[Serve][2/n] add batching metrics#59232
Merged
abrarsheikh merged 5 commits intomasterfrom Dec 15, 2025
Merged
Conversation
Signed-off-by: abrar <abrar@anyscale.com>
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces metrics for batching functionality in Ray Serve. New constants for histogram buckets are added, and the batching logic is updated to record metrics for wait time, execution time, queue length, utilization, and processed batches. A new test is also added to verify these metrics.
The changes are well-implemented. I have a couple of suggestions for the new test file:
- Move local imports to the top of the file to follow PEP 8 guidelines.
- Enhance the test to also verify the sum of the batch utilization metric, which would make the test more robust.
Signed-off-by: abrar <abrar@anyscale.com>
Signed-off-by: abrar <abrar@anyscale.com>
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
ray-gardener
bot
added
serve
Signed-off-by: abrar <abrar@anyscale.com>
kriyanshii
pushed a commit
to kriyanshii/ray
that referenced
this pull request
Dec 16, 2025
fixes ray-project#59218 ### Performance Delta ```python from ray import serve from typing import List @serve.deployment(max_ongoing_requests=1000) class MyDeployment: @serve.batch(max_batch_size=10, batch_wait_timeout_s=1) async def handle_batch(self, requests: List[int]) -> List[int]: return [request + 1 for request in requests] async def __call__(self) -> List[int]: return await self.handle_batch(1) app = MyDeployment.bind() ``` `ray start --head --metrics-export-port=8080` -> `serve run batch_test:app` locust 100 users Metric | With Change | Master | Δ (Master – With Change) -- | -- | -- | -- Requests | 32,033 | 33,541 | +1,508 Fails | 0 | 0 | 0 Median (ms) | 170 | 170 | 0 95%ile (ms) | 240 | 240 | 0 99%ile (ms) | 280 | 270 | –10 ms Average (ms) | 172.98 | 171.87 | –1.11 ms Min (ms) | 70 | 84 | +14 ms Max (ms) | 352 | 365 | +13 ms Average size (bytes) | 1 | 1 | 0 Current RPS | 581.9 | 604.1 | +22.2 Current Failures/s | 0 | 0 | 0 --------- Signed-off-by: abrar <abrar@anyscale.com> Signed-off-by: kriyanshii <kriyanshishah06@gmail.com>
Yicheng-Lu-llll
pushed a commit
to Yicheng-Lu-llll/ray
that referenced
this pull request
Dec 22, 2025
fixes ray-project#59218 ### Performance Delta ```python from ray import serve from typing import List @serve.deployment(max_ongoing_requests=1000) class MyDeployment: @serve.batch(max_batch_size=10, batch_wait_timeout_s=1) async def handle_batch(self, requests: List[int]) -> List[int]: return [request + 1 for request in requests] async def __call__(self) -> List[int]: return await self.handle_batch(1) app = MyDeployment.bind() ``` `ray start --head --metrics-export-port=8080` -> `serve run batch_test:app` locust 100 users Metric | With Change | Master | Δ (Master – With Change) -- | -- | -- | -- Requests | 32,033 | 33,541 | +1,508 Fails | 0 | 0 | 0 Median (ms) | 170 | 170 | 0 95%ile (ms) | 240 | 240 | 0 99%ile (ms) | 280 | 270 | –10 ms Average (ms) | 172.98 | 171.87 | –1.11 ms Min (ms) | 70 | 84 | +14 ms Max (ms) | 352 | 365 | +13 ms Average size (bytes) | 1 | 1 | 0 Current RPS | 581.9 | 604.1 | +22.2 Current Failures/s | 0 | 0 | 0 --------- Signed-off-by: abrar <abrar@anyscale.com>
peterxcli
pushed a commit
to peterxcli/ray
that referenced
this pull request
Feb 25, 2026
fixes ray-project#59218 ### Performance Delta ```python from ray import serve from typing import List @serve.deployment(max_ongoing_requests=1000) class MyDeployment: @serve.batch(max_batch_size=10, batch_wait_timeout_s=1) async def handle_batch(self, requests: List[int]) -> List[int]: return [request + 1 for request in requests] async def __call__(self) -> List[int]: return await self.handle_batch(1) app = MyDeployment.bind() ``` `ray start --head --metrics-export-port=8080` -> `serve run batch_test:app` locust 100 users Metric | With Change | Master | Δ (Master – With Change) -- | -- | -- | -- Requests | 32,033 | 33,541 | +1,508 Fails | 0 | 0 | 0 Median (ms) | 170 | 170 | 0 95%ile (ms) | 240 | 240 | 0 99%ile (ms) | 280 | 270 | –10 ms Average (ms) | 172.98 | 171.87 | –1.11 ms Min (ms) | 70 | 84 | +14 ms Max (ms) | 352 | 365 | +13 ms Average size (bytes) | 1 | 1 | 0 Current RPS | 581.9 | 604.1 | +22.2 Current Failures/s | 0 | 0 | 0 --------- Signed-off-by: abrar <abrar@anyscale.com> Signed-off-by: peterxcli <peterxcli@gmail.com>
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
2 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.
fixes #59218
Performance Delta
ray start --head --metrics-export-port=8080->serve run batch_test:applocust 100 users