Distributed Data Systems LabLynn Lee / Engineering notebook

Recorded / Synthetic / Reproducible

Inspect the evidence.

These are saved local runs, not live services or illustrative simulations. Read full results, code and limitations before comparing timings.

Versioned baseline: PyArrow 20.0.0 / HDFS 3.4.2 + JDK 11 / CockroachDB 24.1.24 / PyIceberg 0.10.0. All data is synthetic; all nodes share one host.

Loading recorded results… JSON files remain available below if JavaScript is disabled.

parquet.json · hdfs.json · database.json · iceberg.json

Browse the executable code →