You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@samza.apache.org by "Lakshmi Manasa Gaduputi (Jira)" <ji...@apache.org> on 2022/03/03 17:50:00 UTC

[jira] [Created] (SAMZA-2725) [Elasticity] optimize consumption by smart grouping of task names into containers

Lakshmi Manasa Gaduputi created SAMZA-2725:
----------------------------------------------

             Summary: [Elasticity] optimize consumption by smart grouping of task names into containers
                 Key: SAMZA-2725
                 URL: https://issues.apache.org/jira/browse/SAMZA-2725
             Project: Samza
          Issue Type: Sub-task
            Reporter: Lakshmi Manasa Gaduputi
            Assignee: Lakshmi Manasa Gaduputi


In TaskNameGrouper, try smarter grouping such that key buckets of same ssp are grouped together in same container to reduce the number of containers consuming an ssp. for example, if there are 4 containers and 4 key buckets per ssp then instead of giving ssp0 key bucket 0 to container 0, ssp 0 bucket 1 to container 1 and so on. give all 4 buckets of ssp0 to container 1 to reduce all containers fetching all messages of ssp0.



--
This message was sent by Atlassian Jira
(v8.20.1#820001)