Github user nongli commented on the pull request:
https://github.com/apache/spark/pull/11435#issuecomment-191513355
This patch is abusing the existing abstractions which will be/is being
cleaned up in other patches. For a benchmark of the partition reading speed, I
tested this on a table with 2 int cols, one in the data, one as the partition
column. The results are:
```
Partitioned Table: Best/Avg Time(ms) Rate(M/s) Per
Row(ns) Relative
-------------------------------------------------------------------------------------------
Read data column 217 / 262 72.3
13.8 1.0X
Read partition column 104 / 150 150.6
6.6 2.1X
Read both columns 240 / 266 65.5
15.3 0.9X
```
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
