[–] aleda145 5mo ago ↗ Very exciting! The numbers seem to crush iceberg. Has anyone tried it out for "real" workloads? [–] orthoxerox 5mo ago ↗ Where did you find these numbers? The way I see it, it's basically Iceberg, but with all metadata and small data changes stored in an RDBMS. [–] cbility 5mo ago ↗ It depends what you're measuring. For streaming workloads they're reporting 923x speedup for aggregations, and 105x for insertions, over iceberg [1].There are also some improvements other areas, e.g. cross table transactions are not possible in iceberg/delta, but they are in ducklake. [2][1] https://ducklake.select/2026/04/02/data-inlining-in-ducklake...[2] https://ducklake.select/manifesto/#features
[–] orthoxerox 5mo ago ↗ Where did you find these numbers? The way I see it, it's basically Iceberg, but with all metadata and small data changes stored in an RDBMS. [–] cbility 5mo ago ↗ It depends what you're measuring. For streaming workloads they're reporting 923x speedup for aggregations, and 105x for insertions, over iceberg [1].There are also some improvements other areas, e.g. cross table transactions are not possible in iceberg/delta, but they are in ducklake. [2][1] https://ducklake.select/2026/04/02/data-inlining-in-ducklake...[2] https://ducklake.select/manifesto/#features
[–] cbility 5mo ago ↗ It depends what you're measuring. For streaming workloads they're reporting 923x speedup for aggregations, and 105x for insertions, over iceberg [1].There are also some improvements other areas, e.g. cross table transactions are not possible in iceberg/delta, but they are in ducklake. [2][1] https://ducklake.select/2026/04/02/data-inlining-in-ducklake...[2] https://ducklake.select/manifesto/#features
3 comments
[ 10.3 ms ] story [ 32.7 ms ] threadThere are also some improvements other areas, e.g. cross table transactions are not possible in iceberg/delta, but they are in ducklake. [2]
[1] https://ducklake.select/2026/04/02/data-inlining-in-ducklake...
[2] https://ducklake.select/manifesto/#features