[
https://issues.apache.org/jira/browse/MESOS-6481?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16963011#comment-16963011
]
Andrei Sekretenko commented on MESOS-6481:
------------------------------------------
Observed a similar failure in tests of 1.7 branch in internal CI:
{code}
[ RUN ] MesosContainerizerSlaveRecoveryTest.ResourceStatistics
I1029 18:20:19.150781 32254 cluster.cpp:173] Creating default 'local' authorizer
I1029 18:20:19.153787 32255 master.cpp:441] Master
17736b02-db5b-40bb-ac46-32abffc4ecec (ip-172-16-10-116.ec2.internal) started on
172.16.10.116:44212
I1029 18:20:19.153808 32255 master.cpp:444] Flags at startup: --acls=""
--agent_ping_timeout="15secs" --agent_reregister_timeout="10mins"
--allocation_interval="1secs" --allocator="hierarchical"
--authenticate_agents="true" --authenticate_frameworks="true"
--authenticate_http_frameworks="true" --authenticate_http_readonly="true"
--authenticate_http_readwrite="true" --authentication_v0_timeout="15secs"
--authenticators="crammd5" --authorizers="local"
--credentials="/tmp/bOwSpZ/credentials" --filter_gpu_resources="true"
--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" --memory_profiling="false"
--min_allocatable_resources="cpus:0.01|mem:32" --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"
--require_agent_domain="false" --role_sorter="drf" --root_submissions="true"
--version="false" --webui_dir="/usr/local/share/mesos/webui"
--work_dir="/tmp/bOwSpZ/master" --zk_session_timeout="10secs"
I1029 18:20:19.154145 32255 master.cpp:493] Master only allowing authenticated
frameworks to register
I1029 18:20:19.154155 32255 master.cpp:499] Master only allowing authenticated
agents to register
I1029 18:20:19.154160 32255 master.cpp:505] Master only allowing authenticated
HTTP frameworks to register
I1029 18:20:19.154167 32255 credentials.hpp:37] Loading credentials for
authentication from '/tmp/bOwSpZ/credentials'
I1029 18:20:19.154376 32255 master.cpp:549] Using default 'crammd5'
authenticator
I1029 18:20:19.154554 32255 http.cpp:977] Creating default 'basic' HTTP
authenticator for realm 'mesos-master-readonly'
I1029 18:20:19.154726 32255 http.cpp:977] Creating default 'basic' HTTP
authenticator for realm 'mesos-master-readwrite'
I1029 18:20:19.154858 32255 http.cpp:977] Creating default 'basic' HTTP
authenticator for realm 'mesos-master-scheduler'
I1029 18:20:19.154986 32255 master.cpp:630] Authorization enabled
I1029 18:20:19.155378 32257 hierarchical.cpp:218] Initialized hierarchical
allocator process
I1029 18:20:19.155542 32257 whitelist_watcher.cpp:77] No whitelist given
I1029 18:20:19.157781 32255 master.cpp:2165] Elected as the leading master!
I1029 18:20:19.157809 32255 master.cpp:1688] Recovering from registrar
I1029 18:20:19.158134 32255 registrar.cpp:339] Recovering registrar
I1029 18:20:19.158830 32255 registrar.cpp:383] Successfully fetched the
registry (0B) in 661248ns
I1029 18:20:19.158967 32255 registrar.cpp:487] Applied 1 operations in 41723ns;
attempting to update the registry
I1029 18:20:19.159968 32258 registrar.cpp:544] Successfully updated the
registry in 948224ns
I1029 18:20:19.160099 32258 registrar.cpp:416] Successfully recovered registrar
I1029 18:20:19.160521 32260 master.cpp:1814] Recovered 0 agents from the
registry (176B); allowing 10mins for agents to reregister
I1029 18:20:19.160600 32258 hierarchical.cpp:256] Skipping recovery of
hierarchical allocator: nothing to recover
I1029 18:20:19.163169 32254 containerizer.cpp:309] Using isolation {
cgroups/cpu, filesystem/posix, environment_secret, cgroups/mem, network/cni }
I1029 18:20:19.168272 32254 linux_launcher.cpp:144] Using
/sys/fs/cgroup/freezer as the freezer hierarchy for the Linux launcher
I1029 18:20:19.169111 32254 provisioner.cpp:292] Using default backend 'copy'
W1029 18:20:19.187597 32254 process.cpp:2829] Attempted to spawn already
running process [email protected]:44212
I1029 18:20:19.188158 32254 cluster.cpp:485] Creating default 'local' authorizer
W1029 18:20:19.190341 32254 process.cpp:2829] Attempted to spawn already
running process [email protected]:44212
I1029 18:20:19.190788 32259 slave.cpp:261] Mesos agent started on
(332)@172.16.10.116:44212
I1029 18:20:19.190804 32259 slave.cpp:262] Flags at startup: --acls=""
--appc_simple_discovery_uri_prefix="http://";
--appc_store_dir="/tmp/bOwSpZ/4numNO/store/appc"
--authenticate_http_readonly="true" --authenticate_http_readwrite="false"
--authenticatee="crammd5" --authentication_backoff_factor="1secs"
--authentication_timeout_max="1mins" --authentication_timeout_min="5secs"
--authorizer="local" --cgroups_cpu_enable_pids_and_tids_count="false"
--cgroups_destroy_timeout="1mins" --cgroups_enable_cfs="false"
--cgroups_hierarchy="/sys/fs/cgroup" --cgroups_limit_swap="false"
--cgroups_root="mesos_test_82c37294-024f-4d12-a359-c842c5dddd23"
--container_disk_watch_interval="15secs" --containerizers="mesos"
--credential="/tmp/bOwSpZ/4numNO/credential" --default_role="*"
--disallow_sharing_agent_pid_namespace="false" --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/bOwSpZ/4numNO/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/bOwSpZ/4numNO/fetch" --fetcher_cache_size="2GB"
