[
https://issues.apache.org/jira/browse/IGNITE-17738?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Anton Vinogradov updated IGNITE-17738:
--------------------------------------
Description:
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 as well as counters may contain gaps even on primary).
1) 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.
See [^PartialHistoricalRebalanceTest.java]
2) In case LWM is the same on primary and backup, rebalance will be skipped for
such partition.
See [^SkippedRebalanceBecauseOfTheSameLwmTest.java]
Proposals:
1) Cheap fix
A possible solution is for the case when the cluster failed and restarted (same
baseline) is to fix the counters automatically (when cluster composition is
equal to the baseline specified before the crash).
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.
2) Complex fix (when baseline changed)
Rebalance must honor whole counter state (LWM, HWM, gaps).
2.0) Primary HWM must be set to the highest HWM across the copies to avoid
reapplying of already applied update counters on backups.
2.1) In case when WAL is available all entries between LWM and HWM (including)
must be rebalanced to other nodes where they are required.
Even from backups to the primary.
Such approach *may require rebalance as a prerequisite to activation finish*.
was:
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 as well as counters may contain gaps even on primary).
1) 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.
See [^PartialHistoricalRebalanceTest.java]
2) In case LWM is the same on primary and backup, rebalance will be skipped for
such partition.
See [^SkippedRebalanceBecauseOfTheSameLwmTest.java]
Proposals:
1) Cheap fix
A possible solution for the case when the cluster failed and restarted (same
baseline) is to fix the counters automatically (when cluster composition is
equal to the baseline specified before the crash).
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.
2) Complex fix (when baseline changed)
Rebalance must honor whole counter state (LWM, HWM, gaps).
2.0) Primary HWM must be set to the highest HWM across the copies to avoid
reapplying of already applied update counters on backups.
2.1) In case when WAL is available all entries between LWM and HWM (including)
must be rebalanced to other nodes where they are required.
Even from backups to the primary.
Such approach *may require rebalance as a prerequisite to activation finish*.
> Cluster must be able to fix the partition inconsistency on restart/node_join
> by itself
> --------------------------------------------------------------------------------------
>
> Key: IGNITE-17738
> URL: https://issues.apache.org/jira/browse/IGNITE-17738
> Project: Ignite
> Issue Type: Sub-task
> Reporter: Anton Vinogradov
> Assignee: Maxim Muzafarov
> Priority: Major
> Labels: iep-31, ise
> Fix For: 2.15
>
> Attachments: PartialHistoricalRebalanceTest.java,
> SkippedRebalanceBecauseOfTheSameLwmTest.java
>
>
> 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 as well as counters may contain gaps even on primary).
> 1) 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.
> See [^PartialHistoricalRebalanceTest.java]
> 2) In case LWM is the same on primary and backup, rebalance will be skipped
> for such partition.
> See [^SkippedRebalanceBecauseOfTheSameLwmTest.java]
> Proposals:
> 1) Cheap fix
> A possible solution is for the case when the cluster failed and restarted
> (same baseline) is to fix the counters automatically (when cluster
> composition is equal to the baseline specified before the crash).
> 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.
> 2) Complex fix (when baseline changed)
> Rebalance must honor whole counter state (LWM, HWM, gaps).
> 2.0) Primary HWM must be set to the highest HWM across the copies to avoid
> reapplying of already applied update counters on backups.
> 2.1) In case when WAL is available all entries between LWM and HWM
> (including) must be rebalanced to other nodes where they are required.
> Even from backups to the primary.
> Such approach *may require rebalance as a prerequisite to activation finish*.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
