support system_metrics_cmd in config.properties #3000
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
lxning
added
documentation
agunapal
requested changes
Mar 5, 2024
There was a problem hiding this comment.
Thanks. This should support something like this, where the user passes this as an extra file.
torch-model-archiver --model-name mnist --version 1.0 --model-file examples/image_classifier/mnist/mnist.py --serialized-file examples/image_classifier/mnist/mnist_cnn.pt --handler examples/image_classifier/mnist/mnist_handler.py --extra-files "examples/custom_system_metrics/metric_collector.py"
and in the config.properties, I specify
system_metrics_cmd="metric_collector.py --gpu 0"
I tried this, currently it gives an error
can't open file '/home/ubuntu/anaconda3/envs/torchserve/lib/python3.10/site-packages/"metric_collector.py': [Errno 2] No such file or directory
Q1: |
|
Case1: it is invalid to add system metrics in model archiver in TorchServe architecture. The reason is system metrics is global, not model specific. The scripts included in model archiver is invisible for frontend when TorchServe is started. Case2: By format definition in config.properties, the value |
Confirmed this to be working. Will send a separate PR to show this can be used with a custom python script |
agunapal
approved these changes
Mar 5, 2024
| @@ -297,6 +297,7 @@ e.g. : To allow base URLs `https://s3.amazonaws.com/` and `https://torchserve.py | |||
| * For security reason, `use_env_allowed_urls=true` is required in config.properties to read `allowed_urls` from environment variable. | |||
| * `workflow_store` : Path of workflow store directory. Defaults to model store directory. | |||
| * `disable_system_metrics` : Disable collection of system metrics when set to "true". Default value is "false". | |||
| * `system_metrics_cmd`: The customized system metrics python script name with arguments. For example:`ts/metrics/metric_collector.py --gpu 0`. Default: empty which means TorchServe collects system metrics via "ts/metrics/metric_collector.py --gpu $CUDA_VISIBLE_DEVICES". | |||
There was a problem hiding this comment.
Suggest changing the example to system_metrics_cmd=ts/metrics/metric_collector.py --gpu 0 to disable GPU metrics
8 tasks
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
Please read our CONTRIBUTING.md prior to creating your first pull request.
Please include a summary of the feature or issue being fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.
Fixes #(issue)
Type of change
Please delete options that are not relevant.
Feature/Issue validation/testing
Please describe the Unit or Integration tests that you ran to verify your changes and relevant result summary. Provide instructions so it can be reproduced.
Please also list any relevant details for your test configuration.
Checklist:
cc @namannandan