--fetcher_stall_timeout="1mins" --frameworks_home="" --gc_delay="1weeks"
--gc_disk_headroom="0.1" --gc_non_executor_container_sandboxes="false"
--help="false" --hostname_lookup="true" --http_command_executor="false"
--http_credentials="/tmp/bOwSpZ/4numNO/http_credentials"
--http_heartbeat_interval="30secs" --initialize_driver_logging="true"
--isolation="cgroups/cpu,cgroups/mem" --launcher="linux"
--launcher_dir="/home/centos/workspace/mesos/Mesos_CI-build/FLAG/CMake/label/mesos-ec2-centos-7/mesos/build/src"
--logbufsecs="0" --logging_level="INFO"
--max_completed_executors_per_framework="150" --memory_profiling="false"
--network_cni_metrics="true" --network_cni_root_dir_persist="false"
--oversubscribed_resources_interval="15secs" --perf_duration="10secs"
--perf_interval="1mins" --port="5051" --qos_correction_interval_min="0ns"
--quiet="false" --reconfiguration_policy="equal" --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/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_MMTb0c"
--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/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB"
--zk_session_timeout="10secs"
I1029 18:20:19.191210 32259 credentials.hpp:86] Loading credential for
authentication from '/tmp/bOwSpZ/4numNO/credential'
I1029 18:20:19.191331 32259 slave.cpp:294] Agent using credential for:
test-principal
I1029 18:20:19.191345 32259 credentials.hpp:37] Loading credentials for
authentication from '/tmp/bOwSpZ/4numNO/http_credentials'
I1029 18:20:19.191515 32259 http.cpp:977] Creating default 'basic' HTTP
authenticator for realm 'mesos-agent-readonly'
I1029 18:20:19.191808 32259 disk_profile_adaptor.cpp:80] Creating default disk
profile adaptor module
I1029 18:20:19.192065 32254 sched.cpp:232] Version: 1.7.3
I1029 18:20:19.193575 32260 sched.cpp:336] New master detected at
[email protected]:44212
I1029 18:20:19.193420 32259 slave.cpp:609] Agent resources:
[{"name":"cpus","scalar":{"value":2.0},"type":"SCALAR"},{"name":"mem","scalar":{"value":1024.0},"type":"SCALAR"},{"name":"disk","scalar":{"value":1024.0},"type":"SCALAR"},{"name":"ports","ranges":{"range":[{"begin":31000,"end":32000}]},"type":"RANGES"}]
I1029 18:20:19.193603 32259 slave.cpp:617] Agent attributes: [ ]
I1029 18:20:19.193614 32259 slave.cpp:626] Agent hostname:
ip-172-16-10-116.ec2.internal
I1029 18:20:19.193681 32260 sched.cpp:401] Authenticating with master
[email protected]:44212
I1029 18:20:19.193694 32260 sched.cpp:408] Using default CRAM-MD5 authenticatee
I1029 18:20:19.194157 32260 task_status_update_manager.cpp:181] Pausing sending
task status updates
I1029 18:20:19.194298 32260 authenticatee.cpp:121] Creating new client SASL
connection
I1029 18:20:19.194972 32262 master.cpp:9889] Authenticating
[email protected]:44212
I1029 18:20:19.195161 32262 authenticator.cpp:414] Starting authentication
session for crammd5-authenticatee(646)@172.16.10.116:44212
I1029 18:20:19.195492 32262 authenticator.cpp:98] Creating new server SASL
connection
I1029 18:20:19.195663 32262 authenticatee.cpp:213] Received SASL authentication
mechanisms: CRAM-MD5
I1029 18:20:19.195678 32262 authenticatee.cpp:239] Attempting to authenticate
with mechanism 'CRAM-MD5'
I1029 18:20:19.195745 32262 authenticator.cpp:204] Received SASL authentication
start
I1029 18:20:19.195777 32262 authenticator.cpp:326] Authentication requires more
steps
I1029 18:20:19.195835 32262 authenticatee.cpp:259] Received SASL authentication
step
I1029 18:20:19.195917 32262 authenticator.cpp:232] Received SASL authentication
step
I1029 18:20:19.195940 32262 auxprop.cpp:109] Request to lookup properties for
user: 'test-principal' realm: 'ip-172-16-10-116.ec2.internal' server FQDN:
'ip-172-16-10-116.ec2.internal' SASL_AUXPROP_VERIFY_AGAINST_HASH: false
SASL_AUXPROP_OVERRIDE: false SASL_AUXPROP_AUTHZID: false
I1029 18:20:19.195950 32262 auxprop.cpp:181] Looking up auxiliary property
'*userPassword'
I1029 18:20:19.195991 32262 auxprop.cpp:181] Looking up auxiliary property
'*cmusaslsecretCRAM-MD5'
I1029 18:20:19.196008 32262 auxprop.cpp:109] Request to lookup properties for
user: 'test-principal' realm: 'ip-172-16-10-116.ec2.internal' server FQDN:
'ip-172-16-10-116.ec2.internal' SASL_AUXPROP_VERIFY_AGAINST_HASH: false
SASL_AUXPROP_OVERRIDE: false SASL_AUXPROP_AUTHZID: true
I1029 18:20:19.196018 32262 auxprop.cpp:131] Skipping auxiliary property
'*userPassword' since SASL_AUXPROP_AUTHZID == true
I1029 18:20:19.196024 32262 auxprop.cpp:131] Skipping auxiliary property
'*cmusaslsecretCRAM-MD5' since SASL_AUXPROP_AUTHZID == true
I1029 18:20:19.196038 32262 authenticator.cpp:318] Authentication success
I1029 18:20:19.196228 32262 authenticatee.cpp:299] Authentication success
I1029 18:20:19.196421 32262 master.cpp:9921] Successfully authenticated
principal 'test-principal' at
[email protected]:44212
I1029 18:20:19.196696 32260 sched.cpp:513] Successfully authenticated with
master [email protected]:44212
I1029 18:20:19.196713 32260 sched.cpp:817] Sending SUBSCRIBE call to
[email protected]:44212
