You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@orc.apache.org by "Yurui Zhou (JIRA)" <ji...@apache.org> on 2019/02/13 08:38:00 UTC
[jira] [Updated] (ORC-469) Add EncodedStringVectorBatch to expose
string dictionary in VectorBatch
[ https://issues.apache.org/jira/browse/ORC-469?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Yurui Zhou updated ORC-469:
---------------------------
Description:
Propose to add EncodedStringVectorBatch to expose string dictionary in VectorBatch. Exposing string dictionary will benefits as bellow:
* Enable computation over encoded data. By exposing dictionary in vector batch we would be able to implement filter operator in a more efficient way. In our POC, by enabling encoded data based filter, we achieved 8% E2E perf improvement on tpch q1
* Make data serialization more efficient. Currently when serializing Orc Vectorbatch, we have to copy all the strings in a vector even though the string data is already dictionary encoded. Exposing String Dictionary will enable vector batch serializer to remove unnecessary string memcpy, which will greatly improve serialization efficiency.
was:
Propose to add EncodedStringVectorBatch to expose string dictionary in VectorBatch. Exposing string dictionary will benefits as bellow:
* Enable computation over encoded data. By exposing dictionary in vector batch we would be able to implement filter operator in a more efficient way. In our POC, by enabling encoded data based filter, we achieved 8% E2E perf improvement.
* Make data serialization more efficient. Currently when serializing Orc Vectorbatch, we have to copy all the strings in a vector even though the string data is already dictionary encoded. Exposing String Dictionary will enable vector batch serializer to remove unnecessary string memcpy, which will greatly improve serialization efficiency.
> Add EncodedStringVectorBatch to expose string dictionary in VectorBatch
> -----------------------------------------------------------------------
>
> Key: ORC-469
> URL: https://issues.apache.org/jira/browse/ORC-469
> Project: ORC
> Issue Type: Improvement
> Components: Reader
> Affects Versions: 1.5.5, 1.6.0, 2.0.0
> Reporter: Yurui Zhou
> Priority: Major
>
> Propose to add EncodedStringVectorBatch to expose string dictionary in VectorBatch. Exposing string dictionary will benefits as bellow:
> * Enable computation over encoded data. By exposing dictionary in vector batch we would be able to implement filter operator in a more efficient way. In our POC, by enabling encoded data based filter, we achieved 8% E2E perf improvement on tpch q1
> * Make data serialization more efficient. Currently when serializing Orc Vectorbatch, we have to copy all the strings in a vector even though the string data is already dictionary encoded. Exposing String Dictionary will enable vector batch serializer to remove unnecessary string memcpy, which will greatly improve serialization efficiency.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)