Table of Contents
1 The Wall of Water 1
And Then There Was One 1
Commercial Supercomputing Comes of Age 2
A Stitch in Time 2
The Yellow Elephant in the Room 4
Scaling Yahoovians 5
Supercomputers Are Platforms 6
Big Data! Big Bang! 7
Endless Possibilities 8
2 Big Data: The Ultimate Computing Platform 11
Introduction to Platforms 11
Come Fly with Me 12
Computing Platforms 12
The End of an Era 13
Back to the Future 14
Engineering Big Data Platforms 15
The Art and Craft of Platform Engineering 16
KISS Me Kate 17
Perpetual Prototyping 18
Optimize Everything at Internet Scale 19
The Response Time Continuum 20
Epic Fail Insurance 21
Mind the Gap 23
I'll Take Silos for $1000, Alex 24
3 Organizations: The Other Platform 25
From Myelin to Metal 25
Silos 26
Industrial Grain Elevators 28
Platforms 1, Silos 0 29
Panic! Now! 30
Fear and Loathing 30
Risky Business 32
Probability and Outcome 32
Quantitative Qualities 33
The Soft Platform 33
4 The Reservoir of Data 35
The Actual Internet 35
Best of Inbred 36
Drowning Not Waving 38
Spinning Rust 39
A Spectrum of Perishability 3 9
Enclosed Water Towers 41
The Big Data Water District 42
The HDFS Reservoir 43
Third Eye Blind 44
Spectrum of Analytic Visibility 45
The Cost of Flexibility 47
5 Cloudy with a Chance of Meatballs: When Clouds Meet Big Data 49
The Big Tease 49
Scalability 101 50
Motherboards and Apple Pie 52
Being and Nothingness 53
Parity Is for Farmers 54
Google in Reverse 55
Isolated Thunderstorms 56
The Myth of Private Clouds 57
My Other Data Center Is an RV Park 59
Converge Conventionally 59
6 Haystacks and Headgames 61
The Demise of Counting 61
Lose the Haystack 63
Mind Another Gap 64
Believing Is Seeing 65
Spatial Intelligence 67
Associative Supercomputing 68
Back from the Future 69
Acknowledgments 70