data protection • Distributed Mesh Mirror • Extremely fast rebuild times for resiliency
  • 23. © Copyright 2017 Dell Inc.23 Go for a test drive! • Try ScaleIO as a free download! • https://www.emc.com/products-solutions/trial-software-download/scaleio.htm
  • 25. © Copyright 2017 Dell Inc.25 Install Components • Hefty installation manual… but the components are: • MDM cluster – MDM rpm/deb – LIA rpm/deb – Gateway rpm/deb • ScaleIO Data Server – SDS rpm/deb • ScaleIO Data Client – SDC rpm/deb • What about doing this on 100s or 1000s of nodes?
  • 26. © Copyright 2017 Dell Inc.26 Example Deployment • 3 Rack Hyper-converged Deployment • MDM Cluster – 3 MDM nodes – Install packages: 3 x MDM, 3 x LIA, and 3 x Gateway • 41 x 3 racks = 123 servers – Install packages: 123 x SDS, 123 x SDC • 255 packages to install!!
  • 27. © Copyright 2017 Dell Inc.27 Well… DevOps • DevOps isn’t the magic bullet… • Resources on-premise and in the cloud • Different operating systems • Same operating systems, different versions • Understand operation details of applications • Interfaces change with software versions • Hardware isn’t the same
  • 28. © Copyright 2017 Dell Inc.28 Monitoring? • What about maintenance? • Who is going to monitor this thing? • Still need to know when things go south!
  • 29. Easier way? Yes, the ScaleIO Framework
  • 30. © Copyright 2017 Dell Inc.30 Easier way?
  • 31. © Copyright 2017 Dell Inc.31 ScaleIO Framework • Idea! Let’s create a Software-based Storage Framework • ScaleIO + Mesos Framework = Awesome Sauce! • First release in Sept 2016. Now on version 0.3.1 • https://github.com/codedellemc/scaleio-framework
  • 32. © Copyright 2017 Dell Inc.32 What the Framework provides… • Framework installs and configures ScaleIO on all Mesos Agent (compute) nodes • Stand up ScaleIO without knowing operational details • Monitor the storage platform • Persistent storage native to the container scheduling platform • Globally accessible storage! • What storage array? Reduce complexity • Deploy Anywhere!
  • 33. © Copyright 2017 Dell Inc.33 Why do we care? • Many container workloads are long running • Most applications have state: user data, configuration, and etc • Top 7 of 12 Apps in Docker Hub are persistent applications!
  • 34. © Copyright 2017 Dell Inc.34 Death of a Container • Where does my data go? • Turned to the compute node’s local disk to store data • What happens on a node failure? • Production applications require high availability • External Storage /etc /var /bin /opt /data
  • 35. © Copyright 2017 Dell Inc.35 What this means for your Apps… • No data loss on infrastructure failures • Highly Available containers and Apps! • Insulates changes with: – Container scheduler (APIs, etc) – Storage platform (workflows, APIs, etc) • Production ready!
  • 36. © Copyright 2017 Dell Inc.36 Schedulers + SDS = ???
  • 37. © Copyright 2017 Dell Inc.37 Manages the Storage Enablement • ScaleIO Framework installs and configures software that enables Mesos containers to provision and use ScaleIO volumes! • REX-Ray – Vendor agnostic storage orchestration engine – AWS, Azure, Ceph, DigitalOcean, GCE, ScaleIO, VirtualBox, and more – Home: https://rexray.codedellemc.com – GitHub: https://github.com/codedellemc/rexray • mesos-module-dvdi – Provides hooks for Mesos Agent nodes to manage external storage – Contributed back to Apache Mesos – GitHub: https://github.com/codedellemc/mesos-module-dvdi
  • 39. © Copyright 2017 Dell Inc.39 Manage the Storage Enablement • Mesos Configuration – 3 Mesos Master nodes (Management) – 3 Mesos Agent nodes (Compute) • ScaleIO Cluster (Scale-out storage) – Will install on top of 3 Mesos Agent nodes – 180 GB local disks on each node to make up this Storage Pool • ScaleIO Framework – GitHub: https://github.com/codedellemc/scaleio-framework • Persistent External Storage – Using REX-Ray › GitHub: https://github.com/emccode/rexray – Using mesos-module-dvdi › GitHub: https://github.com/emccode/mesos-module-dvdi
  • 40. © Copyright 2017 Dell Inc.40 The Moving Parts Scheduler Mesos Cluster Mesos Agent App Mesos Agent App Offer Offer
  • 41. Take our projects for a spin at the {code} Labs http://github.com/codedellemc/labs
  • 42. © Copyright 2017 Dell Inc.42 codedellemc.com community.codedellemc.com @codeDellEMC blog.codedellemc.com {code} by Dell EMC is a group of passionate open source engineers and advocates working to build a community around software-based infrastructure. rexray.codedellemc.com github.com/codedellemc/labs HOL01 Use REX-Ray & ScaleIO w/ Docker, Mesos and Kubernetes David vonThenen @dvonthenen http://dvonthenen.com

Editor's Notes

  1. I work on the {code} team which is a group within Dell EMC that develops and contributes to various open source projects in the container space. Our group is most known for working on projects enabling different container schedulers to consume different storage platforms easily. Past Life: Backup and Recovery Solution working on Vmware virtualized environments.
