[tinybit_ch]

What's puzzling is ingesting and indexing speed. That part of the test set was 60 times slower than clickhouse. So, whatever Clickhouse takes a day to ingest, Tablespace will take 2 months. Also, massive 13x overhead for storage makes things look even stranger.

All of the above + your benchmark results https://tinyurl.com/4yz87ur4 show that you did trade off visibly improving 9 queries out of 43 at massive expense of disk space and ingest speed. Okay, I guess, maybe there's a usecase for that. But I would not call it a 1.6x speedup over Clickhouse, this is purely misleading.

[smythe123]

Hi there CEO of Tablespace here. I'll address your points. The disk space that Postgres on the Tablespace platform uses is similar to that Vanilla Postgres uses. Also the ingestion time is similar as well - https://n9.cl/g4woz Remember we are still in beta and the indexing time will only be improved as well. We are not optimising for disk space usage, we are optimising execution for speed. Further, although Tablespace uses more disk space as you say, it is still 50% less expensive than ClickHouse Cloud. This cost saving is very conservative as well because users of ClickHouse Cloud still need to maintain a separate transactional database. Tablespace is fully HTAP.

The 1.6x speed-up figure is indeed correct. Have a look at the relative times for Tablespace 1.44 vs. ClickHouse (AWS) 2.34 and ClickHouse (GCP) 2.22 this works out to a 1.6x speed-up.