Merge branch 'main' into kustomizepoc

.buildkite/pull-requests.json

@@ -21,7 +21,7 @@
             "pipelineSlug": "elastic-agent-package",
             "allow_org_users": true,
             "allowed_repo_permissions": ["admin", "write"],
-            "allowed_list": [],
+            "allowed_list": ["dependabot[bot]", "mergify[bot]"],
             "set_commit_status": false,
             "build_on_commit": false,
             "build_on_comment": true,
@@ -37,7 +37,7 @@
             "pipelineSlug": "elastic-agent-binary-dra",
             "allow_org_users": true,
             "allowed_repo_permissions": ["admin", "write"],
-            "allowed_list": [],
+            "allowed_list": ["dependabot[bot]", "mergify[bot]"],
             "set_commit_status": false,
             "build_on_commit": false,
             "build_on_comment": true,

changelog/fragments/1718660806-Add-diagnostics-skip-conn-flag.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: enhancement
+
+# Change summary; a 80ish characters long description of the change.
+summary: Add diagnostics skip-conn flag
+
+# 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: Add --skip-conn flag to elastic-agent diagnostics subcommand to skip collecting connection request diagnostics.
+
+# Affected component; a word indicating the component this changeset affects.
+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/4946
+
+# 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/owner/repo/1234

control_v2.proto

@@ -260,6 +260,7 @@ message DiagnosticAgentRequest {
 // DiagnosticAgentRequestAdditional is an enum of additional diagnostic metrics that can be requested from Elastic Agent.
 enum AdditionalDiagnosticRequest {
   CPU = 0;
+  CONN = 1;
 }
 
 // DiagnosticComponentsRequest is the message to request diagnostics from individual components.

internal/pkg/agent/application/gateway/fleet/fleet_gateway.go

@@ -329,6 +329,10 @@ func (f *FleetGateway) execute(ctx context.Context) (*fleetapi.CheckinResponse,
 	// convert components into checkin components structure
 	components := f.convertToCheckinComponents(state.Components)
 
+	f.log.Debugf("correcting agent loglevel from %s to %s using coordinator state", ecsMeta.Elastic.Agent.LogLevel, state.LogLevel.String())
+	// Fix loglevel with the current log level used by coordinator
+	ecsMeta.Elastic.Agent.LogLevel = state.LogLevel.String()
+
 	// checkin
 	cmd := fleetapi.NewCheckinCmd(f.agentInfo, f.client)
 	req := &fleetapi.CheckinRequest{

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

@@ -29,6 +29,10 @@ func TestECSMetadata(t *testing.T) {
 	metadata, err := agentInfo.ECSMetadata(l)
 	require.NoError(t, err)
 
+	if assert.NotNil(t, metadata.Elastic, "metadata.Elastic must not be nil") {
+		assert.NotNil(t, metadata.Elastic.Agent, "metadata.Elastic.Agent must not be nil")
+	}
+
 	sysInfo, err := sysinfo.Host()
 	require.NoError(t, err)
 

internal/pkg/agent/cmd/diagnostics.go

@@ -36,6 +36,7 @@ func newDiagnosticsCommand(_ []string, streams *cli.IOStreams) *cobra.Command {
 
 	cmd.Flags().StringP("file", "f", "", "name of the output diagnostics zip archive")
 	cmd.Flags().BoolP("cpu-profile", "p", false, "wait to collect a CPU profile")
+	cmd.Flags().BoolP("skip-conn", "", false, "Skip connection request diagnostics")
 	cmd.Flags().Bool("exclude-events", false, "do not collect events log file")
 
 	return cmd
@@ -64,7 +65,8 @@ func diagnosticCmd(streams *cli.IOStreams, cmd *cobra.Command) error {
 	defer f.Close()
 
 	cpuProfile, _ := cmd.Flags().GetBool("cpu-profile")
-	agentDiag, unitDiags, compDiags, err := collectDiagnostics(ctx, streams, cpuProfile)
+	connSkip, _ := cmd.Flags().GetBool("skip-conn")
+	agentDiag, unitDiags, compDiags, err := collectDiagnostics(ctx, streams, cpuProfile, connSkip)
 	if err != nil {
 		return fmt.Errorf("failed collecting diagnostics: %w", err)
 	}
@@ -77,7 +79,7 @@ func diagnosticCmd(streams *cli.IOStreams, cmd *cobra.Command) error {
 	return nil
 }
 
-func collectDiagnostics(ctx context.Context, streams *cli.IOStreams, cpuProfile bool) ([]client.DiagnosticFileResult, []client.DiagnosticUnitResult, []client.DiagnosticComponentResult, error) {
+func collectDiagnostics(ctx context.Context, streams *cli.IOStreams, cpuProfile, connSkip bool) ([]client.DiagnosticFileResult, []client.DiagnosticUnitResult, []client.DiagnosticComponentResult, error) {
 	daemon := client.New()
 	err := daemon.Connect(ctx)
 	if err != nil {
@@ -86,10 +88,13 @@ func collectDiagnostics(ctx context.Context, streams *cli.IOStreams, cpuProfile
 	defer daemon.Disconnect()
 
 	var additionalDiags []cproto.AdditionalDiagnosticRequest
+	if !connSkip {
+		additionalDiags = append(additionalDiags, cproto.AdditionalDiagnosticRequest_CONN)
+	}
 	if cpuProfile {
 		// console will just hang while we wait for the CPU profile; print something so user doesn't get confused
 		fmt.Fprintf(streams.Out, "Creating diagnostics archive, waiting for CPU profile...\n")
-		additionalDiags = []cproto.AdditionalDiagnosticRequest{cproto.AdditionalDiagnosticRequest_CPU}
+		additionalDiags = append(additionalDiags, cproto.AdditionalDiagnosticRequest_CPU)
 	}
 
 	agentDiag, err := daemon.DiagnosticAgent(ctx, additionalDiags)