[serving] Adds mutliple node cluster configuration support #2190
Conversation
This file contains 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
zachgk
reviewed
Jul 17, 2024
| binding = prop.getProperty(INFERENCE_ADDRESS, "http://127.0.0.1:8080"); | ||
| } else { | ||
| binding = prop.getProperty(CLUSTER_ADDRESS, "http://127.0.0.1:8888"); |
There was a problem hiding this comment.
This isn't correct for ConnectorType.BOTH
There was a problem hiding this comment.
I will change to switch case to make it more readable
| private String error; | ||
|
|
||
| private ClusterConfig() { | ||
| clusterSize = Integer.parseInt(Utils.getenv("DJL_CLUSTER_SIZE", "1")); |
There was a problem hiding this comment.
It might be slightly nicer to configure this using the config manager rather than just environment variables
There was a problem hiding this comment.
- This is configured by LWS, and it only support env var so far
- There are other code (PyEnv) is also just use this env var
frankfliu
force-pushed
the
cluster
branch
3 times, most recently
from
f3fb43b to
7a4fd07
Compare
nikhil-sk
reviewed
Jul 18, 2024
| @@ -1,5 +1,6 @@ | |||
| inference_address=http://0.0.0.0:8080 | |||
| management_address=http://0.0.0.0:8080 | |||
| cluster_address=http://0.0.0.0:8888 | |||
There was a problem hiding this comment.
Nit: any reason for choosing 8888? Should it be a closer port like 8081?
There was a problem hiding this comment.
User may choose management port as 8081
lanking520
approved these changes
Jul 18, 2024
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Outdated suggestions cannot be applied.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.
Description
Brief description of what this PR is about