[jira] [Comment Edited] (IGNITE-1093) Rebalancing with default parameters is very slow

["Anton Vinogradov (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/IGNITE-1093?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14659634#comment-14659634 ] 

Anton Vinogradov edited comment on IGNITE-1093 at 8/6/15 7:39 AM:
------------------------------------------------------------------

Design points
1) Demand pool should handle supply messages in parallel way
2) Each supply message should contains partition or ot part ( limited by batch size)
3) Demand pool should request N partition at start and request new when one of previous rebalanced
4) Demand pool shoul request M batches for each partition at start and request new when one of previous handled



was (Author: avinogradov):
Ideas:
1) Demand pool should handle supply messages in parallel way
2) Each supply message should contains partition or ot part ( limited by batch size)
3) Demand pool should request N partition at start and request new when one of previous rebalanced
4) Demand pool shoul request M batches for each partition at start and request new when one of previous handled


> Rebalancing with default parameters is very slow
> ------------------------------------------------
>
>                 Key: IGNITE-1093
>                 URL: https://issues.apache.org/jira/browse/IGNITE-1093
>             Project: Ignite
>          Issue Type: Bug
>          Components: cache
>    Affects Versions: sprint-7
>            Reporter: Pavel Konstantinov
>            Assignee: Anton Vinogradov
>            Priority: Critical
>             Fix For: sprint-8
>
>
> # Start one node with partitioned cache with one backup.
> # Load into the cache 40billions of keys using DataStreamer
> # Start second node on the same host



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)