Skip to content

Introduce separate shard limit for frozen shards (#71392)#71760

Merged
henningandersen merged 3 commits intoelastic:7.xfrom
henningandersen:enhance_frozen_shard_limit_7x
Apr 17, 2021
Merged

Introduce separate shard limit for frozen shards (#71392)#71760
henningandersen merged 3 commits intoelastic:7.xfrom
henningandersen:enhance_frozen_shard_limit_7x

Conversation

@henningandersen
Copy link
Copy Markdown
Contributor

@henningandersen henningandersen commented Apr 15, 2021

Backport of #71392

Frozen indices (partial searchable snapshots) require less heap per
shard and the limit can therefore be raised for those. We pick 3000
frozen shards per frozen data node, since we think 2000 is reasonable
to use in production.

Relates #71042 and #34021

Includes #71781 and #71777

Frozen indices (partial searchable snapshots) require less heap per
shard and the limit can therefore be raised for those. We pick 3000
frozen shards per frozen data node, since we think 2000 is reasonable
to use in production.

Relates elastic#71042 and elastic#34021
@henningandersen henningandersen added >enhancement :Distributed/Snapshot/Restore Anything directly related to the `_snapshot/*` APIs :Data Management/Indices APIs DO NOT USE. Use ":Distributed/Indices APIs" or ":StorageEngine/Templates" instead. backport :Distributed/Autoscaling Automatically adding or removing nodes in a cluster v7.13.0 labels Apr 15, 2021
@elasticmachine elasticmachine added Team:Distributed Meta label for distributed team. Team:Data Management (obsolete) DO NOT USE. This team no longer exists. labels Apr 15, 2021
@elasticmachine
Copy link
Copy Markdown
Collaborator

Pinging @elastic/es-core-features (Team:Core/Features)

@elasticmachine
Copy link
Copy Markdown
Collaborator

Pinging @elastic/es-distributed (Team:Distributed)

If master ends up on a newer version than other cluster members, we
cannot apply the new index setting for shard limits. We skip doing so
for now.
henningandersen added a commit that referenced this pull request Apr 17, 2021
Test would fail one out of 20 runs due to off by one error.

Relates to #71760
@henningandersen henningandersen merged commit 12314f6 into elastic:7.x Apr 17, 2021
henningandersen added a commit to henningandersen/elasticsearch that referenced this pull request Apr 17, 2021
After elastic#71760 has been backported, we can adjust the version for when to
apply the new shard limit.
henningandersen added a commit that referenced this pull request Apr 17, 2021
After #71760 has been backported, we can adjust the version for when to
apply the new shard limit.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

backport :Data Management/Indices APIs DO NOT USE. Use ":Distributed/Indices APIs" or ":StorageEngine/Templates" instead. :Distributed/Autoscaling Automatically adding or removing nodes in a cluster :Distributed/Snapshot/Restore Anything directly related to the `_snapshot/*` APIs >enhancement Team:Data Management (obsolete) DO NOT USE. This team no longer exists. Team:Distributed Meta label for distributed team. v7.13.0

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants