Merge branch 'cnv-4.20' into updateWinDeployment-cnv-4.20

Author: OhadRevah

conftest.py

@@ -77,7 +77,6 @@
     "node_remediation",
     "swap",
     "numa",
-    "bgp",
 ]
 
 TEAM_MARKERS = {

containers/utility/Dockerfile

@@ -4,6 +4,24 @@ RUN if [ "$TARGETARCH" = "s390x" ] ; then \
       yum install yum-utils -y ; \
       yum-config-manager --add-repo='https://buildlogs.centos.org/centos/9-stream/nfv/s390x/openvswitch-2' ; \
     else \
-      yum install epel-release centos-release-nfv-openvswitch -y ; \
-    fi ; \
-    yum update -y && yum install iproute tcpdump qemu-img NetworkManager xfreerdp xauth xorg-x11-server-Xvfb which nftables stress-ng nmap -y && yum install --nogpgcheck openvswitch3.1 -y && yum clean all
+        yum install -y epel-release centos-release-nfv-openvswitch; \
+    fi; \
+    yum -y update && \
+    yum install -y \
+        NetworkManager \
+        dhcp-client \
+        iperf3 \
+        iproute \
+        nftables \
+        nmap \
+        openvswitch3.1 --nogpgcheck \
+        procps-ng \
+        qemu-img \
+        stress-ng \
+        tcpdump \
+        which \
+        xauth \
+        xfreerdp \
+        xorg-x11-server-Xvfb && \
+    yum clean all && \
+    rm -rf /var/cache/yum

libs/net/traffic_generator.py

@@ -4,7 +4,7 @@
 
 from ocp_resources.pod import Pod
 from ocp_utilities.exceptions import CommandExecFailed
-from timeout_sampler import TimeoutExpiredError, TimeoutSampler, retry
+from timeout_sampler import retry
 
 from libs.vm.vm import BaseVirtualMachine
 
@@ -15,7 +15,7 @@
 LOGGER = logging.getLogger(__name__)
 
 
-class BaseClient(ABC):
+class BaseTcpClient(ABC):
     """Base abstract class for network traffic generator client."""
 
     def __init__(self, server_ip: str, server_port: int):
@@ -24,7 +24,7 @@ def __init__(self, server_ip: str, server_port: int):
         self._cmd = f"{_IPERF_BIN} --client {self._server_ip} --time 0 --port {self.server_port} --connect-timeout 300"
 
     @abstractmethod
-    def __enter__(self) -> "BaseClient":
+    def __enter__(self) -> "BaseTcpClient":
         pass
 
     @abstractmethod
@@ -36,7 +36,7 @@ def is_running(self) -> bool:
         pass
 
 
-class Server:
+class TcpServer:
     """
     Represents a server running on a virtual machine for testing network performance.
     Implemented with iperf3
@@ -55,11 +55,13 @@ def __init__(
         self._port = port
         self._cmd = f"{_IPERF_BIN} --server --port {self._port} --one-off"
 
-    def __enter__(self) -> "Server":
+    def __enter__(self) -> "TcpServer":
         self._vm.console(
             commands=[f"{self._cmd} &"],
             timeout=_DEFAULT_CMD_TIMEOUT_SEC,
         )
+        self._ensure_is_running()
+
         return self
 
     def __exit__(self, exc_type: BaseException, exc_value: BaseException, traceback: object) -> None:
@@ -72,10 +74,13 @@ def vm(self) -> BaseVirtualMachine:
     def is_running(self) -> bool:
         return _is_process_running(vm=self._vm, cmd=self._cmd)
 
+    @retry(wait_timeout=30, sleep=2, exceptions_dict={})
+    def _ensure_is_running(self) -> bool:
+        return self.is_running()
+
 
-class Client(BaseClient):
-    """
-    Represents a client that connects to a server to test network performance.
+class VMTcpClient(BaseTcpClient):
+    """Represents a TCP client that connects to a server to test network performance.
     Implemented with iperf3
 
     Args:
@@ -93,11 +98,13 @@ def __init__(
         super().__init__(server_ip=server_ip, server_port=server_port)
         self._vm = vm
 
-    def __enter__(self) -> "Client":
+    def __enter__(self) -> "VMTcpClient":
         self._vm.console(
             commands=[f"{self._cmd} &"],
             timeout=_DEFAULT_CMD_TIMEOUT_SEC,
         )
+        self._ensure_is_running()
+
         return self
 
     def __exit__(self, exc_type: BaseException, exc_value: BaseException, traceback: object) -> None:
@@ -110,6 +117,10 @@ def vm(self) -> BaseVirtualMachine:
     def is_running(self) -> bool:
         return _is_process_running(vm=self._vm, cmd=self._cmd)
 
+    @retry(wait_timeout=30, sleep=2, exceptions_dict={})
+    def _ensure_is_running(self) -> bool:
+        return self.is_running()
+
 
 def _stop_process(vm: BaseVirtualMachine, cmd: str) -> None:
     try:
@@ -118,25 +129,18 @@ def _stop_process(vm: BaseVirtualMachine, cmd: str) -> None:
         LOGGER.warning(str(e))
 
 
-def _is_process_running(  # type: ignore[return]
-    vm: BaseVirtualMachine, cmd: str
-) -> bool:
+def _is_process_running(vm: BaseVirtualMachine, cmd: str) -> bool:
     try:
-        for sample in TimeoutSampler(
-            wait_timeout=60,
-            sleep=5,
-            func=vm.console,
+        vm.console(
             commands=[f"pgrep -fx '{cmd}'"],
             timeout=_DEFAULT_CMD_TIMEOUT_SEC,
-        ):
-            if sample:
-                return True
-    except TimeoutExpiredError as e:
-        LOGGER.warning(f"Process is not running on VM {vm.name}. Error: {str(e.last_exp)}")
+        )
+        return True
+    except CommandExecFailed:
         return False
 
 
-class PodClient(BaseClient):
+class PodTcpClient(BaseTcpClient):
     """Represents a TCP client that connects to a server to test network performance.
 
     Expects pod to have iperf3 container.
@@ -155,7 +159,7 @@ def __init__(self, pod: Pod, server_ip: str, server_port: int, bind_interface: s
         self._container = _IPERF_BIN
         self._cmd += f" --bind {bind_interface}" if bind_interface else ""
 
-    def __enter__(self) -> "PodClient":
+    def __enter__(self) -> "PodTcpClient":
         # run the command in the background using nohup to ensure it keeps running after the exec session ends
         self._pod.execute(
             command=["sh", "-c", f"nohup {self._cmd} >/tmp/{_IPERF_BIN}.log 2>&1 &"], container=self._container
@@ -178,5 +182,5 @@ def _ensure_is_running(self) -> bool:
         return self.is_running()
 
 
-def is_tcp_connection(server: Server, client: Client | PodClient) -> bool:
+def is_tcp_connection(server: TcpServer, client: BaseTcpClient) -> bool:
     return server.is_running() and client.is_running()

libs/vm/affinity.py

@@ -15,7 +15,7 @@ def new_label(key_prefix: str) -> tuple[str, str]:
     return f"{key_prefix}-{uuid.uuid4().hex[:8]}", "true"
 
 
-def new_pod_anti_affinity(label: tuple[str, str]) -> Affinity:
+def new_pod_anti_affinity(label: tuple[str, str], namespaces: list[str] | None = None) -> Affinity:
     (key, value) = label
     return Affinity(
         podAntiAffinity=PodAntiAffinity(
@@ -25,6 +25,7 @@ def new_pod_anti_affinity(label: tuple[str, str]) -> Affinity:
                         matchExpressions=[LabelSelectorRequirement(key=key, values=[value], operator="In")]
                     ),
                     topologyKey=f"{Resource.ApiGroup.KUBERNETES_IO}/hostname",
+                    namespaces=namespaces,
                 )
             ]
         )

libs/vm/spec.py

@@ -110,6 +110,7 @@ class PodAffinityTerm:
     labelSelector: LabelSelector  # noqa: N815
     topologyKey: str  # noqa: N815
     namespaceSelector: dict[str, Any] | None = None  # noqa: N815
+    namespaces: list[str] | None = None
 
 
 @dataclass

tests/conftest.py

@@ -1076,13 +1076,6 @@ def sriov_workers(schedulable_nodes):
     yield [node for node in schedulable_nodes if node.labels.get(sriov_worker_label) == "true"]
 
 
-@pytest.fixture(scope="session")
-def vlan_base_iface(worker_node1, nodes_available_nics):
-    # Select the last NIC from the list as a way to ensure that the selected NIC
-    # is not already used (e.g. as a bond's port).
-    return nodes_available_nics[worker_node1.name][-1]
-
-
 @pytest.fixture(scope="session")
 def sriov_ifaces(sriov_nodes_states, workers_utility_pods):
     node = sriov_nodes_states[0]

tests/install_upgrade_operators/product_install/conftest.py

@@ -9,7 +9,9 @@
 from ocp_resources.installplan import InstallPlan
 from ocp_resources.persistent_volume import PersistentVolume
 from ocp_resources.resource import get_client
+from ocp_resources.storage_class import StorageClass
 from pytest_testconfig import py_config
+from timeout_sampler import TimeoutSampler
 
 from tests.install_upgrade_operators.product_install.constants import (
     HCO_NOT_INSTALLED_ALERT,
@@ -27,6 +29,7 @@
     PENDING_STR,
     PRODUCTION_CATALOG_SOURCE,
     TIMEOUT_5MIN,
+    TIMEOUT_5SEC,
     TIMEOUT_10MIN,
     StorageClassNames,
 )
@@ -58,6 +61,8 @@
     HppCsiStorageClass,
     HPPWithStoragePool,
     create_hpp_storage_class,
+    get_default_storage_class,
+    persist_storage_class_default,
 )
 
