Skip to content
This repository has been archived by the owner on Nov 17, 2023. It is now read-only.

Fix engine stop/start #10911

Merged
merged 5 commits into from
May 15, 2018
Merged

Fix engine stop/start #10911

merged 5 commits into from
May 15, 2018

Conversation

zhreshold
Copy link
Member

Description

Continued fixes as in #10820.

Checklist

Essentials

Please feel free to remove inapplicable items for your PR.

  • The PR title starts with [MXNET-$JIRA_ID], where $JIRA_ID refers to the relevant JIRA issue created (except PRs with tiny changes)
  • Changes are complete (i.e. I finished coding on this PR)
  • All changes have test coverage:
  • Unit tests are added for small changes to verify correctness (e.g. adding a new operator)
  • Nightly tests are added for complicated/long-running ones (e.g. changing distributed kvstore)
  • Build tests will be added for build configuration changes (e.g. adding a new build option with NCCL)
  • Code is well-documented:
  • For user-facing API changes, API doc string has been updated.
  • For new C++ functions in header files, their functionalities and arguments are documented.
  • For new examples, README.md is added to explain the what the example does, the source of the dataset, expected performance on test set and reference to the original paper if applicable
  • Check the API doc at http://mxnet-ci-doc.s3-accelerate.dualstack.amazonaws.com/PR-$PR_ID/$BUILD_ID/index.html
  • To the my best knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change

Changes

  • Feature1, tests, (and when applicable, API doc)
  • Feature2, tests, (and when applicable, API doc)

Comments

  • If this change is a backward incompatible change, why must this change be made.
  • Interesting edge cases to note here

@@ -121,6 +121,19 @@ double EvaluateWorloads(const std::vector<Workload>& workloads,
return dmlc::GetTime() - t;
}

TEST(Engine, start_stop) {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please add documentation


for (int i = 0; i < num_engine; ++i) {
engine[i]->Stop();
engine[i]->Start();
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you verify whether the actions have actually been successful?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Without adding new API, I cannot think of a way to verify except sanity test.

@@ -0,0 +1,44 @@
# Licensed to the Apache Software Foundation (ASF) under one
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please don't create a new test directory.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done.

@zhreshold zhreshold requested a review from szha as a code owner May 15, 2018 00:57
Copy link
Member

@szha szha left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM pending on other reviews being sufficiently addressed.

@zhreshold
Copy link
Member Author

@piiswrong Can you have a look at the engine part to see if it's correct?

@piiswrong piiswrong merged commit 57c8ca1 into apache:master May 15, 2018
@zhreshold zhreshold deleted the fix-mp branch May 15, 2018 19:52
jinhuang415 pushed a commit to jinhuang415/incubator-mxnet that referenced this pull request May 29, 2018
* fix engine start/stop

* add tests

* fix test

* fix

* fix tests
rahul003 pushed a commit to rahul003/mxnet that referenced this pull request Jun 4, 2018
* fix engine start/stop

* add tests

* fix test

* fix

* fix tests
streams_.reset(new StreamManager<kMaxNumGpus, kNumStreamsPerGpu>());
task_queue_.reset(new dmlc::ConcurrentBlockingQueue<OprBlock*>());
io_task_queue_.reset(new dmlc::ConcurrentBlockingQueue<OprBlock*>());
thread_pool_.reset(new ThreadPool(kNumWorkingThreads, [this]() {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Shouldn't this contain change to another constructor of ThreadPool? Only the one accepting std::shared_ptr<dmlc::ManualEvent> ready_event will wait until ready, which might be the issue fixed in #8995.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Fixed in #11065

zheng-da pushed a commit to zheng-da/incubator-mxnet that referenced this pull request Jun 28, 2018
* fix engine start/stop

* add tests

* fix test

* fix

* fix tests
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants