Make delayed enrollment try indefinitely (#4727) (#4800)

* Make delay enrollment indefinite.

* Add changelog entry.

(cherry picked from commit c14df02)

Co-authored-by: Blake Rouse <blake.rouse@elastic.co>
Co-authored-by: Pierre HILBERT <pierre.hilbert@elastic.co>

Author: 3 people

changelog/fragments/1715266989-Make-delayed-enrollment-try-indefinitely.yaml

@@ -0,0 +1,32 @@
+# Kind can be one of:
+# - breaking-change: a change to previously-documented behavior
+# - deprecation: functionality that is being removed in a later release
+# - bug-fix: fixes a problem in a previous version
+# - enhancement: extends functionality but does not break or fix existing behavior
+# - feature: new functionality
+# - known-issue: problems that we are aware of in a given version
+# - security: impacts on the security of a product or a user’s deployment.
+# - upgrade: important information for someone upgrading from a prior version
+# - other: does not fit into any of the other categories
+kind: bug-fix
+
+# Change summary; a 80ish characters long description of the change.
+summary: Make delayed enrollment try indefinitely
+
+# Long description; in case the summary is not enough to describe the change
+# this field accommodate a description without length limits.
+# NOTE: This field will be rendered only for breaking-change and known-issue kinds at the moment.
+#description:
+
+# Affected component; usually one of "elastic-agent", "fleet-server", "filebeat", "metricbeat", "auditbeat", "all", etc.
+component:
+
+# PR URL; optional; the PR number that added the changeset.
+# If not present is automatically filled by the tooling finding the PR where this changelog fragment has been added.
+# NOTE: the tooling supports backports, so it's able to fill the original PR number instead of the backport PR number.
+# Please provide it if you are adding a fragment for a different PR.
+pr: https://github.com/elastic/elastic-agent/pull/4727
+
+# Issue URL; optional; the GitHub issue related to this changeset (either closes or is part of).
+# If not present is automatically filled by the tooling with the issue linked to the PR number.
+issue: https://github.com/elastic/elastic-agent/issues/4716

internal/pkg/agent/cmd/run.go

@@ -548,9 +548,18 @@ func tryDelayEnroll(ctx context.Context, logger *logger.Logger, cfg *configurati
 	if err != nil {
 		return nil, err
 	}
-	err = c.Execute(ctx, cli.NewIOStreams())
-	if err != nil {
-		return nil, err
+	// perform the enrollment in a loop, it should keep trying to enroll no matter what
+	// the enrollCmd has built in backoff so no need to wrap this in its own backoff as well
+	for {
+		if ctx.Err() != nil {
+			return nil, ctx.Err()
+		}
+		err = c.Execute(ctx, cli.NewIOStreams())
+		if err == nil {
+			// enrollment was successful
+			break
+		}
+		logger.Error(fmt.Errorf("failed to perform delayed enrollment (will try again): %w", err))
 	}
 	err = os.Remove(enrollPath)
 	if err != nil {