Uploaded image for project: 'Mesos'
  1. Mesos
  2. MESOS-7562

MasterTest.IgnoreOldAgentReregistration is flaky

    XMLWordPrintableJSON

Details

    Description

      [ RUN      ] MasterTest.IgnoreOldAgentReregistration
      I0524 16:29:07.143152 29236 cluster.cpp:162] Creating default 'local' authorizer
      I0524 16:29:07.149690 29287 master.cpp:436] Master 3912ae61-36a4-468c-bef5-82f082370f3d (core-dev) started on 10.0.49.2:42980
      I0524 16:29:07.149724 29287 master.cpp:438] Flags at startup: --acls="" --agent_ping_timeout="15secs" --agent_reregister_timeout="10mins" --allocation_interval="1secs" --allocator="HierarchicalDRF" --authenticate_agents="true" --authenticate_frameworks="true" --authenticate_http_frameworks="true" --authenticate_http_readonly="true" --authenticate_http_readwrite="true" --authenticators="crammd5" --authorizers="local" --credentials="/tmp/gg4ie7/credentials" --framework_sorter="drf" --help="false" --hostname_lookup="true" --http_authenticators="basic" --http_framework_authenticators="basic" --initialize_driver_logging="true" --log_auto_initialize="true" --logbufsecs="0" --logging_level="INFO" --max_agent_ping_timeouts="5" --max_completed_frameworks="50" --max_completed_tasks_per_framework="1000" --max_unreachable_tasks_per_framework="1000" --port="5050" --quiet="false" --recovery_agent_removal_limit="100%" --registry="in_memory" --registry_fetch_timeout="1mins" --registry_gc_interval="15mins" --registry_max_agent_age="2weeks" --registry_max_agent_count="102400" --registry_store_timeout="100secs" --registry_strict="false" --root_submissions="true" --user_sorter="drf" --version="false" --webui_dir="/usr/local/share/mesos/webui" --work_dir="/tmp/gg4ie7/master" --zk_session_timeout="10secs"
      I0524 16:29:07.149896 29287 master.cpp:488] Master only allowing authenticated frameworks to register
      I0524 16:29:07.149905 29287 master.cpp:502] Master only allowing authenticated agents to register
      I0524 16:29:07.149912 29287 master.cpp:515] Master only allowing authenticated HTTP frameworks to register
      I0524 16:29:07.149920 29287 credentials.hpp:37] Loading credentials for authentication from '/tmp/gg4ie7/credentials'
      I0524 16:29:07.150065 29287 master.cpp:560] Using default 'crammd5' authenticator
      I0524 16:29:07.150133 29287 http.cpp:975] Creating default 'basic' HTTP authenticator for realm 'mesos-master-readonly'
      I0524 16:29:07.150168 29287 http.cpp:975] Creating default 'basic' HTTP authenticator for realm 'mesos-master-readwrite'
      I0524 16:29:07.150223 29287 http.cpp:975] Creating default 'basic' HTTP authenticator for realm 'mesos-master-scheduler'
      I0524 16:29:07.150259 29287 master.cpp:640] Authorization enabled
      I0524 16:29:07.151617 29274 master.cpp:2161] Elected as the leading master!
      I0524 16:29:07.151644 29274 master.cpp:1700] Recovering from registrar
      I0524 16:29:07.152218 29261 registrar.cpp:389] Successfully fetched the registry (0B) in 505088ns
      I0524 16:29:07.152268 29261 registrar.cpp:493] Applied 1 operations in 4200ns; attempting to update the registry
      I0524 16:29:07.152664 29261 registrar.cpp:550] Successfully updated the registry in 371200ns
      I0524 16:29:07.152703 29261 registrar.cpp:422] Successfully recovered registrar
      I0524 16:29:07.153328 29291 master.cpp:1799] Recovered 0 agents from the registry (119B); allowing 10mins for agents to re-register
      I0524 16:29:07.160094 29236 containerizer.cpp:230] Using isolation: posix/cpu,posix/mem,filesystem/posix,network/cni,environment_secret
      W0524 16:29:07.160295 29236 backend.cpp:76] Failed to create 'overlay' backend: OverlayBackend requires root privileges
