Tuning Apache Ambari performance for Big Data at scale with 3000 agentsDataWorks Summit
Apache Ambari manages Hadoop at large-scale and it becomes increasingly difficult for cluster admins to keep the machinery running smoothly as data grows and nodes scale from 30 to 3000 agents. To test at scale, Ambari has a Performance Stack that allows a VM to host as many as 50 Ambari Agents. The simulated stack and 50 Agents per VM can stress-test Ambari Server with the same load as a 3000 node cluster. This talk will cover how to tune the performance of Ambari and MySQL, and share performance benchmarks for features like deploy times, bulk operations, installation of bits, Rolling & Express Upgrade. Moreover, the speaker will show how to use Ambari Metrics System and Grafana to plot performance, detect anomalies, and pinpoint tips on how to improve performance for a more responsive experience. Lastly, the talk will discuss roadmap features in Ambari 3.0 for improving performance and scale.
Azure Pipelines for Automatic DeploymentSafe Software
Modern tools to facilitate development and operations include Kanban boards, source control and methods for automated deployment and testing. One of these toolchains is Azure Devops. The swimming lanes with tasks and product backlog items are probably familiar with many a FME developer. I hope source control is too.
But, what if Azure Devops could help you get the latest fruits of your labor on your Staging Environment, and when approved, deploy it to Production? If you know Azure Devops, you've probably seen the blue rocket 'Pipelines' button. If you've pressed this, and thought 'eh…. well… interesting… maybe later…', this presentation is for you. I'll show you it is actually not that hard to deploy FME components from a GIT repository to your server. Get inspired and expand on this in your own way.
Deep Dive on Amazon Aurora MySQL Performance Tuning (DAT429-R1) - AWS re:Inve...Amazon Web Services
Amazon Aurora offers several options for monitoring and optimizing MySQL database performance. These include Enhanced Monitoring and Performance Insights, an easy-to-use tool for assessing the load on your database and identifying slow-performing queries. In this session, learn how to tune the performance of your Aurora database with MySQL compatibility, whether your application is in development or in production.
Hive Training -- Motivations and Real World Use Casesnzhang
Hive is an open source data warehouse systems based on Hadoop, a MapReduce implementation.
This presentation introduces the motivations of developing Hive and how Hive is used in the real world situation, particularly in Facebook.
Техносфера Mail.ru Group, МГУ им. М.В. Ломоносова.
Курс "Методы распределенной обработки больших объемов данных в Hadoop"
Видео лекции курса https://www.youtube.com/playlist?list=PLrCZzMib1e9rPxMIgPri9YnOpvyDAL9HD
Tuning Apache Ambari performance for Big Data at scale with 3000 agentsDataWorks Summit
Apache Ambari manages Hadoop at large-scale and it becomes increasingly difficult for cluster admins to keep the machinery running smoothly as data grows and nodes scale from 30 to 3000 agents. To test at scale, Ambari has a Performance Stack that allows a VM to host as many as 50 Ambari Agents. The simulated stack and 50 Agents per VM can stress-test Ambari Server with the same load as a 3000 node cluster. This talk will cover how to tune the performance of Ambari and MySQL, and share performance benchmarks for features like deploy times, bulk operations, installation of bits, Rolling & Express Upgrade. Moreover, the speaker will show how to use Ambari Metrics System and Grafana to plot performance, detect anomalies, and pinpoint tips on how to improve performance for a more responsive experience. Lastly, the talk will discuss roadmap features in Ambari 3.0 for improving performance and scale.
Azure Pipelines for Automatic DeploymentSafe Software
Modern tools to facilitate development and operations include Kanban boards, source control and methods for automated deployment and testing. One of these toolchains is Azure Devops. The swimming lanes with tasks and product backlog items are probably familiar with many a FME developer. I hope source control is too.
But, what if Azure Devops could help you get the latest fruits of your labor on your Staging Environment, and when approved, deploy it to Production? If you know Azure Devops, you've probably seen the blue rocket 'Pipelines' button. If you've pressed this, and thought 'eh…. well… interesting… maybe later…', this presentation is for you. I'll show you it is actually not that hard to deploy FME components from a GIT repository to your server. Get inspired and expand on this in your own way.
Deep Dive on Amazon Aurora MySQL Performance Tuning (DAT429-R1) - AWS re:Inve...Amazon Web Services
Amazon Aurora offers several options for monitoring and optimizing MySQL database performance. These include Enhanced Monitoring and Performance Insights, an easy-to-use tool for assessing the load on your database and identifying slow-performing queries. In this session, learn how to tune the performance of your Aurora database with MySQL compatibility, whether your application is in development or in production.
Hive Training -- Motivations and Real World Use Casesnzhang
Hive is an open source data warehouse systems based on Hadoop, a MapReduce implementation.
This presentation introduces the motivations of developing Hive and how Hive is used in the real world situation, particularly in Facebook.
Техносфера Mail.ru Group, МГУ им. М.В. Ломоносова.
Курс "Методы распределенной обработки больших объемов данных в Hadoop"
Видео лекции курса https://www.youtube.com/playlist?list=PLrCZzMib1e9rPxMIgPri9YnOpvyDAL9HD