SlideShare a Scribd company logo
Making clouds:
turning OpenNebula into a product
Carlo Daffara, CloudWeavers
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
The Cloud extends the traditional advantages of“ ”
virtualization platforms to scale-out software. It is an
opportunity to rethink hardware deployment ...
…it does not means that all clouds need to be public
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
http: blippex.github.io updates 2013 09 23 why-we-moved-away-from-aws.html// / / / / /
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
Why OpenNebula?
Four major platforms:
•
CloudStack
•
Eucalyptus
•
OpenNebula
•
OpenStack
Lots of minor ones:
Proxmox, Ovirt, Ganeti, OpenQRM, Enomaly,
Archipel...
Let's debate first about what architecture
we are aiming for. OpenStack & Eucalyptus
are modeled and structured around
AWS EC2, that is the clear market leader in/
the public cloud market.
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
Service Manager database 8-core 2.66 gigahertz (GHz) CPU 8
gigabytes (GB) of RAM 80 GB of
available disk space RAID Level 1 or
Level 10 drive*
Service Manager management server 4-Core 2.66 GHz CPU 8 GB of RAM 10
GB of available disk space
Service Manager console 2-core 2.0 GHz CPU 4 GB of RAM 10
GB of available disk space
Data warehouse management server 4-Core 2.66 GHz CPU 8 GB of RAM 10
GB of available disk space
Data warehouse databases 8-core 2.66 GHz CPU 8 GB of RAM
400 GB of available disk space RAID
Level 1 or Level (1+0) drive
Self-Service Portal: Web Content
Server with SharePoint Web Parts
8-Core 2.66 GHz CPU 8-core, 16GB
RAM, 80 GB of available hard disk
space
http: technet.microsoft.com en-us library hh524328.aspx// / / /
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
CloudStack 3.22MLoc
Eucalyptus 1.43MLoc
OpenStack 1.67MLoc
OpenNebula 190KLoc
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
I O Access pattern/ I O Characteristics/ Typical Applications
Streaming Reads 100 Reads; Large contiguous requests; 1-64%
concurrent requests. May be threaded.
Media Servers ( ideo on-demand, etc.).V
irtual Tape Libraries ( TL), ApplicationV V
Servers
Streaming Writes 100 Writes; Large contiguous requests; 1-64%
concurrent requests. May be threaded.
Media Capture, TL, Medical Imaging,V
Archiving, Backup, ideo Surveillance,V
Reference Data
OLTP Typically 2KB 16KB request sizes; Read modify,–
write, verify operations resulting in 2 reads for
every write; Primarily random accesses. Large
number of concurrent requests. When running SQL
statements in parallel, Database will perform
typically large random I Os./
Databases (SAP, Oracle, SQL), Online
Transaction Servers
File Server Moderate distribution of request sizes from 4KB to
64KB, however 4KB and 64KB comprise 70 of%
requests; Primarily random; Generally 4 reads for
every write operation. Large number of concurrent
requests during peak operational periods.
File and Printer Servers, e-mail (Exchange,
Notes), Decision Support Systems
Web Server Wide distribution of request sizes from 512 bytes to
512KB; Primarily random accesses; Large number
of concurrent requests during peak operational
periods
Web Services, Blogs, RSS Feeds, Shopping
Carts, Search Engines, Storage Services
Workstations Primarily small to medium request sizes; 80%
sequential and 20 random; Generally 4 reads for%
every write operation. 1-4 concurrent requests.
Business Productivity, Scientific Engineering/
Applications
http: gerardnico.com wiki data storage input output access pattern// / / _ / _ _ _
Making Clouds: Turning OpenNebula into a Product
Some additional tips for Windows:
•
K M badly interacts with Windows 7 8 clock drivers, causing high cpuV /
consumption. Use:
bcdedit /set {default} useplatformclock true
and
RAW = [ type= "KVM", data = "<clock offset='localtime'/>" ]
•
“Default cirrus GA driver unsuitable for Windows due to pathologicalV
performance issues in text mode”
This is not a problem in latest K M, however having vga std is betterV =
anyway
•
For Windows servers with lots of small files:
fsutil behaviour set disablelastaccess 1
(equivalent to noatime on linux)
fsutil behaviour set mftzone 2
(adds another 12.5 disk space to the MFT zone)%
•
Disable 8.3 namespace creation:
fsutil.exe behavior set disable8dot3 1
(huge boost for dirs, files with matching initial names)
Some useful additions:
GateOne (https: github.com liftoff GateOne// / / ) a very efficient web SSH
interface, similar to vncproxy. Works well added as a link in Sunstone.
M ray (https: github.com coriolis vmxray): a pure javascript MV X // / / V
explorer, allows to enter inside of an image, view and extract files.
Some additional tools:
LibGuestFS (http: libguestfs.org// /) the swiss army knife of M images. AllowsV
for copy in and out of a M, file operations, mount guest filesystem on host,V
Windows registry editing...
S3QL (http: code.google.com p s3ql// / / /) a FUSE filesystem that mounts and
operates on Amazon S3, Google storage and OpenStack-compatible storage.
Supports compression, encryption and deduplication. Quite useful if you want
to move images to-from Amazon or Google.
IPOP (http: www.grid-appliance.org wiki index.php IPOP// / / / ) IPOP (IP over P2P)
is an open-source research development project that provides a decentralized,/
distributed overlay virtual network. It allows users to easily deploy PNsV
across multiple domains, and is used in applications including virtual private
clusters for cloud grid computing./
Only thin features added directly to the platform...“ ”
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
We use Ms to provide additional features:V
Guacamole (http: sourceforge.net projects guacamole// / / /) exceptional
gateway that turns RDP into HTML5. Allows for pure web-based access to
Windows desktops from everywhere:
Other examples: Zenoss for agentless monitoring (or Hyperic for agent-based
monitors), backup tools like OpenDedup...
A special note on DI:V
Jerry Chen of Mware is generally credited with coining the term DI whichV “V ”
led to the redefinition of an entire industry. Mware had 10,400 employees.V
Of that group, about one-third of them use DI-based virtual desktops as theirV
primary production work desktops. About 1,000 of them use a thin-client
device as their only corporate-issued client device.
First problem: Microsoft licensing.
“dedicating an entire Remote Desktop virtual server to just one single user is
cheaper than most DI scenarios and gives users the same benefits, namelyV
having their own Desktop M where they can do what they want. This single‘ ’ V ‘
user terminal server scenario is with about 475 per user (6 years) not only’ – $
60 cheaper, but less complicated and legally more safe than standard MS%
DI licensing. Decoding the Microsoft DI Licensing Arcanum, LoginV " V
Consulting
Making Clouds: Turning OpenNebula into a Product
Making Clouds: Turning OpenNebula into a Product
A useful trick: on hook RUNNING increase the readahead of the rotative“ ”
medium (blockdev --setra 2048 or higher); you can reduce the boot time of
a Windows7 machine by 35 . You time it to return to much lower values%
after a predetermined interval.
Apps are moving to be pure webapps, no client installation needed so“ ” –
you can skip Windows. Having the M ready to use also facilitates theV
adoption of new tools, and lots of experimentation. Locally hosted Ms thatV
export a web application are becoming the norm, and you can remote the
remaining Windows apps through RDP, so you are actually free to build your
desktop as you like.
Royal Academy of Engineering, The future of computing , 2012“ ”
Making Clouds: Turning OpenNebula into a Product
We have our own thin desktop based on Linux called EveryDesk (
http://sourceforge.net/projects/everydesk/) that requires just 90MB
of ram per desktop, or for the more daring users:
..you can use ChromeOS from Google. There is an unofficial build for 86X
and x86 64 available daily here (_ http://chromium.arnoldthebat.co.uk/)
that runs perfectly within OpenNebula. You create the images as
non-persistent, and destroy them later on.
Bt using a WB cache and snapshots to create the non-persistent images you
end up with most of the pages already in cache, so boot is nearly
instantaneous. Write are small and sparse, so you are basically CPU-bound
and can run reasonably well 10-15 ChromeOS desktops per core.
38 , 5W, no moving part. Use Android aSPICE as a client+Autostart$
The MTBF of a standard PC is 30,000 hours or 3.4 years; for every 10c
temperature increase, MTBF is cut in half. Since in many pc closet the“ ”
temperature is 10 to 20 degrees higher, we assume a MTBF of 1yr.
4pc cloud: 4 failures yr, Ms on failed node are down for 5-10 mins - 20/ V >
to 40 min year, 99.99 assuming available power/ %
Availability per day per month per year
99.999% 00:00:00.4 00:00:26 00:05:15
99.99% 00:00:08 00:04:22 00:52:35
99.9% 00:01:26 00:43:49 08:45:56
99% 00:14:23 07:18:17 87:39:29
Thanks!
Carlo Daffara
carlo.daffara@cloudweavers.eu
Twitter: cdaffara

More Related Content

PDF
Enabling Scientific Workflows on FermiCloud using OpenNebula
PDF
Adventures in Research
PDF
Monitoring Large-scale Cloud Infrastructures with OpenNebula
PDF
Contrail Virtual Execution Platform
PDF
Monitoring of OpenNebula installations
PDF
Supercomputing by API: Connecting Modern Web Apps to HPC
PPTX
OpenNebula in a Multiuser Environment
PDF
Status of Embedded Linux
Enabling Scientific Workflows on FermiCloud using OpenNebula
Adventures in Research
Monitoring Large-scale Cloud Infrastructures with OpenNebula
Contrail Virtual Execution Platform
Monitoring of OpenNebula installations
Supercomputing by API: Connecting Modern Web Apps to HPC
OpenNebula in a Multiuser Environment
Status of Embedded Linux

What's hot (20)

PDF
Disaggregating Ceph using NVMeoF
PDF
XCP-ng - past, present and future
PDF
Top Ten Security Considerations when Setting up your OpenNebula Cloud
PDF
OpenNebulaConf 2016 - Measuring and tuning VM performance by Boyan Krosnov, S...
PPT
Applying OpenStack at iNET use case
PDF
Ceph with CloudStack
PDF
Open stack in action enovance-quantum in action
PDF
[OpenStack Days Korea 2016] Track1 - Mellanox CloudX - Acceleration for Cloud...
PDF
John Spray - Ceph in Kubernetes
PDF
OpenStack Networks the Web-Scale Way - Scott Laffer, Cumulus Networks
PPT
HA in OpenStack service - meetup #9
PDF
Boyan Krosnov - Building a software-defined cloud - our experience
PPTX
Tối ưu hiệu năng đáp ứng các yêu cầu của hệ thống 4G core
PDF
Is there still room for innovation in container orchestration and scheduling
PPTX
Puppet + Windows Nano Server
PDF
OpenNebulaConf 2016 - OpenNebula 5.0 Highlights and Beyond by Ruben S. Monter...
PDF
OpenNebulaConf2018 - We use OpenNebula everywhere now - Florian Heigl and Tho...
PDF
Routed Fabrics For Ceph
PDF
Deploying CloudStack and Ceph with flexible VXLAN and BGP networking
Disaggregating Ceph using NVMeoF
XCP-ng - past, present and future
Top Ten Security Considerations when Setting up your OpenNebula Cloud
OpenNebulaConf 2016 - Measuring and tuning VM performance by Boyan Krosnov, S...
Applying OpenStack at iNET use case
Ceph with CloudStack
Open stack in action enovance-quantum in action
[OpenStack Days Korea 2016] Track1 - Mellanox CloudX - Acceleration for Cloud...
John Spray - Ceph in Kubernetes
OpenStack Networks the Web-Scale Way - Scott Laffer, Cumulus Networks
HA in OpenStack service - meetup #9
Boyan Krosnov - Building a software-defined cloud - our experience
Tối ưu hiệu năng đáp ứng các yêu cầu của hệ thống 4G core
Is there still room for innovation in container orchestration and scheduling
Puppet + Windows Nano Server
OpenNebulaConf 2016 - OpenNebula 5.0 Highlights and Beyond by Ruben S. Monter...
OpenNebulaConf2018 - We use OpenNebula everywhere now - Florian Heigl and Tho...
Routed Fabrics For Ceph
Deploying CloudStack and Ceph with flexible VXLAN and BGP networking
Ad

Viewers also liked (7)

PDF
Welcome talk unleashing the future of open-source enterprise cloud computing
PDF
High Performance Computing Cloud at SURFsara: Experiences with OpenNebula 3.x
PDF
Community Clouds from Scratch
PDF
rOCCI – Providing Interoperability through OCCI 1.1 Support for OpenNebula
PDF
CentOS and OpenNebula, a Perfect Match
PDF
How Can OpenNebula Fit Your Needs: A European Project Feedback
PPTX
Opening the Path to Technical Excellence
Welcome talk unleashing the future of open-source enterprise cloud computing
High Performance Computing Cloud at SURFsara: Experiences with OpenNebula 3.x
Community Clouds from Scratch
rOCCI – Providing Interoperability through OCCI 1.1 Support for OpenNebula
CentOS and OpenNebula, a Perfect Match
How Can OpenNebula Fit Your Needs: A European Project Feedback
Opening the Path to Technical Excellence
Ad

Similar to Making Clouds: Turning OpenNebula into a Product (20)

PPTX
Openstack Diablo Survey
PPT
IBM SmartCloud Enterprise - A Secure Infrastructure for Test and Development
PPTX
Sanger, upcoming Openstack for Bio-informaticians
PPTX
Flexible compute
PDF
Vstorm Storage Architecture V1.1
PDF
Linuxtag 2012 - OpenNebula
PDF
Open nebula froscon
PDF
Building IaaS Clouds and the Art of Virtual Machine Management: A Practical G...
PPTX
Overview: Building Open Source Cloud Computing Environments
PPT
Farms, Fabrics and Clouds
PDF
OpenStack Tutorial
PPTX
Windows Azure IaaS
PPTX
10052016115118 (2).pptx
PDF
Txlf2012
PPTX
Cloud stack overview
PDF
How DreamHost builds a Public Cloud with OpenStack
PDF
How DreamHost builds a public cloud with OpenStack.pdf
PPTX
Building Blocks of the Private Cloud - Compute
PDF
Crash Course on Open Source Cloud Computing
Openstack Diablo Survey
IBM SmartCloud Enterprise - A Secure Infrastructure for Test and Development
Sanger, upcoming Openstack for Bio-informaticians
Flexible compute
Vstorm Storage Architecture V1.1
Linuxtag 2012 - OpenNebula
Open nebula froscon
Building IaaS Clouds and the Art of Virtual Machine Management: A Practical G...
Overview: Building Open Source Cloud Computing Environments
Farms, Fabrics and Clouds
OpenStack Tutorial
Windows Azure IaaS
10052016115118 (2).pptx
Txlf2012
Cloud stack overview
How DreamHost builds a Public Cloud with OpenStack
How DreamHost builds a public cloud with OpenStack.pdf
Building Blocks of the Private Cloud - Compute
Crash Course on Open Source Cloud Computing

Recently uploaded (20)

PPTX
Cloud computing and distributed systems.
PPTX
Digital-Transformation-Roadmap-for-Companies.pptx
PDF
Electronic commerce courselecture one. Pdf
PPTX
KOM of Painting work and Equipment Insulation REV00 update 25-dec.pptx
PDF
NewMind AI Weekly Chronicles - August'25 Week I
PDF
Unlocking AI with Model Context Protocol (MCP)
PPTX
20250228 LYD VKU AI Blended-Learning.pptx
PDF
Peak of Data & AI Encore- AI for Metadata and Smarter Workflows
PDF
The Rise and Fall of 3GPP – Time for a Sabbatical?
PPT
“AI and Expert System Decision Support & Business Intelligence Systems”
PPTX
sap open course for s4hana steps from ECC to s4
PDF
Empathic Computing: Creating Shared Understanding
PPT
Teaching material agriculture food technology
PDF
Dropbox Q2 2025 Financial Results & Investor Presentation
PDF
7 ChatGPT Prompts to Help You Define Your Ideal Customer Profile.pdf
PDF
Optimiser vos workloads AI/ML sur Amazon EC2 et AWS Graviton
PDF
TokAI - TikTok AI Agent : The First AI Application That Analyzes 10,000+ Vira...
PDF
Architecting across the Boundaries of two Complex Domains - Healthcare & Tech...
PDF
Machine learning based COVID-19 study performance prediction
PDF
Network Security Unit 5.pdf for BCA BBA.
Cloud computing and distributed systems.
Digital-Transformation-Roadmap-for-Companies.pptx
Electronic commerce courselecture one. Pdf
KOM of Painting work and Equipment Insulation REV00 update 25-dec.pptx
NewMind AI Weekly Chronicles - August'25 Week I
Unlocking AI with Model Context Protocol (MCP)
20250228 LYD VKU AI Blended-Learning.pptx
Peak of Data & AI Encore- AI for Metadata and Smarter Workflows
The Rise and Fall of 3GPP – Time for a Sabbatical?
“AI and Expert System Decision Support & Business Intelligence Systems”
sap open course for s4hana steps from ECC to s4
Empathic Computing: Creating Shared Understanding
Teaching material agriculture food technology
Dropbox Q2 2025 Financial Results & Investor Presentation
7 ChatGPT Prompts to Help You Define Your Ideal Customer Profile.pdf
Optimiser vos workloads AI/ML sur Amazon EC2 et AWS Graviton
TokAI - TikTok AI Agent : The First AI Application That Analyzes 10,000+ Vira...
Architecting across the Boundaries of two Complex Domains - Healthcare & Tech...
Machine learning based COVID-19 study performance prediction
Network Security Unit 5.pdf for BCA BBA.

