Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ducktape: Increase partition density to 2k per shard in the MPT #24710

Open
wants to merge 2 commits into
base: dev
Choose a base branch
from

Conversation

StephanDollberg
Copy link
Member

@StephanDollberg StephanDollberg commented Jan 7, 2025

Increase the partition density in the MPT to 2k per shard and use the new memory group aware config.

As discussed the plan is to raise this to 3k but that makes us currently run into an oversized alloc (large enough to fail the test) so that needs to be fixed first before we can increase the density in the test further (see https://redpandadata.slack.com/archives/C04B5T58QQ1/p1736265968267079).

Backports Required

  • none - not a bug fix
  • none - this is a backport
  • none - issue does not exist in previous branches
  • none - papercut/not impactful enough to backport
  • v24.3.x
  • v24.2.x
  • v24.1.x

Release Notes

  • none

Increase partition density to 2k partitions per shard and adapt the test
to use the new memory group aware config.
kgo-repeaters start to get pretty loaded at higher partition densities
so the status query can take a bit longer.
@travisdowns
Copy link
Member

@@ -43,12 +43,16 @@
BIG_FETCH = 104857600

# How much memory to assign to redpanda per partition. Redpanda will be started
# with MIB_PER_PARTITION * PARTITIONS_PER_SHARD * CORE_COUNT memory
DEFAULT_MIB_PER_PARTITION = 4
# with (MIB_PER_PARTITION * PARTITIONS_PER_SHARD * CORE_COUNT) / (PARTITIONS_MEMORY_ALLOCATION_PERCENT / 100) memory
Copy link
Member

@travisdowns travisdowns Jan 7, 2025

Choose a reason for hiding this comment

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

Should be / (PARTITIONS_MEMORY_ALLOCATION_PERCENT be * / (PARTITIONS_MEMORY_ALLOCATION_PERCENT)?

Copy link
Member Author

@StephanDollberg StephanDollberg Jan 8, 2025

Choose a reason for hiding this comment

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

* / (PARTITIONS_MEMORY_ALLOCATION_PERCENT)

Do you mean * 100 / PARTITIONS_MEMORY_ALLOCATION_PERCENT?


# How many partitions we will create per shard: this is the primary scaling
# factor that controls how many partitions a given cluster will get.
DEFAULT_PARTITIONS_PER_SHARD = 1000
DEFAULT_PARTITIONS_PER_SHARD = 2000
Copy link
Member

Choose a reason for hiding this comment

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

Almost feels like we should read it from config, but anyway LGTM.

partition_replicas_per_node + per_node_slack)
memory_setting = mib_per_partition * (
partition_replicas_per_node +
per_node_slack) * (self.partition_memory_reserve_percentage / 100.)
Copy link
Member Author

Choose a reason for hiding this comment

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

Miscommitted some last minute changes I was playing around with. Needs to be /

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants