Pulpito :: Results Dashboard

Posted	Started	Updated	Runtime	Duration	In Waiting	Machine	Teuthology Branch	OS Type	OS Version	Nodes	Status
2024-09-01 20:08:34	2024-09-02 06:28:15	2024-09-02 06:51:51	0:23:36	0:15:39	0:07:57	smithi	main	centos	9.stream	3	fail

Nodes: smithi016 smithi083 smithi167

Description: rados/cephadm/workunits/{0-distro/centos_9.stream_runc agent/off mon_election/connectivity task/test_monitoring_stack_basic}

Log: http://qa-proxy.ceph.com/teuthology/teuthology-2024-09-01_20:00:18-rados-main-distro-default-smithi/7884974/teuthology.log

Sentry event: https://sentry.ceph.com/organizations/ceph/?query=556063cfc027477bb19fec500a58fa28

Failure Reason:

Command failed on smithi016 with status 5: 'sudo /home/ubuntu/cephtest/cephadm --image quay-quay-quay.apps.os.sepia.ceph.com/ceph-ci/ceph:83fc625b564ccf3927977ee1f86e2936b1b884e2 shell -c /etc/ceph/ceph.conf -k /etc/ceph/ceph.client.admin.keyring --fsid 1164b3f4-68f6-11ef-bcd4-c7b262605968 -- bash -c \'set -e\nset -x\nceph orch apply node-exporter\nceph orch apply grafana\nceph orch apply alertmanager\nceph orch apply prometheus\nsleep 240\nceph orch ls\nceph orch ps\nceph orch host ls\nMON_DAEMON=$(ceph orch ps --daemon-type mon -f json | jq -r \'"\'"\'last | .daemon_name\'"\'"\')\nGRAFANA_HOST=$(ceph orch ps --daemon-type grafana -f json | jq -e \'"\'"\'.[]\'"\'"\' | jq -r \'"\'"\'.hostname\'"\'"\')\nPROM_HOST=$(ceph orch ps --daemon-type prometheus -f json | jq -e \'"\'"\'.[]\'"\'"\' | jq -r \'"\'"\'.hostname\'"\'"\')\nALERTM_HOST=$(ceph orch ps --daemon-type alertmanager -f json | jq -e \'"\'"\'.[]\'"\'"\' | jq -r \'"\'"\'.hostname\'"\'"\')\nGRAFANA_IP=$(ceph orch host ls -f json | jq -r --arg GRAFANA_HOST "$GRAFANA_HOST" \'"\'"\'.[] | select(.hostname==$GRAFANA_HOST) | .addr\'"\'"\')\nPROM_IP=$(ceph orch host ls -f json | jq -r --arg PROM_HOST "$PROM_HOST" \'"\'"\'.[] | select(.hostname==$PROM_HOST) | .addr\'"\'"\')\nALERTM_IP=$(ceph orch host ls -f json | jq -r --arg ALERTM_HOST "$ALERTM_HOST" \'"\'"\'.[] | select(.hostname==$ALERTM_HOST) | .addr\'"\'"\')\n# check each host node-exporter metrics endpoint is responsive\nALL_HOST_IPS=$(ceph orch host ls -f json | jq -r \'"\'"\'.[] | .addr\'"\'"\')\nfor ip in $ALL_HOST_IPS; do\n curl -s http://${ip}:9100/metric\ndone\n# check grafana endpoints are responsive and database health is okay\ncurl -k -s https://${GRAFANA_IP}:3000/api/health\ncurl -k -s https://${GRAFANA_IP}:3000/api/health | jq -e \'"\'"\'.database == "ok"\'"\'"\'\n# stop mon daemon in order to trigger an alert\nceph orch daemon stop $MON_DAEMON\nsleep 120\n# check prometheus endpoints are responsive and mon down alert is firing\ncurl -s http://${PROM_IP}:9095/api/v1/status/config\ncurl -s http://${PROM_IP}:9095/api/v1/status/config | jq -e \'"\'"\'.status == "success"\'"\'"\'\ncurl -s http://${PROM_IP}:9095/api/v1/alerts\ncurl -s http://${PROM_IP}:9095/api/v1/alerts | jq -e \'"\'"\'.data | .alerts | .[] | select(.labels | .alertname == "CephMonDown") | .state == "firing"\'"\'"\'\n# check alertmanager endpoints are responsive and mon down alert is active\ncurl -s http://${ALERTM_IP}:9093/api/v1/status\ncurl -s http://${ALERTM_IP}:9093/api/v1/alerts\ncurl -s http://${ALERTM_IP}:9093/api/v1/alerts | jq -e \'"\'"\'.data | .[] | select(.labels | .alertname == "CephMonDown") | .status | .state == "active"\'"\'"\'\n\''

All Details...

log_href: http://qa-proxy.ceph.com/teuthology/teuthology-2024-09-01_20:00:18-rados-main-distro-default-smithi/7884974/teuthology.log
archive_path: /home/teuthworker/archive/teuthology-2024-09-01_20:00:18-rados-main-distro-default-smithi/7884974
description: rados/cephadm/workunits/{0-distro/centos_9.stream_runc agent/off mon_election/connectivity task/test_monitoring_stack_basic}
duration: 0:15:39
email: ceph-qa@ceph.com
failure_reason: Command failed on smithi016 with status 5: 'sudo /home/ubuntu/cephtest/cephadm --image quay-quay-quay.apps.os.sepia.ceph.com/ceph-ci/ceph:83fc625b564ccf3927977ee1f86e2936b1b884e2 shell -c /etc/ceph/ceph.conf -k /etc/ceph/ceph.client.admin.keyring --fsid 1164b3f4-68f6-11ef-bcd4-c7b262605968 -- bash -c \'set -e\nset -x\nceph orch apply node-exporter\nceph orch apply grafana\nceph orch apply alertmanager\nceph orch apply prometheus\nsleep 240\nceph orch ls\nceph orch ps\nceph orch host ls\nMON_DAEMON=$(ceph orch ps --daemon-type mon -f json | jq -r \'"\'"\'last | .daemon_name\'"\'"\')\nGRAFANA_HOST=$(ceph orch ps --daemon-type grafana -f json | jq -e \'"\'"\'.[]\'"\'"\' | jq -r \'"\'"\'.hostname\'"\'"\')\nPROM_HOST=$(ceph orch ps --daemon-type prometheus -f json | jq -e \'"\'"\'.[]\'"\'"\' | jq -r \'"\'"\'.hostname\'"\'"\')\nALERTM_HOST=$(ceph orch ps --daemon-type alertmanager -f json | jq -e \'"\'"\'.[]\'"\'"\' | jq -r \'"\'"\'.hostname\'"\'"\')\nGRAFANA_IP=$(ceph orch host ls -f json | jq -r --arg GRAFANA_HOST "$GRAFANA_HOST" \'"\'"\'.[] | select(.hostname==$GRAFANA_HOST) | .addr\'"\'"\')\nPROM_IP=$(ceph orch host ls -f json | jq -r --arg PROM_HOST "$PROM_HOST" \'"\'"\'.[] | select(.hostname==$PROM_HOST) | .addr\'"\'"\')\nALERTM_IP=$(ceph orch host ls -f json | jq -r --arg ALERTM_HOST "$ALERTM_HOST" \'"\'"\'.[] | select(.hostname==$ALERTM_HOST) | .addr\'"\'"\')\n# check each host node-exporter metrics endpoint is responsive\nALL_HOST_IPS=$(ceph orch host ls -f json | jq -r \'"\'"\'.[] | .addr\'"\'"\')\nfor ip in $ALL_HOST_IPS; do\n curl -s http://${ip}:9100/metric\ndone\n# check grafana endpoints are responsive and database health is okay\ncurl -k -s https://${GRAFANA_IP}:3000/api/health\ncurl -k -s https://${GRAFANA_IP}:3000/api/health | jq -e \'"\'"\'.database == "ok"\'"\'"\'\n# stop mon daemon in order to trigger an alert\nceph orch daemon stop $MON_DAEMON\nsleep 120\n# check prometheus endpoints are responsive and mon down alert is firing\ncurl -s http://${PROM_IP}:9095/api/v1/status/config\ncurl -s http://${PROM_IP}:9095/api/v1/status/config | jq -e \'"\'"\'.status == "success"\'"\'"\'\ncurl -s http://${PROM_IP}:9095/api/v1/alerts\ncurl -s http://${PROM_IP}:9095/api/v1/alerts | jq -e \'"\'"\'.data | .alerts | .[] | select(.labels | .alertname == "CephMonDown") | .state == "firing"\'"\'"\'\n# check alertmanager endpoints are responsive and mon down alert is active\ncurl -s http://${ALERTM_IP}:9093/api/v1/status\ncurl -s http://${ALERTM_IP}:9093/api/v1/alerts\ncurl -s http://${ALERTM_IP}:9093/api/v1/alerts | jq -e \'"\'"\'.data | .[] | select(.labels | .alertname == "CephMonDown") | .status | .state == "active"\'"\'"\'\n\''
flavor: default
job_id: 7884974
kernel:
- kdb: 1
- sha1: distro
last_in_suite: False
machine_type: smithi
name: teuthology-2024-09-01_20:00:18-rados-main-distro-default-smithi
nuke_on_error:
