Answering the Database Scale Out Problem: SSDs in the Data Center April 14, 2010 Dan Marriott Director - Production Operations

Slides:



Advertisements
Similar presentations
Scalable Web Site Antipatterns Justin Leitgeb Stack Builders Inc.
Advertisements

Capacity Planning for LAMP Architectures John Allspaw Manager, Operations Flickr.com Web Builder 2.0 Las Vegas.
From Startup to Enterprise A Story of MySQL Evolution Vidur Apparao, CTO Stephen OSullivan, Manager of Data and Grid Technologies April 2009.
Case Study: Photo.net March 20, What is photo.net? An online learning community for amateur and professional photographers 90,000 registered users.
CloudStack Scalability Testing, Development, Results, and Futures Anthony Xu Apache CloudStack contributor.
2 Proprietary & Confidential What is Sharding Benefits of Sharding Alternatives of Sharding When to start Sharding Agenda.
Oracle Exadata for SAP.
Living with Exadata Presented by: Shaun Dewberry, OS Administrator, RDC Tom de Jongh van Arkel, Database Administrator, RDC Komaran Hansragh, Data Warehouse.
Big Data Working with Terabytes in SQL Server Andrew Novick
EHarmony in Cloud Subtitle Brian Ko. eHarmony Online subscription-based matchmaking service Available in United States, Canada, Australia and United Kingdom.
The Power of Platform Solutions to Transform Higher Education
By: Chris Hayes. Facebook Today, Facebook is the most commonly used social networking site for people to connect with one another online. People of all.
2 June 2015 © Enterprise Storage Group, Inc. 1 The Case for File Server Consolidation using NAS Nancy Marrone Senior Analyst The Enterprise Storage Group,
© 2011 Citrusleaf. All rights reserved.1 A Real-Time NoSQL DB That Preserves ACID Citrusleaf Srini V. Srinivasan Brian Bulkowski VLDB, 09/01/11.
Implementation Considerations for FAST Search For SharePoint (FS4SP) Presenter : Shyam Narayan MOSSIG – February 2011 Meeting b:
Nikolay Tomitov Technical Trainer SoftAcad.bg.  What are Amazon Web services (AWS) ?  What’s cool when developing with AWS ?  Architecture of AWS 
CMU SCS Carnegie Mellon Univ. Dept. of Computer Science /615 - DB Applications C. Faloutsos – A. Pavlo How to Scale a Database System.
0 AdvOSS is a Canadian company and a developer and vendor of different high technology solutions for Communications Service Providers. 0 Target Markets.
Exchange 2010 Project Presentation/Discussion August 12, 2015 Project Team: Mark Dougherty – Design John Ditto – Project Manager Joel Eussen – Project.
© Hitachi Data Systems Corporation All rights reserved. 1 1 Det går pænt stærkt! Tony Franck Senior Solution Manager.
Google AppEngine. Google App Engine enables you to build and host web apps on the same systems that power Google applications. App Engine offers fast.
Copyright © 2013, Oracle and/or its affiliates. All rights reserved. 1 Preview of Oracle Database 12 c In-Memory Option Thomas Kyte
1© Copyright 2013 EMC Corporation. All rights reserved. EMC and Microsoft SharePoint Server Performance Name Title Date.
SQL Server 2008 & Solid State Drives Jon Reade SQL Server Consultant SQL Server 2008 MCITP, MCTS Co-founder SQLServerClub.com, SSC
MySQL Data Warehousing Survival Guide Marius Moscovici Steffan Mejia
Take An Internal Look at Hadoop Hairong Kuang Grid Team, Yahoo! Inc
CERN IT Department CH-1211 Genève 23 Switzerland t Next generation of virtual infrastructure with Hyper-V Michal Kwiatek, Juraj Sucik, Rafal.
How WebMD Maintains Operational Flexibility with NoSQL Rajeev Borborah, Sr. Director, Engineering Matt Wilson – Director, Production Engineering – Consumer.
22-Aug-15 | 1 |1 | Help! I need more servers! What do I do? Scaling a PHP application.
Distributed Data Stores – Facebook Presented by Ben Gooding University of Arkansas – April 21, 2015.
Database Services for Physics at CERN with Oracle 10g RAC HEPiX - April 4th 2006, Rome Luca Canali, CERN.
What makes Facebook do what it does? By Gavin Mais.
Saturday, September 05, 2015 © Cloudmark Inc. ioMemory: Higher performance in a smaller foot-print 14 th April, 2010.
JOnAS developer workshop – /02/2004 status Emmanuel Cecchet
Facebook: Infrastructure at Scale Using Emerging Hardware Bill Jia, PhD Manager, Performance and Capacity Engineering Oct 8 th, 2013.
Scaling the Windows Stack George PICC ‘12.
STEALTH Content Store for SharePoint using Caringo CAStor  Boosting your SharePoint to the MAX! "Optimizing your Business behind the scenes"
So, Jung-ki Distributed Computing System LAB School of Computer Science and Engineering Seoul National University Implementation of Package Management.
The Industry’s only Unified Flash + Flash Hybrid Storage with Inline De-Duplication Hard Disk at the Speed of Flash.
1EMC CONFIDENTIAL—INTERNAL USE ONLY Why EMC for SQL Performance Optimization.
ArcGIS for Server: Reference Implementations
AUTHORS: STIJN POLFLIET ET. AL. BY: ALI NIKRAVESH Studying Hardware and Software Trade-Offs for a Real-Life Web 2.0 Workload.
FlashSystem family 2014 © 2014 IBM Corporation IBM® FlashSystem™ V840 Product Overview.
Oracle Advanced Compression – Reduce Storage, Reduce Costs, Increase Performance Session: S Gregg Christman -- Senior Product Manager Vineet Marwah.
Copyright 2006 MySQL AB The World’s Most Popular Open Source Database MySQL Cluster: An introduction Geert Vanderkelen MySQL AB.
Designing and Deploying a Scalable EPM Solution Ken Toole Platform Test Manager MS Project Microsoft.
SQL Server 2014: Overview Phil ssistalk.com.
Usenix Annual Conference, Freenix track – June 2004 – 1 : Flexible Database Clustering Middleware Emmanuel Cecchet – INRIA Julie Marguerite.
ArcGIS Server for Administrators
Database Administrator RAL Proposed Workshop Goals Dirk Duellmann, CERN.
Eric Burgener VP, Product Management A New Approach to Storage in Virtual Environments March 2012.
Fast Crash Recovery in RAMCloud. Motivation The role of DRAM has been increasing – Facebook used 150TB of DRAM For 200TB of disk storage However, there.
ATUL PATANKAR [ ASUG INSTALLATION MEMBER MEMBER SINCE: 2000 LINDA WILSON [ ASUG INSTALLATION MEMBER MEMBER SINCE: 1999 JUERGEN LINDNER [ SAP POINT OF CONTACT.
PHP Performance w/APC + thaicyberpoint.com thaithinkpad.com thaihi5.com.
Dynamo: Amazon’s Highly Available Key-value Store DAAS – Database as a service.
1 #compromisenothing ©Copyright 2014 Tegile Systems Inc. All Rights Reserved. Company Confidential Think And not Or.
Scalable Data Scale #2 site on the Internet (time on site) >200 billion monthly page views Over 1 million developers in 180 countries.
Storage Netværk Mød Microsoft Feb 2005, Agenda Data Protection Server (opdatering) Microsoft og iSCSI Demo.
BNL dCache Status and Plan CHEP07: September 2-7, 2007 Zhenping (Jane) Liu for the BNL RACF Storage Group.
Cloud Computing: Pay-per-Use for On-Demand Scalability Developing Cloud Computing Applications with Open Source Technologies Shlomo Swidler.
Configuring SQL Server for a successful SharePoint Server Deployment Haaron Gonzalez Solution Architect & Consultant Microsoft MVP SharePoint Server
1 Paolo Bianco Storage Architect Sun Microsystems An overview on Hybrid Storage Technologies.
Presented by: Aaron Stanley King.  Benefits of SQL Azure  Features of SQL Azure  Demos, Demos, Demos!  How to query in SQL Azure  More Demos!  Recent.
Cassandra as Memcache Edward Capriolo Media6Degrees.com.
Nagios Performance Tuning Nick Scott
Calgary Oracle User Group
100% Exam Passing Guarantee & Money Back Assurance
HPE Persistent Memory Microsoft Ignite 2017
Database hidden disasters…
Presentation transcript:

