You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@ignite.apache.org by "Anton Vinogradov (Jira)" <ji...@apache.org> on 2022/09/21 17:45:00 UTC
[jira] [Updated] (IGNITE-17738) Historical rebalance must be able to fix the consistency on cluster restart by itself
[ https://issues.apache.org/jira/browse/IGNITE-17738?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Anton Vinogradov updated IGNITE-17738:
--------------------------------------
Summary: Historical rebalance must be able to fix the consistency on cluster restart by itself (was: Historical rebalance must be able to fix the consistency on cluster restart)
> Historical rebalance must be able to fix the consistency on cluster restart by itself
> -------------------------------------------------------------------------------------
>
> Key: IGNITE-17738
> URL: https://issues.apache.org/jira/browse/IGNITE-17738
> Project: Ignite
> Issue Type: Sub-task
> Reporter: Anton Vinogradov
> Priority: Major
> Labels: ise
>
> On cluster restart (because of power-off, OOM or some other problem) it's possible to have PDS inconsistent (primary partitions may contain operations missed on backups).
> Currently, "historical rebalance" is able to sync the data to the highest LWM for every partition.
> Most likely, a primary will be chosen as a rebalance source, but the data after the LWM will not be rebalanced. So, all updates between LWM and HWM will not be synchronized.
> A possible solution for the case when the cluster failed and restarted (same baseline) is to fix counters to help "historical rebalance" perform the sync.
> Counters should be set as
> - HWM at primary and as LWM at backups for caches with 2+ backups,
> - LWM at primary and as HWM at backups for caches with a single backup.
> This can be implemented as an extension for the "-consistency finalize` command, for example `-consistency finalize-on-restart`.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)