Percona Live: Data Performance Conference 2016 Logo

April 18-21, 2016

Santa Clara, California

Schedule - Day 2 | Wednesday 20 April 2016

Wednesday 20 April 2016
8:00am to 9:00am
None
9:00am to 9:20am
None
  • Sponsored
Anurag Gupta
Find out about the data challenges and trends that drove AWS to reimagine data processing and bet the future on new Big Data services that are innovating data infrastructure from NoSQL databases to data warehouses. We believe that one size doesn’t fit all and multiple services are often necessary to address different challenges of Big Data.
Other
9:25am to 9:45am
None
  • Sponsored
Reddy Chagam, Thomas Hazel, Peter Zaitsev, Mark Callaghan, Matt Yonkovit, Kyle Bader
As larger and larger datasets move to the cloud new challenges and opportunities emerge in handling such workloads. New technologies, revamped products, and a never ending stream of idea’s follow in the wake of this advance. These aim to improve the performance and manageability of cloud based data, but are they enough? What issues still need to be worked out?
Other
9:50am to 10:10am
None
  • Sponsored
Tomas Ulin
MySQL 5.7 is GA and delivered major improvements in performance, scalability & manageability. Lets explore how MySQL can deliver on the promises of NoSQL, while keeping all the proven benefits of SQL. Join Tomas Ulin, VP of MySQL Engineering at Oracle, to better understand the MySQL development priorities and what the future holds for the world's most popular open source database.
Other
10:15am to 10:40am
None
  • Sponsored
Mark Callaghan
RocksDB is an embedded database engine. MyRocks and MongoRocks are RocksDB storage engines for MySQL and MongoDB. All of this is open-source. Facebook started these projects to get better performance, efficiency and compression with fast storage devices like flash-based SSD but they also work great with disks.
Other
10:45am to 11:10am
None

11:10am to 12:00pm

11:10am to 12:00pm
Ballroom A
  • Development
  • Operations and Management
Ryan Lowe, John Cesario
So you want to transition to GTID? Great! However, GTID fundamentally changes many assumptions in instance management, incident response, and high-availability tooling. In this talk, we’ll provide practical examples of how Square had to update its tooling to support GTID clusters as a first-class citizen in its production environment.
MySQL Tools and Techniques Replication
11:10am to 12:00pm
Ballroom B
  • Development
Kat Styons
Several teams across The Washington Post collected content in different ways and it was not easily shared or accessible. So, we built a tool called Submission Platform to collect and curate the content in one location. We will cover why and how we chose to use MongoDB and MEAN (MongoDB, ExpressJS, AngularJS, NodeJS) a full Javascript stack to build this tool.
MongoDB Programming NoSQL
11:10am to 12:00pm
Ballroom C
  • Development
Bill Karwin
When does InnoDB lock a row? Multiple rows? Why would it lock a gap? How do transactions affect these scenarios? Locking is one of the more opaque features of MySQL, but it’s very important for both developers and DBA’s to understand if they want their applications to work with high performance and concurrency.
MySQL InnoDB Monitoring
11:10am to 12:00pm
Ballroom D
  • Architecture/Design
  • Scalability/Performance
Siying Dong
RocksDB is an embedded persistent key-value store for low-latency and high-throughput workload. It has been adapted to a wide range of workloads, including RocksDB as an embedded DBMS and as storage engines of other DBMS systems. Our benchmarks show RocksDB can achieve 126K random reads per second on flash and 7 million random reads per second on memory.
Other
11:10am to 12:00pm
Ballroom E
  • Architecture/Design
  • Operations and Management
Ernie Souhrada
The rise of utility computing has revolutionized much about the way organizations think about infrastructure and back-end serving systems compared to the "olden days" of dedicated physical data centers. However, in the final analysis, success is still driven by meeting your SLAs. If services are up and sufficiently performant, you win.
AWS Devops High Availability
11:10am to 12:00pm
Ballroom F
  • New and Trending Topics
  • Scalability/Performance
Spencer Kimball
A surprising number of companies are building proprietary databases and refuse to admit it. Worse, most are doing a terrible job. A traditional RDBMS is a great choice for both building applications and doing complex or ad-hoc analytics...until it fails to scale.
MySQL MongoDB Docker
11:10am to 12:00pm
Ballroom G
  • Case Stories
  • Operations and Management
Emily Slocombe, Pim van der Wal
Drupal is one of the more widely adopted CMSs. It is open source and has a huge developer base. However, I rarely hear a DBA mention having to administer Drupal with anything but frustration and pessimism. At Acquia, we have thousands of Amazon instances running Drupal databases. Most sites are quite different from each other, but some basic principles apply to all.
MySQL Tools and Techniques Web Services
11:10am to 12:00pm
Ballroom H
  • Case Stories
David Turner, René Cannaò, Thomas Manville
In this talk we'll run through numerous performance problems and how to troubleshoot them using Performance Schema. Many of these performance issues are based off actual problems experienced in our production environment at Dropbox.
MySQL Metrics Monitoring
11:10am to 12:00pm
Room 203
  • Analytics
  • Development
Gou Rao
Linux containers such as Docker dramatically improve packaging and deploying applications directly onto bare metal servers. You can now get the manageability benefits of virtualized applications without the IO overhead of traditional hypervisors. In this session, we will discuss best practices for running databases on Linux containers and achieving higher performance through hyper-convergence.
Docker Tools and Techniques
11:10am to 12:00pm
Room 204
  • MongoDB 101
  • Operations and Management
Alexander Rubin
If you are a MySQL DBA and want to learn MongoDB quickly - this talk is for you.
MySQL MongoDB NoSQL
11:10am to 12:00pm
Room 209
  • New and Trending Topics
  • Scalability/Performance
Frank Celler
Multi-model databases are becoming very popular as they offer unprecedented flexibility for data modeling. ArangoDB is a native multi-model database, which means it is a document store, a key/value store and a graph database, all in one engine and with a query language that supports all three data models - single document operations, graph traversal as well as joins and transactions.
NoSQL Sharding
11:10am to 12:00pm
Room 210
  • Architecture/Design
  • Case Stories
VAMSI PONNEKANTI, Tian-Ying Chang
Zen is Pinterest’s graph storage service. Our first implementation of Zen used HBase as the backend, and we've since expanded its use to core parts of the product, including homefeed, notifications, topic feeds and the interest graph.
MySQL Java Sharding
12:00pm to 1:00pm
None

1:00pm to 1:50pm

1:00pm to 1:50pm
Ballroom A
  • Scalability/Performance
Seppo Jaakola
Database schema definition is not supposed to change, at least not so often. The problem with MySQL schema changes is that they are not transactional, and this sets some constraints for how replication of schema changes must be performed. In synchronous database clusters the problem of schema changes is amplified. All cluster nodes are working on same view of data.
MySQL High Availability Replication
1:00pm to 1:50pm
Ballroom B
  • Operations and Management
Patrick Galbraith
Mongo 3.0 has a lot of great new features, and particularly those that allow you to build an excellent HA sharded MongoDB cluster. Building clusters can be difficult and doing so in a way that allows you to quickly create these clusters and make them readily available for applications to use is invaluable.
Ansible NoSQL
1:00pm to 1:50pm
Ballroom C
  • Scalability/Performance
ying qiang zhang
This session introduces Alibaba Group's branch of the Oracle MySQL —— AliSQL. In this session, we will talk about how AliSQL could support 140,000 order creation per second, and supported more than thousands of stock deductions per second for single hot SKU in 2015 Alibaba Singles's Day shopping festival (China's version of "Cyber Monday").
MySQL InnoDB Optimization
1:00pm to 1:50pm
Ballroom D
  • Development
  • New and Trending Topics
Slava Akhmechet
Modern games, collaborative apps, and connected devices require sending data directly to the user in realtime. Web browsers support this via WebSockets, but adapting database systems still presents a huge engineering challenge. RethinkDB is an open source database for the realtime web.
NoSQL
1:00pm to 1:50pm
Ballroom E
  • Case Stories
Tom Krouper, Jonah Berquist
The GitHub DBA "team" historically has been 1 person and a friendly chat bot named Hubot. The reason this has been able to last so long is because of the automation built around everything GitHub does. The team is growing this year.
MySQL Devops
1:00pm to 1:50pm
Ballroom F
  • Analytics
  • Big Data
Alexander Rubin
Apache Spark is a cluster computing framework, similar to Apache Hadoop. There are a number of tasks where MySQL (out-of-the-box) does not show great performance (for example, one of the MySQL limitations is: one query = one CPU core, which means that even if you have 48 CPU cores it will not utilize the full computing power).
MySQL Hadoop Spark
1:00pm to 1:50pm
Ballroom G
  • Case Stories
  • Operations and Management
Charity Majors
Upgrading databases can be terrifying and perilous, and for good reason: you can totally screw yourself!
MongoDB Devops Tools and Techniques
1:00pm to 1:50pm
Ballroom H
  • New and Trending Topics
  • Scalability/Performance
Giuseppe Maxia
A Modern Approach to Schema Management - Evan Elias (https://www.percona.com/live/data-performance-conference-2016/sessions/modern-approach-schema-management) The 5 minute introduction to MySQL and MariaDB on POWER - Stewart Smith (https://www.percona.com/live/data-performance-conference-2016/sessions/5-minute-introduction-mysql-and-mariadb-power) Inventions, inventors, DBAs and Open S
MySQL MongoDB
1:00pm to 1:50pm
Room 203
  • Analytics
  • Development
David Tuhy
The primary storage for many of today’s databases is usually arrays of rotational media which can typically quickly becomes the largest bottleneck for database application performance.
MySQL InnoDB Tools and Techniques
1:00pm to 1:50pm
Room 204
  • MongoDB 101
  • New and Trending Topics
Abdelhak Errami
Let's have a discussion about which technology to use. Is it MySQL, MongoDB or both? Then let's go a little bit deeper: which is the right storage engine for your application, business, as a student. This talk will help you learn about the cutting edge technologies.
MySQL MongoDB
1:00pm to 1:50pm
Room 209
  • Analytics
  • Big Data
John De Goes
Modern databases like Couchbase, MarkLogic, and MongoDB offer a flexible data model (NoSQL), powerful horizontal scalability, and an ease-of-use that's almost unprecedented in the relational world.
Couchbase NoSQL Business Intelligence
1:00pm to 1:50pm
Room 210
  • Operations and Management
Jesse Dearing
You're sitting in a meeting when your phone alerts you to a page you've received. Somewhere in your datacenter, evil is afoot. You pull out your laptop and try to connect to the database: no luck. SSH: swing and a miss.
MySQL Devops Tools and Techniques

2:00pm to 2:50pm

2:00pm to 2:50pm
Ballroom A
  • Architecture/Design
  • New and Trending Topics
Marcos Albe
MySQL Router is a plugin-based, packet-level router that provides an easy way to implement high availability (HA) and load balancing for MySQL replication setups.
MySQL High Availability Replication
2:00pm to 2:50pm
Ballroom B
  • Architecture/Design
  • Scalability/Performance
Kimberly Wilkins
Indexing Strategies and Tips for MongoDB In this presentation Kimberly will cover general indexing, options, and strategies. And with new indexing improvements and changes in MongoDB 3.2, there are more indexing options than ever before including automated index builds and partial indexes.
MongoDB Optimization NoSQL
2:00pm to 2:50pm
Ballroom C
  • Development
  • Scalability/Performance
Sveta Smirnova
The performance schema in MySQL version 5.6, released in February, 2013, is a very powerful tool that can help DBAs discover why even the trickiest performance issues occur. Version 5.7 introduces even more instruments and tables. And while all these give you great power, you can get stuck choosing which instrument to use.
MySQL Optimization Tools and Techniques
2:00pm to 2:50pm
Ballroom E
  • Architecture/Design
  • Scalability/Performance
Anthony Yeh, Sugu Sougoumarane
YouTube's vitess has been under development since 2010. The earliest version was just a connection proxy that helped us buy some headroom. Over time, the features evolved, while the tools and servers grew to be more efficient, fault tolerant, and manageable.
MySQL Sharding Replication
2:00pm to 2:50pm
Ballroom F
  • New and Trending Topics
  • Scalability/Performance
Konstantin Osipov
In my talk I will focus on a practical use case: task queue application, using Tarantool as an application server and a database. The idea of the task queue is that producers put tasks (objects) into a queue, and consumers take tasks, perform them, mark as completed.
Tools and Techniques Programming High Availability
2:00pm to 2:50pm
Ballroom G
  • Operations and Management
Jaakko Pesonen
Nobody cares about backups. Everyone should care about restores. This talk is about improving MySQL backup solution to shift focus from making backups to restoring them. Spilgames backup solution uses BackupPC, Xtrabackup, mysqldump, Glacier and just a bunch of shell/python scripts.
MySQL Devops Tools and Techniques
2:00pm to 2:50pm
Ballroom H
  • Development
  • Scalability/Performance
Janis Griffin
Performance tuning can be complex. It's often hard to know which knob to turn or button to press to get the biggest performance boost. In this presentation, Janis Griffin, Database Performance Evangelist, SolarWinds, will detail 12 steps to quickly identify performance issues and resolve them.
MySQL Optimization Tools and Techniques
2:00pm to 2:50pm
Room 203
  • Architecture/Design
  • Operations and Management
Brett Hesterberg, Rob Clevenger
What underpins Google's Cloud SQL managed MySQL service?
MySQL Data in the Cloud
2:00pm to 2:50pm
Room 204
  • MongoDB 101
  • New and Trending Topics
David Murphy
A primer on how replication works including elections, and how replica sets are also shards. From there we will go into how sharding works from what meta data lives where, to how primaries hide data they do not “own” such as orphans. Next we will talk through some basic rules to keep in mind with sharding and give some ideas on how you start chasing a shard key.
MongoDB Sharding Replication
2:00pm to 2:50pm
Room 209
  • Architecture/Design
  • Big Data
Anastasia Ailamaki
Integrating and ingesting data into databases is quickly becoming a bottleneck in face of massive data as well as increasingly heterogeneous data formats. Queries, on the other hand, are often ad-hoc and supported by pre-cooked operators which are not adaptive enough to optimize access to data.
Spark Other Data in the Cloud
2:00pm to 2:50pm
Room 210
  • Analytics
Vicentiu-Marian Ciorbaru, Sergei Petrunia
Window functions are a new feature in MariaDB 10.2 This talk gives it a comprehensive coverage.
MySQL Tools and Techniques Programming
2:50pm to 3:30pm
None

3:30pm to 4:20pm

3:30pm to 4:20pm
Ballroom A
  • Architecture/Design
  • Operations and Management
René Cannaò
ProxySQL is an open source proxy for MySQL able to provide HA and high performance with no changes in the application, using several built-in features and integration with clustering software. It is the only proxy for MySQL that scales to the point of supporting hundreds of thousands of concurrent clients and thousands of servers.
MySQL High Availability Sharding
3:30pm to 4:20pm
Ballroom B
  • Scalability/Performance
John Schulz
Sharding a database is hard. MongoDB folks will tell you they have already done it for you. And they have sort of. In the MySQL world Oracle via MySQL fabric and Scale Arc will tell you that they have done it for you. Cassandra folks will tell you they have avoided the need all together.
MySQL MongoDB Sharding
3:30pm to 4:20pm
Ballroom C
  • Architecture/Design
  • Scalability/Performance
Dimitri KRAVTCHUK
This session will be interesting to everyone looking for the latest news about MySQL Performance: - Overview on progress in MySQL Performance - The latest benchmark results obtained on the current MySQL dev version -vs- others - The latest improvements made in MySQL/InnoDB design, resolved contentions, new features ans solutions - The latest findings in MySQL Performance tuning, workaround
MySQL InnoDB Optimization
3:30pm to 4:20pm
Ballroom D
  • Big Data
  • Scalability/Performance
Anurag Gupta
Amazon Aurora is a MySQL-compatible, relational database engine that combines the speed and availability of high-end commercial databases with the simplicity and cost-effectiveness of open source databases.
MySQL AWS High Availability
3:30pm to 4:20pm
Ballroom E
  • Architecture/Design
  • Scalability/Performance
Daren Seagrave
Any engineer interested at how we run MySQL at Facebook can tell you that we shard our data, and run multiple shards per MySQL instance. This has been the widely accepted approach to “shared nothing” scaling of MySQL in large installations. What do you do when classic sharding is no longer sufficient? Older shards can grow beyond their expected size, and cause imbalance.
MySQL Optimization Sharding
3:30pm to 4:20pm
Ballroom F
  • Architecture/Design
  • Case Stories
Ivan Kruglov
Searches are hard, fast searches are harder and even more with growing dataset. At Booking.com we face these problems, especially the last one: we have doubled the number of properties in the last two years. Searching across normalized data in MySQL stopped working for us 3-4 years ago.
MySQL Optimization NoSQL
3:30pm to 4:20pm
Ballroom G
  • Architecture/Design
  • New and Trending Topics
Giuseppe Maxia, Patrick Galbraith
Docker is a great new project for managing containers. Containers are operating system resource isolation and allocation benefits as virtual machines yet are more lightweight and allow you a lot of flexibility and how you can design your application and database architecture.
MySQL Docker
3:30pm to 4:20pm
Ballroom H
  • Analytics
  • Architecture/Design
Charity Majors, Jeremy Tinley
Jeremy and Charity have built monitoring systems for a positively stupid number of databases. We will give a ~20 minute overview of some common best practices over the lifecycle of a company, from the first day of your startup to a publicly traded company at scale, and then open it up for audience stories and Q&A for the rest of the slot time.
MySQL MongoDB AWS
3:30pm to 4:20pm
Room 203
  • Architecture/Design
  • New and Trending Topics
Yves Trudeau, Kyle Bader
With the popularity of virtualization, running MySQL in a virtual environment is now almost the norm -- with many technology options. Since the storage layer is also commonly virtualized, a virtual server instance is not bound to the local storage of a physical host. The most popular OpenStack cinder backend is Ceph, but Ceph is not restricted to the OpenStack world.
MySQL OpenStack Docker
3:30pm to 4:20pm
Room 204
  • MongoDB 101
  • New and Trending Topics
David Murphy
We will cover the big new features in Mongo 3.2 Community and Percona Server 3.2 Some of the main topics we will cover are: WiredTiger default engine type Replication Protocol updates Config server improvements readConcern Partial Index Document Validation Audit Log LDAP / External Auth Aggregation new features Changes to Geo and Text searching Breaking compatibility changes Issue f
MongoDB
3:30pm to 4:20pm
Room 209
  • Architecture/Design
  • Case Stories
Christine Yen
This talk will cover the architecture and reasoning behind using Cassandra to power Parse's initial Analytics product, then walk through the trials, tribulations, and occasional successes of providing analytics for developers within an existing backend-as-a-service. We'll discuss things that Cassandra did well, things that Cassandra and its ecosystem did not do well, and our design de
Cassandra Data as a Service NoSQL
3:30pm to 4:20pm
Room 210
  • Architecture/Design
  • Case Stories
Dylan Butler
What if you were asked to support a database platform that you had never worked with before? First you would probably say no, but after you lost that fight, then what? That is exactly how I came to support MySQL.
MySQL Monitoring High Availability

