This message was deleted.

some generic performance advice: 1) consider schema design best practices— https://druid.apache.org/docs/latest/ingestion/schema-design.html#general-tips-and-best-practices 2) try adding more data servers and see if that helps. if it does then it means your bottleneck is dat servers. if it doesn't, then your bottleneck is likely at the Broker 3) try to attack the bottleneck by looking at HW metrics: for example, if you are I/O bound then try adding memory or try looking into the performance of your I/O layer 4) also consider grabbing a flame graph to understand the bottleneck further (https://support.imply.io/hc/en-us/articles/360033747953-Profiling-Druid-queries-using-flame-graphs)

Thanks @Gian Merlino will go through these docs.

hi @Bharat Kumar Singh! also, be mindful of how you are usually accessing the data and how it's physically stored in the segments; I was using a specific dimension for filtering 100% of the time, so using

single_dim

as partitioning helped a ton