Skip to content

Conversation

pracucci
Copy link
Contributor

What this PR does:
When running a blocks storage cluster with many tenants, you may end up with a large amount of blocks (and thus index-headers) managed by each store-gateway. This could end up to hit the limit of the max per-process mmap areas (because each index-header gets mmap-ed). To overcome this, I built into Thanos the ability to lazy mmap index-headers (thanos-io/thanos#3431) and in this PR I'm upgrading Thanos to bring this enhancement (optional and experimental).

I checked other Thanos changes and should be fine.

Which issue(s) this PR fixes:
N/A

Checklist

  • Tests updated
  • Documentation added
  • CHANGELOG.md updated - the order of entries should be [CHANGE], [FEATURE], [ENHANCEMENT], [BUGFIX]

Copy link
Contributor

@pstibrany pstibrany left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, nice improvement.

pracucci and others added 2 commits November 18, 2020 09:30
Signed-off-by: Marco Pracucci <[email protected]>

Co-authored-by: Peter Štibraný <[email protected]>
Signed-off-by: Marco Pracucci <[email protected]>

Co-authored-by: Peter Štibraný <[email protected]>
@pracucci pracucci merged commit cf6f899 into cortexproject:master Nov 18, 2020
@pracucci pracucci deleted the upgrade-thanos-to-bring-lazy-mmap branch November 18, 2020 09:15
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants