pingcap / pingcap/ticdc

event service received resolved-ts lag should not spike if the downstream sink is the bottleneck

Open
#3,460 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

severity/moderate type/enhancement
Dominant language
Go
Stars
56
Forks
63
Avg merge
2d 20h
Merged PRs (30d)
34

Description

run kafka sink changefeed, and inject network latency chaos, the latency is around 10 ~ 20 ms

  • The checkpoint lag increase is expected, since write to the downstream is too slow now.
Image
  • resolved-ts lag also increased, this is not expected. resolved-ts should only relevant to receive data from the upstream.
Image
  • event store resolved-ts lag is stable, this is expected.
Image
  • event service received resolved-ts lag is almost identical to the changefeed resolved-ts. It also spikes, it's not expected.
Image

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Reproduce the Kafka sink changefeed with injected network latency and compare checkpoint lag, changefeed resolved-ts lag, event store resolved-ts lag, and event service received resolved-ts lag. Trace how resolved-ts moves through the event service and confirm that downstream sink latency no longer causes the received resolved-ts metric to spike.

Written by the indexing model from the issue text.

Assessment

Tech stack
go, kafka
Domain
observability, stream-processing
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.