Sheena Iyengar on the art of choosing | Video on TED.com

Sheena Iyengar on the art of choosing | Video on TED.com

http://www.ted.com/talks/lang/eng/clay_shirky_how_cognitive_surplus_will_change_the_world.html?utm_source=newsletter_weekly_2010-06-29

http://www.ted.com/talks/lang/eng/clay_shirky_how_cognitive_surplus_will_change_the_world.html?utm_source=newsletter_weekly_2010-06-29

Warehouse scale computing: Lessons from Google's datacenter design

Google's approach to datacenter design is interesting: Google released a 6.5 minute video of their datacenter. Amazing is understatement. It looks like set of Matrix . Google Datacenter has 45 containers (like ship containers) in which they host 45000 servers.

Luiz André Barroso and Urs Hölzle of Google have shared best practices of datacenter design in thier book 'Datacenter as a machine; Introduction to design of warehouse scale computing' . Very interesting ideas there.

Warehouse scale computing views entire datacenter as a computer and not individual server (pizza box approach) Message: Come out of pizza box computing/regrigerator computing ; warehouse scale computing is here.

Link to Google's 6.5 minute video on their datacenter. http://www.youtube.com/watch?v=zRwPSFpLX8I&feature=player_embedded

The ideas incorporated in Barroso and Hölzle book 'Warehouse scale computing' are too important to be not available in this blog. Presenting abstract from their book :

=======

Abstract of Luiz André Barroso and Urs Hölzle book
'The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines'

As computation continues to move into the cloud, the computing platform of interest no longer resembles a pizza box or a refrigerator, but a warehouse full of computers. These new large datacenters are quite different from traditional hosting facilities of earlier times and cannot be viewed simply as a collection of co-located servers. Large portions of the hardware and software resources in these facilities must work in concert to efficiently deliver good levels of Internet service performance, something that can only be achieved by a holistic approach to their design and deployment. In other words, we must treat the datacenter itself as one massive warehouse-scale computer (WSC). We describe the architecture of WSCs, the main factors influencing their design, operation, and cost structure, and the characteristics of their software base. We hope it will be useful to architects and programmers of today’s WSCs, as well as those of future many-core platforms which may one day implement the equivalent of today’s WSCs on a single board.

Book can be downloaded from site: http://www.morganclaypool.com/doi/pdf/10.2200/S00193ED1V01Y200905CAC006

Read it for important ideas on Google way of cost effective . energy efficent way to computing.

OSS BSS Cost of Ownership

For Telecom Operators OSS and BSS acquisition and maintenance takes up lion's share of IT Spend. Just how much does it cost the tel co to acquire and maintain OSS & BSS? A perspective.

------------
Indian newspapers and telecoms sites have been carrying articles about BSNL Phase six tender.
Part 4 of phase 6 tender is focused on procurement of Operations support systems and business support systems.
According to press reports, lowest bid for OSS/BSS is approximately INR 3600 crores to support around 249 million subscribers.
How 249 million subs? 93 million subs for ph6.1 ; 93 million for 6.2 and 60 million existing subs totals to 249 million subs.
Assuming existing infrastructure of INR 200 crores of hardware will be reused;this translates to additional 16 cents per sub.

This translates to approximately INR 149 per sub or USD 3 per sub for entire OSS/BSS stack. Scope includes software licenses, hardware, deployment, implementation and support for period of 7 years after implementation. USD 3 per sub is possibly a benchmark ; actually figures will be lower than that. Assuming existing hardware infrastructure of approximately INR 200 crores will be reused.
India/BSNL can certainly be sourcing hub for telco's in emerging markets like Africa.

Open private discussion on following:
How does USD 3 rate compare with private operators in India? Are they also doing similar investments in OSS/BSS?
Is it possible to cut investment costs in OSS/BSS given declining ARPU's.
Are technology options available that can help cut the cost further.

Can Google's infrastructure design and operations based on warehouse scale computing offer way to bring down this cost?

What models can be deployed to achieve similar level of IT support with lower capital intensity.
Is capital intensity consistent across other operators in other countries.