Create installation marker on upgrade from versions < 8.8.0 (#2655) (#…

…2668)

* Create installation marker on upgrade from versions < 8.8.0

* Removing debugging lines

* Mention re-exec for additional clarity

* Adding changelog entry

* Removing scratch statement

* Re-ordering imports

* Error check

* Do not depend on parsing pre-upgrade version from upgrade marker file

* Clarify comment about only installed Agent being eligible for self-upgrade

(cherry picked from commit 9df6514)

Co-authored-by: Shaunak Kashyap <[email protected]>

changelog/fragments/1683748237-upgrade-install-marker.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: Create install marker file during upgrade from versions < 8.8.0
+
+# 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; a word indicating the component this changeset affects.
+component: agent
+
+# 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/2655
+
+# 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/2645

internal/pkg/agent/application/info/state.go

@@ -27,3 +27,12 @@ func RunningInstalled() bool {
 
 	return true
 }
+
+func CreateInstallMarker(topPath string) error {
+	markerFilePath := filepath.Join(topPath, MarkerFileName)
+	if _, err := os.Create(markerFilePath); err != nil {
+		return err
+	}
+
+	return nil
+}

internal/pkg/agent/cmd/install.go

@@ -219,23 +219,14 @@ func installCmd(streams *cli.IOStreams, cmd *cobra.Command) error {
 		}
 	}
 
-	if err := createInstallMarker(topPath); err != nil {
+	if err := info.CreateInstallMarker(topPath); err != nil {
 		return fmt.Errorf("failed to create install marker: %w", err)
 	}
 
 	fmt.Fprint(streams.Out, "Elastic Agent has been successfully installed.\n")
 	return nil
 }
 
-func createInstallMarker(topPath string) error {
-	markerFilePath := filepath.Join(topPath, info.MarkerFileName)
-	if _, err := os.Create(markerFilePath); err != nil {
-		return err
-	}
-
-	return nil
-}
-
 func installPath(basePath string) string {
 	return filepath.Join(basePath, "Elastic", "Agent")
 }

internal/pkg/agent/cmd/run.go

@@ -14,19 +14,16 @@ import (
 	"path/filepath"
 	"syscall"
 
-	"github.com/elastic/elastic-agent/pkg/control/v2/server"
-
-	"github.com/elastic/elastic-agent-libs/logp"
-
 	"github.com/spf13/cobra"
 	"go.elastic.co/apm"
 	apmtransport "go.elastic.co/apm/transport"
 	"gopkg.in/yaml.v2"
 
-	monitoringLib "github.com/elastic/elastic-agent-libs/monitoring"
-
 	"github.com/elastic/elastic-agent-libs/api"
+	"github.com/elastic/elastic-agent-libs/logp"
+	monitoringLib "github.com/elastic/elastic-agent-libs/monitoring"
 	"github.com/elastic/elastic-agent-libs/service"
+
 	"github.com/elastic/elastic-agent-system-metrics/report"
 	"github.com/elastic/elastic-agent/internal/pkg/agent/application"
 	"github.com/elastic/elastic-agent/internal/pkg/agent/application/coordinator"
@@ -47,6 +44,7 @@ import (
 	"github.com/elastic/elastic-agent/internal/pkg/diagnostics"
 	"github.com/elastic/elastic-agent/internal/pkg/release"
 	"github.com/elastic/elastic-agent/pkg/component"
+	"github.com/elastic/elastic-agent/pkg/control/v2/server"
 	"github.com/elastic/elastic-agent/pkg/core/logger"
 	"github.com/elastic/elastic-agent/version"
 )
@@ -103,6 +101,10 @@ func run(override cfgOverrider, testingMode bool, modifiers ...component.Platfor
 		service.WaitExecutionDone()
 	}()
 
+	if err := handleUpgrade(); err != nil {
+		return fmt.Errorf("error checking for and handling upgrade: %w", err)
+	}
+
 	locker := filelock.NewAppLocker(paths.Data(), paths.AgentLockFileName)
 	if err := locker.TryLock(); err != nil {
 		return err
@@ -557,3 +559,40 @@ func setupMetrics(
 func isProcessStatsEnabled(cfg *monitoringCfg.MonitoringConfig) bool {
 	return cfg != nil && cfg.HTTP.Enabled
 }
+
+// handleUpgrade checks if agent is being run as part of an
+// ongoing upgrade operation, i.e. being re-exec'd and performs
+// any upgrade-specific work, if needed.
+func handleUpgrade() error {
+	upgradeMarker, err := upgrade.LoadMarker()
+	if err != nil {
+		return fmt.Errorf("unable to load upgrade marker to check if Agent is being upgraded: %w", err)
+	}
+
+	if upgradeMarker == nil {
+		// We're not being upgraded. Nothing more to do.
+		return nil
+	}
+
+	// In v8.8.0, we introduced a new installation marker file to indicate that
+	// an Agent was running as installed. When an installed Agent that's older
+	// than v8.8.0 is upgraded, this installation marker file is not present.
+	// So, in such cases, we need to create it manually post-upgrade.
+	// Otherwise, the upgrade will be unsuccessful (see
+	// https://github.com/elastic/elastic-agent/issues/2645).
+
+	// Only an installed Elastic Agent can be self-upgraded. So, if the
+	// installation marker file is already present, we're all set.
+	if info.RunningInstalled() {
+		return nil
+	}
+
+	// Otherwise, we're being upgraded from a version of an installed Agent
+	// that didn't use an installation marker file (that is, before v8.8.0).
+	// So create the file now.
+	if err := info.CreateInstallMarker(paths.Top()); err != nil {
+		return fmt.Errorf("unable to create installation marker file during upgrade: %w", err)
+	}
+
+	return nil
+}