      W0524 16:29:07.160326 29236 backend.cpp:76] Failed to create 'bind' backend: BindBackend requires root privileges
      I0524 16:29:07.160334 29236 provisioner.cpp:255] Using default backend 'copy'
      I0524 16:29:07.161916 29236 cluster.cpp:448] Creating default 'local' authorizer
      I0524 16:29:07.162616 29276 slave.cpp:225] Mesos agent started on (7738)@10.0.49.2:42980
      I0524 16:29:07.162644 29276 slave.cpp:226] Flags at startup: --acls="" --appc_simple_discovery_uri_prefix="http://" --appc_store_dir="/tmp/mesos/store/appc" --authenticate_http_readonly="true" --authenticate_http_readwrite="true" --authenticatee="crammd5" --authentication_backoff_factor="1secs" --authorizer="local" --cgroups_cpu_enable_pids_and_tids_count="false" --cgroups_enable_cfs="false" --cgroups_hierarchy="/sys/fs/cgroup" --cgroups_limit_swap="false" --cgroups_root="mesos" --container_disk_watch_interval="15secs" --containerizers="mesos" --credential="/tmp/MasterTest_IgnoreOldAgentReregistration_WX8CZz/credential" --default_role="*" --disk_watch_interval="1mins" --docker="docker" --docker_kill_orphans="true" --docker_registry="https://registry-1.docker.io" --docker_remove_delay="6hrs" --docker_socket="/var/run/docker.sock" --docker_stop_timeout="0ns" --docker_store_dir="/tmp/mesos/store/docker" --docker_volume_checkpoint_dir="/var/run/mesos/isolators/docker/volume" --enforce_container_disk_quota="false" --executor_registration_timeout="1mins" --executor_reregistration_timeout="2secs" --executor_shutdown_grace_period="5secs" --fetcher_cache_dir="/tmp/MasterTest_IgnoreOldAgentReregistration_WX8CZz/fetch" --fetcher_cache_size="2GB" --frameworks_home="" --gc_delay="1weeks" --gc_disk_headroom="0.1" --hadoop_home="" --help="false" --hostname_lookup="true" --http_command_executor="false" --http_credentials="/tmp/MasterTest_IgnoreOldAgentReregistration_WX8CZz/http_credentials" --http_heartbeat_interval="30secs" --initialize_driver_logging="true" --isolation="posix/cpu,posix/mem" --launcher="posix" --launcher_dir="/home/nrc/build-mesos-opt/src" --logbufsecs="0" --logging_level="INFO" --max_completed_executors_per_framework="150" --oversubscribed_resources_interval="15secs" --perf_duration="10secs" --perf_interval="1mins" --port="5051" --qos_correction_interval_min="0ns" --quiet="false" --recover="reconnect" --recovery_timeout="15mins" --registration_backoff_factor="10ms" --resources="cpus:2;gpus:0;mem:1024;disk:1024;ports:[31000-32000]" --revocable_cpu_low_priority="true" --runtime_dir="/tmp/MasterTest_IgnoreOldAgentReregistration_WX8CZz" --sandbox_directory="/mnt/mesos/sandbox" --strict="true" --switch_user="true" --systemd_enable_support="true" --systemd_runtime_directory="/run/systemd/system" --version="false" --work_dir="/tmp/MasterTest_IgnoreOldAgentReregistration_iBMXBQ"
      I0524 16:29:07.162876 29276 credentials.hpp:86] Loading credential for authentication from '/tmp/MasterTest_IgnoreOldAgentReregistration_WX8CZz/credential'
      I0524 16:29:07.162966 29276 slave.cpp:258] Agent using credential for: test-principal
      I0524 16:29:07.162979 29276 credentials.hpp:37] Loading credentials for authentication from '/tmp/MasterTest_IgnoreOldAgentReregistration_WX8CZz/http_credentials'
      I0524 16:29:07.163080 29276 http.cpp:975] Creating default 'basic' HTTP authenticator for realm 'mesos-agent-readonly'
      I0524 16:29:07.163144 29276 http.cpp:975] Creating default 'basic' HTTP authenticator for realm 'mesos-agent-readwrite'
      I0524 16:29:07.169524 29276 slave.cpp:529] Agent resources: cpus(*):2; mem(*):1024; disk(*):1024; ports(*):[31000-32000]
