You are viewing a plain text version of this content. The canonical link for it is here.
Posted to jira@kafka.apache.org by GitBox <gi...@apache.org> on 2021/09/24 10:54:55 UTC
[GitHub] [kafka] mprusakov commented on pull request #11353: KAFKA-13322: Reducing amount of garbage that gets generated during a poll operation
mprusakov commented on pull request #11353:
URL: https://github.com/apache/kafka/pull/11353#issuecomment-926534122
@showuon Raised KAFKA-13322 for this and similar issues
for the complexity argument, the present implementation starts off with an empty array list and adds a potentially large amount of entries. To accommodate them the list needs to grow and so copy the existing vaues (https://github.com/openjdk/jdk/blob/739769c8fc4b496f08a92225a12d07414537b6c0/src/java.base/share/classes/java/util/ArrayList.java#L237). Since the new implementation doesn't need to do any of that it is actualy a lot more efficient.
In my test that particular allocation was 19.4%
Please let me know if any further changes are required. Thanks.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: jira-unsubscribe@kafka.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org