Set KFServing default worker to 1 #1106
Merged
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
KFServer uses the number of cores on the machine to set the number of process in its tornado service which can delay the initialization time and increase the memory usage a lot. A local testing suggests that KFServer loaded 64 processes and used more than 500Mb for a simple SKLearn model. Once I set the worker number to 1, the memory usage was reduced to around 100Mb. ``` [I 200927 18:26:06 kfserver:88] Registering model: mlguild-iris-svm [I 200927 18:26:06 kfserver:77] Listening on port 8080 [I 200927 18:26:06 kfserver:79] Will fork 0 workers [I 200927 18:26:06 process:126] Starting 64 processes ```
|
This change is |
|
/lgtm |
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: yuzisun The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
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Outdated suggestions cannot be applied.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.
KFServer uses the number of cores on the machine to set the number of process in its tornado service which can delay the initialization time and increase the memory usage a lot.
A local testing suggests that KFServer loaded 64 processes and used more than 500Mb for a simple SKLearn model. Once I set the worker number to 1, the memory usage was reduced to around 100Mb.
What this PR does / why we need it:
Which issue(s) this PR fixes (optional, in
fixes #<issue number>(, fixes #<issue_number>, ...)format, will close the issue(s) when PR gets merged):Fixes #
Special notes for your reviewer:
Release note: