From b53b0f3ba892d1864a11ee3592d45d7a88982fdd Mon Sep 17 00:00:00 2001
From: Argannor <4489279+Argannor@users.noreply.github.com>
Date: Fri, 8 Nov 2024 22:15:02 +0100
Subject: [PATCH] [fix][prometheusexporter] Race condition between start and
 shutdown (#36164)

#### Description

Adjusted the Start and Shutdown sequence of the prometheusexporter to
prevent a race condition causing the `close tcp 127.0.0.1:8999: use of
closed network connection` error as observed in #36139.

The behaviour was changed in the following ways:

- If an error occurs during the creation of the server, close the
listener immediately, leaving shutdown a noop
- Since `srv.Shutdown` will close all open listeners, the explicit call
to `ln.Close` in the shutdown routine was removed

#### Link to tracking issue
Fixes #36139

#### Testing

Unit testing, I temporarily increased the number of iterations on
`TestPrometheusExporter` to 2000. The error did no longer occur. However
sporadically another error occured:

```
=== RUN   TestPrometheusExporter
    prometheus_test.go:103:
        	Error Trace:	C:/development/code/opentelemetry-collector-contrib/exporter/prometheusexporter/prometheus_test.go:84
        	Error:      	Received unexpected error:
        	            	listen tcp 127.0.0.1:8999: bind: Only one usage of each socket address (protocol/network address/port) is normally permitted.
        	Test:       	TestPrometheusExporter
--- FAIL: TestPrometheusExporter (1.16s)
```

I assume that this is because the OS (in my case Windows) won't always
close the underlying sockets immediately, blocking it for some time
afterwards. I'm not sure there is anything we can do about that.

---------

Signed-off-by: Argannor <arga@argannor.com>
---
 ..._prometheusexporter-shutdown-server-2.yaml | 27 +++++++++++++++++++
 exporter/prometheusexporter/prometheus.go     | 14 ++++------
 2 files changed, 32 insertions(+), 9 deletions(-)
 create mode 100644 .chloggen/fix_prometheusexporter-shutdown-server-2.yaml

diff --git a/.chloggen/fix_prometheusexporter-shutdown-server-2.yaml b/.chloggen/fix_prometheusexporter-shutdown-server-2.yaml
new file mode 100644
index 000000000000..7b01af232225
--- /dev/null
+++ b/.chloggen/fix_prometheusexporter-shutdown-server-2.yaml
@@ -0,0 +1,27 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: bug_fix
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: prometheusexporter
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: "Fixes a race condition between the exporter start and shutdown functions."
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [36139]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:
+
+# If your change doesn't affect end users or the exported elements of any package,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: [user]
\ No newline at end of file
diff --git a/exporter/prometheusexporter/prometheus.go b/exporter/prometheusexporter/prometheus.go
index 438fb3acdd07..8de4fa367e88 100644
--- a/exporter/prometheusexporter/prometheus.go
+++ b/exporter/prometheusexporter/prometheus.go
@@ -66,16 +66,12 @@ func (pe *prometheusExporter) Start(ctx context.Context, host component.Host) er
 	mux := http.NewServeMux()
 	mux.Handle("/metrics", pe.handler)
 	srv, err := pe.config.ToServer(ctx, host, pe.settings, mux)
-	pe.shutdownFunc = func(ctx context.Context) error {
-		errLn := ln.Close()
-		if srv == nil {
-			return errLn
-		}
-		errSrv := srv.Shutdown(ctx)
-		return errors.Join(errLn, errSrv)
-	}
 	if err != nil {
-		return err
+		lnerr := ln.Close()
+		return errors.Join(err, lnerr)
+	}
+	pe.shutdownFunc = func(ctx context.Context) error {
+		return srv.Shutdown(ctx)
 	}
 	go func() {
 		_ = srv.Serve(ln)