Tweet
Tweet

Slide 1

Slide 1 text

Marco Slot Principal Engineer & Lead of Citus Open Source project/ with intro by Claire Giordano DEMO High performance HTAP with Postgres & Hyperscale (Citus)

Slide 2

Slide 2 text

Marco Slot

Slide 3

Slide 3 text

Hybrid Transactional Analytical Processing @clairegiordano / @marcoslot

Slide 4

Slide 4 text

Postgres

Slide 5

Slide 5 text

Hyperscale (Citus) now available as part of Azure Database for PostgreSQL

Slide 6

Slide 6 text

Hyperscale (Citus) now available as part of Azure Database for PostgreSQL

Slide 7

Slide 7 text

Citus extension to Postgres

Slide 8

Slide 8 text

aka.ms/citus

Slide 9

Slide 9 text

What is Citus? /// github.com/citusdata/citus ž Transforms Postgres into a distributed database

Slide 10

Slide 10 text

What is Citus? /// github.com/citusdata/citus ž Transforms Postgres into a distributed database ž Distributes your data & queries

Slide 11

Slide 11 text

What is Citus? /// github.com/citusdata/citus ž Transforms Postgres into a distributed database ž Distributes your data & queries ž Parallelism

Slide 12

Slide 12 text

What is Citus? /// github.com/citusdata/citus ž Transforms Postgres into a distributed database ž Distributes your data & queries ž Parallelism ž All the cpu, memory, & disk of cluster

Slide 13

Slide 13 text

Can you tell us a bit about what you will demo today? What’s the anatomy of the demo? @clairegiordano / @marcoslot

Slide 14

Slide 14 text

Order Processing System for Warehouses

Slide 15

Slide 15 text

What you will see in today’s HTAP database demo All running on Azure Side-by-side performance compare: Hyperscale (Citus) vs. single node Millisecond analytics queries with rollups Retail: Order processing system for warehouses (using HammerDB)

Slide 16

Slide 16 text

What you will see in today’s HTAP database demo All running on Azure Side-by-side performance compare: Hyperscale (Citus) vs. single node Millisecond analytics queries with rollups Retail: Order processing system for warehouses (using HammerDB)

Slide 17

Slide 17 text

A bit about HammerDB (it’s NOT a database) hammerdb.com

Slide 18

Slide 18 text

What you will see in today’s HTAP database demo All running on Azure Side-by-side performance compare: Hyperscale (Citus) vs. single node Millisecond analytics queries with rollups Retail: Order processing system for warehouses (using HammerDB)

Slide 19

Slide 19 text

What you will see in today’s HTAP database demo All running on Azure Side-by-side performance compare: Hyperscale (Citus) vs. single node Millisecond analytics queries with rollups Retail: Order processing system for warehouses (using HammerDB)

Slide 20

Slide 20 text

What you will see in today’s HTAP database demo All running on Azure Side-by-side performance compare: Hyperscale (Citus) v. single node Millisecond analytics queries with rollups Retail: Order processing system for warehouses (using HammerDB)

Slide 21

Slide 21 text

Demo: HTAP Database with Hyperscale (Citus) Marco Slot @clairegiordano / @marcoslot / @azuredbpostgres / @citusdata

Slide 22

Slide 22 text

Hyperscale (Citus) 10-node cluster 53 minutes 10 sec Transactions Analytical query ~900K transactions/min ~40-50K transactions/min 20x faster 300x faster 20 milliseconds Analytical query with rollups Single Postgres Server ~150,000x faster

Slide 23

Slide 23 text

METADATA W7 W6 W5 W4 W10 W9 W8 W3 W2 W1 Hyperscale (Citus) 10-node database cluster Coordinator CITUS WORKER NODES

Slide 24

Slide 24 text

Power of HTAP with Hyperscale (Citus) on Azure Database for PostgreSQL

Slide 25

Slide 25 text

Will all apps see the performance increase you just showed us? @clairegiordano / @marcoslot / @azuredbpostgres / @citusdata

Slide 26

Slide 26 text

No content

Slide 27

Slide 27 text

It’s important to find a good distribution column, something that is common to all large tables SELECT create_distributed_table( 'table_name', 'distribution_column'); @clairegiordano / @marcoslot / @azuredbpostgres / @citusdata

Slide 28

Slide 28 text

At the end of the demo, you called Citus an “almost anything” database. What did you mean? @clairegiordano / @marcoslot / @azuredbpostgres / @citusdata

Slide 29

Slide 29 text

As an extensible, relational database, Postgres is capable of so many things on a single server…

Slide 30

Slide 30 text

By transforming Postgres into a distributed database, Hyperscale (Citus) makes Postgres capable of almost anything

Slide 31

Slide 31 text

How best to get started with Hyperscale (Citus)? @clairegiordano / @marcoslot / @azuredbpostgres / @citusdata

Slide 32

Slide 32 text

Download Citus open source packages aka.ms/citus

Slide 33

Slide 33 text

Multi-tenant (SaaS) tutorial aka.ms/hyperscale-citus-multi-tenant-tutorial

Slide 34

Slide 34 text

Tutorial: Real-time analytics dashboard aka.ms/hyperscale-citus-real-time-tutorial

Slide 35

Slide 35 text

Do you have a favorite blog post? @clairegiordano / @marcoslot / @azuredbpostgres / @citusdata

Slide 36

Slide 36 text

Architecting petabyte-scale analytics by scaling out Postgres on Azure with the Citus extension aka.ms/blog-petabyte-scale-analytics

Slide 37

Slide 37 text

@clairegiordano / @marcoslot / @azuredbpostgres / @citusdata Petabyte-scale service architecture used by Windows

Slide 38

Slide 38 text

Min Wei, Principal Engineer at Microsoft Distributed PostgreSQL is a game changer." source: https://aka.ms/blog-petabyte-scale-analytics

Slide 39

Slide 39 text

© Copyright Microsoft Corporation. All rights reserved. Marco Slot & @marcoslot @citusdata @clairegiordano @AzureDBPostgres Claire Giordano Thank you!