Merge 16bc55f67e into 3cc6a882c8

If pod-1 is not the primary we'd fail anyway because a timeline
bump would make all assertions about the walLogDir fail.
Also there's no reason why there should have been a switchover,
so we should not hide a failure if that happens.

Signed-off-by: Niccolò Fei <niccolo.fei@enterprisedb.com>

internal/cnpgi/operator/lifecycle.go

@@ -403,9 +403,8 @@ func reconcilePodSpec(
 	envs = append(envs, config.env...)
 
 	baseProbe := &corev1.Probe{
-		PeriodSeconds:    1,
+		FailureThreshold: 10,
-		FailureThreshold: 30,
+		TimeoutSeconds:   10,
-		TimeoutSeconds:   5,
 		ProbeHandler: corev1.ProbeHandler{
 			Exec: &corev1.ExecAction{
 				Command: []string{"/manager", "healthcheck", "unix"},

renovate.json5

@@ -12,14 +12,14 @@
   rebaseWhen: 'never',
   prConcurrentLimit: 5,
   // Override default ignorePaths to scan test/e2e for emulator image dependencies
-  // Removed: '**/test/**', '**/tests/**' (this repo's e2e Ginkgo packages live
+  // Removed: '**/test/**'
-  // under test/e2e/internal/tests/**, which the plural pattern was excluding)
   ignorePaths: [
     '**/node_modules/**',
     '**/bower_components/**',
     '**/vendor/**',
     '**/examples/**',
     '**/__tests__/**',
+    '**/tests/**',
     '**/__fixtures__/**',
   ],
   lockFileMaintenance: {

test/e2e/internal/tests/walrestore/fixtures.go

@@ -121,8 +121,7 @@ func newS3ClientDeployment(namespace string) *appsv1.Deployment {
 						{
 							Name: s3ClientName,
 							// renovate: datasource=docker depName=amazon/aws-cli versioning=docker
-							// Version: 2.35.11
+							Image:   "docker.io/amazon/aws-cli:2.35.11",
-							Image:   "docker.io/amazon/aws-cli@sha256:749bfaf91d690b9a1768083822d620f96c19defdf9ca2dc227eb3695281fda5b",
 							Command: []string{"sleep", "infinity"},
 							Env: []corev1.EnvVar{
 								{

test/e2e/internal/tests/walrestore/walrestore.go

@@ -21,7 +21,6 @@ package walrestore
 
 import (
 	"context"
-	"errors"
 	"fmt"
 	"strconv"
 	"strings"
@@ -31,7 +30,6 @@ import (
 	apitypes "k8s.io/apimachinery/pkg/types"
 	"k8s.io/client-go/kubernetes"
 	"k8s.io/client-go/rest"
-	executil "k8s.io/client-go/util/exec"
 	"sigs.k8s.io/controller-runtime/pkg/client"
 
 	internalClient "github.com/cloudnative-pg/plugin-barman-cloud/test/e2e/internal/client"
@@ -69,8 +67,9 @@ const (
 )
 
 // walFile returns the name of the n-th forged WAL segment (segment 0xF0+n on
-// timeline 1, log 0, for n <= 15). The high segment number keeps it out of the
+// timeline 1, log 0). The high segment number keeps it out of the range an idle
-// range an idle PostgreSQL would archive on its own.
+// PostgreSQL would archive on its own. Hex formatting keeps the name a valid
+// 24-character segment for any small n.
 func walFile(n int) string {
 	return fmt.Sprintf("0000000100000000%08X", 0xF0+n)
 }
@@ -200,8 +199,8 @@ var _ = Describe("Parallel WAL restore", func() {
 					"sh", "-c", "rm -f "+spoolDirectory+"/* 2>/dev/null; true")
 			}
 			forge := func(src, dst string) {
-				// ExecuteInContainer drops stdout/stderr on a non-zero exit, so on
+				// ExecuteInContainer folds a non-zero exit (and its output) into the
-				// failure this only reports the exit code, not the aws CLI's error text.
+				// returned error, so we surface that rather than the empty stderr.
 				_, _, err := execInPod(ctx, clientSet, cfg, ns, s3Client, s3ClientName,
 					"aws", "s3", "cp", walObjectURI(src), walObjectURI(dst))
 				Expect(err).NotTo(HaveOccurred(), "forging %s -> %s", src, dst)
@@ -212,6 +211,7 @@ var _ = Describe("Parallel WAL restore", func() {
 				return err == nil && strings.TrimSpace(out) != ""
 			}
 
+			var latestWAL string
 			By("archiving a real WAL on the primary and learning its name")
 			_, _, err := execInPod(ctx, clientSet, cfg, ns, primary, postgresContainer,
 				"psql", "-tAc", "CHECKPOINT")
@@ -219,7 +219,7 @@ var _ = Describe("Parallel WAL restore", func() {
 			out, _, err := execInPod(ctx, clientSet, cfg, ns, primary, postgresContainer,
 				"psql", "-tAc", "SELECT pg_walfile_name(pg_switch_wal())")
 			Expect(err).NotTo(HaveOccurred(), "switching WAL on the primary failed")
-			latestWAL := strings.TrimSpace(out)
+			latestWAL = strings.TrimSpace(out)
 			Expect(latestWAL).To(HavePrefix(walLogDir),
 				"the freshly bootstrapped cluster should still be on the first WAL log")
 
@@ -288,11 +288,7 @@ var _ = Describe("Parallel WAL restore", func() {
 			// #6 (first): flag is set, so the request fails fast (exit 1) and the
 			// flag is consumed, leaving an empty spool.
 			By("requesting WAL #6: fails fast on the end-of-wal-stream flag, spool cleared")
-			restoreErr := restore(walFile(6))
+			Expect(restore(walFile(6))).To(HaveOccurred(), "exit code should be 1")
-			var exitErr executil.CodeExitError
-			Expect(errors.As(restoreErr, &exitErr)).To(BeTrue(),
-				"expected a CodeExitError, got %T: %v", restoreErr, restoreErr)
-			Expect(exitErr.ExitStatus()).To(Equal(1), "exit code should be 1")
 			Eventually(func(g Gomega) {
 				g.Expect(existsIn(pgWalPath, walFile(6))).To(BeFalse(), "#6 not restored")
 				g.Expect(spoolSegments()).To(Equal(0), "no WAL segments in spool")