4:30pm to 5:20pm

4:30pm to 5:20pm
Ballroom A
  • Architecture/Design
Patrick Galbraith
Kubernetes is an open-source system for managing containerized applications across multiple hosts in a cluster. Kubernetes provides mechanisms for application deployment, scheduling, updating, maintenance, and scaling. Kubernetes has the concept of pods— one or more cooperative containers running on a given host.
MySQL Docker
4:30pm to 5:20pm
Ballroom B
  • Operations and Management
Michael Kania
What should you know about running MongoDB on AWS? We'll cover a wide range of tips and tricks for squeezing the most performance out of your replica sets, as well as achieving maximum reliability and cost-effectiveness.
MongoDB AWS Devops
4:30pm to 5:20pm
Ballroom C
  • Architecture/Design
  • Scalability/Performance
Muhammad Irfan, Stephane Combaudon
MySQL is lightweight, stable and fast. But it is not uncommon to meet people having performance issues with MySQL -- even when the workload is moderate. What happened to them? Did they have excessive expectations about MySQL performance and scalability? Did they misconfigure their system?
MySQL Optimization
4:30pm to 5:20pm
Ballroom D
  • Development
Simon Mudd, Geir Høydalsvik
MySQL 5.7 is an extremely exciting new version of the world’s most popular open source database that is 2x faster than MySQL 5.6, while also improving usability, manageability, and security.
MySQL
4:30pm to 5:20pm
Ballroom E
  • Architecture/Design
  • Case Stories
Davi Arnaut, Eun-Gyu Kim, Yun Sun
Espresso is LinkedIn’s new online, distributed, fault-tolerant NoSQL database that currently powers several LinkedIn applications.
MySQL Data as a Service NoSQL
4:30pm to 5:20pm
Ballroom F
  • Architecture/Design
  • Development
Shaunak Kashyap
How do you mix SQL and NoSQL worlds without starting a messy revolution? This live coding talk will show you how to add Elasticsearch to your legacy application without changing all your current development habits.
MySQL Tools and Techniques NoSQL
4:30pm to 5:20pm
Ballroom G
  • Operations and Management
Dan Reif, Shlomo Priymak
MySQL is at the core of Facebook's persistent storage. The graph itself, including every like, comment, post and status, is stored in MySQL, along with many other things. This data is the company's most important asset, and we take great care to make sure everything is properly backed up. Yes, even the lol cats and puppy picture posts.
MySQL Python Data in the Cloud
4:30pm to 5:20pm
Ballroom H
  • Case Stories
  • Development
Jon Hyman
Appboy, the world's leading marketing automation and intelligent CRM platform for mobile apps, collects over 100 billion data points each month from our customers. MongoDB is the cornerstone of our data storage and processing, but no one database is perfect in all dimensions.
MongoDB Redis Tools and Techniques
4:30pm to 5:20pm
Room 203
  • Operations and Management
Johan Andersson
MySQL Cluster is a write-scalable, real-time, ACID-compliant transactional database, designed to deliver 99.999% availability. It provides shared-nothing clustering and auto-sharding for MySQL, accessed via SQL and NoSQL interfaces. It is designed to provide high availability and high throughput with low latency, while allowing for near linear scalability.
MySQL Tools and Techniques High Availability
4:30pm to 5:20pm
Room 204
  • Architecture/Design
  • MongoDB 101
Jon Tobin
MongoDB document design is one of the more abstract topics for many users familiar with relational databases. In this talk, we’ll cover what a document is, how they can be structured, and what structures work (and don’t work) for a particular use case. We will also touch on design decisions and how they will affect the ability of the cluster to scale in the future.
MongoDB NoSQL
4:30pm to 5:20pm
Room 209
  • Architecture/Design
  • Case Stories
Miroslav Kvasnica, Tomáš Komenda
Seznam.cz is the largest and the most visited web portal and search engine in the Czech Republic. It is one of a few search engines in the World which successfully competes with Google in the field of local full-text search. Besides the Search engine, Seznam runs over 40 different web services such as news portals, map portal, email service and many more.
Hadoop Other Tools and Techniques
4:30pm to 5:20pm
Room 210
  • Scalability/Performance
Vadim Tkachenko
The rise of Solid State or Flash storage is one of the great technology changes impacting the database world. With this impact comes many questions for potential users of the technology. Traditionally, databases were designed based on the premise that storage is slow and that sequential IO operations are much faster than "random" ones. This is not the case with Solid State storage.
MySQL Optimization
7:00pm to 10:00pm
None