Merge branch 'sonic-net:master' into test_orchagent_standby_tor_downs…

…tream_failure_fix

.azure-pipelines/baseline_test/baseline.test.mgmt.public.master.yml

@@ -0,0 +1,84 @@
+name: BaselineTest_$(Build.DefinitionName)_$(SourceBranchName)_$(Date:yyyyMMdd)$(Rev:.r)
+
+trigger: none
+pr: none
+
+schedules:
+  - cron: "0 4 * * *"
+    displayName: Baseline test Scheduler
+    branches:
+      include:
+        - master
+    always: true
+
+stages:
+- stage: Pre_test
+  variables:
+  - group: GIT_SECRETS
+  jobs:
+  - job: validate_test_cases
+    displayName: "Validate Test Cases"
+    timeoutInMinutes: 20
+    continueOnError: false
+    pool: ubuntu-20.04
+    steps:
+    - template: ../pytest-collect-only.yml
+
+- stage: Test_round_1
+  dependsOn:
+  - Pre_test
+  condition: succeeded('Pre_test')
+  variables:
+  - group: SONiC-Elastictest
+  - name: inventory
+    value: veos_vtb
+  - name: testbed_file
+    value: vtestbed.yaml
+  - group: GIT_SECRETS
+  jobs:
+  - template: baseline.test.template.yml
+
+- stage: Test_round_2
+  dependsOn:
+  - Pre_test
+  - Test_round_1
+  condition: and(succeeded('Pre_test'), succeededOrFailed('Test_round_1'))
+  variables:
+  - group: SONiC-Elastictest
+  - name: inventory
+    value: veos_vtb
+  - name: testbed_file
+    value: vtestbed.yaml
+  - group: GIT_SECRETS
+  jobs:
+  - template: baseline.test.template.yml
+
+- stage: Test_round_3
+  dependsOn:
+  - Pre_test
+  - Test_round_2
+  condition: and(succeeded('Pre_test'), succeededOrFailed('Test_round_2'))
+  variables:
+  - group: SONiC-Elastictest
+  - name: inventory
+    value: veos_vtb
+  - name: testbed_file
+    value: vtestbed.yaml
+  - group: GIT_SECRETS
+  jobs:
+  - template: baseline.test.template.yml
+
+- stage: Test_round_4
+  dependsOn:
+  - Pre_test
+  - Test_round_3
+  condition: and(succeeded('Pre_test'), succeededOrFailed('Test_round_3'))
+  variables:
+  - group: SONiC-Elastictest
+  - name: inventory
+    value: veos_vtb
+  - name: testbed_file
+    value: vtestbed.yaml
+  - group: GIT_SECRETS
+  jobs:
+  - template: baseline.test.template.yml

