Preserve component state on upgrade (#2207)

Preserve component state on upgrade (#2207)

(cherry picked from commit 9c03fae)

changelog/fragments/1675085396-preserve-state-on-upgrade.yaml

@@ -0,0 +1,31 @@
+# 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
+
+# Change summary; a 80ish characters long description of the change.
+summary: Preserve component state on upgrade
+
+# Long description; in case the summary is not enough to describe the change
+# this field accommodate a description without length limits.
+#description:
+
+# Affected component; a word indicating the component this changeset affects.
+component:
+
+# PR number; 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: 2207
+
+# Issue number; 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: 2136

internal/pkg/agent/application/upgrade/upgrade.go

@@ -31,6 +31,7 @@ const (
 	agentName       = "elastic-agent"
 	hashLen         = 6
 	agentCommitFile = ".elastic-agent.active.commit"
+	runDirMod       = 0770
 )
 
 var (
@@ -150,6 +151,10 @@ func (u *Upgrader) Upgrade(ctx context.Context, version string, sourceURI string
 		return nil, errors.New(err, "failed to copy action store")
 	}
 
+	if err := copyRunDirectory(u.log, newHash); err != nil {
+		return nil, errors.New(err, "failed to copy run directory")
+	}
+
 	if err := ChangeSymlink(ctx, u.log, newHash); err != nil {
 		u.log.Errorw("Rolling back: changing symlink failed", "error.message", err)
 		rollbackInstall(ctx, u.log, newHash)
@@ -252,6 +257,25 @@ func copyActionStore(log *logger.Logger, newHash string) error {
 	return nil
 }
 
+func copyRunDirectory(log *logger.Logger, newHash string) error {
+	newRunPath := filepath.Join(filepath.Dir(paths.Home()), fmt.Sprintf("%s-%s", agentName, newHash), "run")
+	oldRunPath := filepath.Join(filepath.Dir(paths.Home()), fmt.Sprintf("%s-%s", agentName, release.ShortCommit()), "run")
+
+	log.Infow("Copying run directory", "new_run_path", newRunPath, "old_run_path", oldRunPath)
+
+	if err := os.MkdirAll(newRunPath, runDirMod); err != nil {
+		return errors.New(err, "failed to create run directory")
+	}
+
+	err := copyDir(oldRunPath, newRunPath)
+	if os.IsNotExist(err) {
+		// nothing to copy, operation ok
+		log.Debugw("Run directory not present", "old_run_path", oldRunPath)
+		return nil
+	}
+	return errors.New(err, "failed to copy %q to %q", oldRunPath, newRunPath)
+}
+
 // shutdownCallback returns a callback function to be executing during shutdown once all processes are closed.
 // this goes through runtime directory of agent and copies all the state files created by processes to new versioned
 // home directory with updated process name to match new version.