[
https://issues.apache.org/jira/browse/SOLR-18315?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Pierre Salagnac updated SOLR-18315:
-----------------------------------
Summary: Replace CPU intensive UTF conversion tool by JVM calls (was:
Replicate CPU intensive UTF conversion tool by JVM calls)
> Replace CPU intensive UTF conversion tool by JVM calls
> ------------------------------------------------------
>
> Key: SOLR-18315
> URL: https://issues.apache.org/jira/browse/SOLR-18315
> Project: Solr
> Issue Type: Improvement
> Components: SolrJ
> Affects Versions: 10.0
> Reporter: Pierre Salagnac
> Priority: Minor
>
> When sending updates, I noticed the code that converts Java strings (UTF16)
> into UTF8 for {{JavaBinCodec}} is a CPU hotspot.
> This may be either in ingesting clients or in Solr nodes when forwarding data.
> All the code for UTF conversion in class {{ByteUtils}} is very CPU intensive.
> The JVM provides methods for UTF conversion that are intrinsic candidates and
> will be much more efficient, both in term of CPU and memory consumption.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
