[native][Coordinator throttling] Endpoint on worker reporting node load metrics#25686
Open
prashantgolash wants to merge 1 commit into
Open
[native][Coordinator throttling] Endpoint on worker reporting node load metrics#25686prashantgolash wants to merge 1 commit into
prashantgolash wants to merge 1 commit into
Conversation
Collaborator
|
This pull request was exported from Phabricator. Differential Revision: D76357677 |
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 5, 2025
Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 5, 2025
Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 5, 2025
Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 5, 2025
Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
88d5f58 to
1077929
Compare
Collaborator
|
This pull request was exported from Phabricator. Differential Revision: D76357677 |
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 5, 2025
…cs (prestodb#25686) Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
1077929 to
2ca89b5
Compare
Collaborator
|
This pull request was exported from Phabricator. Differential Revision: D76357677 |
2ca89b5 to
22a7a97
Compare
Collaborator
|
This pull request was exported from Phabricator. Differential Revision: D76357677 |
22a7a97 to
aa16de1
Compare
Collaborator
|
This pull request was exported from Phabricator. Differential Revision: D76357677 |
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 5, 2025
…cs (prestodb#25686) Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 5, 2025
…cs (prestodb#25686) Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
aa16de1 to
4ae7132
Compare
Collaborator
|
This pull request was exported from Phabricator. Differential Revision: D76357677 |
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 5, 2025
…cs (prestodb#25686) Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 5, 2025
…cs (prestodb#25686) Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
4ae7132 to
b10fb57
Compare
Collaborator
|
This pull request was exported from Phabricator. Differential Revision: D76357677 |
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 5, 2025
…cs (prestodb#25686) Summary: Pull Request resolved: prestodb#25686 **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 11, 2025
…cs (prestodb#25686) Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
Collaborator
|
This pull request was exported from Phabricator. Differential Revision: D76357677 |
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 11, 2025
…cs (prestodb#25686) Summary: Pull Request resolved: prestodb#25686 **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
701f42a to
ddeadaa
Compare
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 11, 2025
…cs (prestodb#25686) Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 11, 2025
…cs (prestodb#25686) Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 11, 2025
…cs (prestodb#25686) Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 11, 2025
…cs (prestodb#25686) Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
ddeadaa to
e1f2b7c
Compare
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 11, 2025
…cs (prestodb#25686) Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 11, 2025
…cs (prestodb#25686) Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
Collaborator
|
This pull request was exported from Phabricator. Differential Revision: D76357677 |
prashantgolash
added a commit
to prashantgolash/presto
that referenced
this pull request
Aug 11, 2025
…cs (prestodb#25686) Summary: Pull Request resolved: prestodb#25686 **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Differential Revision: D76357677
e1f2b7c to
a7644cd
Compare
Collaborator
|
This pull request was exported from Phabricator. Differential Revision: D76357677 |
Contributor
Author
|
Test case doesn’t look related to this change. |
tdcmeehan
requested changes
Aug 26, 2025
tdcmeehan
left a comment
Contributor
There was a problem hiding this comment.
Is it possible to test this endpoint?
Comment on lines
+49
to
+52
| @JsonProperty("cpuUsedPercent") Double cpuUsedPercent, | ||
| @JsonProperty("memoryUsedInBytes") Double memoryUsedInBytes, | ||
| @JsonProperty("cpuOverload") Boolean cpuOverload, | ||
| @JsonProperty("memoryOverload") Boolean memoryOverload) |
Contributor
There was a problem hiding this comment.
Suggested change
| @JsonProperty("cpuUsedPercent") Double cpuUsedPercent, | |
| @JsonProperty("memoryUsedInBytes") Double memoryUsedInBytes, | |
| @JsonProperty("cpuOverload") Boolean cpuOverload, | |
| @JsonProperty("memoryOverload") Boolean memoryOverload) | |
| @JsonProperty("cpuUsedPercent") double cpuUsedPercent, | |
| @JsonProperty("memoryUsedInBytes") double memoryUsedInBytes, | |
| @JsonProperty("cpuOverload") boolean cpuOverload, | |
| @JsonProperty("memoryOverload") boolean memoryOverload) |
Collaborator
|
This pull request was exported from Phabricator. Differential Revision: D76357677 |
Contributor
Author
Added the stand alone end point testing. |
spershin
requested changes
Aug 26, 2025
spershin
left a comment
Contributor
There was a problem hiding this comment.
Tim was asking for some endpoint test. Do we have tests for other endpoints, so we can craft this was similarly?
Collaborator
|
This pull request was exported from Phabricator. Differential Revision: D76357677 |
Contributor
Author
We don't have any existing tests for endpoints. I updated my test plan. |
Collaborator
|
This pull request was exported from Phabricator. Differential Revision: D76357677 |
spershin
previously approved these changes
Aug 26, 2025
Collaborator
|
This pull request was exported from Phabricator. Differential Revision: D76357677 |
1 similar comment
Collaborator
|
This pull request was exported from Phabricator. Differential Revision: D76357677 |
…ad metrics (prestodb#25686) Summary: **Context:** We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state. **Approach:** Added a new end point to get nodeStats. The idea is that we would replace "/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + <worker load metrics>. This will help coordinator making scheduling decisions Reviewed By: spershin Differential Revision: D76357677
Collaborator
|
This pull request was exported from Phabricator. Differential Revision: D76357677 |
tdcmeehan
approved these changes
Aug 27, 2025
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
5 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.
Summary:
Context:
We want to consider worker load metrics to make scheduling decision from coordinator. Currently in single coordinator setup, it invokes /v1/info/state to get worker's state.
Approach:
Added a new end point to get nodeStats. The idea is that we would replace
"/v1/info/state" -> "/v1/info/nodestate" which will include nodeState + . This will help coordinator making scheduling decisions
Differential Revision: D76357677
Testing
curl <worker_host>/v1/info/stats
{
"loadMetrics": {
"cpuOverload": false,
"cpuUsedPercent": 0,
"memoryOverload": true,
"memoryUsedInBytes": 0,
"numQueuedDrivers": 0
},
"nodeState": "ACTIVE"
}