X-Git-Url: https://git.opendaylight.org/gerrit/gitweb?a=blobdiff_plain;f=csit%2Flibraries%2FClusterManagement.robot;h=92c861e1f42cb5e3d4d6bdcc5338c6ff2e0bd2f3;hb=94651ca9711d8eb316721775561e815830bc6c7e;hp=e1e4bdc4dd352813af6df80d997f7d6ecf51520d;hpb=091e6d0c6995bce74f524c59d3924220f251ac10;p=integration%2Ftest.git diff --git a/csit/libraries/ClusterManagement.robot b/csit/libraries/ClusterManagement.robot index e1e4bdc4dd..92c861e1f4 100644 --- a/csit/libraries/ClusterManagement.robot +++ b/csit/libraries/ClusterManagement.robot @@ -36,6 +36,7 @@ Resource ${CURDIR}/KarafKeywords.robot Resource ${CURDIR}/SSHKeywords.robot Resource ${CURDIR}/TemplatedRequests.robot # for Get_As_Json_From_Uri Resource ${CURDIR}/Utils.robot # for Run_Command_On_Controller +Resource ../variables/Variables.robot *** Variables *** ${ENTITY_OWNER_URI} restconf/operational/entity-owners:entity-owners @@ -43,24 +44,33 @@ ${GC_LOG_PATH} ${KARAF_HOME}/data/log ${JAVA_HOME} ${EMPTY} # releng/builder scripts should provide correct value ${JOLOKIA_CONF_SHARD_MANAGER_URI} jolokia/read/org.opendaylight.controller:Category=ShardManager,name=shard-manager-config,type=DistributedConfigDatastore ${JOLOKIA_OPER_SHARD_MANAGER_URI} jolokia/read/org.opendaylight.controller:Category=ShardManager,name=shard-manager-operational,type=DistributedOperationalDatastore +${JOLOKIA_CONFIG_LOCAL_SHARDS_URI} jolokia/read/org.opendaylight.controller:type=DistributedConfigDatastore,Category=ShardManager,name=shard-manager-config/LocalShards +${JOLOKIA_OPER_LOCAL_SHARDS_URI} jolokia/read/org.opendaylight.controller:type=DistributedOperationalDatastore,Category=ShardManager,name=shard-manager-operational/LocalShards ${JOLOKIA_READ_URI} jolokia/read/org.opendaylight.controller -${KARAF_HOME} ${WORKSPACE}${/}${BUNDLEFOLDER} # TODO: Migrate to Variables.robot # Bug 9044 workaround: delete etc/host.key before restart. @{ODL_DEFAULT_DATA_PATHS} tmp/ data/ cache/ snapshots/ journal/ etc/opendaylight/current/ etc/host.key ${RESTCONF_MODULES_DIR} ${CURDIR}/../variables/restconf/modules -${SINGLETON_NETCONF_DEVICE_ID_PREFIX} /odl-general-entity:entity[odl-general-entity:name='KeyedInstanceIdentifier{targetType=interface org.opendaylight.yang.gen.v1.urn.tbd.params.xml.ns.yang.network.topology.rev131021.network.topology.topology.Node, path=[org.opendaylight.yang.gen.v1.urn.tbd.params.xml.ns.yang.network.topology.rev131021.NetworkTopology, org.opendaylight.yang.gen.v1.urn.tbd.params.xml.ns.yang.network.topology.rev131021.network.topology.Topology[key=TopologyKey [_topologyId=Uri [_value=topology-netconf]]], org.opendaylight.yang.gen.v1.urn.tbd.params.xml.ns.yang.network.topology.rev131021.network.topology.topology.Node[key=NodeKey [_nodeId=Uri [_value= -${SINGLETON_NETCONF_DEVICE_ID_SUFFIX} ]]]]}'] +${SINGLETON_NETCONF_DEVICE_ID_PREFIX_OLD} /odl-general-entity:entity[odl-general-entity:name='KeyedInstanceIdentifier{targetType=interface org.opendaylight.yang.gen.v1.urn.tbd.params.xml.ns.yang.network.topology.rev131021.network.topology.topology.Node, path=[org.opendaylight.yang.gen.v1.urn.tbd.params.xml.ns.yang.network.topology.rev131021.NetworkTopology, org.opendaylight.yang.gen.v1.urn.tbd.params.xml.ns.yang.network.topology.rev131021.network.topology.Topology[key=TopologyKey [_topologyId=Uri [_value=topology-netconf]]], org.opendaylight.yang.gen.v1.urn.tbd.params.xml.ns.yang.network.topology.rev131021.network.topology.topology.Node[key=NodeKey [_nodeId=Uri [_value= +${SINGLETON_NETCONF_DEVICE_ID_SUFFIX_OLD} ]]]]}'] +${SINGLETON_NETCONF_DEVICE_ID_PREFIX} /odl-general-entity:entity[odl-general-entity:name='KeyedInstanceIdentifier{targetType=interface org.opendaylight.yang.gen.v1.urn.tbd.params.xml.ns.yang.network.topology.rev131021.network.topology.topology.Node, path=[org.opendaylight.yang.gen.v1.urn.tbd.params.xml.ns.yang.network.topology.rev131021.NetworkTopology, org.opendaylight.yang.gen.v1.urn.tbd.params.xml.ns.yang.network.topology.rev131021.network.topology.Topology[key=TopologyKey{_topologyId=Uri{_value=topology-netconf}}], org.opendaylight.yang.gen.v1.urn.tbd.params.xml.ns.yang.network.topology.rev131021.network.topology.topology.Node[key=NodeKey{_nodeId=Uri{_value= +${SINGLETON_NETCONF_DEVICE_ID_SUFFIX} }}]]}'] +${SINGLETON_BGPCEP_DEVICE_ID_PREFIX} /odl-general-entity:entity[odl-general-entity:name=' +${SINGLETON_BGPCEP_DEVICE_ID_SUFFIX} -service-group'] +${SINGLETON_SXP_DEVICE_ID_PREFIX} /odl-general-entity:entity[odl-general-entity:name=' +${SINGLETON_SXP_DEVICE_ID_SUFFIX} '] ${SINGLETON_ELECTION_ENTITY_TYPE} org.opendaylight.mdsal.ServiceEntityType ${SINGLETON_CHANGE_OWNERSHIP_ENTITY_TYPE} org.opendaylight.mdsal.AsyncServiceCloseEntityType +${NODE_ROLE_INDEX_START} 1 ${NODE_START_COMMAND} ${KARAF_HOME}/bin/start ${NODE_STOP_COMMAND} ${KARAF_HOME}/bin/stop +${NODE_KARAF_COUNT_COMMAND} ps axf | grep org.apache.karaf | grep -v grep | wc -l ${NODE_KILL_COMMAND} ps axf | grep org.apache.karaf | grep -v grep | awk '{print \"kill -9 \" $1}' | sh ${NODE_FREEZE_COMMAND} ps axf | grep org.apache.karaf | grep -v grep | awk '{print \"kill -STOP \" $1}' | sh ${NODE_UNFREEZE_COMMAND} ps axf | grep org.apache.karaf | grep -v grep | awk '{print \"kill -CONT \" $1}' | sh *** Keywords *** ClusterManagement_Setup - [Arguments] ${http_timeout}=1 ${http_retries}=0 + [Arguments] ${http_timeout}=${DEFAULT_TIMEOUT_HTTP} ${http_retries}=0 [Documentation] Detect repeated call, or detect number of members and initialize derived suite variables. ... Http sessions are created with parameters to not waste time when ODL is no accepting connections properly. # Avoid multiple initialization by several downstream libraries. @@ -76,10 +86,11 @@ Check_Cluster_Is_In_Sync [Arguments] ${member_index_list}=${EMPTY} [Documentation] Fail if no-sync is detected on a member from list (or any). ${index_list} = List_Indices_Or_All given_list=${member_index_list} - : FOR ${index} IN @{index_list} # usually: 1, 2, 3. - \ ${status} = Get_Sync_Status_Of_Member member_index=${index} - \ BuiltIn.Continue_For_Loop_If 'True' == '${status}' - \ BuiltIn.Fail Index ${index} has incorrect status: ${status} + FOR ${index} IN @{index_list} # usually: 1, 2, 3. + ${status} = Get_Sync_Status_Of_Member member_index=${index} + BuiltIn.Continue_For_Loop_If 'True' == '${status}' + BuiltIn.Fail Index ${index} has incorrect status: ${status} + END Get_Sync_Status_Of_Member [Arguments] ${member_index} @@ -96,11 +107,12 @@ Verify_Leader_Exists_For_Each_Shard [Arguments] ${shard_name_list} ${shard_type}=operational ${member_index_list}=${EMPTY} ${verify_restconf}=True [Documentation] For each shard name, call Get_Leader_And_Followers_For_Shard. ... Not much logic there, but single Keyword is useful when using BuiltIn.Wait_Until_Keyword_Succeeds. - : FOR ${shard_name} IN @{shard_name_list} - \ Get_Leader_And_Followers_For_Shard shard_name=${shard_name} shard_type=${shard_type} validate=True member_index_list=${member_index_list} verify_restconf=${verify_restconf} + FOR ${shard_name} IN @{shard_name_list} + Get_Leader_And_Followers_For_Shard shard_name=${shard_name} shard_type=${shard_type} validate=True member_index_list=${member_index_list} verify_restconf=${verify_restconf} + END Get_Leader_And_Followers_For_Shard - [Arguments] ${shard_name}=default ${shard_type}=operational ${validate}=True ${member_index_list}=${EMPTY} ${verify_restconf}=True ${http_timeout}=5 + [Arguments] ${shard_name}=default ${shard_type}=operational ${validate}=True ${member_index_list}=${EMPTY} ${verify_restconf}=True ${http_timeout}=${EMPTY} [Documentation] Get role lists, validate there is one leader, return the leader and list of followers. ... Optionally, issue GET to a simple restconf URL to make sure subsequent operations will not encounter 503. ${leader_list} ${follower_list} = Get_State_Info_For_Shard shard_name=${shard_name} shard_type=${shard_type} validate=True member_index_list=${member_index_list} @@ -112,7 +124,7 @@ Get_Leader_And_Followers_For_Shard [Return] ${leader} ${follower_list} Get_State_Info_For_Shard - [Arguments] ${shard_name}=default ${shard_type}=operational ${validate}=False ${member_index_list}=${EMPTY} ${verify_restconf}=False ${http_timeout}=5 + [Arguments] ${shard_name}=default ${shard_type}=operational ${validate}=False ${member_index_list}=${EMPTY} ${verify_restconf}=False ${http_timeout}=${EMPTY} [Documentation] Return lists of Leader and Follower member indices from a given member index list ... (or from the full list if empty). If \${shard_type} is not 'config', 'operational' is assumed. ... If \${validate}, Fail if raft state is not Leader or Follower (for example on Candidate). @@ -124,16 +136,17 @@ Get_State_Info_For_Shard ${ds_type} = BuiltIn.Set_Variable_If '${shard_type}' != 'config' operational config ${leader_list} = BuiltIn.Create_List ${follower_list} = BuiltIn.Create_List - : FOR ${index} IN @{index_list} # usually: 1, 2, 3. - \ ${raft_state} = Get_Raft_State_Of_Shard_At_Member shard_name=${shard_name} shard_type=${ds_type} member_index=${index} verify_restconf=${verify_restconf} - \ ... http_timeout=${http_timeout} - \ BuiltIn.Run_Keyword_If 'Follower' == '${raft_state}' Collections.Append_To_List ${follower_list} ${index} - \ ... ELSE IF 'Leader' == '${raft_state}' Collections.Append_To_List ${leader_list} ${index} - \ ... ELSE IF ${validate} BuiltIn.Fail Unrecognized Raft state: ${raft_state} + FOR ${index} IN @{index_list} # usually: 1, 2, 3. + ${raft_state} = Get_Raft_State_Of_Shard_At_Member shard_name=${shard_name} shard_type=${ds_type} member_index=${index} verify_restconf=${verify_restconf} + ... http_timeout=${http_timeout} + BuiltIn.Run_Keyword_If 'Follower' == '${raft_state}' Collections.Append_To_List ${follower_list} ${index} + ... ELSE IF 'Leader' == '${raft_state}' Collections.Append_To_List ${leader_list} ${index} + ... ELSE IF ${validate} BuiltIn.Fail Unrecognized Raft state: ${raft_state} + END [Return] ${leader_list} ${follower_list} Get_Raft_State_Of_Shard_At_Member - [Arguments] ${shard_name} ${shard_type} ${member_index} ${verify_restconf}=False ${http_timeout}=5 + [Arguments] ${shard_name} ${shard_type} ${member_index} ${verify_restconf}=False ${http_timeout}=${EMPTY} [Documentation] Send request to Jolokia on indexed member, return extracted Raft status. ... Optionally, check restconf works. ${raft_state} = Get_Raft_Property_From_Shard_Member RaftState ${shard_name} ${shard_type} ${member_index} verify_restconf=${verify_restconf} @@ -141,14 +154,15 @@ Get_Raft_State_Of_Shard_At_Member [Return] ${raft_state} Get_Raft_Property_From_Shard_Member - [Arguments] ${property} ${shard_name} ${shard_type} ${member_index} ${verify_restconf}=False ${http_timeout}=5 + [Arguments] ${property} ${shard_name} ${shard_type} ${member_index} ${verify_restconf}=False ${http_timeout}=${EMPTY} [Documentation] Send request to Jolokia on indexed member, return extracted Raft property. ... Optionally, check restconf works. ${session} = Resolve_Http_Session_For_Member member_index=${member_index} # TODO: Does the used URI tend to generate large data which floods log.html? BuiltIn.Run_Keyword_If ${verify_restconf} TemplatedRequests.Get_As_Json_Templated session=${session} folder=${RESTCONF_MODULES_DIR} verify=False http_timeout=${http_timeout} ${type_class} = Resolve_Shard_Type_Class shard_type=${shard_type} - ${uri} = BuiltIn.Set_Variable ${JOLOKIA_READ_URI}:Category=Shards,name=member-${member_index}-shard-${shard_name}-${shard_type},type=${type_class} + ${cluster_index} = Evaluate ${member_index}+${NODE_ROLE_INDEX_START}-1 + ${uri} = BuiltIn.Set_Variable ${JOLOKIA_READ_URI}:Category=Shards,name=member-${cluster_index}-shard-${shard_name}-${shard_type},type=${type_class} ${data_text} = TemplatedRequests.Get_As_Json_From_Uri uri=${uri} session=${session} http_timeout=${http_timeout} ${data_object} = RequestsLibrary.To_Json ${data_text} ${value} = Collections.Get_From_Dictionary ${data_object} value @@ -227,10 +241,11 @@ Get_Owner_And_Candidates_For_Device_Old ${owner} = String.Replace_String ${entity_owner} member- ${EMPTY} ${owner} = BuiltIn.Convert_To_Integer ${owner} ${entity_candidates_list} = Collections.Get_From_Dictionary @{entity_list}[${entity_index}] candidate - : FOR ${entity_candidate} IN @{entity_candidates_list} - \ ${candidate} = String.Replace_String &{entity_candidate}[name] member- ${EMPTY} - \ ${candidate} = BuiltIn.Convert_To_Integer ${candidate} - \ Collections.Append_To_List ${candidate_list} ${candidate} + FOR ${entity_candidate} IN @{entity_candidates_list} + ${candidate} = String.Replace_String &{entity_candidate}[name] member- ${EMPTY} + ${candidate} = BuiltIn.Convert_To_Integer ${candidate} + Collections.Append_To_List ${candidate_list} ${candidate} + END Collections.Sort_List ${candidate_list} [Return] ${owner} ${candidate_list} @@ -248,11 +263,41 @@ Get_Owner_And_Candidates_For_Device_Singleton_Netconf ... Parsing method is set as netconf (using netconf device id prefix and suffix) # Get election entity type results ${type} = BuiltIn.Set_Variable ${SINGLETON_ELECTION_ENTITY_TYPE} - ${id} = BuiltIn.Set_Variable ${SINGLETON_NETCONF_DEVICE_ID_PREFIX}${device_name}${SINGLETON_NETCONF_DEVICE_ID_SUFFIX} + ${id} = CompareStream.Set_Variable_If_At_Least_Fluorine ${SINGLETON_NETCONF_DEVICE_ID_PREFIX}${device_name}${SINGLETON_NETCONF_DEVICE_ID_SUFFIX} ${SINGLETON_NETCONF_DEVICE_ID_PREFIX_OLD}${device_name}${SINGLETON_NETCONF_DEVICE_ID_SUFFIX_OLD} ${owner_1} ${candidate_list_1} = Get_Owner_And_Candidates_For_Type_And_Id ${type} ${id} ${member_index} http_timeout=${http_timeout} # Get change ownership entity type results ${type} = BuiltIn.Set_Variable ${SINGLETON_CHANGE_OWNERSHIP_ENTITY_TYPE} - ${id} = BuiltIn.Set_Variable ${SINGLETON_NETCONF_DEVICE_ID_PREFIX}${device_name}${SINGLETON_NETCONF_DEVICE_ID_SUFFIX} + ${id} = CompareStream.Set_Variable_If_At_Least_Fluorine ${SINGLETON_NETCONF_DEVICE_ID_PREFIX}${device_name}${SINGLETON_NETCONF_DEVICE_ID_SUFFIX} ${SINGLETON_NETCONF_DEVICE_ID_PREFIX_OLD}${device_name}${SINGLETON_NETCONF_DEVICE_ID_SUFFIX_OLD} + ${owner_2} ${candidate_list_2} = Get_Owner_And_Candidates_For_Type_And_Id ${type} ${id} ${member_index} http_timeout=${http_timeout} + # Owners must be same, if not, there is still some election or change ownership in progress + BuiltIn.Should_Be_Equal_As_Integers ${owner_1} ${owner_2} Owners for device ${device_name} are not same + [Return] ${owner_1} ${candidate_list_1} + +Get_Owner_And_Candidates_For_Device_Singleton_Bgpcep + [Arguments] ${device_name} ${member_index} ${http_timeout}=${EMPTY} + [Documentation] Returns the owner and a list of candidates for the SB device ${device_name}. Request is sent to member ${member_index}. + # Get election entity type results + ${type} = BuiltIn.Set_Variable ${SINGLETON_ELECTION_ENTITY_TYPE} + ${id} = BuiltIn.Set_Variable ${SINGLETON_BGPCEP_DEVICE_ID_PREFIX}${device_name}${SINGLETON_BGPCEP_DEVICE_ID_SUFFIX} + ${owner_1} ${candidate_list_1} = Get_Owner_And_Candidates_For_Type_And_Id ${type} ${id} ${member_index} http_timeout=${http_timeout} + # Get change ownership entity type results + ${type} = BuiltIn.Set_Variable ${SINGLETON_CHANGE_OWNERSHIP_ENTITY_TYPE} + ${id} = BuiltIn.Set_Variable ${SINGLETON_BGPCEP_DEVICE_ID_PREFIX}${device_name}${SINGLETON_BGPCEP_DEVICE_ID_SUFFIX} + ${owner_2} ${candidate_list_2} = Get_Owner_And_Candidates_For_Type_And_Id ${type} ${id} ${member_index} http_timeout=${http_timeout} + # Owners must be same, if not, there is still some election or change ownership in progress + BuiltIn.Should_Be_Equal_As_Integers ${owner_1} ${owner_2} Owners for device ${device_name} are not same + [Return] ${owner_1} ${candidate_list_1} + +Get_Owner_And_Candidates_For_Device_Singleton_Sxp + [Arguments] ${device_name} ${member_index} ${http_timeout}=${EMPTY} + [Documentation] Returns the owner and a list of candidates for the SB device ${device_name}. Request is sent to member ${member_index}. + # Get election entity type results + ${type} = BuiltIn.Set_Variable ${SINGLETON_ELECTION_ENTITY_TYPE} + ${id} = BuiltIn.Set_Variable ${SINGLETON_SXP_DEVICE_ID_PREFIX}${device_name}${SINGLETON_SXP_DEVICE_ID_SUFFIX} + ${owner_1} ${candidate_list_1} = Get_Owner_And_Candidates_For_Type_And_Id ${type} ${id} ${member_index} http_timeout=${http_timeout} + # Get change ownership entity type results + ${type} = BuiltIn.Set_Variable ${SINGLETON_CHANGE_OWNERSHIP_ENTITY_TYPE} + ${id} = BuiltIn.Set_Variable ${SINGLETON_SXP_DEVICE_ID_PREFIX}${device_name}${SINGLETON_SXP_DEVICE_ID_SUFFIX} ${owner_2} ${candidate_list_2} = Get_Owner_And_Candidates_For_Type_And_Id ${type} ${id} ${member_index} http_timeout=${http_timeout} # Owners must be same, if not, there is still some election or change ownership in progress BuiltIn.Should_Be_Equal_As_Integers ${owner_1} ${owner_2} Owners for device ${device_name} are not same @@ -316,10 +361,11 @@ Get_Owner_And_Candidates_For_Type_And_Id ${owner} = String.Replace_String ${entity_owner} member- ${EMPTY} ${owner} = BuiltIn.Convert_To_Integer ${owner} ${entity_candidates_list} = Collections.Get_From_Dictionary @{entity_list}[${entity_index}] candidate - : FOR ${entity_candidate} IN @{entity_candidates_list} - \ ${candidate} = String.Replace_String &{entity_candidate}[name] member- ${EMPTY} - \ ${candidate} = BuiltIn.Convert_To_Integer ${candidate} - \ Collections.Append_To_List ${candidate_list} ${candidate} + FOR ${entity_candidate} IN @{entity_candidates_list} + ${candidate} = String.Replace_String &{entity_candidate}[name] member- ${EMPTY} + ${candidate} = BuiltIn.Convert_To_Integer ${candidate} + Collections.Append_To_List ${candidate_list} ${candidate} + END Collections.Sort_List ${candidate_list} BuiltIn.Comment TODO: Separate check lines into Verify_Owner_And_Candidates_For_Type_And_Id BuiltIn.Run_Keyword_If """${require_candidate_list}""" BuiltIn.Should_Be_Equal ${require_candidate_list} ${candidate_list} Candidate list does not match: ${candidate_list} is not ${require_candidate_list} @@ -374,20 +420,25 @@ Kill_Members_From_List_Or_All BuiltIn.Return_From_Keyword_If not ${confirm} ${updated_index_list} # TODO: Convert to WUKS with configurable timeout if it turns out 1 second is not enough. BuiltIn.Sleep 1s Kill -9 closes open files, which may take longer than ssh overhead, but not long enough to warrant WUKS. - : FOR ${index} IN @{kill_index_list} - \ Verify_Karaf_Is_Not_Running_On_Member member_index=${index} + FOR ${index} IN @{kill_index_list} + Verify_Karaf_Is_Not_Running_On_Member member_index=${index} + END + Run_Bash_Command_On_List_Or_All command=netstat -pnatu | grep 2550 [Return] ${updated_index_list} Stop_Single_Member - [Arguments] ${member} ${original_index_list}=${EMPTY} ${confirm}=True + [Arguments] ${member} ${original_index_list}=${EMPTY} ${confirm}=True ${msg}=${EMPTY} [Documentation] Convenience keyword that stops the specified member of the cluster. ... The KW will return a list of available members: \${updated index_list}=\${original_index_list}-\${member} ${index_list} = ClusterManagement__Build_List ${member} + ${member_ip} = Return_Member_IP ${member} + ${msg} = Builtin.Set Variable If "${msg}" == "${EMPTY}" Stopping ODL${member} ${member_ip} Stopping ODL${member} ${member_ip}, ${msg} + KarafKeywords.Log_Message_To_Controller_Karaf ${msg} ${updated_index_list} = Stop_Members_From_List_Or_All ${index_list} ${original_index_list} ${confirm} [Return] ${updated_index_list} Stop_Members_From_List_Or_All - [Arguments] ${member_index_list}=${EMPTY} ${original_index_list}=${EMPTY} ${confirm}=True ${timeout}=120s + [Arguments] ${member_index_list}=${EMPTY} ${original_index_list}=${EMPTY} ${confirm}=True ${timeout}=240s [Documentation] If the list is empty, stops all ODL instances. Otherwise stop members based on \${stop_index_list} ... If \${confirm} is True, verify stopped instances are not there anymore. ... The KW will return a list of available members: \${updated index_list}=\${original_index_list}-\${member_index_list} @@ -397,18 +448,25 @@ Stop_Members_From_List_Or_All ${updated_index_list} = BuiltIn.Create_List @{index_list} Collections.Remove_Values_From_List ${updated_index_list} @{stop_index_list} BuiltIn.Return_From_Keyword_If not ${confirm} ${updated_index_list} - : FOR ${index} IN @{stop_index_list} - \ BuiltIn.Wait Until Keyword Succeeds ${timeout} 2s Verify_Karaf_Is_Not_Running_On_Member member_index=${index} + FOR ${index} IN @{stop_index_list} + BuiltIn.Wait Until Keyword Succeeds ${timeout} 2s Verify_Karaf_Is_Not_Running_On_Member member_index=${index} + END + Run_Bash_Command_On_List_Or_All command=netstat -pnatu | grep 2550 [Return] ${updated_index_list} Start_Single_Member - [Arguments] ${member} ${wait_for_sync}=True ${timeout}=300s + [Arguments] ${member} ${wait_for_sync}=True ${timeout}=300s ${msg}=${EMPTY} ${check_system_status}=False ${verify_restconf}=True + ... ${service_list}=${EMPTY_LIST} [Documentation] Convenience keyword that starts the specified member of the cluster. ${index_list} = ClusterManagement__Build_List ${member} - Start_Members_From_List_Or_All ${index_list} ${wait_for_sync} ${timeout} + ${member_ip} = Return_Member_IP ${member} + ${msg} = Builtin.Set Variable If "${msg}" == "${EMPTY}" Starting ODL${member} ${member_ip} Starting ODL${member} ${member_ip}, ${msg} + KarafKeywords.Log_Message_To_Controller_Karaf ${msg} + Start_Members_From_List_Or_All ${index_list} ${wait_for_sync} ${timeout} check_system_status=${check_system_status} verify_restconf=${verify_restconf} service_list=${service_list} Start_Members_From_List_Or_All [Arguments] ${member_index_list}=${EMPTY} ${wait_for_sync}=True ${timeout}=300s ${karaf_home}=${EMPTY} ${export_java_home}=${EMPTY} ${gc_log_dir}=${EMPTY} + ... ${check_system_status}=False ${verify_restconf}=True ${service_list}=${EMPTY_LIST} [Documentation] If the list is empty, start all cluster members. Otherwise, start members based on present indices. ... If ${wait_for_sync}, wait for cluster sync on listed members. ... Optionally karaf_home can be overriden. Optionally specific JAVA_HOME is used for starting. @@ -417,11 +475,31 @@ Start_Members_From_List_Or_All ${command} = BuiltIn.Set_Variable_If """${export_java_home}""" != "" export JAVA_HOME="${export_java_home}"; ${base_command} ${base_command} ${epoch} = DateTime.Get_Current_Date time_zone=UTC result_format=epoch exclude_millis=False ${gc_filepath} = BuiltIn.Set_Variable_If """${karaf_home}""" != "" ${karaf_home}/data/log/gc_${epoch}.log ${GC_LOG_PATH}/gc_${epoch}.log - ${gc_options} = BuiltIn.Set_Variable -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:${gc_filepath} + ${gc_options} = BuiltIn.Set_Variable_If "docker" not in """${node_start_command}""" -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:${gc_filepath} ${EMPTY} Run_Bash_Command_On_List_Or_All command=${command} ${gc_options} member_index_list=${member_index_list} - BuiltIn.Return_From_Keyword_If not ${wait_for_sync} - BuiltIn.Wait_Until_Keyword_Succeeds ${timeout} 10s Check_Cluster_Is_In_Sync member_index_list=${member_index_list} - # TODO: Do we also want to check Shard Leaders here? + BuiltIn.Wait_Until_Keyword_Succeeds ${timeout} 10s Verify_Members_Are_Ready ${member_index_list} ${wait_for_sync} ${verify_restconf} + ... ${check_system_status} ${service_list} + [Teardown] Run_Bash_Command_On_List_Or_All command=netstat -pnatu | grep 2550 + +Verify_Members_Are_Ready + [Arguments] ${member_index_list} ${verify_cluster_sync} ${verify_restconf} ${verify_system_status} ${service_list} + [Documentation] Verifies the specified readiness conditions for the given listed members after startup. + ... If ${verify_cluster_sync}, verifies the datastores have synced with the rest of the cluster. + ... If ${verify_restconf}, verifies RESTCONF is available. + ... If ${verify_system_status}, verifies the system services are OPERATIONAL. + BuiltIn.Run_Keyword_If ${verify_cluster_sync} Check_Cluster_Is_In_Sync ${member_index_list} + BuiltIn.Run_Keyword_If ${verify_restconf} Verify_Restconf_Is_Available ${member_index_list} + # for backward compatibility, some consumers might not be passing @{service_list}, but since we can't set a list to a default + # value, we need to check here if it's empty in order to skip the check which would throw an error + BuiltIn.Run_Keyword_If ${verify_system_status} and ("${service_list}" != "[[]]") ClusterManagement.Check Status Of Services Is OPERATIONAL @{service_list} + +Verify_Restconf_Is_Available + [Arguments] ${member_index_list} + ${index_list} = List_Indices_Or_All given_list=${member_index_list} + FOR ${index} IN @{index_list} + ${session} = Resolve_Http_Session_For_Member member_index=${index} + TemplatedRequests.Get_As_Json_Templated session=${session} folder=${RESTCONF_MODULES_DIR} verify=False + END Freeze_Single_Member [Arguments] ${member} @@ -443,15 +521,16 @@ Freeze_Or_Unfreeze_Members_From_List_Or_All ${freeze_index_list} = List_Indices_Or_All given_list=${member_index_list} Run_Bash_Command_On_List_Or_All command=${command} member_index_list=${member_index_list} -Clean_Journals_And_Snapshots_On_List_Or_All +Clean_Journals_Data_And_Snapshots_On_List_Or_All [Arguments] ${member_index_list}=${EMPTY} ${karaf_home}=${KARAF_HOME} [Documentation] Delete journal and snapshots directories on every node listed (or all). ... BEWARE: If only a subset of members is cleaned, this causes RetiredGenerationException in Carbon after the affected node re-start. ... See https://bugs.opendaylight.org/show_bug.cgi?id=8138 ${index_list} = List_Indices_Or_All given_list=${member_index_list} - ${command} = Set Variable rm -rf "${karaf_home}/journal" "${karaf_home}/snapshots" - : FOR ${index} IN @{index_list} # usually: 1, 2, 3. - \ Run_Bash_Command_On_Member command=${command} member_index=${index} + ${command} = Set Variable rm -rf "${karaf_home}/journal" "${karaf_home}/snapshots" "${karaf_home}/data" + FOR ${index} IN @{index_list} # usually: 1, 2, 3. + Run_Bash_Command_On_Member command=${command} member_index=${index} + END Verify_Karaf_Is_Not_Running_On_Member [Arguments] ${member_index} @@ -468,20 +547,22 @@ Verify_Single_Karaf_Is_Running_On_Member Count_Running_Karafs_On_Member [Arguments] ${member_index} [Documentation] Remotely execute grep for karaf process, return count as string. - ${command} = BuiltIn.Set_Variable ps axf | grep org.apache.karaf | grep -v grep | wc -l + ${command} = BuiltIn.Set_Variable ${NODE_KARAF_COUNT_COMMAND} ${count} = Run_Bash_Command_On_Member command=${command} member_index=${member_index} [Return] ${count} Isolate_Member_From_List_Or_All - [Arguments] ${isolate_member_index} ${member_index_list}=${EMPTY} + [Arguments] ${isolate_member_index} ${member_index_list}=${EMPTY} ${protocol}=all ${port}=${EMPTY} [Documentation] If the list is empty, isolate member from all ODL instances. Otherwise, isolate member based on present indices. ... The KW will return a list of available members: \${updated index_list}=\${member_index_list}-\${isolate_member_index} ${index_list} = List_Indices_Or_All given_list=${member_index_list} ${source} = Collections.Get_From_Dictionary ${ClusterManagement__index_to_ip_mapping} ${isolate_member_index} - : FOR ${index} IN @{index_list} - \ ${destination} = Collections.Get_From_Dictionary ${ClusterManagement__index_to_ip_mapping} ${index} - \ ${command} = BuiltIn.Set_Variable sudo /sbin/iptables -I OUTPUT -p all --source ${source} --destination ${destination} -j DROP - \ BuiltIn.Run_Keyword_If "${index}" != "${isolate_member_index}" Run_Bash_Command_On_Member command=${command} member_index=${isolate_member_index} + ${dport} = BuiltIn.Set_Variable_If '${port}' != '${EMPTY}' --dport ${port} ${EMPTY} + FOR ${index} IN @{index_list} + ${destination} = Collections.Get_From_Dictionary ${ClusterManagement__index_to_ip_mapping} ${index} + ${command} = BuiltIn.Set_Variable sudo /sbin/iptables -I OUTPUT -p ${protocol} ${dport} --source ${source} --destination ${destination} -j DROP + BuiltIn.Run_Keyword_If "${index}" != "${isolate_member_index}" Run_Bash_Command_On_Member command=${command} member_index=${isolate_member_index} + END ${command} = BuiltIn.Set_Variable sudo /sbin/iptables -L -n ${output} = Run_Bash_Command_On_Member command=${command} member_index=${isolate_member_index} BuiltIn.Log ${output} @@ -490,17 +571,20 @@ Isolate_Member_From_List_Or_All [Return] ${updated_index_list} Rejoin_Member_From_List_Or_All - [Arguments] ${rejoin_member_index} ${member_index_list}=${EMPTY} + [Arguments] ${rejoin_member_index} ${member_index_list}=${EMPTY} ${protocol}=all ${port}=${EMPTY} ${timeout}=60s [Documentation] If the list is empty, rejoin member from all ODL instances. Otherwise, rejoin member based on present indices. ${index_list} = List_Indices_Or_All given_list=${member_index_list} ${source} = Collections.Get_From_Dictionary ${ClusterManagement__index_to_ip_mapping} ${rejoin_member_index} - : FOR ${index} IN @{index_list} - \ ${destination} = Collections.Get_From_Dictionary ${ClusterManagement__index_to_ip_mapping} ${index} - \ ${command} = BuiltIn.Set_Variable sudo /sbin/iptables -D OUTPUT -p all --source ${source} --destination ${destination} -j DROP - \ BuiltIn.Run_Keyword_If "${index}" != "${rejoin_member_index}" Run_Bash_Command_On_Member command=${command} member_index=${rejoin_member_index} + ${dport} = BuiltIn.Set_Variable_If '${port}' != '${EMPTY}' --dport ${port} ${EMPTY} + FOR ${index} IN @{index_list} + ${destination} = Collections.Get_From_Dictionary ${ClusterManagement__index_to_ip_mapping} ${index} + ${command} = BuiltIn.Set_Variable sudo /sbin/iptables -D OUTPUT -p ${protocol} ${dport} --source ${source} --destination ${destination} -j DROP + BuiltIn.Run_Keyword_If "${index}" != "${rejoin_member_index}" Run_Bash_Command_On_Member command=${command} member_index=${rejoin_member_index} + END ${command} = BuiltIn.Set_Variable sudo /sbin/iptables -L -n ${output} = Run_Bash_Command_On_Member command=${command} member_index=${rejoin_member_index} BuiltIn.Log ${output} + BuiltIn.Wait_Until_Keyword_Succeeds ${timeout} 10s Check_Cluster_Is_In_Sync Flush_Iptables_From_List_Or_All [Arguments] ${member_index_list}=${EMPTY} @@ -512,9 +596,10 @@ Check_Bash_Command_On_List_Or_All [Arguments] ${command} ${member_index_list}=${EMPTY} ${return_success_only}=False ${log_on_success}=True ${log_on_failure}=True ${stderr_must_be_empty}=True [Documentation] Cycle through indices (or all), run bash command on each, using temporary SSH session and restoring the previously active one. ${index_list} = List_Indices_Or_All given_list=${member_index_list} - : FOR ${index} IN @{index_list} - \ Check_Bash_Command_On_Member command=${command} member_index=${index} return_success_only=${return_success_only} log_on_success=${log_on_success} log_on_failure=${log_on_failure} - \ ... stderr_must_be_empty=${stderr_must_be_empty} + FOR ${index} IN @{index_list} + Check_Bash_Command_On_Member command=${command} member_index=${index} return_success_only=${return_success_only} log_on_success=${log_on_success} log_on_failure=${log_on_failure} + ... stderr_must_be_empty=${stderr_must_be_empty} + END Check_Bash_Command_On_Member [Arguments] ${command} ${member_index} ${return_success_only}=False ${log_on_success}=True ${log_on_failure}=True ${stderr_must_be_empty}=True @@ -534,8 +619,9 @@ Run_Bash_Command_On_List_Or_All [Documentation] Cycle through indices (or all), run command on each. # TODO: Migrate callers to Check_Bash_Command_* ${index_list} = List_Indices_Or_All given_list=${member_index_list} - : FOR ${index} IN @{index_list} - \ Run_Bash_Command_On_Member command=${command} member_index=${index} + FOR ${index} IN @{index_list} + Run_Bash_Command_On_Member command=${command} member_index=${index} + END Run_Bash_Command_On_Member [Arguments] ${command} ${member_index} @@ -543,15 +629,17 @@ Run_Bash_Command_On_Member # TODO: Migrate callers to Check_Bash_Command_* ${member_ip} = Collections.Get_From_Dictionary dictionary=${ClusterManagement__index_to_ip_mapping} key=${member_index} ${output} = SSHKeywords.Run_Keyword_Preserve_Connection Utils.Run_Command_On_Controller ${member_ip} ${command} + Log ${output} [Return] ${output} Run_Karaf_Command_On_List_Or_All [Arguments] ${command} ${member_index_list}=${EMPTY} ${timeout}=10s [Documentation] Cycle through indices (or all), run karaf command on each. ${index_list} = List_Indices_Or_All given_list=${member_index_list} - : FOR ${index} IN @{index_list} - \ ${member_ip} = Collections.Get_From_Dictionary dictionary=${ClusterManagement__index_to_ip_mapping} key=${index} - \ KarafKeywords.Safe_Issue_Command_On_Karaf_Console ${command} ${member_ip} timeout=${timeout} + FOR ${index} IN @{index_list} + ${member_ip} = Collections.Get_From_Dictionary dictionary=${ClusterManagement__index_to_ip_mapping} key=${index} + KarafKeywords.Safe_Issue_Command_On_Karaf_Console ${command} ${member_ip} timeout=${timeout} + END Run_Karaf_Command_On_Member [Arguments] ${command} ${member_index} ${timeout}=10s @@ -566,13 +654,15 @@ Install_Feature_On_List_Or_All [Documentation] Attempt installation on each member from list (or all). Then look for failures. ${index_list} = List_Indices_Or_All given_list=${member_index_list} ${status_list} = BuiltIn.Create_List - : FOR ${index} IN @{index_list} - \ ${status} ${text} = BuiltIn.Run_Keyword_And_Ignore_Error Install_Feature_On_Member feature_name=${feature_name} member_index=${index} - \ ... timeout=${timeout} - \ BuiltIn.Log ${text} - \ Collections.Append_To_List ${status_list} ${status} - : FOR ${status} IN @{status_list} - \ BuiltIn.Run_Keyword_If "${status}" != "PASS" BuiltIn.Fail ${feature_name} installation failed, see log. + FOR ${index} IN @{index_list} + ${status} ${text} = BuiltIn.Run_Keyword_And_Ignore_Error Install_Feature_On_Member feature_name=${feature_name} member_index=${index} + ... timeout=${timeout} + BuiltIn.Log ${text} + Collections.Append_To_List ${status_list} ${status} + END + FOR ${status} IN @{status_list} + BuiltIn.Run_Keyword_If "${status}" != "PASS" BuiltIn.Fail ${feature_name} installation failed, see log. + END Install_Feature_On_Member [Arguments] ${feature_name} ${member_index} ${timeout}=60s @@ -590,9 +680,10 @@ With_Ssh_To_List_Or_All_Run_Keyword # TODO: For_Index_From_List_Or_All_Run_Keyword applied to With_Ssh_To_Member_Run_Keyword? # TODO: Imagine another keyword, using ScalarClosures and adding member index as first argument for each call. Worth it? ${index_list} = List_Indices_Or_All given_list=${member_index_list} - : FOR ${member_index} IN @{index_list} - \ ${member_ip} = Resolve_IP_Address_For_Member ${member_index} - \ SSHKeywords.Run_Unsafely_Keyword_Over_Temporary_Odl_Session ${member_ip} ${keyword_name} @{args} &{kwargs} + FOR ${member_index} IN @{index_list} + ${member_ip} = Resolve_IP_Address_For_Member ${member_index} + SSHKeywords.Run_Unsafely_Keyword_Over_Temporary_Odl_Session ${member_ip} ${keyword_name} @{args} &{kwargs} + END Safe_With_Ssh_To_List_Or_All_Run_Keyword [Arguments] ${member_index_list} ${keyword_name} @{args} &{kwargs} @@ -622,8 +713,9 @@ Restore_Karaf_Log_On_List_Or_All ClusterManagement__Clean_Directories [Arguments] ${relative_path_list} ${karaf_home} [Documentation] For each relative path, remove files with respect to ${karaf_home}. Return None. - : FOR ${relative_path} IN @{relative_path_list} - \ SSHLibrary.Execute_Command rm -rf ${karaf_home}${/}${relative_path} + FOR ${relative_path} IN @{relative_path_list} + SSHLibrary.Execute_Command rm -rf ${karaf_home}${/}${relative_path} + END Put_As_Json_And_Check_Member_List_Or_All [Arguments] ${uri} ${data} ${member_index} ${member_index_list}=${EMPTY} @@ -667,27 +759,30 @@ Check_Json_Member_List_Or_All [Documentation] Send a GET with the supplied uri to all or some members defined in ${member_index_list}. ... Then check received data is = ${expected data}. ${index_list} = List_Indices_Or_All given_list=${member_index_list} - : FOR ${index} IN @{index_list} - \ ${data} = Get_From_Member uri=${uri} member_index=${index} - \ TemplatedRequests.Normalize_Jsons_And_Compare ${expected_data} ${data} + FOR ${index} IN @{index_list} + ${data} = Get_From_Member uri=${uri} member_index=${index} + TemplatedRequests.Normalize_Jsons_And_Compare ${expected_data} ${data} + END Check_Item_Occurrence_Member_List_Or_All [Arguments] ${uri} ${dictionary} ${member_index_list}=${EMPTY} [Documentation] Send a GET with the supplied uri to all or some members defined in ${member_index_list}. ... Then check received for occurrences of items expressed in a dictionary ${dictionary}. ${index_list} = List_Indices_Or_All given_list=${member_index_list} - : FOR ${index} IN @{index_list} - \ ${data} = Get_From_Member uri=${uri} member_index=${index} - \ Utils.Check Item Occurrence ${data} ${dictionary} + FOR ${index} IN @{index_list} + ${data} = Get_From_Member uri=${uri} member_index=${index} + Utils.Check Item Occurrence ${data} ${dictionary} + END Check_No_Content_Member_List_Or_All [Arguments] ${uri} ${member_index_list}=${EMPTY} [Documentation] Send a GET with the supplied uri to all or some members defined in ${member_index_list}. ... Then check there is no content. ${index_list} = List_Indices_Or_All given_list=${member_index_list} - : FOR ${index} IN @{index_list} - \ ${session} = Resolve_Http_Session_For_Member member_index=${index} - \ Utils.No_Content_From_URI ${session} ${uri} + FOR ${index} IN @{index_list} + ${session} = Resolve_Http_Session_For_Member member_index=${index} + Utils.No_Content_From_URI ${session} ${uri} + END Get_From_Member [Arguments] ${uri} ${member_index} ${access}=${ACCEPT_EMPTY} @@ -706,9 +801,10 @@ Resolve_IP_Address_For_Members [Arguments] ${member_index_list} [Documentation] Return a list of IP address of given indexes. ${member_ip_list} = BuiltIn.Create_List - : FOR ${index} IN @{member_index_list} - \ ${ip_address} = Collections.Get From Dictionary dictionary=${ClusterManagement__index_to_ip_mapping} key=${index} - \ Collections.Append_To_List ${member_ip_list} ${ip_address} + FOR ${index} IN @{member_index_list} + ${ip_address} = Collections.Get From Dictionary dictionary=${ClusterManagement__index_to_ip_mapping} key=${index} + Collections.Append_To_List ${member_ip_list} ${ip_address} + END [Return] ${member_ip_list} Resolve_Http_Session_For_Member @@ -761,20 +857,21 @@ List_Indices_Minus_Member [Return] ${index_list} ClusterManagement__Compute_Derived_Variables - [Arguments] ${int_of_members} ${http_timeout}=1 ${http_retries}=0 + [Arguments] ${int_of_members} ${http_timeout}=${DEFAULT_TIMEOUT_HTTP} ${http_retries}=0 [Documentation] Construct index list, session list and IP mapping, publish them as suite variables. @{member_index_list} = BuiltIn.Create_List @{session_list} = BuiltIn.Create_List &{index_to_ip_mapping} = BuiltIn.Create_Dictionary - : FOR ${index} IN RANGE 1 ${int_of_members+1} - \ ClusterManagement__Include_Member_Index ${index} ${member_index_list} ${session_list} ${index_to_ip_mapping} http_timeout=${http_timeout} - \ ... http_retries=${http_retries} + FOR ${index} IN RANGE 1 ${int_of_members+1} + ClusterManagement__Include_Member_Index ${index} ${member_index_list} ${session_list} ${index_to_ip_mapping} http_timeout=${http_timeout} + ... http_retries=${http_retries} + END BuiltIn.Set_Suite_Variable \${ClusterManagement__member_index_list} ${member_index_list} BuiltIn.Set_Suite_Variable \${ClusterManagement__index_to_ip_mapping} ${index_to_ip_mapping} BuiltIn.Set_Suite_Variable \${ClusterManagement__session_list} ${session_list} ClusterManagement__Include_Member_Index - [Arguments] ${index} ${member_index_list} ${session_list} ${index_to_ip_mapping} ${http_timeout}=1 ${http_retries}=0 + [Arguments] ${index} ${member_index_list} ${session_list} ${index_to_ip_mapping} ${http_timeout}=${DEFAULT_TIMEOUT_HTTP} ${http_retries}=0 [Documentation] Add a corresponding item based on index into the last three arguments. ... Create the Http session whose alias is added to list. Collections.Append_To_List ${member_index_list} ${index} @@ -804,3 +901,20 @@ Return_Member_IP ${member_int} = BuiltIn.Convert_To_Integer ${member_index} ${member_ip} = Collections.Get_From_Dictionary dictionary=${ClusterManagement__index_to_ip_mapping} key=${member_int} [Return] ${member_ip} + +Check Service Status + [Arguments] ${odl_ip} ${system_ready_state} ${service_state} @{service_list} + [Documentation] Issues the karaf shell command showSvcStatus to verify the ready and service states are the same as the arguments passed + ${service_status_output} = BuiltIn.Run Keyword If ${NUM_ODL_SYSTEM} > 1 KarafKeywords.Issue_Command_On_Karaf_Console showSvcStatus -n ${odl_ip} ${odl_ip} ${KARAF_SHELL_PORT} + ... ELSE KarafKeywords.Issue_Command_On_Karaf_Console showSvcStatus ${odl_ip} ${KARAF_SHELL_PORT} + BuiltIn.Should Contain ${service_status_output} ${system_ready_state} + FOR ${service} IN @{service_list} + BuiltIn.Should Match Regexp ${service_status_output} ${service} +: ${service_state} + END + +Check Status Of Services Is OPERATIONAL + [Arguments] @{service_list} + [Documentation] This keyword will verify whether all the services are operational in all the ODL nodes + FOR ${i} IN RANGE ${NUM_ODL_SYSTEM} + ClusterManagement.Check Service Status ${ODL_SYSTEM_${i+1}_IP} ACTIVE OPERATIONAL @{service_list} + END