Ἑ κατόν by Niko Neugebauer. Niko Neugebauer PASS EvangelistPASS Evangelist SQL Server MVPSQL Server MVP SQLPort (http://www.sqlport.com) founder & leaderSQLPort.

Slides:



Advertisements
Similar presentations
Module 13: Performance Tuning. Overview Performance tuning methodologies Instance level Database level Application level Overview of tools and techniques.
Advertisements

new database engine component fully integrated into SQL Server 2014 optimized for OLTP workloads accessing memory resident data achive improvements.
1. SQL Server 2014 In-Memory by Design Arthur Zubarev June 21, 2014.
Big Data Working with Terabytes in SQL Server Andrew Novick
6 SQL Server Integration Same manageability, administration & development experience Integrated queries & transactions Integrated HA and backup/restore.
SQL Server 2014 – Features Drilldown Tara Shankar Jana Senior Premier Field Engineer (Microsoft)
Project “Hekaton” adds in-memory technology to boost performance of OLTP workloads in SQL Server.
What’s New in SQL Server 2014: Database Engine Aaron Bertrand SQL Sentry
Dandy Weyn Sr. Technical Product Mkt.
Presented by Marie-Gisele Assigue Hon Shea Thursday, March 31 st 2011.
Microsoft Ignite /16/2017 3:29 PM
Meanwhile RAM cost continues to drop Moore’s Law on total CPU processing power holds but in parallel processing… CPU clock rate stalled… Because.
Evolving SQL Server for Modern Hardware Paul Larson, Eric N. Hanson, Mike Zwilling Microsoft plus to the many members of the Apollo and Hekaton teams Paul.
Working with SQL and PL/SQL/ Session 1 / 1 of 27 SQL Server Architecture.
Kevin Kline, SQL Sentry Director of Engineering Services, Microsoft SQL Server MVP since 2003 Twitter, Facebook, KEKline.
Chapter 2 CIS Sungchul Hong
SQL Server 2014: In In-memory OLTP for Database Developers.
SQL Server 2014: Overview Phil ssistalk.com.
Applications hitting a wall today with SQL Server Locking/Latching Scale-up Throughput or latency SLA Applications which do not use SQL Server.
SQL Server 2014 adds in-memory technology to boost performance of OLTP workloads.
IN-MEMORY OLTP By Manohar Punna SQL Server Geeks – Regional Mentor, Hyderabad Blogger, Speaker.
Srik Raghavan Principal Lead Program Manager Kevin Cox Principal Program Manager SESSION CODE: DAT206.
Meet Kevin Liu Principal Lead Program Manager Kevin Liu has been with Microsoft and the SQL Server engine team for 7 years, working on key projects like.
Moore’s Law means more transistors and therefore cores, but… CPU clock rate stalled… Meanwhile RAM cost continues to drop.
SQL Server 2005 Engine Optimistic Concurrency Tony Rogerson, SQL Server MVP Independent Consultant 26 th.
Sofia Event Center November 2013 Margarita Naumova SQL Master Academy.
CS 540 Database Management Systems
DMBS Internals I February 24 th, What Should a DBMS Do? Store large amounts of data Process queries efficiently Allow multiple users to access the.
DMBS Architecture May 15 th, Generic Architecture Query compiler/optimizer Execution engine Index/record mgr. Buffer manager Storage manager storage.
The Baker’s Dozen Business Intelligence 13 Productivity Tips for In-Memory OLTP Enhancements in SQL 2016 Kevin S. Goff Microsoft SQL.
How to kill SQL Server Performance Håkan Winther.
In-Memory OLTP The faster is now simpler in SQL Server 2016.
Scott Fallen Sales Engineer, SQL Sentry Blog: scottfallen.blogspot.com.
Vedran Kesegić. About me  M.Sc., FER, Zagreb  HRPro d.o.o. Before: Vipnet, FER  13+ years with SQL Server (since SQL 2000)  Microsoft Certified.
What Should a DBMS Do? Store large amounts of data Process queries efficiently Allow multiple users to access the database concurrently and safely. Provide.
SQL Server 2014: In-Memory OLTP Adoption Considerations Mike
Redmond Protocols Plugfest 2016 Jos de Bruijn, Borko Novakovic SQL In-Memory OLTP Senior Program Manager.
Mladen Prajdić SQL Server MVP Hekaton The New SQL Server In-Memory OLTP Engine.
Session Name Pelin ATICI SQL Premier Field Engineer.
Introducing Hekaton The next step in SQL Server OLTP performance Mladen Prajdić
Use Cases for In-Memory OLTP Warner Chaves SQL MCM / MVP SQLTurbo.com Pythian.com.
SQL Server Internals & Architecture Naomi Williams, SQL DBA LinkedIn
Memory-Optimized Tables Querying at the speed of light.
In-Memory Capabilities
Thank You! #sqlsatdnipro Denis
SQL Server In-Memory OLTP: What Every SQL Professional Should Know
Lecture 16: Data Storage Wednesday, November 6, 2006.
SQL Server Internals Overview
UFC #1433 In-Memory tables 2014 vs 2016
7/17/2018 © 2014 Microsoft Corporation. All rights reserved. Microsoft, Windows, and other product names are or may be registered trademarks and/or trademarks.
# - it’s not about social media it’s about temporary tables and data
# - it’s not about social media it’s about temporary tables and data
Building Modern Transaction Systems on SQL Server
SQL Server 2014 In-Memory Overview
Hustle and Bustle of SQL Pages
මොඩියුල විශ්ලේෂණය Buffer Pool Extension භාවිතය.
Super Scaling The LMAX Queue Pattern.
Migrating a Disk-based Table to a Memory-optimized one in SQL Server
In-Memory OLTP (IMOLTP) What Can It Do For Me?
Real world In-Memory OLTP
SQL 2014 In-Memory OLTP What, Why, and How
SQL Server 2014 Hidden Treasures Denis Reznik Microsoft SQL Server MVP
Hidden Gems of SQL Server 2014
Microsoft Ignite /1/ :19 PM
Statistics for beginners – In-Memory OLTP
In-Memory OLTP for Database Developers
Hidden Gems of SQL Server 2014
Hidden Gems of SQL Server 2014
Hidden Gems of SQL Server 2014
SQL Server 2014: In-Memory OLTP Overview
Presentation transcript:

ἑ κατόν by Niko Neugebauer

Niko Neugebauer PASS EvangelistPASS Evangelist SQL Server MVPSQL Server MVP SQLPort ( founder & leaderSQLPort ( founder & leaderhttp:// BITuga ( co-founderBITuga ( co-founderhttp:// 15+ years in IT15+ years in IT

HeKATON HEK-A-TON, HEK-A-TON, HEK-A-TON

HekAton ἑ κατόν – means 100 in Greek ἑ κατόν – means 100 in Greek Targeted to improve OLTP performance, 100 TimesTargeted to improve OLTP performance, 100 Times

Conceptionally? Imagine that you have a number of CPU steps to perform a typical OLTP actionImagine that you have a number of CPU steps to perform a typical OLTP action Optimize it 100 times by removing obstacles like latches and parallelize itOptimize it 100 times by removing obstacles like latches and parallelize it Yes, you will need start from the bottom and from the very beginning?Yes, you will need start from the bottom and from the very beginning?

Hardware Trends Look at the CPU speed increaseLook at the CPU speed increase Look at the Memory PricesLook at the Memory Prices You can’t buy a SQL Server Enterprise License for a price of a TBYou can’t buy a SQL Server Enterprise License for a price of a TB Think, think, thinkThink, think, think

New generation DB Hekaton

History Sybase SQL Server (1989)1980 (1989) Hardware ExpensiveHardware Expensive CPU BoundCPU Bound Pages 8K Pages 8K SQL Server Hardware CheapHardware Cheap IO & Memory BoundIO & Memory Bound Pages 8K Pages 8K

Hekaton In-Memory DatabaseIn-Memory Database Multi-Core Awareness and OptimizationsMulti-Core Awareness and Optimizations xVelocity compression algorithm (hint: ColumnStore)xVelocity compression algorithm (hint: ColumnStore) No Pages (no more splits, allocations, etc)No Pages (no more splits, allocations, etc) No Locks, No Latches + different Concurrency ControlNo Locks, No Latches + different Concurrency Control StreamInsight (no more 8K’s)StreamInsight (no more 8K’s) Hash Index (no more b-trees)Hash Index (no more b-trees) Existing T-SQL can be reusedExisting T-SQL can be reused

Hekaton Highly scalable concurrency control mechanismHighly scalable concurrency control mechanism Lock-free data structuresLock-free data structures

Hekaton ACID compliantACID compliant Optimized for extreme Transaction Processing scenarios likeOptimized for extreme Transaction Processing scenarios like Financial ServicesFinancial Services Online GamblingOnline Gambling There are customers who are using it NOWThere are customers who are using it NOW

Integrated into the DataBase Engine Hekaton

Particular Features Snapshot_Isolation ONLYSnapshot_Isolation ONLY No support for LOB data typesNo support for LOB data types No TriggersNo Triggers AlwaysOn SupportAlwaysOn Support

features Durable TablesDurable Tables Non-Durable TablesNon-Durable Tables TempDB is used inside of the Hekaton, in-memoryTempDB is used inside of the Hekaton, in-memory Shares memory with Buffer Pool, but has its own spaceShares memory with Buffer Pool, but has its own space

Architecture Different space allocation for memory bufferDifferent space allocation for memory buffer The very same transaction log, but with fewer writesThe very same transaction log, but with fewer writes Different filegroupsDifferent filegroups Different treatment for IndexesDifferent treatment for Indexes A lot of new, different stuffA lot of new, different stuff

HEKATON It actually looks like a …

Programability Create table dbo.Hekaton(Create table dbo.Hekaton( Id int primary key hash with (bucketcount = 65535),Id int primary key hash with (bucketcount = 65535), Nome varchar(50)Nome varchar(50) ) WITH (MEMORY_OPTIMIZED = ON, DURABILITY = SCHEMA_AND_DATA ); GO

T-SQL Stored Procs: Uses C as internal intermediate presentation, and then compiles into native codeUses C as internal intermediate presentation, and then compiles into native code Atomic blocksAtomic blocks Can’t reference non-hekaton tablesCan’t reference non-hekaton tables

T-SQL Programability Create procedure dbo.HekatonNowCreate procedure dbo.HekatonNow WITH NATIVE_COMPILATIONWITH NATIVE_COMPILATIONBEGIN select name from dbo.Hekaton; ENDGO

Details Uses StreamInsightUses StreamInsight No actual updates, but deletes & insertsNo actual updates, but deletes & inserts

UTils Migration from the normal DB tables to HekatonMigration from the normal DB tables to Hekaton Stored Procedures Migration to Hekaton Stored Procedures Migration to Hekaton

WHEN ? Next major version of SQL Server

BUT Isn’t it too fast ?Isn’t it too fast ? – No, there is no such concept as too fast. (as long as it does not create other problems)– No, there is no such concept as too fast. (as long as it does not create other problems)

Thank you