retry net.ErrClosed by default (#2949)

Author: lucix-aws

.changelog/b2213048b0dd4619bd611e41eb07bcb0.json

@@ -0,0 +1,8 @@
+{
+ "id": "b2213048-b0dd-4619-bd61-1e41eb07bcb0",
+ "type": "bugfix",
+ "description": "Retry transient net.ErrClosed errors by default.",
+ "modules": [
+ "."
+ ]
+}

aws/retry/retryable_error.go

@@ -116,7 +116,13 @@ func (r RetryableConnectionError) IsErrorRetryable(err error) aws.Ternary {
 case errors.As(err, &conErr) && conErr.ConnectionError():
 retryable = true
 
+case strings.Contains(err.Error(), "use of closed network connection"):
+fallthrough
 case strings.Contains(err.Error(), "connection reset"):
+// The errors "connection reset" and "use of closed network connection"
+// are effectively the same. It appears to be the difference between
+// sync and async read of TCP RST in the stdlib's net.Conn read loop.
+// see #2737
 retryable = true
 
 case errors.As(err, &urlErr):

aws/retry/retryable_error_test.go

@@ -136,6 +136,10 @@ func TestRetryConnectionErrors(t *testing.T) {
 Err: fmt.Errorf("some error %w", mockTimeoutError{b: true}),
 },
 },
+"net.ErrClosed": {
+Retryable: aws.TrueTernary,
+Err: net.ErrClosed,
+},
 }
 
 for name, c := range cases {