drtprod: add drt-1m-tables cluster configuration#170912
Open
srosenberg wants to merge 1 commit into
Open
Conversation
Adds a new DRT cluster topology for the schema foundations team's long-running ~1 million descriptor scale test. The cluster is 9 nodes of n2-highmem-16 across three zones in us-east1 (single region), plus one n2-standard-16 workload node colocated in us-east1-c. Each crdb node has 4 local SSDs (1.5 TB raw per node) and is started with --wal-failover=among-stores. n2-highmem-16 (16 vCPU, 128 GB) is chosen over the standard n2-standard machine type because at ~1M descriptors the leased descriptor cache, range descriptor cache, and SQL plan/stats caches grow substantially, and the extra memory leaves headroom for the Pebble block cache and workload connections without OOMs. VMs are labeled usage=1m_tables for cost attribution. Workload init/run scripts are intentionally omitted; the schema-foundations team will plug in their own descriptor-generation driver once it is finalized. Epic: none Release note: None
srosenberg
requested review from
cpj2195 and
herkolategan
and removed request for
a team
Contributor
|
Merging to
After your PR is submitted to the merge queue, this comment will be automatically updated with its status. If the PR fails, failure details will also be posted here |
Member
|
This change is |
srosenberg
requested review from
rafiss and
shailendra-patel
and removed request for
herkolategan
rafiss
approved these changes
Jun 2, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds a new DRT cluster topology for the schema foundations team's long-running ~1 million descriptor scale test. The cluster is 9 nodes of
n2-highmem-16across three zones inus-east1(single region), plus onen2-standard-16workload node colocated inus-east1-c. Each crdb node has 4 local SSDs (1.5 TB raw per node) and is started with--wal-failover=among-stores.n2-highmem-16(16 vCPU, 128 GB) is chosen over the standardn2-standardmachine type because at ~1M descriptors the leased descriptor cache, range descriptor cache, and SQL plan/stats caches grow substantially, and the extra memory leaves headroom for the Pebble block cache and workload connections without OOMs.VMs are labeled
usage=1m_tablesfor cost attribution. Workload init/run scripts are intentionally omitted; the schema-foundations team will plug in their own descriptor-generation driver once it is finalized.Epic: none
Release note: None