Making Clouds: Turning OpenNebula into a Product

  • 1. Making clouds: turning OpenNebula into a product Carlo Daffara, CloudWeavers
  • 5. The Cloud extends the traditional advantages of“ ” virtualization platforms to scale-out software. It is an opportunity to rethink hardware deployment ... …it does not means that all clouds need to be public
  • 9. http: blippex.github.io updates 2013 09 23 why-we-moved-away-from-aws.html// / / / / /
  • 13. Four major platforms: • CloudStack • Eucalyptus • OpenNebula • OpenStack Lots of minor ones: Proxmox, Ovirt, Ganeti, OpenQRM, Enomaly, Archipel...
  • 14. Let's debate first about what architecture we are aiming for. OpenStack & Eucalyptus are modeled and structured around AWS EC2, that is the clear market leader in/ the public cloud market.
  • 20. Service Manager database 8-core 2.66 gigahertz (GHz) CPU 8 gigabytes (GB) of RAM 80 GB of available disk space RAID Level 1 or Level 10 drive* Service Manager management server 4-Core 2.66 GHz CPU 8 GB of RAM 10 GB of available disk space Service Manager console 2-core 2.0 GHz CPU 4 GB of RAM 10 GB of available disk space Data warehouse management server 4-Core 2.66 GHz CPU 8 GB of RAM 10 GB of available disk space Data warehouse databases 8-core 2.66 GHz CPU 8 GB of RAM 400 GB of available disk space RAID Level 1 or Level (1+0) drive Self-Service Portal: Web Content Server with SharePoint Web Parts 8-Core 2.66 GHz CPU 8-core, 16GB RAM, 80 GB of available hard disk space http: technet.microsoft.com en-us library hh524328.aspx// / / /
  • 30. I O Access pattern/ I O Characteristics/ Typical Applications Streaming Reads 100 Reads; Large contiguous requests; 1-64% concurrent requests. May be threaded. Media Servers ( ideo on-demand, etc.).V irtual Tape Libraries ( TL), ApplicationV V Servers Streaming Writes 100 Writes; Large contiguous requests; 1-64% concurrent requests. May be threaded. Media Capture, TL, Medical Imaging,V Archiving, Backup, ideo Surveillance,V Reference Data OLTP Typically 2KB 16KB request sizes; Read modify,– write, verify operations resulting in 2 reads for every write; Primarily random accesses. Large number of concurrent requests. When running SQL statements in parallel, Database will perform typically large random I Os./ Databases (SAP, Oracle, SQL), Online Transaction Servers File Server Moderate distribution of request sizes from 4KB to 64KB, however 4KB and 64KB comprise 70 of% requests; Primarily random; Generally 4 reads for every write operation. Large number of concurrent requests during peak operational periods. File and Printer Servers, e-mail (Exchange, Notes), Decision Support Systems Web Server Wide distribution of request sizes from 512 bytes to 512KB; Primarily random accesses; Large number of concurrent requests during peak operational periods Web Services, Blogs, RSS Feeds, Shopping Carts, Search Engines, Storage Services Workstations Primarily small to medium request sizes; 80% sequential and 20 random; Generally 4 reads for% every write operation. 1-4 concurrent requests. Business Productivity, Scientific Engineering/ Applications http: gerardnico.com wiki data storage input output access pattern// / / _ / _ _ _
  • 32. Some additional tips for Windows: • K M badly interacts with Windows 7 8 clock drivers, causing high cpuV / consumption. Use: bcdedit /set {default} useplatformclock true and RAW = [ type= "KVM", data = "<clock offset='localtime'/>" ] • “Default cirrus GA driver unsuitable for Windows due to pathologicalV performance issues in text mode” This is not a problem in latest K M, however having vga std is betterV = anyway • For Windows servers with lots of small files: fsutil behaviour set disablelastaccess 1 (equivalent to noatime on linux) fsutil behaviour set mftzone 2 (adds another 12.5 disk space to the MFT zone)% • Disable 8.3 namespace creation: fsutil.exe behavior set disable8dot3 1 (huge boost for dirs, files with matching initial names)
  • 33. Some useful additions: GateOne (https: github.com liftoff GateOne// / / ) a very efficient web SSH interface, similar to vncproxy. Works well added as a link in Sunstone.
  • 34. M ray (https: github.com coriolis vmxray): a pure javascript MV X // / / V explorer, allows to enter inside of an image, view and extract files.
