Skip to content

[CORE-16628]: Cloud Topics: HTT and more scale tests#30818

Draft
oleiman wants to merge 5 commits into
devfrom
ct/core-16628/htt-and-st
Draft

[CORE-16628]: Cloud Topics: HTT and more scale tests#30818
oleiman wants to merge 5 commits into
devfrom
ct/core-16628/htt-and-st

Conversation

@oleiman

@oleiman oleiman commented Jun 16, 2026

Copy link
Copy Markdown
Member

.

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
  • v26.1.x
  • v25.3.x
  • v25.2.x

Release Notes

  • none

oleiman added 5 commits June 15, 2026 16:28
Dedup concurrent work keyed by a path. run(key, as, work) runs the
work once on the first caller (the leader) and merges later callers
onto its outcome. Bounded per shard; at capacity callers run
uncoordinated.

Signed-off-by: Oren Leiman <oren.leiman@redpanda.com>
Concurrent reads missing the cloud cache on the same extent each
issue their own S3 GET. Route read_object's cold-miss download
through single_flight so one GET serves all waiters on a shard.

A gate drains in-flight reads before file_io destruction.

Signed-off-by: Oren Leiman <oren.leiman@redpanda.com>
Per-shard counters to gauge dedup: reads, cache_misses, and
concurrent_read_merges. Plumbed through app and read-replica
refreshers.

Signed-off-by: Oren Leiman <oren.leiman@redpanda.com>
CDT-scale gate for the cloud-topics read-under-produce path: a steady
producer writes while a large backlog drains cold from object storage, so
cold fetches and L0 uploads contend for the per-shard S3 pool. Asserts
produce keeps progressing, the backlog drains, and the cluster stays healthy.
Sets disable_batch_cache to force the reads cold (cloud topics keep ~zero
local retention). Coarse regression gate, not the reservation-vs-passthrough
A/B.
stage_cloud_topics_cold_read + test_cloud_topics_cold_read: a cloud-topics
analog of stage_tiered_storage_consuming that runs on a real Redpanda Cloud
cluster at the sold tier (cloud topics is available there). Steady produce at
max tier ingress + an RpkConsumer draining the backlog cold from oldest;
asserts produce advances and the backlog drains. Backlog volume and drain
timeout are calibration knobs.
@oleiman oleiman self-assigned this Jun 16, 2026
@oleiman oleiman changed the title Ct/core 16628/htt and st [CORE-16628]: Cloud Topics: HTT and more scale tests Jun 16, 2026
@oleiman

oleiman commented Jun 17, 2026

Copy link
Copy Markdown
Member Author

/cdt
rp_version=build
tests/rptest/scale_tests/cloud_topics_cold_read_scale_test.py

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant