Archives of Support Questions (Read Only)

This is an archived board for historical reference. Information and links may no longer be available or relevant
Announcements
This board is archived and read-only for historical reference. To ask a new question, please post a new topic on the appropriate active board.

Overall peak memory usage of a query?

avatar
New Contributor

Where can I see the overall peak memory usage of a query. In the textplan I get an estimated per-host requirement. But we want to compare RDF queries with up to 200 joins for memory efficiency and need the real per-host peak memory usage. Where can I find it?

2 ACCEPTED SOLUTIONS

avatar

You can find that information in the runtime profile. There are various ways to get it - e.g. from impala-shell you can run profile; after the query. The PerHostPeakMemUsage counter will tell you the peak memory usage for each impala instance executing the query. I think getting the numbers for each host and summing them gives you roughly what you want.

 

200 joins sounds like an interesting query  - let us know how it goes.

View solution in original post

avatar

I misread your question and didn't realise you wanted the per-host peak, PerHostPeakMemUsage gives you exactly what you want.

View solution in original post

2 REPLIES 2

avatar

You can find that information in the runtime profile. There are various ways to get it - e.g. from impala-shell you can run profile; after the query. The PerHostPeakMemUsage counter will tell you the peak memory usage for each impala instance executing the query. I think getting the numbers for each host and summing them gives you roughly what you want.

 

200 joins sounds like an interesting query  - let us know how it goes.

avatar

I misread your question and didn't realise you wanted the per-host peak, PerHostPeakMemUsage gives you exactly what you want.