I1029 18:20:19.196816 32260 sched.cpp:850] Will retry registration in
88.148192ms if necessary
I1029 18:20:19.197057 32256 master.cpp:2941] Received SUBSCRIBE call for
framework 'default' at
[email protected]:44212
I1029 18:20:19.197134 32256 master.cpp:2237] Authorizing framework principal
'test-principal' to receive offers for roles '{ * }'
I1029 18:20:19.197809 32255 state.cpp:66] Recovering state from
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/meta'
I1029 18:20:19.197995 32259 master.cpp:3022] Subscribing framework default with
checkpointing enabled and capabilities [ MULTI_ROLE, RESERVATION_REFINEMENT ]
I1029 18:20:19.198079 32255 slave.cpp:6976] Finished recovering checkpointed
state from
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/meta',
beginning agent recovery
I1029 18:20:19.198232 32255 task_status_update_manager.cpp:207] Recovering task
status update manager
I1029 18:20:19.199707 32259 master.cpp:10119] Adding framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000 (default) at
[email protected]:44212 with roles {
} suppressed
I1029 18:20:19.200430 32259 sched.cpp:744] Framework registered with
17736b02-db5b-40bb-ac46-32abffc4ecec-0000
I1029 18:20:19.200479 32259 sched.cpp:758] Scheduler::registered took 27582ns
I1029 18:20:19.200719 32258 containerizer.cpp:764] Recovering Mesos containers
I1029 18:20:19.200964 32258 linux_launcher.cpp:286] Recovering Linux launcher
I1029 18:20:19.201254 32260 hierarchical.cpp:342] Added framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000
I1029 18:20:19.201333 32258 containerizer.cpp:1090] Recovering isolators
I1029 18:20:19.201465 32260 hierarchical.cpp:1566] Performed allocation for 0
agents in 81224ns
I1029 18:20:19.202486 32262 authenticator.cpp:432] Authentication session
cleanup for crammd5-authenticatee(646)@172.16.10.116:44212
I1029 18:20:19.202764 32260 containerizer.cpp:1129] Recovering provisioner
I1029 18:20:19.203372 32256 provisioner.cpp:516] Provisioner recovery complete
I1029 18:20:19.203969 32260 composing.cpp:339] Finished recovering all
containerizers
I1029 18:20:19.204208 32260 slave.cpp:7205] Recovering executors
I1029 18:20:19.204308 32260 slave.cpp:7358] Finished recovery
I1029 18:20:19.205004 32262 slave.cpp:1269] New master detected at
[email protected]:44212
I1029 18:20:19.205054 32257 task_status_update_manager.cpp:181] Pausing sending
task status updates
I1029 18:20:19.205104 32262 slave.cpp:1334] Detecting new master
I1029 18:20:19.214965 32257 slave.cpp:1361] Authenticating with master
[email protected]:44212
I1029 18:20:19.215045 32257 slave.cpp:1370] Using default CRAM-MD5 authenticatee
I1029 18:20:19.215420 32257 authenticatee.cpp:121] Creating new client SASL
connection
I1029 18:20:19.215628 32257 master.cpp:9889] Authenticating
slave(332)@172.16.10.116:44212
I1029 18:20:19.215811 32257 authenticator.cpp:414] Starting authentication
session for crammd5-authenticatee(647)@172.16.10.116:44212
I1029 18:20:19.216172 32257 authenticator.cpp:98] Creating new server SASL
connection
I1029 18:20:19.216387 32257 authenticatee.cpp:213] Received SASL authentication
mechanisms: CRAM-MD5
I1029 18:20:19.216404 32257 authenticatee.cpp:239] Attempting to authenticate
with mechanism 'CRAM-MD5'
I1029 18:20:19.216498 32257 authenticator.cpp:204] Received SASL authentication
start
I1029 18:20:19.216537 32257 authenticator.cpp:326] Authentication requires more
steps
I1029 18:20:19.216619 32257 authenticatee.cpp:259] Received SASL authentication
step
I1029 18:20:19.216698 32257 authenticator.cpp:232] Received SASL authentication
step
I1029 18:20:19.216719 32257 auxprop.cpp:109] Request to lookup properties for
user: 'test-principal' realm: 'ip-172-16-10-116.ec2.internal' server FQDN:
'ip-172-16-10-116.ec2.internal' SASL_AUXPROP_VERIFY_AGAINST_HASH: false
SASL_AUXPROP_OVERRIDE: false SASL_AUXPROP_AUTHZID: false
I1029 18:20:19.216729 32257 auxprop.cpp:181] Looking up auxiliary property
'*userPassword'
I1029 18:20:19.216768 32257 auxprop.cpp:181] Looking up auxiliary property
'*cmusaslsecretCRAM-MD5'
I1029 18:20:19.216785 32257 auxprop.cpp:109] Request to lookup properties for
user: 'test-principal' realm: 'ip-172-16-10-116.ec2.internal' server FQDN:
'ip-172-16-10-116.ec2.internal' SASL_AUXPROP_VERIFY_AGAINST_HASH: false
SASL_AUXPROP_OVERRIDE: false SASL_AUXPROP_AUTHZID: true
I1029 18:20:19.216794 32257 auxprop.cpp:131] Skipping auxiliary property
'*userPassword' since SASL_AUXPROP_AUTHZID == true
I1029 18:20:19.216799 32257 auxprop.cpp:131] Skipping auxiliary property
'*cmusaslsecretCRAM-MD5' since SASL_AUXPROP_AUTHZID == true
I1029 18:20:19.216809 32257 authenticator.cpp:318] Authentication success
I1029 18:20:19.216996 32258 authenticatee.cpp:299] Authentication success
I1029 18:20:19.217052 32257 master.cpp:9921] Successfully authenticated
principal 'test-principal' at slave(332)@172.16.10.116:44212
I1029 18:20:19.217144 32257 authenticator.cpp:432] Authentication session
cleanup for crammd5-authenticatee(647)@172.16.10.116:44212
I1029 18:20:19.217666 32258 slave.cpp:1461] Successfully authenticated with
master [email protected]:44212
I1029 18:20:19.218066 32258 slave.cpp:1892] Will retry registration in
16.273791ms if necessary
I1029 18:20:19.218232 32260 master.cpp:6740] Received register agent message
from slave(332)@172.16.10.116:44212 (ip-172-16-10-116.ec2.internal)
I1029 18:20:19.218441 32260 master.cpp:3998] Authorizing agent providing
resources 'cpus:2; mem:1024; disk:1024; ports:[31000-32000]' with principal
'test-principal'
I1029 18:20:19.218955 32256 master.cpp:6807] Authorized registration of agent
at slave(332)@172.16.10.116:44212 (ip-172-16-10-116.ec2.internal)
I1029 18:20:19.219040 32256 master.cpp:6922] Registering agent at
slave(332)@172.16.10.116:44212 (ip-172-16-10-116.ec2.internal) with id
17736b02-db5b-40bb-ac46-32abffc4ecec-S0
I1029 18:20:19.219599 32260 registrar.cpp:487] Applied 1 operations in
142487ns; attempting to update the registry
I1029 18:20:19.220229 32260 registrar.cpp:544] Successfully updated the
registry in 569088ns
I1029 18:20:19.220448 32260 master.cpp:6970] Admitted agent
17736b02-db5b-40bb-ac46-32abffc4ecec-S0 at slave(332)@172.16.10.116:44212
(ip-172-16-10-116.ec2.internal)
I1029 18:20:19.221081 32260 master.cpp:7015] Registered agent
17736b02-db5b-40bb-ac46-32abffc4ecec-S0 at slave(332)@172.16.10.116:44212
(ip-172-16-10-116.ec2.internal) with cpus:2; mem:1024; disk:1024;
ports:[31000-32000]
I1029 18:20:19.221155 32256 slave.cpp:1494] Registered with master
[email protected]:44212; given agent ID
17736b02-db5b-40bb-ac46-32abffc4ecec-S0
I1029 18:20:19.221446 32260 hierarchical.cpp:598] Added agent
17736b02-db5b-40bb-ac46-32abffc4ecec-S0 (ip-172-16-10-116.ec2.internal) with
cpus:2; mem:1024; disk:1024; ports:[31000-32000] (allocated: {})
I1029 18:20:19.221573 32256 slave.cpp:1514] Checkpointing SlaveInfo to
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/meta/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/slave.info'
I1029 18:20:19.222491 32256 slave.cpp:1563] Forwarding agent update
{"operations":{},"resource_version_uuid":{"value":"SsjgOoOASlu5Oy68Ou0YAA=="},"slave_id":{"value":"17736b02-db5b-40bb-ac46-32abffc4ecec-S0"},"update_oversubscribed_resources":false}
I1029 18:20:19.222575 32260 hierarchical.cpp:1566] Performed allocation for 1
agents in 966802ns
I1029 18:20:19.222632 32260 task_status_update_manager.cpp:188] Resuming
sending task status updates
I1029 18:20:19.223609 32260 master.cpp:9704] Sending offers [
17736b02-db5b-40bb-ac46-32abffc4ecec-O0 ] to framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000 (default) at
[email protected]:44212
I1029 18:20:19.224218 32261 sched.cpp:914] Scheduler::resourceOffers took
134971ns
I1029 18:20:19.225399 32260 master.cpp:8074] Ignoring update on agent
17736b02-db5b-40bb-ac46-32abffc4ecec-S0 at slave(332)@172.16.10.116:44212
(ip-172-16-10-116.ec2.internal) as it reports no changes
I1029 18:20:19.226065 32260 master.cpp:11712] Removing offer
17736b02-db5b-40bb-ac46-32abffc4ecec-O0
I1029 18:20:19.226433 32260 master.cpp:4497] Processing ACCEPT call for offers:
[ 17736b02-db5b-40bb-ac46-32abffc4ecec-O0 ] on agent
17736b02-db5b-40bb-ac46-32abffc4ecec-S0 at slave(332)@172.16.10.116:44212
(ip-172-16-10-116.ec2.internal) for framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000 (default) at
[email protected]:44212
I1029 18:20:19.226531 32260 master.cpp:3585] Authorizing framework principal
'test-principal' to launch task 4209e4bd-5190-4599-9fab-54e83ff2d13d
I1029 18:20:19.228400 32259 master.cpp:12443] Adding task
4209e4bd-5190-4599-9fab-54e83ff2d13d with resources cpus(allocated: *):2;
mem(allocated: *):1024; disk(allocated: *):1024; ports(allocated:
*):[31000-32000] on agent 17736b02-db5b-40bb-ac46-32abffc4ecec-S0 at
slave(332)@172.16.10.116:44212 (ip-172-16-10-116.ec2.internal)
I1029 18:20:19.228811 32259 master.cpp:5476] Launching task
4209e4bd-5190-4599-9fab-54e83ff2d13d of framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000 (default) at
[email protected]:44212 with
resources
[{"allocation_info":{"role":"*"},"name":"cpus","scalar":{"value":2.0},"type":"SCALAR"},{"allocation_info":{"role":"*"},"name":"mem","scalar":{"value":1024.0},"type":"SCALAR"},{"allocation_info":{"role":"*"},"name":"disk","scalar":{"value":1024.0},"type":"SCALAR"},{"allocation_info":{"role":"*"},"name":"ports","ranges":{"range":[{"begin":31000,"end":32000}]},"type":"RANGES"}]
on agent 17736b02-db5b-40bb-ac46-32abffc4ecec-S0 at
slave(332)@172.16.10.116:44212 (ip-172-16-10-116.ec2.internal) on new executor
I1029 18:20:19.230067 32262 slave.cpp:2029] Got assigned task
'4209e4bd-5190-4599-9fab-54e83ff2d13d' for framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000
I1029 18:20:19.230223 32262 slave.cpp:8982] Checkpointing FrameworkInfo to
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/meta/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/framework.info'
I1029 18:20:19.230618 32262 slave.cpp:8993] Checkpointing framework pid
'[email protected]:44212' to
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/meta/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/framework.pid'
I1029 18:20:19.231789 32262 slave.cpp:2403] Authorizing task
