RED's Journey to a 7x Performance Boost by Replacing Presto with StarRocks
CelerData CelerData
512 subscribers
50 views
0

 Published On Dec 7, 2023

šŸŒ Explores Red, a social media company with a vast user base of over 200 million monthly active users, and their use of StarRocks for real-time analytics. Red processes over 100 billion rows of data daily on more than 30,000 CPU cores, achieving an average latency of just 200 milliseconds, a critical factor for their customer-facing applications.

šŸ“ˆ Red also employs StarRocks for internal reporting analytics on Hive, managing an enormous data scale exceeding a thousand petabytes with over 10,000 Hive tables. Initially using Presto, they faced operational and performance challenges, including high availability concerns.

šŸš€ The highlight of Red's journey is their switch to StarRocks for their data lake, which brought a 6x-7x performance boost and a 90% reduction in P90 latency. This move significantly lowered their operational overhead and simplified their technology infrastructure, benefiting deployment, maintenance, and the learning curve for their engineers.

šŸ“Š Additionally, the video details how StarRocks' support for Trino and Presto dialects facilitated an efficient and effective migration process, allowing seamless integration with their existing Hive setup without extensive SQL modifications.

šŸŽ„ This video is part of our 'Trino vs. StarRocks - How to Get Data Warehouse Performance on the Lakehouse' webinar. To watch in full, visit Ā Ā Ā ā€¢Ā TrinoĀ VsĀ StarRocksĀ -Ā HowĀ toĀ GetĀ DataĀ ...Ā Ā 

-----------------------------------------------------------------------------------------------------------------------
Learn more at https://celerdata.com/

Connect with us:
LinkedIn: Ā Ā /Ā celerdataĀ Ā 
Twitter: Ā Ā /Ā celerdataĀ Ā 
StarRocks GitHub: https://github.com/StarRocks/StarRocks
StarRocks Website: https://www.starrocks.io/
Slack: https://try.starrocks.com/join-starro...


#DataAnalytics #DataEngineering #DataLakeAnalytics #OLAP #DataAnalyst #DataEngineer #DataInfrastructure #UserFacingAnalytics #Database #AnalyticalDatabase #DataLake #DataLakeHouse #Trino #Presto #DataWarehouse #DataScience #Presto

show more

Share/Embed