Github user winningsix commented on the pull request:
https://github.com/apache/spark/pull/8880#issuecomment-169181174
In fact, native optimization(using Openssl cipher) with AES-NI is very
necessary.
Regards the performance, I have some rough data about the performance
impacts by enabling Shuffle file encryption using Chimera.
Using [spark-terasort](https://github.com/ehiggs/spark-terasort), we test
the shuffle file encryption running tera sort test on 1G data. Here comes some
rough information:
Unencrypted | Using JCE cipher | Using Openssl cipher
------------ | ------------- | -------------
1min31s | 1min46s | 1min30s
1min27s | 1min47s | 1min26s
1min27s | 1min44s | 1min30s
From the table, we can see that little impacts will be introduced if we
using Openssl cipher.
---
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]
