Conversation
wschin
reviewed
May 24, 2020
| return Status(ONNXRUNTIME, INVALID_ARGUMENT, "Null model_proto ptr."); | ||
| } | ||
| google::protobuf::io::IstreamInputStream zero_copy_input(&model_istream); | ||
| google::protobuf::io::IstreamInputStream zero_copy_input(&model_istream, 1 << 20); |
Contributor
There was a problem hiding this comment.
If 1<<20 is a constant for multiple places, we'd better to define it as a constexpr.
Contributor
Author
There was a problem hiding this comment.
Thank you. I'll resolve it next week when I add the static_analysis job back.
wschin
reviewed
May 24, 2020
|
|
||
| - template: templates/clean-agent-build-directory-step.yml | ||
|
|
||
| - job: 'static_analysis' |
Contributor
There was a problem hiding this comment.
Great. I encounter the same problem too.
wschin
approved these changes
May 24, 2020
snnn
pushed a commit
that referenced
this pull request
Jun 1, 2020
1. Fix the nuget cpu pipeline and put code coverage pipeline back. 2. Reduce onnx_test_runner's default logging level from WARNING to ERROR. Because there are too many log messages now. 3. Enlarge the protobuf read buffer size for onnx_test_runner. It was missed from PR #4020.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description:
Our Azure build VM has a IOPS cap of 500, which is far less a physical SSD can do.
https://azure.microsoft.com/en-us/pricing/details/managed-disks/
A real SSD can do 100k-500k reads per second!
https://www.intel.com/content/dam/www/public/us/en/documents/product-specifications/ssd-750-spec.pdf
With 500 IOPS and 8KB buffer size, we can only achieve 3.9MB/s disk speed, which means it need about 2-3 minutes to load an ONNX model zoo model, 2 hours to read all of our test data, which is not acceptable. That's why you can frequently see job timeout in our Windows CI build pipeline.
Because the latest protobuf changed the proto classes to final, so some of our code can't be compiled. I don't know how to fix it. In order to unblock the other PRs, I'll temporarily disable the job and try to seek help in the next week when everyone is back.
p.s. Don't use std::fstream. The buffer size is hard coded to 4095, there is no way to change it.
Motivation and Context