[serve] Enable setting queue length response deadline via environment variable #42001
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
sihanwang41
approved these changes
Dec 18, 2023
Unfortunately I think won't make 2.9 cut :( going to try |
8 tasks
edoakes
added a commit
that referenced
this pull request
Dec 21, 2023
…42041) We currently have a flat deadline of 0.1s (by default). Under heavy load or high network latency conditions, this deadline might be consistently missed and cause requests to pile up because they're unable to be scheduled. #42001 made this deadline configurable, but setting it high by default defeats its purpose (to reduce tail latency when a single replica is overloaded/blocked/unresponsive). This change backs off the deadline exponentially so the initial deadline can still be low while avoiding "halting" under degraded conditions. The max is set to 1s by default but can be configured using `RAY_SERVE_MAX_QUEUE_LENGTH_RESPONSE_DEADLINE_S`. --------- Signed-off-by: Edward Oakes <ed.nmi.oakes@gmail.com>
edoakes
added a commit
to edoakes/ray
that referenced
this pull request
Jan 4, 2024
… variable (ray-project#42001) Signed-off-by: Edward Oakes <ed.nmi.oakes@gmail.com>
edoakes
added a commit
to edoakes/ray
that referenced
this pull request
Jan 4, 2024
…ay-project#42041) We currently have a flat deadline of 0.1s (by default). Under heavy load or high network latency conditions, this deadline might be consistently missed and cause requests to pile up because they're unable to be scheduled. ray-project#42001 made this deadline configurable, but setting it high by default defeats its purpose (to reduce tail latency when a single replica is overloaded/blocked/unresponsive). This change backs off the deadline exponentially so the initial deadline can still be low while avoiding "halting" under degraded conditions. The max is set to 1s by default but can be configured using `RAY_SERVE_MAX_QUEUE_LENGTH_RESPONSE_DEADLINE_S`. --------- Signed-off-by: Edward Oakes <ed.nmi.oakes@gmail.com>
8 tasks
vickytsang
pushed a commit
to ROCm/ray
that referenced
this pull request
Jan 12, 2024
…ay-project#42041) We currently have a flat deadline of 0.1s (by default). Under heavy load or high network latency conditions, this deadline might be consistently missed and cause requests to pile up because they're unable to be scheduled. ray-project#42001 made this deadline configurable, but setting it high by default defeats its purpose (to reduce tail latency when a single replica is overloaded/blocked/unresponsive). This change backs off the deadline exponentially so the initial deadline can still be low while avoiding "halting" under degraded conditions. The max is set to 1s by default but can be configured using `RAY_SERVE_MAX_QUEUE_LENGTH_RESPONSE_DEADLINE_S`. --------- Signed-off-by: Edward Oakes <ed.nmi.oakes@gmail.com>
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.
Why are these changes needed?
Need to be able to adjust this in high latency environments.
Can add proper config APIs to proxy/handle options in the future if necessary.
Related issue number
Checks
git commit -s) in this PR.scripts/format.shto lint the changes in this PR.method in Tune, I've added it in
doc/source/tune/api/under thecorresponding
.rstfile.