  • 35. Some additional tools: LibGuestFS (http: libguestfs.org// /) the swiss army knife of M images. AllowsV for copy in and out of a M, file operations, mount guest filesystem on host,V Windows registry editing... S3QL (http: code.google.com p s3ql// / / /) a FUSE filesystem that mounts and operates on Amazon S3, Google storage and OpenStack-compatible storage. Supports compression, encryption and deduplication. Quite useful if you want to move images to-from Amazon or Google. IPOP (http: www.grid-appliance.org wiki index.php IPOP// / / / ) IPOP (IP over P2P) is an open-source research development project that provides a decentralized,/ distributed overlay virtual network. It allows users to easily deploy PNsV across multiple domains, and is used in applications including virtual private clusters for cloud grid computing./ Only thin features added directly to the platform...“ ”
  • 38. We use Ms to provide additional features:V Guacamole (http: sourceforge.net projects guacamole// / / /) exceptional gateway that turns RDP into HTML5. Allows for pure web-based access to Windows desktops from everywhere: Other examples: Zenoss for agentless monitoring (or Hyperic for agent-based monitors), backup tools like OpenDedup...
  • 39. A special note on DI:V Jerry Chen of Mware is generally credited with coining the term DI whichV “V ” led to the redefinition of an entire industry. Mware had 10,400 employees.V Of that group, about one-third of them use DI-based virtual desktops as theirV primary production work desktops. About 1,000 of them use a thin-client device as their only corporate-issued client device. First problem: Microsoft licensing. “dedicating an entire Remote Desktop virtual server to just one single user is cheaper than most DI scenarios and gives users the same benefits, namelyV having their own Desktop M where they can do what they want. This single‘ ’ V ‘ user terminal server scenario is with about 475 per user (6 years) not only’ – $ 60 cheaper, but less complicated and legally more safe than standard MS% DI licensing. Decoding the Microsoft DI Licensing Arcanum, LoginV " V Consulting
  • 42. A useful trick: on hook RUNNING increase the readahead of the rotative“ ” medium (blockdev --setra 2048 or higher); you can reduce the boot time of a Windows7 machine by 35 . You time it to return to much lower values% after a predetermined interval.
  • 43. Apps are moving to be pure webapps, no client installation needed so“ ” – you can skip Windows. Having the M ready to use also facilitates theV adoption of new tools, and lots of experimentation. Locally hosted Ms thatV export a web application are becoming the norm, and you can remote the remaining Windows apps through RDP, so you are actually free to build your desktop as you like. Royal Academy of Engineering, The future of computing , 2012“ ”
  • 45. We have our own thin desktop based on Linux called EveryDesk ( http://sourceforge.net/projects/everydesk/) that requires just 90MB of ram per desktop, or for the more daring users:
  • 46. ..you can use ChromeOS from Google. There is an unofficial build for 86X and x86 64 available daily here (_ http://chromium.arnoldthebat.co.uk/) that runs perfectly within OpenNebula. You create the images as non-persistent, and destroy them later on. Bt using a WB cache and snapshots to create the non-persistent images you end up with most of the pages already in cache, so boot is nearly instantaneous. Write are small and sparse, so you are basically CPU-bound and can run reasonably well 10-15 ChromeOS desktops per core.
  • 47. 38 , 5W, no moving part. Use Android aSPICE as a client+Autostart$
  • 48. The MTBF of a standard PC is 30,000 hours or 3.4 years; for every 10c temperature increase, MTBF is cut in half. Since in many pc closet the“ ” temperature is 10 to 20 degrees higher, we assume a MTBF of 1yr. 4pc cloud: 4 failures yr, Ms on failed node are down for 5-10 mins - 20/ V > to 40 min year, 99.99 assuming available power/ % Availability per day per month per year 99.999% 00:00:00.4 00:00:26 00:05:15 99.99% 00:00:08 00:04:22 00:52:35 99.9% 00:01:26 00:43:49 08:45:56 99% 00:14:23 07:18:17 87:39:29