Allow standby_host to be specified along with s3 path

docs/administrator.md

@@ -1346,10 +1346,12 @@ If you are using [additional environment variables](#custom-pod-environment-vari
 to access your backup location you have to copy those variables and prepend
 the `STANDBY_` prefix for Spilo to find the backups and WAL files to stream.
 
-Alternatively, standby clusters can also stream from a remote primary cluster.
+Standby clusters can also stream from a remote primary cluster.
 You have to specify the host address. Port is optional and defaults to 5432.
-Note, that only one of the options (`s3_wal_path`, `gs_wal_path`,
-`standby_host`) can be present under the `standby` top-level key.
+You can combine `standby_host` with either `s3_wal_path` or `gs_wal_path`
+for additional redundancy. Note that `s3_wal_path` and `gs_wal_path` are
+mutually exclusive. At least one of `s3_wal_path`, `gs_wal_path`, or
+`standby_host` must be specified under the `standby` top-level key.
 
 ## Logical backups
 

docs/reference/cluster_manifest.md

@@ -457,17 +457,21 @@ under the `clone` top-level key and do not affect the already running cluster.
 
 On startup, an existing `standby` top-level key creates a standby Postgres
 cluster streaming from a remote location - either from a S3 or GCS WAL
-archive or a remote primary. Only one of options is allowed and required
-if the `standby` key is present.
+archive, a remote primary, or a combination of both. At least one of
+`s3_wal_path`, `gs_wal_path`, or `standby_host` must be specified.
+Note that `s3_wal_path` and `gs_wal_path` are mutually exclusive.
 
 * **s3_wal_path**
   the url to S3 bucket containing the WAL archive of the remote primary.
+  Can be combined with `standby_host` for additional redundancy.
 
 * **gs_wal_path**
   the url to GS bucket containing the WAL archive of the remote primary.
+  Can be combined with `standby_host` for additional redundancy.
 
 * **standby_host**
   hostname or IP address of the primary to stream from.
+  Can be specified alone or combined with either `s3_wal_path` or `gs_wal_path`.
 
 * **standby_port**
   TCP port on which the primary is listening for connections. Patroni will

docs/user.md

@@ -900,8 +900,9 @@ the PostgreSQL version between source and target cluster has to be the same.
 
 To start a cluster as standby, add the following `standby` section in the YAML
 file. You can stream changes from archived WAL files (AWS S3 or Google Cloud
-Storage) or from a remote primary. Only one option can be specified in the
-manifest:
+Storage), from a remote primary, or combine a remote primary with a WAL archive.
+At least one of `s3_wal_path`, `gs_wal_path`, or `standby_host` must be specified.
+Note that `s3_wal_path` and `gs_wal_path` are mutually exclusive.
 
 ```yaml
 spec:
@@ -929,6 +930,16 @@ spec:
     standby_port: "5433"
 ```
 
+You can also combine a remote primary with a WAL archive for additional redundancy:
+
+```yaml
+spec:
+  standby:
+    standby_host: "acid-minimal-cluster.default"
+    standby_port: "5433"
+    s3_wal_path: "s3://<bucketname>/spilo/<source_db_cluster>/<UID>/wal/<PGVERSION>"
+```
+
 Note, that the pods and services use the same role labels like for normal clusters:
 The standby leader is labeled as `master`. When using the `standby_host` option
 you have to copy the credentials from the source cluster's secrets to successfully

hack/adjust_postgresql_crd.sh

@@ -5,15 +5,17 @@
 #
 # Injections:
 #
-#  * oneOf: for the standby field to enforce that only one of s3_wal_path, gs_wal_path or standby_host is set.
-#    * This can later be done with // +kubebuilder:validation:ExactlyOneOf marker, but this requires latest Kubernetes version. (Currently the operator depends on v1.32.9)
+#  * oneOf: for the standby field to enforce validation rules:
+#    - s3_wal_path and gs_wal_path are mutually exclusive
+#    - standby_host can be specified alone or with either s3_wal_path OR gs_wal_path
+#    - at least one of s3_wal_path, gs_wal_path, or standby_host must be set
 #  * type: string and pattern for the maintenanceWindows items.
 
 file="${1:-"manifests/postgresql.crd.yaml"}"
 
 sed -i '/^[[:space:]]*standby:$/{
     # Capture the indentation
-    s/^\([[:space:]]*\)standby:$/\1standby:\n\1  oneOf:\n\1  - required:\n\1    - s3_wal_path\n\1  - required:\n\1    - gs_wal_path\n\1  - required:\n\1    - standby_host/
+    s/^\([[:space:]]*\)standby:$/\1standby:\n\1  anyOf:\n\1  - required:\n\1    - s3_wal_path\n\1  - required:\n\1    - gs_wal_path\n\1  - required:\n\1    - standby_host\n\1  not:\n\1    required:\n\1    - s3_wal_path\n\1    - gs_wal_path/
 }' "$file"
 
 sed -i '/^[[:space:]]*maintenanceWindows:$/{

manifests/postgresql.crd.yaml

@@ -3924,15 +3924,22 @@ spec:
                 format: int64
                 type: integer
               standby:
-                oneOf:
+                anyOf:
                 - required:
                   - s3_wal_path
                 - required:
                   - gs_wal_path
                 - required:
                   - standby_host
-                description: StandbyDescription contains remote primary config or
-                  s3/gs wal path
+                not:
+                  required:
+                  - s3_wal_path
+                  - gs_wal_path
+                description: StandbyDescription contains remote primary config and/or
+                  s3/gs wal path. standby_host can be specified alone or together with
+                  either s3_wal_path OR gs_wal_path (mutually exclusive). At least
+                  one field must be specified. s3_wal_path and gs_wal_path are mutually
+                  exclusive.
                 properties:
                   gs_wal_path:
                     type: string

manifests/standby-manifest.yaml

@@ -9,7 +9,9 @@ spec:
   numberOfInstances: 1
   postgresql:
     version: "17"
-  # Make this a standby cluster and provide either the s3 bucket path of source cluster or the remote primary host for continuous streaming.
+  # Make this a standby cluster. You can specify s3_wal_path or gs_wal_path for WAL archive,
+  # standby_host for remote primary streaming, or combine standby_host with either WAL path.
+  # Note: s3_wal_path and gs_wal_path are mutually exclusive.
   standby:
     # s3_wal_path: "s3://mybucket/spilo/acid-minimal-cluster/abcd1234-2a4b-4b2a-8c9c-c1234defg567/wal/14/"
     standby_host: "acid-minimal-cluster.default"

pkg/apis/acid.zalan.do/v1/postgresql_type.go

@@ -246,8 +246,9 @@ type Patroni struct {
 	FailsafeMode          *bool                        `json:"failsafe_mode,omitempty"`
 }
 
-// StandbyDescription contains remote primary config or s3/gs wal path
-// +kubebuilder:validation:ExactlyOneOf=s3_wal_path;gs_wal_path;standby_host
+// StandbyDescription contains remote primary config and/or s3/gs wal path.
+// standby_host can be specified alone or together with either s3_wal_path OR gs_wal_path (mutually exclusive).
+// At least one field must be specified. s3_wal_path and gs_wal_path are mutually exclusive.
 type StandbyDescription struct {
 	S3WalPath   string `json:"s3_wal_path,omitempty"`
 	GSWalPath   string `json:"gs_wal_path,omitempty"`

pkg/cluster/k8sres.go

@@ -2207,25 +2207,29 @@ func (c *Cluster) generateStandbyEnvironment(description *acidv1.StandbyDescript
 				Value: description.StandbyPort,
 			})
 		}
-	} else {
-		c.logger.Info("standby cluster streaming from WAL location")
-		if description.S3WalPath != "" {
-			result = append(result, v1.EnvVar{
-				Name:  "STANDBY_WALE_S3_PREFIX",
-				Value: description.S3WalPath,
-			})
-		} else if description.GSWalPath != "" {
-			result = append(result, v1.EnvVar{
-				Name:  "STANDBY_WALE_GS_PREFIX",
-				Value: description.GSWalPath,
-			})
-		} else {
-			c.logger.Error("no WAL path specified in standby section")
-			return result
-		}
+	}
 
+	// WAL archive can be specified with or without standby_host
+	if description.S3WalPath != "" {
+		c.logger.Info("standby cluster using S3 WAL archive")
+		result = append(result, v1.EnvVar{
+			Name:  "STANDBY_WALE_S3_PREFIX",
+			Value: description.S3WalPath,
+		})
 		result = append(result, v1.EnvVar{Name: "STANDBY_METHOD", Value: "STANDBY_WITH_WALE"})
 		result = append(result, v1.EnvVar{Name: "STANDBY_WAL_BUCKET_SCOPE_PREFIX", Value: ""})
+	} else if description.GSWalPath != "" {
+		c.logger.Info("standby cluster using GCS WAL archive")
+		result = append(result, v1.EnvVar{
+			Name:  "STANDBY_WALE_GS_PREFIX",
+			Value: description.GSWalPath,
+		})
+		result = append(result, v1.EnvVar{Name: "STANDBY_METHOD", Value: "STANDBY_WITH_WALE"})
+		result = append(result, v1.EnvVar{Name: "STANDBY_WAL_BUCKET_SCOPE_PREFIX", Value: ""})
+	} else if description.StandbyHost == "" {
+		// Neither WAL path nor standby_host specified
+		c.logger.Error("no WAL path or standby_host specified in standby section")
+		return result
 	}
 
 	return result

pkg/cluster/k8sres_test.go

@@ -1370,7 +1370,20 @@ func TestStandbyEnv(t *testing.T) {
 			envLen: 2,
 		},
 		{
-			subTest: "from remote primary - ignore WAL path",
+			subTest: "from remote primary with S3 WAL path",
+			standbyOpts: &acidv1.StandbyDescription{
+				S3WalPath:   "s3://some/path/",
+				StandbyHost: "remote-primary",
+			},
+			env: v1.EnvVar{
+				Name:  "STANDBY_HOST",
+				Value: "remote-primary",
+			},
+			envPos: 0,
+			envLen: 4,
+		},
+		{
+			subTest: "from remote primary with GCS WAL path",
 			standbyOpts: &acidv1.StandbyDescription{
 				GSWalPath:   "gs://some/path/",
 				StandbyHost: "remote-primary",
@@ -1380,7 +1393,7 @@ func TestStandbyEnv(t *testing.T) {
 				Value: "remote-primary",
 			},
 			envPos: 0,
-			envLen: 1,
+			envLen: 4,
 		},
 	}