From BigQuery to Lakehouse:How We Built a Petabyte-Scale Data Analytics Platform

Y	Hacker News new \| ask \| show \| jobs

	From BigQuery to Lakehouse:How We Built a Petabyte-Scale Data Analytics Platform (trmlabs.com)
	26 points by Vijayshekhawat 507 days ago

3 comments

HermitX 506 days ago

Excellent content! It looks like the Iceberg + StarRocks open lakehouse Architecture is highly effective.

link

rahulr0609 507 days ago

Surprised by Trino's performance here, and curious what is driving the performance for Starrocks

link

Vijayshekhawat 507 days ago

StarRocks is more engine is more optimised for Apache Iceberg and additionally has a aggressive caching mechanism for metadata and data, recent development in Trino are interesting as well

link

chicagobuss 507 days ago

this is awesome. I especially appreciate the detailed testing notes.

link