final CountDownLatch hasConfirmedIsRunning = new CountDownLatch(1);

    /*
     * The main test thread tries to stop() the service shortly after
     * confirming that it is running. Meanwhile, the service itself is trying
     * to confirm that it is running. If the main thread's stop() call happens
     * before it has the chance, the test will fail. To avoid this, the main

    final CountDownLatch hasConfirmedIsRunning = new CountDownLatch(1);

    /*
     * The main test thread tries to stop() the service shortly after
     * confirming that it is running. Meanwhile, the service itself is trying
     * to confirm that it is running. If the main thread's stop() call happens
     * before it has the chance, the test will fail. To avoid this, the main

The key here is the `await`. It tells Python that it has to wait ⏸ for `get_burgers(2)` to finish doing its thing 🕙 before storing the results in `burgers`. With that, Python will know that it can go and do something else 🔀 ⏯ in the meanwhile (like receiving another request).

For `await` to work, it has to be inside a function that supports this asynchronicity. To do that, you just declare it with `async def`:

```Python hl_lines="1"

- Fix: After a Node is down and take some time to get back to up again, the mount point of the evicted Pods cannot be cleaned up successfully. (#111933) Meanwhile Kubelet will print the log `Orphaned pod "xxx" found, but error not a directory occurred when trying to remove the volumes dir` every 2 seconds. (#105536) ([#116134](https://github.com/kubernetes/kubernetes/pull/116134), [@cvvz](https://github.com/cvvz))...

- Fix: After a Node is down and take some time to get back to up again, the mount point of the evicted Pods cannot be cleaned up successfully. (#111933) Meanwhile Kubelet will print the log `Orphaned pod "xxx" found, but error not a directory occurred when trying to remove the volumes dir` every 2 seconds. (#105536) ([#116134](https://github.com/kubernetes/kubernetes/pull/116134), [@cvvz](https://github.com/cvvz))...

            of this change, please inform us (file an issue) about your use case
            and you can unblock yourself by setting
            `experimental_run_tf_function=False` in compile meanwhile. We have
            seen couple of use cases where the model usage pattern is not as
            expected and would not work with this change.
    *   output tensors of one layer is used in the constructor of another.