Correct response code for "inference canceled as process is stopping" failures #123745
Description
Elasticsearch Version
any
Installed Plugins
any
Java Version
bundled
OS Version
any
Problem Description
When making an inference request, its possible that its cancelled due to the process stopping. This likely shouldn't bubble up as a internal server error.
This is possible in a _search request. It seems if its being stopped, that was triggered by the user, and it wasn't a crash. Indicating its a user configuration problem and thus we should return an error indicating as much.
It seems to me that the PyTorchResult should indicate the exception type (or status code) and that needs to be bubbled up to the user.
Steps to Reproduce
na
Logs (if relevant)
org.elasticsearch.ElasticsearchStatusException: Error in inference process: [inference canceled as process is stopping]
at org.elasticsearch.xpack.ml.inference.deployment.AbstractPyTorchAction.onFailure(AbstractPyTorchAction.java:120)
at org.elasticsearch.xpack.ml.inference.deployment.InferencePyTorchAction.processResult(InferencePyTorchAction.java:181)
at org.elasticsearch.xpack.ml.inference.deployment.InferencePyTorchAction.lambda$doRun$3(InferencePyTorchAction.java:150)
at org.elasticsearch.action.ActionListener$2.onResponse(ActionListener.java:257)
at org.elasticsearch.xpack.ml.inference.pytorch.process.PyTorchResultProcessor.lambda$notifyAndClearPendingResults$3(PyTorchResultProcessor.java:148)
at java.util.concurrent.ConcurrentHashMap.forEach(ConcurrentHashMap.java:1608)
at org.elasticsearch.xpack.ml.inference.pytorch.process.PyTorchResultProcessor.notifyAndClearPendingResults(PyTorchResultProcessor.java:147)
at org.elasticsearch.xpack.ml.inference.pytorch.process.PyTorchResultProcessor.process(PyTorchResultProcessor.java:135)
at org.elasticsearch.xpack.ml.inference.deployment.DeploymentManager.lambda$startDeployment$2(DeploymentManager.java:180)
at org.elasticsearch.common.util.concurrent.ThreadContext$ContextPreservingRunnable.run(ThreadContext.java:977)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1144)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:642)
at java.lang.Thread.run(Thread.java:1575)