Answering the Database Scale Out Problem: SSDs in the Data Center April 14, 2010 Dan Marriott Director - Production Operations

Answers.com The world’s leading Q&A site Rank in top Web properties  #18 in the U.S. (02/2010) (1)  #31 worldwide (02/2010) (1) Unique monthly visitors  50 million in the U.S. (02/2010) (1)  72 million worldwide (02/2010) (1) 2 (1) Source: comScore – Hybrid Measurement Methodology (U.S. only) beginning August 2009

ReferenceAnswers 3

WikiAnswers: Q&A the Wiki Way 4

Database layer MySQL b20-percona MySQL a 5

Challenges Keep site fast  while site traffic and stored data are ever-increasing Replication lag = 0  or users get stale data Forever being forced to further optimize queries  constantly vying for dev resources to do this Controlling hardware growth (Cap & OpEx $$$)  regularly adding servers to handle growth 6

Handling high growth – database tier Separate reads and writes Add more read DB slaves Use Memcached where possible Optimize Queries Partition large databases _________ Started hitting a wall: Replication Lag even when servers handling modest # queries/sec 7

Typical DB read cluster 8

Fusion-io for HP Blade Servers March ’09: HP announce IO Accelerator card for blades (manuf. by Fusion-io) Sizes:  80 & 160GB SLC  320GB MLC April ’09: received two cards – began testing 9

Easy to install One man job. Takes 60 secs. 10

Performance Tests Test Blade Server – SAS HDDs Blade Server – Fusion-io cardImprovement 11 Additionally, CPU load dropped from 30% to 18% (even with Fusion-io driver overhead) Replication catch-up time (after restore) > 6 hours12½ mins 3,000% Max Queries/sec (Seconds_Behind_Master: 0) 350 Q/sec3,500 Q/sec 900% Application response time 100 ms70 ms 30% Full DB server recovery > 8 hours 55 mins800%

Typical DB read cluster 12

Fusion-io Value Add for Answers.com Scalability. >Twice the performance capacity on 1/4 servers 100% ROI on day of purchase (repurpose other 3/4) 75% reduction in operating costs:  Rack Space, Power and Cooling  Server Administration  Database Administration 75% fewer failure points 13

Other SSD uses in the Data Center Varnish (Web caching layer) DB Backup Servers Log Analysis Data Warehouse 14

15 Thank you. Slideshow: