Using Hadoop at Badoo

on YouTube ↗52m

" summary

Badoo describes using Hadoop to store and process the full clickstream from the website and mobile app servers—about 1 billion events per day—and additionally about 1 billion client- and server-side user action events. The talk covers how they organize, deploy and use Hadoop for this scale and outlines what is feasible and what is not with Hadoop for these workloads.

AI-written summary · about

" chapters (9)

1. 0:00Hadoop introduction
2. 7:48Old system problems
3. 11:23Hadoop demystified
4. 17:08First Hadoop steps
5. 22:12Hadoop cluster monitoring
6. 26:20Future plans
7. 27:49Cluster specs
8. 31:45Q&A
9. 49:26Q&A

" related talks

• 47mSpeeding Event Processing to 1.6M/sec: Badoo’s ExperienceAleksandr Krasheninnikov · HighLoad++ Moscow 2018
• 05mHadoop in 5 Minutes or LessJohn Schroeder · Strata Conference 2014
• 57mBig Data: Threat or Opportunity?Shaun Connolly · PASS Business Analytics Conference 2013
• 19mDemystifying Big DataMohit Saxena · Great Indian Developer Summit 2015
• 12mBig Impact from Big DataKen Rudin · Strata Conference New York + Hadoop World 2013
• 47mSolving Real & Big (Data) Problems Using HadoopEva Andreasson · GOTO Chicago 2014
• 12mHow BT Uses Hadoop with its CRMPhillip Radley · Strata + Hadoop World London 2015
• 41mFrom Batch to Realtime with HadoopLars George · Berlin Buzzwords 2012