  2. Add talking points to each point OSS projects: Docker (REX-Ray), Mesos (mesos-module-dvdi), Kubernetes, Cloud Foundry Recently the {code} team has been engaged with the Cloud Native Computing Foundation (CNCF) working on the Container Storage Interface (CSI)
  3. How do I divide the resources between my apps When an app goes down, you want to bring the app back up Even more basic than that… Mesos is a Container Scheduler Spread your apps amongst compute Create 3 instances of my app
  4. - How do I efficiently utilize my CPU, memory, and disk? - It makes sense to put a CPU intensive app with an App that requires a lot of memory. Density!
  5. Dive a little deeper… The one really cool thing about Mesos is this concept of Frameworks. Allows you to override the behavior of how your application is placed in your cluster by implementing a customized scheduler. Maybe users out there may only interact with Marathon in their day to day activities.
  6. 3 instances running on different nodes, 3 instances on different racks Special fault tolerance requirements Maybe your application is compute intensive such that you need utilize GPUs Spread your application across different availability zones
  7. Software only Complete flexibility – No HCL Not to say that some infrastructure won’t work better than others. But it’s designed to run on anything. End user supplies server, switch, rack, etc. Worried about a hidden cost of HW integration: Dell PowerEdge servers tuned, optimized and validated for ScaleIO Builds for Hyper-converged or Storage-only ScaleIO can be installed on almost any Operating System; there are plugins or integrations that allow almost any platform to either provide or consume storage. You can combine spinning disks, SSDs, PCI express drives and NVMe in a single system – allowing users to create different performance pools
  8. Some SDS products eat a lot of resources to provide the storage services. Ideal for Hyper-converged Infrastructure because the storage system doesn’t get in the way of the other compute loads. Storage review was so impressed it created an Editors Choice award so it could give it to ScaleIO.
  9. Is built on an elastic architecture, meaning… if you need more capacity, you could add more disk to nodes If you need more throughput, you could add more nodes to your configuration Grow as you need
  10. Bring whatever network and server gear you like, and fill it with the sort of drives you want. Run it on the OS or hypervisor of your choice, and even have the option to combine these in a single system. Open source projects and collaborations continually enable new integrations … and we’ll be hearing about some of them today!
  11. What happens too often is that storage, ends up getting silo’ed leading to poor utilization and/or performance. An example of that is under utilized resources on a storage array because you need to anticipate growth. By pooling resources across all stacks and allowing for consumption back to any stack, ScaleIO allows for better utilization of your hardware. ScaleIO does all of the work to optimize placement of data and balancing resources. If you lose nodes or add more, ScaleIO automatically redistributes and rebalances the data. What this means is that we get predictable performance at large scale even at near full capacity.
  12. Since ScaleIO is a Software-based Storage Platform its can mutliple automation vectors from a wide variety of DevOps tools.
  13. But Operations are simplified just in virtue of relying only on standard x86 servers and Ethernet. Things that all well-known and understood ScaleIO takes the headaches out of certain problems that would be left to Operations teams to solve. A lot this is addressed by the Metadata Management nodes by virtual of doing leader leader election amongst themselves. The elastic architecture handles the data striping and rebalancing when nodes are added or removed.
  14. ScaleIO writes data in a distributed mesh mirroring scheme. There are always two copies, on separate fault units, to ensure that data is always protected. Because of the highly parallelized architecture of ScaleIO, if there is a problem with a disk or a storage-contributing node, it can drop that device and rebuild the data elsewhere within seconds or minutes, rather than hours or days.
  15. The Deployment Guide is 302 pages in its current state.
  16. In terms of automating the installation this is probably the easy scenario which is: - select 3 nodes for the MDM nodes and set them aside for Management/Metadata - then install everything else (SDS and SDC) on the other nodes.
  17. What about if you want multiple protection domains? Or systems earmarked as storage providers (SDSs)? Or storage consumers (SDCs) at scale? How to identify them in your DevOps tool?
  18. That just talks about installation. That is arguably the easy part… what happens when it comes to monitoring and Day 2 type operations.
  19. Operational details – Has been baked into the Framework via the customer scheduler Monitor the storage platform – That’s a principle feature that Mesos Frameworks provide. Application specialization. Native – in the sense that if you bring new Mesos nodes online, the Framework will imprint those new nodes immediately to consume ScaleIO Deploy Anywhere - ScaleIO is infrastructure agnostic
  20. First, a few things about the team that has made this possible. The Dell EMC {code} team is a team made up of open source software engineers and developer advocates, focused on making EMC a well-known name within the open source community. We will focus on one of their projects, REX-Ray, in this presentation.