Slide 1

Slide 1 text

Scorch Marty Schoch @mschoch 2018-08-03 a New Index for Bleve

Slide 2

Slide 2 text

No content

Slide 3

Slide 3 text

No content

Slide 4

Slide 4 text

Too Big and Too Slow Bleve Index

Slide 5

Slide 5 text

No content

Slide 6

Slide 6 text

Tai Marty Sreekanth Abhinav Steve Aruna Alex Couchbase Full Text Search

Slide 7

Slide 7 text

Design

Slide 8

Slide 8 text

No content

Slide 9

Slide 9 text

No content

Slide 10

Slide 10 text

No Top-Level Bleve API Changes

Slide 11

Slide 11 text

No Top-Level Bleve API Changes Bleve

Slide 12

Slide 12 text

No Top-Level Bleve API Changes Bleve Apps

Slide 13

Slide 13 text

No Top-Level Bleve API Changes Bleve Apps Couchbase FTS

Slide 14

Slide 14 text

No content

Slide 15

Slide 15 text

Segmented Index

Slide 16

Slide 16 text

Monolithic Key/Value Index

Slide 17

Slide 17 text

Monolithic Key/Value Index Update

Slide 18

Slide 18 text

Monolithic Key/Value Index Back Index Update

Slide 19

Slide 19 text

Monolithic Key/Value Index Back Index Update

Slide 20

Slide 20 text

Monolithic Key/Value Index Back Index Current Values Update

Slide 21

Slide 21 text

Monolithic Key/Value Index Back Index New Values Current Values Update

Slide 22

Slide 22 text

Monolithic Key/Value Index Back Index New Values Current Values Update

Slide 23

Slide 23 text

Monolithic Key/Value Index Back Index Current Values Update

Slide 24

Slide 24 text

Monolithic Key/Value Index Back Index Current Values Update

Slide 25

Slide 25 text

Monolithic Key/Value Index Update

Slide 26

Slide 26 text

Monolithic Key/Value Index Update

Slide 27

Slide 27 text

Monolithic Key/Value Index Update

Slide 28

Slide 28 text

Monolithic Key/Value Index

Slide 29

Slide 29 text

Segmented Index

Slide 30

Slide 30 text

Segmented Index Update

Slide 31

Slide 31 text

Segmented Index Update

Slide 32

Slide 32 text

Segmented Index Update

Slide 33

Slide 33 text

New Storage Abstractions

Slide 34

Slide 34 text

No content

Slide 35

Slide 35 text

No content

Slide 36

Slide 36 text

No content

Slide 37

Slide 37 text

No content

Slide 38

Slide 38 text

No content

Slide 39

Slide 39 text

No content

Slide 40

Slide 40 text

Term Dictionary

Slide 41

Slide 41 text

Postings List

Slide 42

Slide 42 text

No content

Slide 43

Slide 43 text

randomised

Slide 44

Slide 44 text

randomised

Slide 45

Slide 45 text

Levenshtein Edit Distance randomised randomized ~1

Slide 46

Slide 46 text

No content

Slide 47

Slide 47 text

No content

Slide 48

Slide 48 text

Finite State Transducer Term Dictionary Levenshtein Automata mon, tues, thurs tues~2

Slide 49

Slide 49 text

Vellum backed Term Dictionary

Slide 50

Slide 50 text

Bitmap Postings List 0 1 n … 2 3

Slide 51

Slide 51 text

Roaring Bitmap backed Postings List •Uncompressed Bitsets •Slice of Integers •Run-length encoding •Chunked Encoding, combining each

Slide 52

Slide 52 text

Couchbase Release Schedule

Slide 53

Slide 53 text

No content

Slide 54

Slide 54 text

Proof of Concept

Slide 55

Slide 55 text

$

Slide 56

Slide 56 text

mkdir scorch $

Slide 57

Slide 57 text

Memory Only Segments

Slide 58

Slide 58 text

Index Snapshot Introducer Application Goroutine introduction channel read read/write

Slide 59

Slide 59 text

Index Snapshot Introducer Application Goroutine Batch() introduction channel read read/write

Slide 60

Slide 60 text

Index Snapshot Introducer Application Goroutine Batch() introduction channel read read/write

Slide 61

Slide 61 text

Index Snapshot Introducer Application Goroutine Batch() introduction channel read read/write

Slide 62

Slide 62 text

Index Snapshot Introducer Application Goroutine Segment Introduction Batch() introduction channel read read/write

Slide 63

Slide 63 text

Index Snapshot Introducer Application Goroutine Batch() introduction channel read read/write

Slide 64

Slide 64 text

Index Snapshot Introducer Application Goroutine Batch() introduction channel read read/write Segment Introduction

Slide 65

Slide 65 text

Index Snapshot Introducer Application Goroutine Batch() introduction channel read read/write Segment Introduction

Slide 66

Slide 66 text

Index Snapshot Introducer Application Goroutine Batch() introduction channel read read/write Segment Introduction

Slide 67

Slide 67 text

Index Snapshot Introducer Application Goroutine Batch() introduction channel read read/write Segment Introduction

Slide 68

Slide 68 text

Index Snapshot Introducer Application Goroutine Batch() introduction channel read read/write

Slide 69

Slide 69 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write f Persister - lastEpoch 26 Persister - lastEpoch 26

Slide 70

Slide 70 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write f Persister - lastEpoch 26 Persister - lastEpoch 26

