Accelerate SQL Server on Linux Performance Kannan Mani

Accelerate SQL Server on Linux Performance Kannan Mani WW Sr. Principal Product Manager/Architect – Enterprise Data Platforms Dinara Alieva – MS Solutions Product Manager

Unleash the potential of your data-centric applications Microsoft SQL Server Challenges Escalating complexity - Database landscape - Data growth - Reduced performance Objectives Empower business processing High costs - Managing IT environment - Database licensing - Missed opportunities Accelerate analytics Technology limitations - Aging infrastructure - Scalability - Availability Optimize infrastructure 2

SQL Server Use Cases 1. SQL Server Environment Infrastructure Refresh Ø Engineered/Converged Systems (MS APS) Increase Performance Ø Consolidation for cost savings Reduce Cost 2. Migrating to SQL Server Windows/Linux 3. Enterprise and Microsoft Applications on SQL Databases Ø Virtualizing SQL Server Ø Test/Dev consolidation Ø Mixed workloads OLTP & OLAP Ø Dev. Ops for SQL Server Ø Business Continuity & Disaster Recovery (BC/DR) 4. Business Intelligence/Analytics on SQL Server 5. SQL in Cloud (SQL DBaa. S, SQL DB in Azure - Private/Hybrid/Managed)

HPE simplifies common App/DBA tasks Complicated or simple? App/DB design, storage and capacity planning Install, configure, upgrade, migrate and provisioning Troubleshooting and support Architects/ DBA’s Performance tuning and monitoring App/Database security Backup and recovery, high availability

SQL Server 2017 Run anywhere and build apps using the language of your choice Analyze complex relationships with support for graph objects & queries SQL Server 2017 Advanced Machine Learning with R & Python Unparalleled performance with adaptive query processing

#1 performance and price/performance on non-clustered TPC-H@1000 GB HPE, Microsoft, and Red Hat deliver first-ever result with SQL Server 2017 Enterprise Edition Winning partnerships! HPE Pro. Liant DL 380 Gen 9 Key performance takeaways – SQL Server 2017 on Red Hat Enterprise Linux surpasses the previous #1 TPC-H@1000 GB result achieved with SQL Server 2016 – 6% higher performance SQL Server 2017 Enterprise Edition Higher performance – Results achieved on similarly configured servers with two Intel® Xeon® E 5 -2699 v 4 processors Better price/performance $1. 00 750, 000 678, 492 717, 101 500, 000 $0. 50 – 5% better price/performance – The first and only result with Microsoft SQL Server 2017 Enterprise Edition Red Hat Enterprise Linux 7 $0. 64 $0. 61 250, 000 0 Qph. H $0. 00 HPE Pro. Liant DL 380 Gen 9 w/SQL Server 2016 on Microsoft Windows HPE Pro. Liant DL 380 Gen 9 w/SQL Server 2017 on Red Hat Enterprise Linux HPE Pro. Liant DL 380 Gen 9 w/SQL Server 2016 on Microsoft Windows $ USD/Qph. H HPE Pro. Liant DL 380 Gen 9 w/SQL Server 2017 on Red Hat Enterprise Linux Read the performance brief at hpe. com/servers/benchmarks. © Copyright 2017 Hewlett Packard Enterprise Development LP. Microsoft and Windows are U. S. registered trademarks of Microsoft Corporation. Red Hat, Red Hat Enterprise Linux, and the Shadowman logo are registered trademarks of Red Hat, Inc. Linux is a registered trademark of Linus Torvalds. Intel and Xeon are trademarks of Intel Corporation in the U. S. and other countries. TPC and TPC-H are trademarks of the Transaction Processing Performance Council. TPC-H results show the HPE Pro. Liant DL 380 Gen 9 with a result of 717, 101 Qph. H @ 1000 GB and $0. 61 USD/Qph. H @ 1000 GB with system availability as of 10 -19 -2017 (results published 04 -19 -2017; see tpc. org/3327); the HPE Pro. Liant DL 380 Gen 9 with a result of 678, 492 Qph. H @1000 GB and $0. 64 USD/Qph. H @ 1000 GB with system availability as of 07 -31 -2016 (results published 03 -24 -2016; see tpc. org/3320). The TPC believes that comparisons of TPC-H results published with different scale factors are misleading and discourages such comparisons. Please see tpc. org for up-to-date information. Competitive claims valid as of 04 -19 -2017. Microsoft SQL Server, Linux and HPE Performance Benchmark Love Story

SQL Server 2017 on Linux with HPE 3 PAR 9450 Storage 16 Gb FC Red Hat Enterprise Linux 7. 3 Microsoft SQL Server 2017 16 Gb FC SQL Server Management Studio v 17. 0+ HPE 3 PAR Stor. Serv Management Console v 3. 1+ LAN HPE 3 PAR Store. Serv 9450 7

3 PAR Compression Ratios SQL Server Volumes Database Transaction Logs HPE 3 PAR Compression Ratio up to 3. 0: 1 up to 2. 4: 1 Note: SQL transaction speed was the same on both standard and compressed volumes 8

A new category of infrastructure is needed to power the Idea Economy Composable s end r T g putin Application optimized Com Simplify Infrastructure as a Service Hyper-converged Simplify deployments Converged Traditional Siloed Infrastructure • Complex processes • Static, siloed IT • Silo defined • Physical, virtual, and containerized workloads Improve staff productivity • Masks some complexity with people and software • Preconfigured physical IT • Hardware defined • Targeted workloads • Remove complexity by eliminating SAN • Fluid virtual IT • Software defined storage • Virtual workloads Operations optimized • Hardware & Software architected as one • Fluid IT • Software defined everything • Physical, virtual and containerized workloads Composability

Why Deploy Mission Critical Workloads on HPE? Licensing Consolidate licensing – Potentially Increase utilization of Database/App licenses (Depends on degree of consolidation) Server consolidation Reduce hardware costs > 50% – Consolidate servers based on workload, avoid Server Sprawl (Depends on the environment) Server on demand Provision databases on demand – Minutes to provision in production and in the dev/test environment – Automated Migration from Physical to Virtual Quality of Service Increase application/DB Quality of Service – Scale dynamically – Simplified high availability and simple disaster recovery Security Complete isolation between Production and Test/Dev systems – Protects databases and applications against network-based threats

Where to Learn more? http: //www. hpe. com/info/dm-ra 11

Resources – HPE 3 PAR Store. Serv Storage, https: //www. hpe. com/storage/3 PAR – HPE 3 PAR Store. Serv Architecture, https: //www. hpe. com/h 20195/V 2/Get. Document. aspx? docname=4 AA 3 -3516 ENW – HPE 3 PAR Adaptive Data Reduction, https: //www. hpe. com/h 20195/v 2/getpdf. aspx/4 AA 4 -9573 ENW. pdf – HPE Reference Architecture for Microsoft SQL Server 2017 on Linux with HPE 3 PAR Storage with compression, http: //h 20565. www 2. hpe. com/hpsc/doc/public/display? doc. Id=a 000 xxxxxen_us 12

Why HPE for our Customer Business? HPE has the right solution for your workload Industry-leading performance and availability Accelerated speed-ofinsights with the right architecture for the workload Increased cost savings on standardized platforms Increased scalability for taking advantage of inmemory processing Innovative, proven partnerships with many ISVs 13

Call to action Check Enterprise Information Library for all Data Management RAs, Solution Briefs Schedule meeting with HPE Account team to provide solutions for your data platforms! 14

Thank you! kannan. mani@hpe. com 15