From 3f6ad67412d06ed5d8012ee3ce498607c326ce1a Mon Sep 17 00:00:00 2001
From: Jackson Owens <jackson@cockroachlabs.com>
Date: Fri, 12 May 2023 11:40:30 -0400
Subject: [PATCH] roachtest: always unstall on disk-stall failure

Previously, if the disk-stalled/* raochtests failed while the disk was stalled,
a defer would attempt to unstall the disk before completing the test. This
could fail if the context was cancelled. The stalled disk would then prevent
collection of artifacts.

This change updates the defer'd Unstall call to use a background context that
will never be cancelled.

Epic: none
Informs #102946
Release note: none
---
 pkg/cmd/roachtest/tests/disk_stall.go | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/pkg/cmd/roachtest/tests/disk_stall.go b/pkg/cmd/roachtest/tests/disk_stall.go
index 13eee2858266..10065d9941a1 100644
--- a/pkg/cmd/roachtest/tests/disk_stall.go
+++ b/pkg/cmd/roachtest/tests/disk_stall.go
@@ -159,7 +159,15 @@ func runDiskStalledDetection(
 		m.ExpectDeath()
 	}
 	s.Stall(ctx, c.Node(1))
-	defer s.Unstall(ctx, c.Node(1))
+	{
+		// NB: We use a background context in the defer'ed unstall command,
+		// otherwise on test failure our c.Run calls will be ignored. Leaving
+		// the disk stalled will prevent artifact collection, making debugging
+		// difficult.
+		ctx, cancel := context.WithTimeout(context.Background(), time.Minute)
+		defer cancel()
+		defer s.Unstall(ctx, c.Node(1))
+	}
 
 	// Wait twice the maximum sync duration and check if our SQL connection to
 	// node 1 is still alive. It should've been terminated.