dkgs
- Karma
- 0
- Created
- ()
- Submissions
- 0
- Making GROUP BY faster by doing more (CPU) work (pivotlake.io)
- TiDB Breached (pingcap.com)
- The Sun Never Sets on the Ant Empire (sqonline.ucsd.edu)
- In Defense of Curiosity (davidbau.com)
- Does ClickHouse need its own storage format? (pivotlake.io)
- Boring Iceberg Catalog (github.com)
- Why vector databases are a scam (simon-frey.com)
- WarpSpeed rewrites Pandas to run 38.4x faster on PDS-H (doubleai.com)
- Agentic Coding at ClickHouse (clickhouse.com)
- Are open-table-formats and lakehouses the future of observability? (clickhouse.com)
- I love UUID, I hate UUID (blog.epsiolabs.com)
- Stream Processing Without Duplications (blog.epsiolabs.com)
- Real-Time Mode in Apache Spark Structured Streaming (databricks.com)
- The Bidirectional Stream Processor: Why Pull Beats Push for Crash Recovery (blog.epsiolabs.com)
- How we made our streaming joins 50% faster (blog.epsiolabs.com)
- The equality delete problem in Apache Iceberg (blog.dataengineerthings.org)
- Stream processing doesn't need to suck (blog.epsiolabs.com)
- Not duplicating messages: a surprisingly hard problem (blog.epsiolabs.com)