.azure-pipelines/baseline_test/baseline.test.template.yml

@@ -0,0 +1,134 @@
+jobs:
+- job: t0_elastictest
+  displayName: "kvmtest-t0 by Elastictest"
+  timeoutInMinutes: 240
+  continueOnError: false
+  pool: ubuntu-20.04
+  steps:
+  - template: ../run-test-elastictest-template.yml
+    parameters:
+      TOPOLOGY: t0
+      MIN_WORKER: $(T0_INSTANCE_NUM)
+      MAX_WORKER: $(T0_INSTANCE_NUM)
+      KVM_IMAGE_BRANCH: "master"
+      MGMT_BRANCH: "master"
+      BUILD_REASON: "BaselineTest"
+      RETRY_TIMES: "0"
+      STOP_ON_FAILURE: "False"
+      TEST_PLAN_NUM: $(BASELINE_MGMT_PUBLIC_MASTER_TEST_NUM)
+
+- job: t0_2vlans_elastictest
+  displayName: "kvmtest-t0-2vlans by Elastictest"
+  timeoutInMinutes: 240
+  continueOnError: false
+  pool: ubuntu-20.04
+  steps:
+  - template: ../run-test-elastictest-template.yml
+    parameters:
+      TOPOLOGY: t0
+      TEST_SET: t0-2vlans
+      MIN_WORKER: $(T0_2VLANS_INSTANCE_NUM)
+      MAX_WORKER: $(T0_2VLANS_INSTANCE_NUM)
+      DEPLOY_MG_EXTRA_PARAMS: "-e vlan_config=two_vlan_a"
+      KVM_IMAGE_BRANCH: "master"
+      MGMT_BRANCH: "master"
+      BUILD_REASON: "BaselineTest"
+      RETRY_TIMES: "0"
+      STOP_ON_FAILURE: "False"
+      TEST_PLAN_NUM: $(BASELINE_MGMT_PUBLIC_MASTER_TEST_NUM)
+
+- job: t1_lag_elastictest
+  displayName: "kvmtest-t1-lag by Elastictest"
+  timeoutInMinutes: 240
+  continueOnError: false
+  pool: ubuntu-20.04
+  steps:
+  - template: ../run-test-elastictest-template.yml
+    parameters:
+      TOPOLOGY: t1-lag
+      MIN_WORKER: $(T1_LAG_INSTANCE_NUM)
+      MAX_WORKER: $(T1_LAG_INSTANCE_NUM)
+      KVM_IMAGE_BRANCH: "master"
+      MGMT_BRANCH: "master"
+      BUILD_REASON: "BaselineTest"
+      RETRY_TIMES: "0"
+      STOP_ON_FAILURE: "False"
+      TEST_PLAN_NUM: $(BASELINE_MGMT_PUBLIC_MASTER_TEST_NUM)
+
+- job: dualtor_elastictest
+  displayName: "kvmtest-dualtor-t0 by Elastictest"
+  timeoutInMinutes: 240
+  continueOnError: false
+  pool: ubuntu-20.04
+  steps:
+    - template: ../run-test-elastictest-template.yml
+      parameters:
+        TOPOLOGY: dualtor
+        MIN_WORKER: $(T0_DUALTOR_INSTANCE_NUM)
+        MAX_WORKER: $(T0_DUALTOR_INSTANCE_NUM)
+        COMMON_EXTRA_PARAMS: "--disable_loganalyzer "
+        KVM_IMAGE_BRANCH: "master"
+        MGMT_BRANCH: "master"
+        BUILD_REASON: "BaselineTest"
+        RETRY_TIMES: "0"
+        STOP_ON_FAILURE: "False"
+        TEST_PLAN_NUM: $(BASELINE_MGMT_PUBLIC_MASTER_TEST_NUM)
+
+- job: multi_asic_elastictest
+  displayName: "kvmtest-multi-asic-t1-lag by Elastictest"
+  timeoutInMinutes: 240
+  continueOnError: false
+  pool: ubuntu-20.04
+  steps:
+    - template: ../run-test-elastictest-template.yml
+      parameters:
+        TOPOLOGY: t1-8-lag
+        TEST_SET: multi-asic-t1-lag
+        MIN_WORKER: $(MULTI_ASIC_INSTANCE_NUM)
+        MAX_WORKER: $(MULTI_ASIC_INSTANCE_NUM)
+        NUM_ASIC: 4
+        KVM_IMAGE_BRANCH: "master"
+        MGMT_BRANCH: "master"
+        BUILD_REASON: "BaselineTest"
+        RETRY_TIMES: "0"
+        STOP_ON_FAILURE: "False"
+        TEST_PLAN_NUM: $(BASELINE_MGMT_PUBLIC_MASTER_TEST_NUM)
+
+- job: sonic_t0_elastictest
+  displayName: "kvmtest-t0-sonic by Elastictest"
+  timeoutInMinutes: 240
+  continueOnError: false
+  pool: ubuntu-20.04
+  steps:
+    - template: ../run-test-elastictest-template.yml
+      parameters:
+        TOPOLOGY: t0-64-32
+        MIN_WORKER: $(T0_SONIC_INSTANCE_NUM)
+        MAX_WORKER: $(T0_SONIC_INSTANCE_NUM)
+        TEST_SET: t0-sonic
+        COMMON_EXTRA_PARAMS: "--neighbor_type=sonic "
+        VM_TYPE: vsonic
+        KVM_IMAGE_BRANCH: "master"
+        MGMT_BRANCH: "master"
+        BUILD_REASON: "BaselineTest"
+        RETRY_TIMES: "0"
+        STOP_ON_FAILURE: "False"
+        TEST_PLAN_NUM: $(BASELINE_MGMT_PUBLIC_MASTER_TEST_NUM)
+
+- job: dpu_elastictest
+  displayName: "kvmtest-dpu by Elastictest"
+  timeoutInMinutes: 240
+  continueOnError: false
+  pool: ubuntu-20.04
+  steps:
+    - template: ../run-test-elastictest-template.yml
+      parameters:
+        TOPOLOGY: dpu
+        MIN_WORKER: $(T0_SONIC_INSTANCE_NUM)
+        MAX_WORKER: $(T0_SONIC_INSTANCE_NUM)
+        KVM_IMAGE_BRANCH: "master"
+        MGMT_BRANCH: "master"
+        BUILD_REASON: "BaselineTest"
+        RETRY_TIMES: "0"
+        STOP_ON_FAILURE: "False"
+        TEST_PLAN_NUM: $(BASELINE_MGMT_PUBLIC_MASTER_TEST_NUM)

