Package version
The command line of the start task. The command line does not run under a shell, and therefore cannot take advantage of shell features such as environment variable expansion. If you want to take advantage of such features, you should invoke the shell in the command line, for example using "cmd /c MyCommand" in Windows or "/bin/sh -c MyCommand" in Linux. If the command line refers to file paths, it should use a relative path (relative to the task working directory), or use the Batch provided environment variable (https://docs.microsoft.com/en-us/azure/batch/batch-compute-node-environment-variables).
The settings for the container under which the start task runs. When this is specified, all directories recursively below the AZ_BATCH_NODE_ROOT_DIR (the root of Azure Batch directories on the node) are mapped into the container, all task environment variables are mapped into the container, and the task command line is executed in the container.
A list of environment variable settings for the start task.
The maximum number of times the task may be retried. The Batch service retries a task if its exit code is nonzero. Note that this value specifically controls the number of retries. The Batch service will try the task once, and may then retry up to this limit. For example, if the maximum retry count is 3, Batch tries the task up to 4 times (one initial try and 3 retries). If the maximum retry count is 0, the Batch service does not retry the task. If the maximum retry count is -1, the Batch service retries the task without limit.
A list of files that the Batch service will download to the compute node before running the command line. There is a maximum size for the list of resource files. When the max size is exceeded, the request will fail and the response error code will be RequestEntityTooLarge. If this occurs, the collection of ResourceFiles must be reduced in size. This can be achieved using .zip files, Application Packages, or Docker Containers. Files listed under this element are located in the task's working directory.
The user identity under which the start task runs. If omitted, the task runs as a non-administrative user unique to the task.
Whether the Batch service should wait for the start task to complete successfully (that is, to exit with exit code 0) before scheduling any tasks on the compute node. If true and the start task fails on a compute node, the Batch service retries the start task up to its maximum retry count (maxTaskRetryCount). If the task has still not completed successfully after all retries, then the Batch service marks the compute node unusable, and will not schedule tasks to it. This condition can be detected via the node state and failure info details. If false, the Batch service will not wait for the start task to complete. In this case, other tasks can start executing on the compute node while the start task is still running; and even if the start task fails, new tasks will continue to be scheduled on the node. The default is false.
Generated using TypeDoc
Batch will retry tasks when a recovery operation is triggered on a compute node. Examples of recovery operations include (but are not limited to) when an unhealthy compute node is rebooted or a compute node disappeared due to host failure. Retries due to recovery operations are independent of and are not counted against the maxTaskRetryCount. Even if the maxTaskRetryCount is 0, an internal retry due to a recovery operation may occur. Because of this, all tasks should be idempotent. This means tasks need to tolerate being interrupted and restarted without causing any corruption or duplicate data. The best practice for long running tasks is to use some form of checkpointing. In some cases the start task may be re-run even though the node was not rebooted. Special care should be taken to avoid start tasks which create breakaway process or install/launch services from the start task working directory, as this will block Batch from being able to re-run the start task.
A task which is run when a compute node joins a pool in the Azure Batch service, or when the compute node is rebooted or reimaged.