Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Big Data and Machine Learning on OpenStack Backed by Nova-LXD

Addressing concerns about virtualized big data environments - hypervisor overhead, resource management, data locality issues.
by

Ryan Beisner

on 20 June 2017

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Big Data and Machine Learning on OpenStack Backed by Nova-LXD

Using Spark for Anomaly (Fraud) Detection
credit: Michael Vogiatzis
Big Data and Machine Learning on
OpenStack Backed by Nova-LXD

Model,
Deploy,
Manage:
{
Applications
}
{
Operations
}
On
Metal
On OpenStack
Nova-LXD
On
Public
Clouds
LXD
On OpenStack
Nova-KVM
Using Spark for Anomaly (Fraud) Detection
Michael Vogiatzis
http://bit.ly/2drqOch
Big Data and Machine Learning on
OpenStack Backed by Nova-LXD
and with special thanks to:
https://maas.io
https://jujucharms.com
https://www.ubuntu.com/cloud/lxd
https://docs.openstack.org/developer/charm-guide
additional links and resources:
Q & A
Ryan Beisner, Andrew McLeod
OpenStack Engineering Team, Canonical

https://github.com/ubuntu-openstack/bigdata-novalxd

OpenStack Summit - Barcelona - October 2016
credit: Michael Vogiatzis
Anomalies
'Unsupervised'
Learning
Hardware
Software
Nova KVM
Nova LXD
Bare Metal
Nova LXD
Nova KVM
Bare Metal
Nova LXD
Nova KVM
Bare Metal
Challenges:
Performance
Cost & Efficiency
Data Security
Big Software
Same Hardware for All Scenarios
12 Physical Machines
Commodity Hardware
Multiple Substrates
Same Software for All Scenarios
Ubuntu Server 16.04 LTS
Juju + MAAS
OpenStack Charms
Big Data Charms
OpenStack Mitaka
Apache Bigtop Spark 1.5.1
Apache Bigtop Hadoop 2.7.1

#openstack-charms
#juju
#ubuntu-server
Ryan Beisner, Andrew McLeod
OpenStack Engineering Team, Canonical
https://github.com/ubuntu-openstack/bigdata-novalxd
Test Duration -->
Lower is Better
Lower is Better
Lower is Better
1.10x metal
1.95x metal
1.02x metal
2.59x metal
1.11x metal
8.95x metal
1.06x
1.23x
1.17x
1.08x
2.47x
8.69x
Full transcript