.azure-pipelines/common.py

@@ -0,0 +1,65 @@
+import os
+import sys
+import logging
+import json
+
+_self_dir = os.path.dirname(os.path.abspath(__file__))
+base_path = os.path.realpath(os.path.join(_self_dir, ".."))
+if base_path not in sys.path:
+    sys.path.append(base_path)
+ansible_path = os.path.realpath(os.path.join(_self_dir, "../ansible"))
+if ansible_path not in sys.path:
+    sys.path.append(ansible_path)
+
+from tests.common.plugins.pdu_controller.pdu_manager import pdu_manager_factory     # noqa E402
+
+logger = logging.getLogger(__name__)
+
+
+def get_pdu_managers(sonichosts, conn_graph_facts):
+    """Get PDU managers for all the devices to be upgraded.
+
+    Args:
+        sonichosts (SonicHosts): Instance of class SonicHosts
+        conn_graph_facts (dict): Connection graph dict.
+
+    Returns:
+        dict: A dict of PDU managers. Key is device hostname. Value is the PDU manager object for the device.
+    """
+    pdu_managers = {}
+    device_pdu_links = conn_graph_facts['device_pdu_links']
+    device_pdu_info = conn_graph_facts['device_pdu_info']
+    for hostname in sonichosts.hostnames:
+        pdu_links = device_pdu_links[hostname]
+        pdu_info = device_pdu_info[hostname]
+        pdu_vars = {}
+        for pdu_name in pdu_info.keys():
+            pdu_vars[pdu_name] = sonichosts.get_host_visible_vars(pdu_name)
+
+        pdu_managers[hostname] = pdu_manager_factory(hostname, pdu_links, pdu_info, pdu_vars)
+    return pdu_managers
+
+
+def check_reachability(localhost, sonichosts):
+    hosts_reachability = {}
+
+    logger.info("Check ICMP ping")
+    for hostname, ip in zip(sonichosts.hostnames, sonichosts.ips):
+        hosts_reachability[hostname] = True
+        logger.info("Ping {} @{} from localhost".format(hostname, ip))
+        ping_failed = localhost.command(
+            "timeout 2 ping {} -c 1".format(ip), module_ignore_errors=True
+        ).get("localhost", {}).get("failed")
+        if ping_failed:
+            logger.info("Ping {} @{} from localhost failed.".format(hostname, ip))
+            hosts_reachability[hostname] = False
+
+    logger.info("Check if ansible can SSH to sonichosts")
+    for hostname, ping_result in sonichosts.ping(module_ignore_errors=True).items():
+        if ping_result["failed"]:
+            logger.info("SSH to {} failed.".format(hostname))
+            hosts_reachability[hostname] = False
+
+    logger.info("Hosts reachability: {}".format(json.dumps(hosts_reachability, indent=2)))
+
+    return hosts_reachability

.azure-pipelines/get_dut_version.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python3
+
 import argparse
 import logging
 import os
@@ -13,7 +15,7 @@
 if ansible_path not in sys.path:
     sys.path.append(ansible_path)
 
-from devutil.devices import init_localhost, init_testbed_sonichosts  # noqa E402
+from devutil.devices.factory import init_localhost, init_testbed_sonichosts  # noqa E402
 
 logger = logging.getLogger(__name__)
 
@@ -122,9 +124,8 @@ def main(args):
 
     parser.add_argument(
         "-i", "--inventory",
-        type=str,
         dest="inventory",
-        required=True,
+        nargs="+",
         help="Ansible inventory file")
 
     parser.add_argument(

.azure-pipelines/pr_test_scripts.yaml

@@ -32,12 +32,14 @@ t0:
   - generic_config_updater/test_ecn_config_update.py
   - iface_namingmode/test_iface_namingmode.py
   - lldp/test_lldp.py
+  - memory_checker/test_memory_checker.py
+  - minigraph/test_masked_services.py
   - monit/test_monit_status.py
   - ntp/test_ntp.py
   - override_config_table/test_override_config_table.py
   - pc/test_po_cleanup.py
   - pc/test_po_update.py
-#  - platform_tests/test_advanced_reboot.py::test_warm_reboot
+  - platform_tests/test_advanced_reboot.py::test_warm_reboot
   - platform_tests/test_cpu_memory_usage.py
   - process_monitoring/test_critical_process_monitoring.py
   - radv/test_radv_ipv6_ra.py
@@ -47,6 +49,7 @@ t0:
   - snmp/test_snmp_cpu.py
   - snmp/test_snmp_default_route.py
   - snmp/test_snmp_interfaces.py
+  - snmp/test_snmp_link_local_ip.py
   - snmp/test_snmp_lldp.py
   - snmp/test_snmp_loopback.py
   - snmp/test_snmp_pfc_counters.py
@@ -62,10 +65,12 @@ t0:
   - tacacs/test_ro_user.py
   - tacacs/test_rw_user.py
   - telemetry/test_telemetry.py
+  - telemetry/test_events.py
   - test_features.py
   - test_interfaces.py
   - test_procdockerstatsd.py
   - database/test_db_scripts.py
+  - system_health/test_watchdog.py
 
 t0-2vlans:
   - dhcp_relay/test_dhcp_relay.py
@@ -78,6 +83,8 @@ t0-sonic:
   - macsec/test_deployment.py
   - macsec/test_fault_handling.py
   - macsec/test_interop_protocol.py
+  - pc/test_retry_count.py
+  - platform_tests/test_advanced_reboot.py::test_warm_reboot
 
 dualtor:
   - arp/test_arp_extended.py
@@ -95,6 +102,7 @@ t1-lag:
   - container_checker/test_container_checker.py
   - generic_config_updater/test_mmu_dynamic_threshold_config_update.py
   - http/test_http_copy.py
+  - iface_namingmode/test_iface_namingmode.py
   - ipfwd/test_mtu.py
   - lldp/test_lldp.py
   - monit/test_monit_status.py
@@ -111,6 +119,7 @@ multi-asic-t1-lag:
   - bgp/test_bgp_fact.py
   - bgp/test_bgp_update_timer.py
   - snmp/test_snmp_default_route.py
+  - snmp/test_snmp_link_local_ip.py
   - snmp/test_snmp_loopback.py
   - snmp/test_snmp_pfc_counters.py
   - snmp/test_snmp_queue.py
@@ -148,3 +157,17 @@ wan-pub:
   - tacacs/test_ro_disk.py
   - tacacs/test_authorization.py
   - tacacs/test_accounting.py
+
+dpu:
+  - dash/test_dash_vnet.py
+
+specific_param:
+  t0-sonic:
+  - name: bgp/test_bgp_fact.py
+    param: "--neighbor_type=sonic --enable_macsec --macsec_profile=128_SCI,256_XPN_SCI"
+#  all the test modules under macsec directory
+  - name: macsec
+    param: "--neighbor_type=sonic --enable_macsec --macsec_profile=128_SCI,256_XPN_SCI"
+  dpu:
+  - name: dash/test_dash_vnet.py
+    param: " --skip_dataplane_checking "