Row-Oriented vs Column-Oriented Execution for Mixed Analytical Workloads
Columnar layouts beat row stores on scans but lose on writes and point lookups.
Priya Venkatasubramanian
Section
Analytical Query Execution
3 stories in Analytical Query Execution.
Predicate Pushdown and Primary Key Skipping in MergeTree Queries
How sparse indexes and granule boundaries limit what data a query can skip.
Tobias Nkemdirim
Denormalization Tradeoffs in BigQuery and Redshift Schemas
Nested arrays cut BigQuery costs while distribution keys matter most on Redshift.
Callum Dzenga