[ 
https://issues.apache.org/jira/browse/HADOOP-10768?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16256359#comment-16256359
 ] 

Dapeng Sun commented on HADOOP-10768:
-------------------------------------

Thank [~daryn] for your attention.

The overhead are coming from {{integrity check}}(MD5) and 
{{crypto}}(En/Decryption).
For INTEGRITY mode, the overhead is HmacMD5;
For PRIVACY mode, the overhead is HmacMD5 + AES/DES.

>From the result, we can see the patch have improved throughput of crypto part 
>a lot, the main bottleneck is not crypto part any more. If we want to reduce 
>the degradation, we need continue to improve the throughput of integrity 
>check. I will investigate how to improve it, if you have any idea or 
>suggestion about it, please tell me:)

> Optimize Hadoop RPC encryption performance
> ------------------------------------------
>
>                 Key: HADOOP-10768
>                 URL: https://issues.apache.org/jira/browse/HADOOP-10768
>             Project: Hadoop Common
>          Issue Type: Improvement
>          Components: performance, security
>    Affects Versions: 3.0.0-alpha1
>            Reporter: Yi Liu
>            Assignee: Dapeng Sun
>         Attachments: HADOOP-10768.001.patch, HADOOP-10768.002.patch, 
> HADOOP-10768.003.patch, HADOOP-10768.004.patch, HADOOP-10768.005.patch, 
> HADOOP-10768.006.patch, HADOOP-10768.007.patch, HADOOP-10768.008.patch, 
> Optimize Hadoop RPC encryption performance.pdf
>
>
> Hadoop RPC encryption is enabled by setting {{hadoop.rpc.protection}} to 
> "privacy". It utilized SASL {{GSSAPI}} and {{DIGEST-MD5}} mechanisms for 
> secure authentication and data protection. Even {{GSSAPI}} supports using 
> AES, but without AES-NI support by default, so the encryption is slow and 
> will become bottleneck.
> After discuss with [~atm], [~tucu00] and [~umamaheswararao], we can do the 
> same optimization as in HDFS-6606. Use AES-NI with more than *20x* speedup.
> On the other hand, RPC message is small, but RPC is frequent and there may be 
> lots of RPC calls in one connection, we needs to setup benchmark to see real 
> improvement and then make a trade-off. 



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: common-issues-h...@hadoop.apache.org

Reply via email to