Scratch file generation information

[#1]

Hello,

A simple question:

How can I know which queries generate Scratch files?

I'm inspecting the Impalad logs and I couldn't find any information about the scratch file generation.

Regards,

Silva

[#2]

They're used for spill to disk - see https://www.cloudera.com/documentation/enterprise/latest/topics/impala_scalability.html#spill_to_dis...

[#3]

But I need to know which specific queries spills into disk, generating the scratch files. Is possible to have that kind of information?.

[#4 · Accepted solution]

The Cloudera Manager queries page has the bytes spilled to disk as one of the metrics it tracks per query. Also in CM, there's a "Cluster utilization report" that has some aggregate information about how much data is spilled to disk over longer time windows. Also, if you're looking at the scratch files themselves the query ID is embedded in the file name (although that's an implementation detail and could change in the future).

[#5]

Thanks a lot for the info