Better graceful shutdown. (#1827)

# What does this PR do?

<!--
Congratulations! You've made it this far! You're not quite done yet
though.

Once merged, your PR is going to appear in the release notes with the
title you set, so make sure it's a great title that fully reflects the
extent of your awesome contribution.

Then, please replace this with a description of the change and which
issue is fixed (if applicable). Please also include relevant motivation
and context. List any dependencies (if any) that are required for this
change.

Once you're done, someone will review your PR shortly (see the section
"Who can review?" below to tag some potential reviewers). They may
suggest changes to make the code even better. If no one reviewed your PR
after a week has passed, don't hesitate to post a new comment
@-mentioning the same persons---sometimes notifications get lost.
-->

<!-- Remove if not applicable -->

Fixes # (issue)


## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Did you read the [contributor
guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
      Pull Request section?
- [ ] Was this discussed/approved via a Github issue or the
[forum](https://discuss.huggingface.co/)? Please add a link
      to it if that's the case.
- [ ] Did you make sure to update the documentation with your changes?
Here are the
[documentation
guidelines](https://github.com/huggingface/transformers/tree/main/docs),
and
[here are tips on formatting
docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
- [ ] Did you write any new necessary tests?


## Who can review?

Anyone in the community is free to review the PR once the tests have
passed. Feel free to tag
members/contributors who may be interested in your PR.

<!-- Your PR will be replied to more quickly if you can figure out the
right person to tag with @


@OlivierDehaene OR @Narsil

 -->

launcher/src/main.rs

@@ -683,9 +683,7 @@ fn shard_manager(
 
         // We received a shutdown signal
         if shutdown.load(Ordering::SeqCst) {
-            p.kill().unwrap();
+            terminate("shard", p, Duration::from_secs(90)).unwrap();
-            let _ = p.wait();
-            tracing::info!("Shard terminated");
             return;
         }
 
@@ -1245,7 +1243,6 @@ fn terminate(process_name: &str, mut process: Child, timeout: Duration) -> io::R
     signal::kill(Pid::from_raw(process.id() as i32), Signal::SIGTERM).unwrap();
 
     tracing::info!("Waiting for {process_name} to gracefully shutdown");
-
     while terminate_time.elapsed() < timeout {
         if let Some(status) = process.try_wait()? {
             tracing::info!("{process_name} terminated");
@@ -1253,7 +1250,6 @@ fn terminate(process_name: &str, mut process: Child, timeout: Duration) -> io::R
         }
         sleep(Duration::from_millis(100));
     }
-
     tracing::info!("Killing {process_name}");
 
     process.kill()?;

server/text_generation_server/server.py

@@ -2,6 +2,7 @@ import asyncio
 import os
 import torch
 import time
+import signal
 
 from grpc import aio
 from loguru import logger
@@ -19,6 +20,21 @@ from text_generation_server.tracing import UDSOpenTelemetryAioServerInterceptor
 from text_generation_server.models.idefics_causal_lm import IdeficsCausalLMBatch
 
 
+class SignalHandler:
+    KEEP_PROCESSING = True
+
+    def __init__(self):
+        signal.signal(signal.SIGINT, self.exit_gracefully)
+        signal.signal(signal.SIGTERM, self.exit_gracefully)
+
+    def exit_gracefully(self, signum, frame):
+        print(f"Exiting gracefully: Signal {signum}")
+        self.KEEP_PROCESSING = False
+
+
+signal_handler = SignalHandler()
+
+
 class TextGenerationService(generate_pb2_grpc.TextGenerationServiceServicer):
     def __init__(
         self,
@@ -231,11 +247,8 @@ def serve(
 
         logger.info("Server started at {}".format(local_url))
 
-        try:
+        while signal_handler.KEEP_PROCESSING:
-            await server.wait_for_termination()
+            await asyncio.sleep(0.5)
-        except KeyboardInterrupt:
-            logger.info("Signal received. Shutting down")
-            await server.stop(0)
 
     asyncio.run(
         serve_inner(