Reformatted cherry-pick of 443416907e.
This PR fixes our {NumPy, Pandas} <--> Arrow interop for boolean tensor columns. NumPy and Pandas represent boolean arrays with a byte per boolean, while Arrow bit-packs booleans with 8 booleans per byte. Previously, when casting NumPy arrays to tensor columns, we were interpreting NumPy's boolean array buffers as being bit-packed when they were not. This PR completes support by packing and unpacking bits for boolean arrays when creating a boolean tensor column from an ndarray and when creating an ndarray from a boolean tensor column, respectively.
Closes https://github.com/ray-project/ray/issues/22265
This was caused by implicitly inferring the namespace from within the HTTP proxy when calling `get_handle`. This makes me think we really need to simplify the namespace handling logic.
* [runtime env] Fix bug where options (e.g. `--extra-index-url`) could not be specified in `requirements.txt` (#22065)
In https://github.com/ray-project/ray/pull/20341 the behavior of `pip` was changed to install the specified packages in the existing environment rather than in a new environment. This posed a problem when specifying Ray libraries like "ray[serve]" in the `pip` field, because the installer would install Ray at runtime and this new Ray would take precedence over the Ray existing on the cluster. This could cause version mismatch issues. Skipping some details, the approach taken in the that PR was essentially to parse the `pip` list and remove Ray.
However not every line in a `pip` `requirements.txt` file is a requirements specifier; a line can also just specify options, like `--extra-index-url my-index-url.com`.
This caused the parsing library to raise an exception when trying to parse the line. This PR fixes this by catching the exception and skipping the line in this case, since it's not a line that specifies `ray` and that's all we're looking for when parsing.
* lint using old linter from pre-1.11.0-branch-cut
This PR moves the sdk to its own folder, then includes everything in `import ray.autoscaler.sdk` in ray's import path.
Note: that there were circular dependencies in naively doing this because the ray core now uses constants that were defined in the autoscaler for internal kv operations (and the autoscaler similarly calls into the ray core). The solution was to move those internal kv keys into ray core constants so the imports flow (more) one way.
Co-authored-by: Alex Wu <alex@anyscale.com>
This patch fixed two issues.
1. log_monitor.py can crash when gcs is not temporarily available. Added retry logic in gcs_pubsub.py.
2. it is possible that the signal handler can raise another exception during exception handling.
This PR adds a `CometLoggerCallback` to the Tune Integrations, allowing users to log runs from Ray to [Comet](https://www.comet.ml/site/).
Co-authored-by: Michael Cullan <mjcullan@gmail.com>
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>
Resubmitting #21705 which was merged then reverted. It seems somehow sphinx building broke in the meantime, not clear how it is connected to this PR.
Here is the original description:
>Part of the effort to enable tests on windows, this enables test_metrics and test_metric_agents, which pass locally.
There was a user request to disable runtime env logs. This is the first PR that allows users to disable runtime env logs through an env var. Basically if users specify `RAY_RUNTIME_ENV_LOG_TO_DRIVER_ENABLED =0`, this will disable runtime env logs.
Note that in the log monitor RAY_RUNTIME_ENV_LOG_TO_DRIVER_ENABLED=1 by default. This is temporary, and I'd like to make this 0 by default after improving runtime error failure messages.
Once we disable log msgs by default, we can unify `RAY_RUNTIME_ENV_LOG_TO_DRIVER_ENABLED` and `RAY_RUNTIME_ENV_LOCAL_DEV_MODE`
Now if an actor throws an exception containing non-ASCII characters, the actor won't die and will be alive.
This is because the following exception occurred during handling the user's exception:
```
File "python/ray/_raylet.pyx", line 587, in ray._raylet.task_execution_handler
File "python/ray/_raylet.pyx", line 434, in ray._raylet.execute_task
File "python/ray/_raylet.pyx", line 551, in ray._raylet.execute_task
File "/home/admin/.local/lib/python3.6/site-packages/ray/utils.py", line 96, in push_error_to_driver
worker.core_worker.push_error(job_id, error_type, message, time.time())
File "python/ray/_raylet.pyx", line 1636, in ray._raylet.CoreWorker.push_error
UnicodeEncodeError: 'ascii' codec can't encode characters in position 2597-2600: ordinal not in range(128)
An unexpected internal error occurred while the worker was executing a task.
```
This PR fixes this issue.
Currently, when we destroy the created placement group, we will kill all workers that are related to this placement group, however, we only killed the running worker at this time, if there is a worker which startup very slow and the related placement group was already destroyed before the worker startup successfully, then there will be a worker leak.
RayDP needs to be updated to work with redisless ray.
To be more specific this [line](c08a786770/python/raydp/spark/ray_cluster_master.py (L146)
) needs to be updated to using `node.address`
We should update this after the release with the feature being turned on by default.
Currently, the docs have an [end-to-end tutorial](https://web.archive.org/web/20211122152843/https://docs.ray.io/en/latest/serve/tutorial.html) walking users through deploying a `Counter` function on Serve. This PR adds an end-to-end tutorial walking users through deploying an entire Hugging Face model using Serve, providing a better understanding of how to deploy an actual model via Serve.