Slide 71

Slide 71 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write f Persister - lastEpoch 26 Persister - lastEpoch 26

Slide 72

Slide 72 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write f Persister - lastEpoch 26 Persister - lastEpoch 26

Slide 73

Slide 73 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write f Persister - lastEpoch 26 Persister - lastEpoch 26 f.bolt

Slide 74

Slide 74 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write f Persister - lastEpoch 26 Persister - lastEpoch 26 f.bolt root.bolt 27 a, b, c, d, e, f

Slide 75

Slide 75 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write f Persister - lastEpoch 26 Persister - lastEpoch 26 f.bolt root.bolt 27 a, b, c, d, e, f Persister - lastEpoch 27

Slide 76

Slide 76 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write f Persister - lastEpoch 26 Persister - lastEpoch 26 f.bolt root.bolt 27 a, b, c, d, e, f Persister - lastEpoch 27

Slide 77

Slide 77 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write f Persister - lastEpoch 26 Persister - lastEpoch 26 f.bolt root.bolt 27 a, b, c, d, e, f Persister - lastEpoch 27

Slide 78

Slide 78 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write f Persister - lastEpoch 26 Persister - lastEpoch 26 f.bolt root.bolt 27 a, b, c, d, e, f Persister - lastEpoch 27

Slide 79

Slide 79 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write f Persister - lastEpoch 26 Persister - lastEpoch 26 f.bolt root.bolt 27 a, b, c, d, e, f Persister - lastEpoch 27

Slide 80

Slide 80 text

No content

Slide 81

Slide 81 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write f Persister - lastEpoch 26 Persister - lastEpoch 26 f.zap root.bolt 27 a, b, c, d, e, f Persister - lastEpoch 27

Slide 82

Slide 82 text

4x Faster and 10x Smaller

Slide 83

Slide 83 text

No content

Slide 84

Slide 84 text

No content

Slide 85

Slide 85 text

Team

Slide 86

Slide 86 text

Merging Segments (Steve)

Slide 87

Slide 87 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write Persister f Merger - lastPlanned 26

Slide 88

Slide 88 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write Persister f Merger - lastPlanned 26

Slide 89

Slide 89 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write Persister f Merger - lastPlanned 26

Slide 90

Slide 90 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write Persister f Merger - lastPlanned 26

Slide 91

Slide 91 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write Persister f Merger - lastPlanned 26 Merge Introduction g.zap

Slide 92

Slide 92 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write Persister f Merger - lastPlanned 26

Slide 93

Slide 93 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write Persister f Merger - lastPlanned 26 Merge Introduction g.zap

Slide 94

Slide 94 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write Persister f Merger - lastPlanned 26 Merge Introduction g.zap Merger - lastPlanned 27

Slide 95

Slide 95 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write Persister f Merger - lastPlanned 26 Merge Introduction g.zap Merger - lastPlanned 27

Slide 96

Slide 96 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write Persister Merger - lastPlanned 26 Merge Introduction g.zap Merger - lastPlanned 27

Slide 97

Slide 97 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write Persister Merger - lastPlanned 26 Merge Introduction g.zap Merger - lastPlanned 27 g

Slide 98

Slide 98 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write Persister Merger - lastPlanned 26 Merge Introduction g.zap Merger - lastPlanned 27 g Index Snapshot - epoch 28

Slide 99

Slide 99 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write Persister Merger - lastPlanned 26 Merge Introduction g.zap Merger - lastPlanned 27 g Index Snapshot - epoch 28

Slide 100

Slide 100 text

Index Snapshot - epoch 27 Introducer Application Goroutine introduction channel read read/write Persister Merger - lastPlanned 26 Merger - lastPlanned 27 g Index Snapshot - epoch 28

Slide 101

Slide 101 text

Document Values (Sreekanth)

Slide 102

Slide 102 text

Rollback (Abhinav)

Slide 103

Slide 103 text

No content

Slide 104

Slide 104 text

No content

Slide 105

Slide 105 text

No content

Slide 106

Slide 106 text

No content

Slide 107

Slide 107 text

No content

Slide 108

Slide 108 text

No content

Slide 109

Slide 109 text

No content

Slide 110

Slide 110 text

No content

Slide 111

Slide 111 text

No content

Slide 112

Slide 112 text

Performance

Slide 113

Slide 113 text

No content

Slide 114

Slide 114 text

No content

Slide 115

Slide 115 text

No content

Slide 116

Slide 116 text

REALLY NEEDS

Slide 117

Slide 117 text

REALLY REALLY NEEDS

Slide 118

Slide 118 text

No content

Slide 119

Slide 119 text

No content

Slide 120

Slide 120 text

No content

Slide 121

Slide 121 text

Introducer Persister Merger

Slide 122

Slide 122 text

Introducer Persister Merger Loosely Coupled

Slide 123

Slide 123 text

Introducer Persister Merger Loosely Coupled

Slide 124

Slide 124 text

Introducer Persister Merger Loosely Coupled increases files decreases files

Slide 125

Slide 125 text

Introducer Persister Merger Loosely Coupled increases files decreases files increases memory

Slide 126

Slide 126 text

Introducer Persister Merger Loosely Coupled increases files decreases files increases memory

Slide 127

Slide 127 text

No content

Slide 128

Slide 128 text

Reflection

Slide 129

Slide 129 text

No content

Slide 130

Slide 130 text

No content

Slide 131

Slide 131 text

No content

Slide 132

Slide 132 text

No content

Slide 133

Slide 133 text

Thanks