Community for the Daft project and all things distributed data

Distributed Data Community

Seeing big regressions for these queries:

• q2: select id1, id2, sum(v1) as v1 from x group by id1, id2
• q10: select id1, id2, id3, id4, id5, id6, sum(v3) as v3, count(*) as count from x group by id1, id2, id3, id4, id5, id6
Might want to take a look at queries with multiple group by columns.

I think that’s actually something <@U07B9PD9W7J> had his eye on… multi groupby columns :stuck_out_tongue_closed_eyes: 

Also other than runtime you should definitely take a look at memory usage. Should see big improvements there! We’re pretty stoked. 