Co-authored-by: Edward Oakes <ed.nmi.oakes@gmail.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
This PR fixes issues with loading ExperimentAnalysis from path or pickle if the trainable used in the trials is not registered. Chiefly, it ensures that the stub attribute set in load_trials_from_experiment_checkpoint doesn't get overridden by the state of the loaded trial, and that when pickling, all trials in ExperimentAnalysis are turned into stubs if they aren't already. A test has also been added.
Support the ability to specify a default lifetime for actors which are not specified lifetime when creating. This is a job level configuration item.
#### API Change
The Python API looks like:
```python
ray.init(job_config=JobConfig(default_actor_lifetime="detached"))
```
Java API looks like:
```java
System.setProperty("ray.job.default-actor-lifetime", defaultActorLifetime.name());
Ray.init();
```
One example usage is:
```python
ray.init(job_config=JobConfig(default_actor_lifetime="detached"))
a1 = A.options(lifetime="non_detached").remote() # a1 is a non-detached actor.
a2 = A.remote() # a2 is a non-detached actor.
```
Co-authored-by: Kai Yang <kfstorm@outlook.com>
Co-authored-by: Qing Wang <jovany.wq@antgroup.com>
By default, ~/ray_results/exp_name/trial_name/checkpoint_name.
Instead of the whole trial checkpoint (~/ray_results/exp_name/trial_name/) directory.
Stuff like progress.csv, result.json, params.pkl, params.json, events.out etc are coming from driver process.
This could also enable us to de-couple sync up and delete - they don't have to wait for each other to finish.
Currently, the `unzip_package` function relies on `extract_file_and_remove_top_level_dir` to unzip and remove the top-level directory from archive working directories. However, `extract_file_and_remove_top_level_dir` uses `os.rename()` to remove the tld by manually unzipping each file from a zip file and moving it to the tld's parent. When the tld contains directories or files with the same name as the tld, `os.rename()` fails to move these files to the tld's parent because of the name collision between the file and the tld.
This change replaces `extract_file_and_remove_top_level_dir` with `remove_dir_from_filepaths`. Now, `unzip_package` unzips the entire zip file before `remove_dir_from_filepaths` moves all the tld's children to the tld's parent using `os.rename()`.
This edge case is tested in the new unit test `test_unzip_with_matching_subdirectory_names`. Additionally, `extract_file_and_remove_top_level_dir`'s unit test is replaced with `TestRemoveDirFromFilepaths`, which tests the new `remove_dir_from_filepaths` function.
`test_traceback.py` was taking ~55s to finish recently, and since today it starts to time out at 60s more frequently. All test cases do succeed so increase its test time out for now. We will look into if there is any performance regression separately.
This is the second last PR to improve `ActorDiedError` exception.
This propagates Actor death cause metadata to the ray error object. In this way, we can raise a better actor died error exception.
After this PR is merged, I will add more metadata to each error message and write a documentation that explains when each error happens.
TODO
- [x] Fix test failures
- [x] Add unit tests
- [x] Fix Java/cpp cases
Follow up PRs
- Not allowing nullptr for RayErrorInfo input.
GCS pubsub uses long polling, so the subscriber waits instead of returning None from polling when there is no buffered log. It needs a different heuristic to decide if the driver is not keeping up with logs from the worker.
Making some minor fixes.
1. Update input `batch_size` to be global batch size. Introduce `worker_batch_size` so each iteration trains same global batch size.
2. Update dataset `size` calculation to only refer to the fraction of the data that is trained on each worker. This allows calculations (e.g. training progress, accuracy) to be correct.
3. Add `model.train()` for generality.
4. Remove `smoke-test` flag since it's not really being used.
- Tolerate GRPC deadline exceeded and transient failures in Python GCS AIO subscribers, which becomes consistent with Python GCS synchronous subscribers.
- Tolerate any exception in dashboard for subscribing to logs and error info, which becomes consistent with how dashboard handles GRPC errors for obtaining node stats.
When a node is dead, reference table should remove locations for those objects on the node. Otherwise locality-aware scheduling will schedule tasks to the dead node.
This is a minimum viable product for Ray Autoscaler integration with Kuberay. It is not ready for prime time/general use, but should be enough for interested parties to get started (see the documentation in kuberay.md).
GCS, when running as an individual component, can cause other components to fail in case of crashes.
Here are two main cases covered in this patch:
1. monitor.py will raise an exception when disconnected from GCS.
2. When GCS becomes available later than other components, the missing KV of GCS address can cause other components to fail to start.
In our patch, we fixed these two issues as well as increased the timeout for redis connection which was too small.
Co-authored-by: Mingwei Tian <mwtian@anyscale.com>
Prior to this PR, sort, groupby, and aggregate defined separate types for extracting values from Dataset records. This was confusing since the user had to understand the differences between the different key types (which were basically exactly the same).
This PR defines a common key type: KeyFn, which is simply Union[None, str, Callable[[T], Any]]. This is used as sort(KeyFn...), aggregate(Agg(KeyFn)...), groupby(KeyFn).agg(Agg(KeyFn), ...).
It also unifies the error generation paths to a common _validate_key_fn utility. This also improves the errors generated when passing explicit AggregateFn classes, which previously failed in the workers if invalid.
