際際滷

際際滷Share a Scribd company logo

Kognitio cloud webinar feb 2013

Kognitio
Kognitio

This document summarizes a web seminar about Kognitio Cloud on Amazon Web Services. The presentation will include a brief overview of Kognitio and Kognitio Cloud, a demonstration of deploying it on AWS, and a Q&A session. It will be hosted by Michael Hiskey, VP of Marketing at Kognitio, and the key presenter will be Ian Bird, VP of Cloud Solutions at Kognitio.

1 of 32
Download to read offline
Kognitio Cloud on Amazon Web Services Web Seminar February 2013
Todays Web Seminar: Kognitio Cloud Format & Agenda Brief Overview Kognitio and Kognitio Cloud Demonstration - spinning up on AWS in minutes Q&A - open discussion Presenters Host Michael Hiskey Vice President, Marketing & Business Development Kognitio is leading the Big Data Analytics market and Michael Leads Marketing there Key Note Presenter Ian Bird As VP Cloud Solutions for Kognitio, Ian is responsible for defining the Kognitio Cloud solutions and delivery. He works closely with clients to ensure successful Kognitio Cloud implementations
Kognitio Kognitio is focused on providing the History of client success premier high-performance analytical platform to power business insight around the world Kognitio invented the in-memory analytical platform, first taking it to market in 1989 Privately held Labs in the UK - HQ in New York, NY
Kognitio Analytical Platform A high performance in-memory analytical platform that doesnt require specialized Hardware Software quick simple deployment on commodity hardware or Cloud Scalable Linear scale-out through best of breed parallelism Powerful Unrivalled MPP analytical performance Harnesses all CPU cores made available Low TCO Linux, commodity hardware, no special hardware needs SQL relational core familiar to most DBAs
For Analytics, the CPU is King The key metric of any analytical platform should be GB/CPU It needs to effectively utilize all available cores Hyper threads are NOT the equivalent of cores Interactive/adhoc analytics: THINK data to core ratios 10GB data per CPU core Every cycle is precious CPU cores need to used efficiently Techniques such as dynamic machine code generation Careful performance impact of compression: Makes disk-based databases go faster Makes in-memory databases go slower
Speed & Scale are the Requirements Memory & CPU on an individual server = NOWHERE near enough for big data Moores Law The power of a processor doubles every two years Data volumes Double every year!! The only way to keep up is to parallelise or scale-out Combine the RAM of many individual servers Many many CPU cores spread across many CPUs, housed in many individual computers Data is split across all the CPU cores All database operations need to be parallelised with no points of serialisation This is true MPP Every CPU core in Every Every server needs to efficiently involved in Every query
How much RAM? Kognitio harnesses the RAM and CPU from large arrays of servers Its not about how much RAM you can squeeze into a single 64bit server Its standard server RAM Commodity price market very affordable capacities continually improving Were talking about Terabytes, tens of Terabytes and above of RAM
Kognitio Analytical Platform Architecture
Beyond SQL SQL is pervasive data management language Not suited to all types of processing Kognitio supports UDFs Plugins - functional extensions to SQL External scripts and binaries In-line within SQL utilize Perl, Java, R, SAS etc. Full control of degree of parallelism External tables Fetch data from other sources Integration with Hadoop to bring data into memory Syntax to define data locality and map reduce access Parallel load API for reduce to feed data to RAM fast Integration with HTTP fetch data from cloud storage e.g. Amazon S3
Kognitio Cloud We want to make in-memory accessible to all Our technology easily deploys onto Cloud architectures such as Amazon Web Services We have architected our Cloud to be as accessible as possible
Kognitio Analytical Platform Free software licence on Amazon Marketplace As a demo with data pre-loaded Load your own data One-click to launch
One-click deployment up to 68GB RAM
Multi-node available via CloudFormation Kognitio configured as a multi-node deployment Available as a trial platform on-demand kognitio.kognitiocloud.com Few steps to deployment
Register
Verify
Create the stack
Your system will spin up
16 nodes all running
That is enough RAM for 10,055,512,068 EPOS rows
That is enough RAM for RAM GB |Used GB |Free GB |Avail GB |% Used 812.5 |339.4 |473.1 |473.0 | 41.8%
Which we scan in 1.6 seconds
10 billion in 1.6 seconds
Find out your week to week performance 4.2 seconds
4.2 seconds
People that like salted peanuts also like just over a minute
Just over a minute
But 16 nodes is a lot of nodes Amazon have announced an new high memory instance type perfect for in-memory databases 240GB RAM per node 2 x Intel Xeon E5-2670 - total of 16 cores 2 x 120 GB SSD Utilises 10 GbE networking that is at the heart of their Cluster Compute environment.
So the same power But with 4 nodes With the same simple deployment These new scale points make big data in-memory analytics in the cloud even more ready to use
Deploy with other technologies on AWS Automatic deployment of Kognitio and BI tool on an AWS platform For self-service BI - see what we have done with NeutrinoBI nbi.kognitiocloud.com
Kognitio & NeutrinoBI demo architecture Web app & services tier Registrations Kognitio NeutrinoBI Client Application tier Root Volume Data Volume Analytical platform tier Kognitio DB Root Volume Security Group Data Volume
Get started now its FREE! kognitio.com/free Or for more information: kognitio.com/cloud
Thank You get in touch ! connect contact Michael Hiskey kognitio.com Vice President, Marketing & Business Development kognitio.tel michael.hiskey@kognitio.com Ian Bird kognitio.com/blog VP, Kognitio Cloud Ian.bird@kognitio.com twitter.com/kognitio NA: +1 855 KOGNITIO linkedin.com/companies/kognitio EMEA: +44 1344 300 770 tinyurl.com/kognitio youtube.com/kognitio

More Related Content

Kognitio cloud webinar feb 2013

  • 1. Kognitio Cloud on Amazon Web Services Web Seminar February 2013
  • 2. Todays Web Seminar: Kognitio Cloud Format & Agenda Brief Overview Kognitio and Kognitio Cloud Demonstration - spinning up on AWS in minutes Q&A - open discussion Presenters Host Michael Hiskey Vice President, Marketing & Business Development Kognitio is leading the Big Data Analytics market and Michael Leads Marketing there Key Note Presenter Ian Bird As VP Cloud Solutions for Kognitio, Ian is responsible for defining the Kognitio Cloud solutions and delivery. He works closely with clients to ensure successful Kognitio Cloud implementations
  • 3. Kognitio Kognitio is focused on providing the History of client success premier high-performance analytical platform to power business insight around the world Kognitio invented the in-memory analytical platform, first taking it to market in 1989 Privately held Labs in the UK - HQ in New York, NY
  • 4. Kognitio Analytical Platform A high performance in-memory analytical platform that doesnt require specialized Hardware Software quick simple deployment on commodity hardware or Cloud Scalable Linear scale-out through best of breed parallelism Powerful Unrivalled MPP analytical performance Harnesses all CPU cores made available Low TCO Linux, commodity hardware, no special hardware needs SQL relational core familiar to most DBAs
  • 5. For Analytics, the CPU is King The key metric of any analytical platform should be GB/CPU It needs to effectively utilize all available cores Hyper threads are NOT the equivalent of cores Interactive/adhoc analytics: THINK data to core ratios 10GB data per CPU core Every cycle is precious CPU cores need to used efficiently Techniques such as dynamic machine code generation Careful performance impact of compression: Makes disk-based databases go faster Makes in-memory databases go slower
  • 6. Speed & Scale are the Requirements Memory & CPU on an individual server = NOWHERE near enough for big data Moores Law The power of a processor doubles every two years Data volumes Double every year!! The only way to keep up is to parallelise or scale-out Combine the RAM of many individual servers Many many CPU cores spread across many CPUs, housed in many individual computers Data is split across all the CPU cores All database operations need to be parallelised with no points of serialisation This is true MPP Every CPU core in Every Every server needs to efficiently involved in Every query
  • 7. How much RAM? Kognitio harnesses the RAM and CPU from large arrays of servers Its not about how much RAM you can squeeze into a single 64bit server Its standard server RAM Commodity price market very affordable capacities continually improving Were talking about Terabytes, tens of Terabytes and above of RAM
  • 9. Beyond SQL SQL is pervasive data management language Not suited to all types of processing Kognitio supports UDFs Plugins - functional extensions to SQL External scripts and binaries In-line within SQL utilize Perl, Java, R, SAS etc. Full control of degree of parallelism External tables Fetch data from other sources Integration with Hadoop to bring data into memory Syntax to define data locality and map reduce access Parallel load API for reduce to feed data to RAM fast Integration with HTTP fetch data from cloud storage e.g. Amazon S3
  • 10. Kognitio Cloud We want to make in-memory accessible to all Our technology easily deploys onto Cloud architectures such as Amazon Web Services We have architected our Cloud to be as accessible as possible
  • 11. Kognitio Analytical Platform Free software licence on Amazon Marketplace As a demo with data pre-loaded Load your own data One-click to launch
  • 12. One-click deployment up to 68GB RAM
  • 13. Multi-node available via CloudFormation Kognitio configured as a multi-node deployment Available as a trial platform on-demand kognitio.kognitiocloud.com Few steps to deployment
  • 17. Your system will spin up
  • 18. 16 nodes all running
  • 19. That is enough RAM for 10,055,512,068 EPOS rows
  • 20. That is enough RAM for RAM GB |Used GB |Free GB |Avail GB |% Used 812.5 |339.4 |473.1 |473.0 | 41.8%
  • 21. Which we scan in 1.6 seconds
  • 22. 10 billion in 1.6 seconds
  • 23. Find out your week to week performance 4.2 seconds
  • 25. People that like salted peanuts also like just over a minute
  • 26. Just over a minute
  • 27. But 16 nodes is a lot of nodes Amazon have announced an new high memory instance type perfect for in-memory databases 240GB RAM per node 2 x Intel Xeon E5-2670 - total of 16 cores 2 x 120 GB SSD Utilises 10 GbE networking that is at the heart of their Cluster Compute environment.
  • 28. So the same power But with 4 nodes With the same simple deployment These new scale points make big data in-memory analytics in the cloud even more ready to use
  • 29. Deploy with other technologies on AWS Automatic deployment of Kognitio and BI tool on an AWS platform For self-service BI - see what we have done with NeutrinoBI nbi.kognitiocloud.com
  • 30. Kognitio & NeutrinoBI demo architecture Web app & services tier Registrations Kognitio NeutrinoBI Client Application tier Root Volume Data Volume Analytical platform tier Kognitio DB Root Volume Security Group Data Volume
  • 31. Get started now its FREE! kognitio.com/free Or for more information: kognitio.com/cloud
  • 32. Thank You get in touch ! connect contact Michael Hiskey kognitio.com Vice President, Marketing & Business Development kognitio.tel michael.hiskey@kognitio.com Ian Bird kognitio.com/blog VP, Kognitio Cloud Ian.bird@kognitio.com twitter.com/kognitio NA: +1 855 KOGNITIO linkedin.com/companies/kognitio EMEA: +44 1344 300 770 tinyurl.com/kognitio youtube.com/kognitio