'4209e4bd-5190-4599-9fab-54e83ff2d13d' for framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000
I1029 18:20:19.231850 32262 slave.cpp:8540] Authorizing framework principal
'test-principal' to launch task 4209e4bd-5190-4599-9fab-54e83ff2d13d
I1029 18:20:19.233637 32259 slave.cpp:2846] Launching task
'4209e4bd-5190-4599-9fab-54e83ff2d13d' for framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000
I1029 18:20:19.233724 32259 paths.cpp:745] Creating sandbox
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/250cb271-95f5-445f-9c54-0cbd021d72f8'
for user 'root'
I1029 18:20:19.234416 32259 slave.cpp:9780] Checkpointing ExecutorInfo to
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/meta/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/executor.info'
I1029 18:20:19.234936 32259 paths.cpp:748] Creating sandbox
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/meta/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/250cb271-95f5-445f-9c54-0cbd021d72f8'
I1029 18:20:19.235167 32259 slave.cpp:9068] Launching executor
'4209e4bd-5190-4599-9fab-54e83ff2d13d' of framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000 with resources
[{"allocation_info":{"role":"*"},"name":"cpus","scalar":{"value":0.1},"type":"SCALAR"},{"allocation_info":{"role":"*"},"name":"mem","scalar":{"value":32.0},"type":"SCALAR"}]
in work directory
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/250cb271-95f5-445f-9c54-0cbd021d72f8'
I1029 18:20:19.236201 32259 slave.cpp:9811] Checkpointing TaskInfo to
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/meta/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/250cb271-95f5-445f-9c54-0cbd021d72f8/tasks/4209e4bd-5190-4599-9fab-54e83ff2d13d/task.info'
I1029 18:20:19.236706 32259 slave.cpp:3078] Queued task
'4209e4bd-5190-4599-9fab-54e83ff2d13d' for executor
'4209e4bd-5190-4599-9fab-54e83ff2d13d' of framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000
I1029 18:20:19.236784 32259 slave.cpp:1003] Successfully attached
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/250cb271-95f5-445f-9c54-0cbd021d72f8'
to virtual path
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/latest'
I1029 18:20:19.237105 32259 slave.cpp:1003] Successfully attached
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/250cb271-95f5-445f-9c54-0cbd021d72f8'
to virtual path
'/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/latest'
I1029 18:20:19.237149 32259 slave.cpp:1003] Successfully attached
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/250cb271-95f5-445f-9c54-0cbd021d72f8'
to virtual path
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/250cb271-95f5-445f-9c54-0cbd021d72f8'
I1029 18:20:19.237404 32259 slave.cpp:3526] Launching container
250cb271-95f5-445f-9c54-0cbd021d72f8 for executor
'4209e4bd-5190-4599-9fab-54e83ff2d13d' of framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000
I1029 18:20:19.237956 32261 containerizer.cpp:1325] Starting container
250cb271-95f5-445f-9c54-0cbd021d72f8
I1029 18:20:19.238821 32261 containerizer.cpp:1497] Checkpointed
ContainerConfig at
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_MMTb0c/containers/250cb271-95f5-445f-9c54-0cbd021d72f8/config'
I1029 18:20:19.238858 32261 containerizer.cpp:3180] Transitioning the state of
container 250cb271-95f5-445f-9c54-0cbd021d72f8 from PROVISIONING to PREPARING
I1029 18:20:19.240214 32257 cgroups.cpp:432] Creating cgroup at
'/sys/fs/cgroup/cpu,cpuacct/mesos_test_82c37294-024f-4d12-a359-c842c5dddd23/250cb271-95f5-445f-9c54-0cbd021d72f8'
for container 250cb271-95f5-445f-9c54-0cbd021d72f8
I1029 18:20:19.241256 32257 cgroups.cpp:488] Chown the cgroup at
'/sys/fs/cgroup/cpu,cpuacct/mesos_test_82c37294-024f-4d12-a359-c842c5dddd23/250cb271-95f5-445f-9c54-0cbd021d72f8'
to user 'root' for container 250cb271-95f5-445f-9c54-0cbd021d72f8
I1029 18:20:19.241359 32257 cgroups.cpp:432] Creating cgroup at
'/sys/fs/cgroup/memory/mesos_test_82c37294-024f-4d12-a359-c842c5dddd23/250cb271-95f5-445f-9c54-0cbd021d72f8'
for container 250cb271-95f5-445f-9c54-0cbd021d72f8
I1029 18:20:19.242262 32257 cgroups.cpp:488] Chown the cgroup at
'/sys/fs/cgroup/memory/mesos_test_82c37294-024f-4d12-a359-c842c5dddd23/250cb271-95f5-445f-9c54-0cbd021d72f8'
to user 'root' for container 250cb271-95f5-445f-9c54-0cbd021d72f8
I1029 18:20:19.242576 32256 memory.cpp:478] Started listening for OOM events
for container 250cb271-95f5-445f-9c54-0cbd021d72f8
I1029 18:20:19.242748 32256 memory.cpp:590] Started listening on 'low' memory
pressure events for container 250cb271-95f5-445f-9c54-0cbd021d72f8
I1029 18:20:19.242848 32256 memory.cpp:590] Started listening on 'medium'
memory pressure events for container 250cb271-95f5-445f-9c54-0cbd021d72f8
I1029 18:20:19.242980 32256 memory.cpp:590] Started listening on 'critical'
memory pressure events for container 250cb271-95f5-445f-9c54-0cbd021d72f8
I1029 18:20:19.244519 32257 memory.cpp:198] Updated
'memory.soft_limit_in_bytes' to 1056MB for container
250cb271-95f5-445f-9c54-0cbd021d72f8
I1029 18:20:19.244655 32257 memory.cpp:227] Updated 'memory.limit_in_bytes' to
1056MB for container 250cb271-95f5-445f-9c54-0cbd021d72f8
I1029 18:20:19.244808 32257 cpu.cpp:92] Updated 'cpu.shares' to 2150 (cpus 2.1)
for container 250cb271-95f5-445f-9c54-0cbd021d72f8
I1029 18:20:19.247782 32256 containerizer.cpp:1998] Launching
'mesos-containerizer' with flags '--help="false"
--launch_info="{"command":{"arguments":["mesos-executor","--launcher_dir=/home/centos/workspace/mesos/Mesos_CI-build/FLAG/CMake/label/mesos-ec2-centos-7/mesos/build/src"],"shell":false,"value":"/proc/self/fd/8"},"environment":{"variables":[{"name":"LIBPROCESS_PORT","type":"VALUE","value":"0"},{"name":"MESOS_AGENT_ENDPOINT","type":"VALUE","value":"172.16.10.116:44212"},{"name":"MESOS_CHECKPOINT","type":"VALUE","value":"1"},{"name":"MESOS_DIRECTORY","type":"VALUE","value":"/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/250cb271-95f5-445f-9c54-0cbd021d72f8"},{"name":"MESOS_EXECUTOR_ID","type":"VALUE","value":"4209e4bd-5190-4599-9fab-54e83ff2d13d"},{"name":"MESOS_EXECUTOR_SHUTDOWN_GRACE_PERIOD","type":"VALUE","value":"5secs"},{"name":"MESOS_FRAMEWORK_ID","type":"VALUE","value":"17736b02-db5b-40bb-ac46-32abffc4ecec-0000"},{"name":"MESOS_HTTP_COMMAND_EXECUTOR","type":"VALUE","value":"0"},{"name":"MESOS_RECOVERY_TIMEOUT","type":"VALUE","value":"15mins"},{"name":"MESOS_SLAVE_ID","type":"VALUE","value":"17736b02-db5b-40bb-ac46-32abffc4ecec-S0"},{"name":"MESOS_SLAVE_PID","type":"VALUE","value":"slave(332)@172.16.10.116:44212"},{"name":"MESOS_SUBSCRIPTION_BACKOFF_MAX","type":"VALUE","value":"2secs"},{"name":"MESOS_SANDBOX","type":"VALUE","value":"/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/250cb271-95f5-445f-9c54-0cbd021d72f8"}]},"task_environment":{},"user":"root","working_directory":"/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/250cb271-95f5-445f-9c54-0cbd021d72f8"}"
--pipe_read="18" --pipe_write="19"
--runtime_directory="/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_MMTb0c/containers/250cb271-95f5-445f-9c54-0cbd021d72f8"
--unshare_namespace_mnt="false"'
I1029 18:20:19.248543 32255 linux_launcher.cpp:492] Launching container
250cb271-95f5-445f-9c54-0cbd021d72f8 and cloning with namespaces
I1029 18:20:19.255053 32256 containerizer.cpp:2107] Checkpointing container's
forked pid 4462 to
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/meta/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/250cb271-95f5-445f-9c54-0cbd021d72f8/pids/forked.pid'
I1029 18:20:19.255720 32256 containerizer.cpp:3180] Transitioning the state of
container 250cb271-95f5-445f-9c54-0cbd021d72f8 from PREPARING to ISOLATING
I1029 18:20:19.259119 32256 containerizer.cpp:3180] Transitioning the state of
container 250cb271-95f5-445f-9c54-0cbd021d72f8 from ISOLATING to FETCHING
I1029 18:20:19.259323 32256 fetcher.cpp:369] Starting to fetch URIs for
container: 250cb271-95f5-445f-9c54-0cbd021d72f8, directory:
/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/250cb271-95f5-445f-9c54-0cbd021d72f8
I1029 18:20:19.261050 32256 containerizer.cpp:3180] Transitioning the state of
container 250cb271-95f5-445f-9c54-0cbd021d72f8 from FETCHING to RUNNING
I1029 18:20:19.495735 4463 exec.cpp:162] Version: 1.7.3
I1029 18:20:19.505275 32262 slave.cpp:4839] Got registration for executor
'4209e4bd-5190-4599-9fab-54e83ff2d13d' of framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000 from executor(1)@172.16.10.116:35340
I1029 18:20:19.505753 32262 slave.cpp:4925] Checkpointing executor pid
'executor(1)@172.16.10.116:35340' to
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/meta/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/250cb271-95f5-445f-9c54-0cbd021d72f8/pids/libprocess.pid'
I1029 18:20:19.507268 32257 slave.cpp:924] Agent terminating
I1029 18:20:19.508224 32255 master.cpp:1301] Agent
17736b02-db5b-40bb-ac46-32abffc4ecec-S0 at slave(332)@172.16.10.116:44212
(ip-172-16-10-116.ec2.internal) disconnected
I1029 18:20:19.508250 32255 master.cpp:3354] Disconnecting agent
17736b02-db5b-40bb-ac46-32abffc4ecec-S0 at slave(332)@172.16.10.116:44212
(ip-172-16-10-116.ec2.internal)
I1029 18:20:19.508301 32255 master.cpp:3373] Deactivating agent
17736b02-db5b-40bb-ac46-32abffc4ecec-S0 at slave(332)@172.16.10.116:44212
(ip-172-16-10-116.ec2.internal)
I1029 18:20:19.508558 32261 hierarchical.cpp:788] Agent
17736b02-db5b-40bb-ac46-32abffc4ecec-S0 deactivated
I1029 18:20:19.508693 32254 containerizer.cpp:309] Using isolation {
cgroups/cpu, filesystem/posix, environment_secret, cgroups/mem, network/cni }
I1029 18:20:19.509590 32255 memory.cpp:198] Updated
'memory.soft_limit_in_bytes' to 1056MB for container
250cb271-95f5-445f-9c54-0cbd021d72f8
I1029 18:20:19.511060 32259 cpu.cpp:92] Updated 'cpu.shares' to 2150 (cpus 2.1)
for container 250cb271-95f5-445f-9c54-0cbd021d72f8
I1029 18:20:19.516171 4469 exec.cpp:236] Executor registered on agent
17736b02-db5b-40bb-ac46-32abffc4ecec-S0
I1029 18:20:19.518065 32254 linux_launcher.cpp:144] Using
/sys/fs/cgroup/freezer as the freezer hierarchy for the Linux launcher
I1029 18:20:19.519266 32254 provisioner.cpp:292] Using default backend 'copy'
I1029 18:20:19.520582 4469 executor.cpp:188] Received SUBSCRIBED event
I1029 18:20:19.521507 4469 executor.cpp:192] Subscribed executor on
ip-172-16-10-116.ec2.internal
W1029 18:20:19.541481 32254 process.cpp:2829] Attempted to spawn already
running process [email protected]:44212
I1029 18:20:19.542059 32254 cluster.cpp:485] Creating default 'local' authorizer
I1029 18:20:19.545063 32261 slave.cpp:261] Mesos agent started on
(333)@172.16.10.116:44212
I1029 18:20:19.545078 32261 slave.cpp:262] Flags at startup: --acls=""
--appc_simple_discovery_uri_prefix="http://";
--appc_store_dir="/tmp/bOwSpZ/4numNO/store/appc"
--authenticate_http_readonly="true" --authenticate_http_readwrite="false"
--authenticatee="crammd5" --authentication_backoff_factor="1secs"
--authentication_timeout_max="1mins" --authentication_timeout_min="5secs"
--authorizer="local" --cgroups_cpu_enable_pids_and_tids_count="false"
--cgroups_destroy_timeout="1mins" --cgroups_enable_cfs="false"
--cgroups_hierarchy="/sys/fs/cgroup" --cgroups_limit_swap="false"
--cgroups_root="mesos_test_82c37294-024f-4d12-a359-c842c5dddd23"
--container_disk_watch_interval="15secs" --containerizers="mesos"
--credential="/tmp/bOwSpZ/4numNO/credential" --default_role="*"
--disallow_sharing_agent_pid_namespace="false" --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/bOwSpZ/4numNO/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/bOwSpZ/4numNO/fetch" --fetcher_cache_size="2GB"
--fetcher_stall_timeout="1mins" --frameworks_home="" --gc_delay="1weeks"
--gc_disk_headroom="0.1" --gc_non_executor_container_sandboxes="false"
--help="false" --hostname_lookup="true" --http_command_executor="false"
--http_credentials="/tmp/bOwSpZ/4numNO/http_credentials"
--http_heartbeat_interval="30secs" --initialize_driver_logging="true"
--isolation="cgroups/cpu,cgroups/mem" --launcher="linux"
--launcher_dir="/home/centos/workspace/mesos/Mesos_CI-build/FLAG/CMake/label/mesos-ec2-centos-7/mesos/build/src"
--logbufsecs="0" --logging_level="INFO"
--max_completed_executors_per_framework="150" --memory_profiling="false"
--network_cni_metrics="true" --network_cni_root_dir_persist="false"
--oversubscribed_resources_interval="15secs" --perf_duration="10secs"
--perf_interval="1mins" --port="5051" --qos_correction_interval_min="0ns"
--quiet="false" --reconfiguration_policy="equal" --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/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_MMTb0c"
--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/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB"
--zk_session_timeout="10secs"
I1029 18:20:19.545485 32261 credentials.hpp:86] Loading credential for
authentication from '/tmp/bOwSpZ/4numNO/credential'
I1029 18:20:19.545630 32261 slave.cpp:294] Agent using credential for:
test-principal
I1029 18:20:19.545645 32261 credentials.hpp:37] Loading credentials for
authentication from '/tmp/bOwSpZ/4numNO/http_credentials'
I1029 18:20:19.545826 32261 http.cpp:977] Creating default 'basic' HTTP
authenticator for realm 'mesos-agent-readonly'
I1029 18:20:19.546133 32261 disk_profile_adaptor.cpp:80] Creating default disk
profile adaptor module
I1029 18:20:19.547816 32261 slave.cpp:609] Agent resources:
[{"name":"cpus","scalar":{"value":2.0},"type":"SCALAR"},{"name":"mem","scalar":{"value":1024.0},"type":"SCALAR"},{"name":"disk","scalar":{"value":1024.0},"type":"SCALAR"},{"name":"ports","ranges":{"range":[{"begin":31000,"end":32000}]},"type":"RANGES"}]
I1029 18:20:19.548041 32261 slave.cpp:617] Agent attributes: [ ]
I1029 18:20:19.548054 32261 slave.cpp:626] Agent hostname:
ip-172-16-10-116.ec2.internal
I1029 18:20:19.549860 32259 task_status_update_manager.cpp:181] Pausing sending
task status updates
I1029 18:20:19.549974 32262 state.cpp:66] Recovering state from
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/meta'
I1029 18:20:19.550019 32262 state.cpp:742] No committed checkpointed resources
found at
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/meta/resources/resources.info'
W1029 18:20:19.551594 32262 state.cpp:649] Failed to find status updates file
'/tmp/MesosContainerizerSlaveRecoveryTest_ResourceStatistics_aXH1cB/meta/slaves/17736b02-db5b-40bb-ac46-32abffc4ecec-S0/frameworks/17736b02-db5b-40bb-ac46-32abffc4ecec-0000/executors/4209e4bd-5190-4599-9fab-54e83ff2d13d/runs/250cb271-95f5-445f-9c54-0cbd021d72f8/tasks/4209e4bd-5190-4599-9fab-54e83ff2d13d/task.updates'
/home/centos/workspace/mesos/Mesos_CI-build/FLAG/CMake/label/mesos-ec2-centos-7/mesos/src/tests/slave_recovery_tests.cpp:5140:
Failure
Expected: 1u
Which is: 1
To be equal to: containers->size()
Which is: 0
I1029 18:20:19.552464 32254 slave.cpp:924] Agent terminating
I1029 18:20:19.553551 32262 master.cpp:1416] Framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000 (default) at
[email protected]:44212 disconnected
I1029 18:20:19.553587 32262 master.cpp:3317] Deactivating framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000 (default) at
[email protected]:44212
I1029 18:20:19.553650 32262 master.cpp:3294] Disconnecting framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000 (default) at
[email protected]:44212
I1029 18:20:19.553691 32262 master.cpp:1431] Giving framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000 (default) at
[email protected]:44212 0ns to
failover
I1029 18:20:19.553886 32262 hierarchical.cpp:448] Deactivated framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000
I1029 18:20:19.555828 32256 master.cpp:9507] Framework failover timeout,
removing framework 17736b02-db5b-40bb-ac46-32abffc4ecec-0000 (default) at
[email protected]:44212
I1029 18:20:19.555857 32256 master.cpp:10440] Removing framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000 (default) at
[email protected]:44212
I1029 18:20:19.556067 32256 master.cpp:11175] Updating the state of task
4209e4bd-5190-4599-9fab-54e83ff2d13d of framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000 (latest state: TASK_KILLED, status
update state: TASK_KILLED)
I1029 18:20:19.556749 32256 master.cpp:11273] Removing task
4209e4bd-5190-4599-9fab-54e83ff2d13d with resources cpus(allocated: *):2;
mem(allocated: *):1024; disk(allocated: *):1024; ports(allocated:
*):[31000-32000] of framework 17736b02-db5b-40bb-ac46-32abffc4ecec-0000 on
agent 17736b02-db5b-40bb-ac46-32abffc4ecec-S0 at slave(332)@172.16.10.116:44212
(ip-172-16-10-116.ec2.internal)
I1029 18:20:19.557238 32259 hierarchical.cpp:1217] Recovered cpus(allocated:
*):2; mem(allocated: *):1024; disk(allocated: *):1024; ports(allocated:
*):[31000-32000] (total: cpus:2; mem:1024; disk:1024; ports:[31000-32000],
allocated: {}) on agent 17736b02-db5b-40bb-ac46-32abffc4ecec-S0 from framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000
I1029 18:20:19.557569 32259 hierarchical.cpp:391] Removed framework
17736b02-db5b-40bb-ac46-32abffc4ecec-0000
I1029 18:20:19.562849 32254 master.cpp:1143] Master terminating
I1029 18:20:19.563258 32260 hierarchical.cpp:764] Removed all filters for agent
17736b02-db5b-40bb-ac46-32abffc4ecec-S0
I1029 18:20:19.563274 32260 hierarchical.cpp:639] Removed agent
17736b02-db5b-40bb-ac46-32abffc4ecec-S0
/home/centos/workspace/mesos/Mesos_CI-build/FLAG/CMake/label/mesos-ec2-centos-7/mesos/src/tests/mesos.cpp:924:
Failure
(cgroups::destroy(hierarchy, cgroup)).failure(): Failed to remove cgroup
'/sys/fs/cgroup/memory/mesos_test_82c37294-024f-4d12-a359-c842c5dddd23/250cb271-95f5-445f-9c54-0cbd021d72f8':
Device or resource busy
[ FAILED ] MesosContainerizerSlaveRecoveryTest.ResourceStatistics (524 ms)
{code}
> MesosContainerizerSlaveRecoveryTest.ResourceStatistics could segfault
> ---------------------------------------------------------------------
>
> Key: MESOS-6481
> URL: https://issues.apache.org/jira/browse/MESOS-6481
> Project: Mesos
> Issue Type: Bug
> Affects Versions: 1.2.0
> Reporter: Jie Yu
> Priority: Major
>
> {noformat}
> [----------] 1 test from MesosContainerizerSlaveRecoveryTest
> [ RUN ] MesosContainerizerSlaveRecoveryTest.ResourceStatistics
> I1025 09:24:00.334599 7253 exec.cpp:162] Version: 1.2.0
> I1025 09:24:00.340852 7269 exec.cpp:237] Executor registered on agent
> 5d7fe7df-aeca-451e-84f9-422cf78e7fee-S0
> Received SUBSCRIBED event
> Subscribed executor on core-dev
> /home/jie/workspace/mesos/src/tests/slave_recovery_tests.cpp:4061: Failure
> Value of: containers.get().size()
> Actual: 0
> Expected: 1u
> Which is: 1
> *** Aborted at 1477412640 (unix time) try "date -d @1477412640" if you are
> using GNU date ***
> I1025 09:24:00.369978 7281 exec.cpp:283] Received reconnect request from
> agent 5d7fe7df-aeca-451e-84f9-422cf78e7fee-S0
> I1025 09:24:00.371438 7250 exec.cpp:260] Executor re-registered on agent
> 5d7fe7df-aeca-451e-84f9-422cf78e7fee-S0
> PC: @ 0x2b1952628a06 mesos::ContainerID::MergeFrom()
> Received SUBSCRIBED event
> Subscribed executor on core-dev
> *** SIGSEGV (@0x18) received by PID 40269 (TID 0x2b194d6ce440) from PID 24;
> stack trace: ***
> @ 0x2b1962cd62f5 (unknown)
> @ 0x2b1962cdaec1 (unknown)
> @ 0x2b1962ccf1b8 (unknown)
> @ 0x2b1953f72100 (unknown)
> @ 0x2b1952628a06 mesos::ContainerID::MergeFrom()
> @ 0x2b1952627e1c mesos::ContainerID::ContainerID()
> @ 0x162b774
> mesos::internal::tests::MesosContainerizerSlaveRecoveryTest_ResourceStatistics_Test::TestBody()
> @ 0x1ad8066
> testing::internal::HandleSehExceptionsInMethodIfSupported<>()
> @ 0x1ad3184
> testing::internal::HandleExceptionsInMethodIfSupported<>()
> @ 0x1ab4815 testing::Test::Run()
> @ 0x1ab4f98 testing::TestInfo::Run()
> @ 0x1ab55de testing::TestCase::Run()
> @ 0x1abbeb8 testing::internal::UnitTestImpl::RunAllTests()
> @ 0x1ad8c8b
> testing::internal::HandleSehExceptionsInMethodIfSupported<>()
> @ 0x1ad3ccc
> testing::internal::HandleExceptionsInMethodIfSupported<>()
> @ 0x1ababfe testing::UnitTest::Run()
> @ 0x1099562 RUN_ALL_TESTS()
> @ 0x1099131 main
> @ 0x2b1954dccb15 __libc_start_main
> @ 0xa16669 (unknown)
> I1025 09:24:03.721460 7281 exec.cpp:487] Agent exited, but framework has
> checkpointing enabled. Waiting 15mins to reconnect with agent
> 5d7fe7df-aeca-451e-84f
> 9-422cf78e7fee-S0
> I1025 09:24:03.721690 7281 exec.cpp:496] Agent exited ... shutting down
> {noformat}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