 INSTALLATION_VERSION_MISMATCH = "98"
@@ -313,3 +318,37 @@ def cnv_version_to_install_info(is_production_source, ocp_current_version, cnv_i
     if not latest_z_stream:
         pytest.exit(reason="CNV version can't be determined for this run", returncode=INSTALLATION_VERSION_MISMATCH)
     return latest_z_stream
+
+
+@pytest.fixture()
+def default_storage_class_from_config(admin_client):
+    # if its not on the matrix - we dont need to test it.
+    default_storage_class_name = py_config["default_storage_class"]
+    if not any(default_storage_class_name in sc_dict for sc_dict in py_config["storage_class_matrix"]):
+        pytest.xfail(f"Storage class {default_storage_class_name} not found in the storage class matrix")
+    # Some storageclasses are created asynchronously, for example ocs-virt,
+    # so we need to wait for them to be created
+    LOGGER.info(f"Waiting for storage class {default_storage_class_name} to be created")
+    default_storage_class = StorageClass(client=admin_client, name=default_storage_class_name)
+    for sample in TimeoutSampler(
+        wait_timeout=TIMEOUT_5MIN,
+        sleep=TIMEOUT_5SEC,
+        func=lambda: default_storage_class.exists,
+    ):
+        if sample:
+            break
+
+    return default_storage_class
+
+
+@pytest.fixture()
+def updated_default_storage_class_from_config(admin_client, default_storage_class_from_config):
+    # Swaps the current default StorageClass with the one defined in our config.
+    try:
+        current_default_sc = get_default_storage_class()
+        if current_default_sc.name == default_storage_class_from_config.name:
+            return
+        persist_storage_class_default(default=False, storage_class=current_default_sc)
+    except ValueError:
+        LOGGER.info("No default storage class exists, setting the config one as default")
+    persist_storage_class_default(default=True, storage_class=default_storage_class_from_config)

tests/install_upgrade_operators/product_install/test_install_openshift_virtualization.py

@@ -26,6 +26,9 @@
     wait_for_firing_alert_clean_up,
     wait_for_gauge_metrics_value,
 )
+from utilities.storage import (
+    verify_boot_sources_reimported,
+)
 
 CNV_INSTALLATION_TEST = "test_cnv_installation"
 CNV_ALERT_CLEANUP_TEST = "test_cnv_installation_alert_cleanup"
@@ -170,6 +173,17 @@ def test_cnv_resources_installed_namespace_scoped(
         raise ResourceMismatch(f"Unexpected namespaced resources found post cnv installation: {mismatch_namespaced}")
 
 
+@pytest.mark.polarion("CNV-12453")
+@pytest.mark.order(after=CNV_INSTALLATION_TEST)
+# Dependency: CNV must be installed before storage class configuration can be verified
+@pytest.mark.dependency(depends=[CNV_INSTALLATION_TEST])
+@pytest.mark.usefixtures("updated_default_storage_class_from_config")
+def test_default_storage_class_set(admin_client, golden_images_namespace):
+    assert verify_boot_sources_reimported(
+        admin_client=admin_client, namespace=golden_images_namespace.name, consecutive_checks_count=3
+    ), "Failed to re-import boot sources"
+
+
 @pytest.mark.polarion("CNV-10528")
 def test_install_hpp(admin_client, schedulable_nodes, installed_hpp, created_cnv_namespace):
     validate_hpp_installation(

tests/network/bgp/README.md

@@ -8,23 +8,3 @@ An external BGP router is required for real-world BGP connectivity, as customers
 cluster. For testing, the router is implemented as a pod running FRR within the cluster, serving the same role as an
 external router. The external BGP router (a pod in this case) must be on the same network as the cluster nodes
 to enable direct BGP sessions.
-
-### Cluster Requirements
-
-The current implementation requires:
-- Each node must have at least two NICs.
-- All secondary NICs must be connected to the same VLAN as the main IP of the `br-ex` interface.
-
-### Environment Variables
-
-Set these before running tests:
-
-- `PRIMARY_NODE_NETWORK_VLAN_TAG`: the VLAN number of the `br-ex` main IP. Setting this variable implies that a cluster
-                                   reflects the requirements mentioned above.
-- `EXTERNAL_FRR_STATIC_IPV4`: reserved IPv4 in CIDR format for the external FRR pod (e.g., 192.0.2.10/24)
-                              within the PRIMARY_NODE_NETWORK_VLAN_TAG network.
-
-```bash
-export PRIMARY_NODE_NETWORK_VLAN_TAG=<vlan_id>
-export EXTERNAL_FRR_STATIC_IPV4=<static_ip_cidr>
-```