      I0524 16:29:07.169559 29276 slave.cpp:537] Agent attributes: [  ]
      I0524 16:29:07.169564 29276 slave.cpp:542] Agent hostname: core-dev
      I0524 16:29:07.169639 29261 status_update_manager.cpp:177] Pausing sending status updates
      I0524 16:29:07.169818 29288 state.cpp:62] Recovering state from '/tmp/MasterTest_IgnoreOldAgentReregistration_iBMXBQ/meta'
      I0524 16:29:07.169981 29287 status_update_manager.cpp:203] Recovering status update manager
      I0524 16:29:07.170370 29253 containerizer.cpp:629] Recovering containerizer
      I0524 16:29:07.171176 29279 provisioner.cpp:416] Provisioner recovery complete
      I0524 16:29:07.171342 29263 slave.cpp:5976] Finished recovery
      I0524 16:29:07.171893 29293 status_update_manager.cpp:177] Pausing sending status updates
      I0524 16:29:07.171903 29250 slave.cpp:922] New master detected at master@10.0.49.2:42980
      I0524 16:29:07.171949 29250 slave.cpp:957] Detecting new master
      I0524 16:29:07.180215 29275 slave.cpp:984] Authenticating with master master@10.0.49.2:42980
      I0524 16:29:07.180270 29275 slave.cpp:995] Using default CRAM-MD5 authenticatee
      I0524 16:29:07.180339 29287 authenticatee.cpp:121] Creating new client SASL connection
      W0524 16:29:12.180481 29263 slave.cpp:1098] Authentication timed out
      I0524 16:29:17.192945 29263 master.cpp:7487] Authenticating slave(7738)@10.0.49.2:42980
      W0524 16:29:17.192967 29287 slave.cpp:1043] Failed to authenticate with master master@10.0.49.2:42980: Authentication discarded
      W0524 16:29:17.193591 29251 master.cpp:7514] Failed to authenticate slave(7738)@10.0.49.2:42980: Failed to communicate with authenticatee
      I0524 16:29:18.729748 29251 slave.cpp:984] Authenticating with master master@10.0.49.2:42980
      I0524 16:29:18.729786 29251 slave.cpp:995] Using default CRAM-MD5 authenticatee
      I0524 16:29:18.729869 29259 authenticatee.cpp:121] Creating new client SASL connection
      I0524 16:29:18.745004 29259 master.cpp:7487] Authenticating slave(7738)@10.0.49.2:42980
      I0524 16:29:18.745142 29265 authenticator.cpp:98] Creating new server SASL connection
      ../../mesos/src/tests/master_tests.cpp:7070: Failure
      Failed to wait 15secs for slaveRegisteredMessage
      *** Aborted at 1495668562 (unix time) try "date -d @1495668562" if you are using GNU date ***
      PC: @          0x15aefb0 testing::UnitTest::AddTestPartResult()
      *** SIGSEGV (@0x0) received by PID 29236 (TID 0x7f886f7438c0) from PID 0; stack trace: ***
          @     0x7f886b614370 (unknown)
          @          0x15aefb0 testing::UnitTest::AddTestPartResult()
          @          0x15af330 testing::internal::AssertHelper::operator=()
          @           0xd0b190 mesos::internal::tests::MasterTest_IgnoreOldAgentReregistration_Test::TestBody()
          @          0x15bb513 testing::internal::HandleExceptionsInMethodIfSupported<>()
          @          0x15b0557 testing::Test::Run()
          @          0x15b05fe testing::TestInfo::Run()
          @          0x15b0705 testing::TestCase::Run()
          @          0x15b09b8 testing::internal::UnitTestImpl::RunAllTests()
          @          0x15b0c64 testing::UnitTest::Run()
          @           0x554f37 main
          @     0x7f886a422b35 __libc_start_main
          @           0x594961 (unknown)
      

      Attachments

        Issue Links

          Activity

            People

              neilc Neil Conway
              neilc Neil Conway
              Votes:
              0 Vote for this issue
              Watchers:
              2 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: