fix(modelgateway): kafka topics with correct number of partitions #5427
Conversation
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
The number of partitions with which model-specific kafka topics is created needs to be the same as the number of partitions for other topics (pipelines/experiments/etc). This is a Kafka Streams constraint in order for joins to work correctly. Until now, an incorrect environment variable was being passed to modelgateway, which meant that it was always creating topics with 1 partition. This in turn led to dataflow processing getting stuck whenever other topics were created with multiple partitions **Fixed issues**: - INFRA-822: Pipelines get stuck on triggers/joins
lc525
commented
Mar 12, 2024
| @@ -252,7 +252,7 @@ serverConfig: | |||
| pullPolicy: IfNotPresent | |||
| registry: docker.io | |||
| repository: seldonio/mlserver | |||
| tag: 1.3.5 | |||
| tag: 1.5.0 | |||
There was a problem hiding this comment.
without this change, on automated re-generation of helm-charts & yamls, 1.3.5 was being introduced instead of 1.5.0
jtayl222
pushed a commit
to jtayl222/seldon-core
that referenced
this pull request
Jul 20, 2025
…ldonIO#5427) The number of partitions with which model-specific kafka topics is created needs to be the same as the number of partitions for other topics (pipelines/experiments/etc). This is a Kafka Streams constraint in order for joins to work correctly. Until now, an incorrect environment variable was being passed to modelgateway, which meant that it was always creating topics with 1 partition. This in turn led to dataflow processing getting stuck whenever other topics were created with multiple partitions **Fixed issues**: - INFRA-822: Pipelines get stuck on triggers/joins
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
The number of partitions with which model-specific kafka topics is created needs to be the same as the number of partitions for other topics (pipelines/experiments/etc). This is a Kafka Streams constraint in order for joins to work correctly.
Until now, an incorrect environment variable was being passed to modelgateway, which meant that it was always creating topics with 1 partition. This in turn led to dataflow processing getting stuck whenever other topics were created with multiple partitions
Fixed issues: