apache / datafusion-comet

Apache DataFusion Comet Spark Accelerator
https://datafusion.apache.org/comet
Apache License 2.0
826 stars 164 forks source link

perf: Add metric for time spent in CometSparkToColumnarExec #931

Closed mbutrovich closed 2 months ago

mbutrovich commented 2 months ago

Which issue does this PR close?

N/A.

Rationale for this change

We want deeper insights to query performance when Spark to Arrow conversions occur.

What changes are included in this PR?

Added a new metric to CometSparkToColumnarExec and wrapped the calls to the batch iterator's next function with timing functions.

How are these changes tested?

Extended an existing test that exercises SparkToColumnar to check for metrics.