os_type: centos
os_version: 9.stream
overrides:
- admin_socket:
  - branch: main
- ceph:
  - conf:
    - global:
      - mon election default strategy: 3
    - mgr:
      - debug mgr: 20
      - debug ms: 1
      - mgr/cephadm/use_agent: False
    - mon:
      - debug mon: 20
      - debug ms: 1
      - debug paxos: 20
    - osd:
      - debug ms: 1
      - debug osd: 20
  - flavor: default
  - log-ignorelist:
    - $MDS_ALL_DOWN$
    - $MDS_UP_LESS_THAN_MAX$
    - MON_DOWN
    - mons down
    - mon down
    - out of quorum
    - CEPHADM_STRAY_DAEMON
    - CEPHADM_FAILED_DAEMON
  - log-only-match:
    - CEPHADM_
  - sha1: 83fc625b564ccf3927977ee1f86e2936b1b884e2
- ceph-deploy:
  - conf:
    - client:
      - log file: /var/log/ceph/ceph-$name.$pid.log
    - mon:
- install:
  - ceph:
    - flavor: default
    - sha1: 83fc625b564ccf3927977ee1f86e2936b1b884e2
- selinux:
  - allowlist:
    - scontext=system_u:system_r:logrotate_t:s0
- workunit:
  - branch: main
  - sha1: 42c1c3d42aaa0b6c9bcbccb51c8b397fb980aa9f
owner: scheduled_teuthology@teuthology
pid:
roles:
- ['host.a', 'mon.a', 'mgr.a', 'osd.0']
- ['host.b', 'mon.b', 'mgr.b', 'osd.1']
- ['host.c', 'mon.c', 'osd.2']
sentry_event: https://sentry.ceph.com/organizations/ceph/?query=556063cfc027477bb19fec500a58fa28
status: fail
success: False
branch: main
seed: 4978
sha1: 83fc625b564ccf3927977ee1f86e2936b1b884e2
subset: 20435/100000
suite: rados
suite_branch: main
suite_path: /home/teuthworker/src/git.ceph.com_ceph_42c1c3d42aaa0b6c9bcbccb51c8b397fb980aa9f/qa
suite_relpath: qa
suite_repo: https://git.ceph.com/ceph.git
suite_sha1: 42c1c3d42aaa0b6c9bcbccb51c8b397fb980aa9f
targets:
- smithi016.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBAdzGaDzuc7Solo0qg7KBdwPzopU10UaXFODCIO4Hr5WGK7yZ+LMMfScmp8igbHg7DpfjPE9wx9HAkirmRGrKmM=
- smithi083.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBCfWoiSPy6C/1zUQP+V4E7uAEOneBth2knbtvBCJhv+JVzvO3anILLh5C1WZEV+LulwsQl+KB0f6hQzrKQ9T1vM=
- smithi167.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBHj6Z+nfdkqAUbCY4xhZis8Jjf+dkP62CwtA/3mpn8TcoYjvHXxIXdHosSyrN+ZvOJlFGi66tMS7n5aQ4JnZ+LQ=
tasks:
- internal.check_packages:
- internal.buildpackages_prep:
- internal.save_config:
- internal.check_lock:
- internal.add_remotes:
- console_log:
- internal.connect:
- internal.push_inventory:
- internal.serialize_remote_roles:
- internal.check_conflict:
- internal.check_ceph_data:
- internal.vm_setup:
- kernel:
  - kdb: 1
  - sha1: distro
- internal.base:
- internal.archive_upload:
- internal.archive:
- internal.coredump:
- internal.sudo:
- internal.syslog:
- internal.timer:
- pcp:
- selinux:
- ansible.cephlab:
- clock:
- pexec:
  - all:
    - sudo dnf remove nvme-cli -y
    - sudo dnf install runc nvmetcli nvme-cli -y
    - sudo sed -i 's/^#runtime = "crun"/runtime = "runc"/g' /usr/share/containers/containers.conf
    - sudo sed -i 's/runtime = "crun"/#runtime = "crun"/g' /usr/share/containers/containers.conf
- install:
- cephadm:
- cephadm.shell:
  - host.a:
    - set -e set -x ceph orch apply node-exporter ceph orch apply grafana ceph orch apply alertmanager ceph orch apply prometheus sleep 240 ceph orch ls ceph orch ps ceph orch host ls MON_DAEMON=$(ceph orch ps --daemon-type mon -f json | jq -r 'last | .daemon_name') GRAFANA_HOST=$(ceph orch ps --daemon-type grafana -f json | jq -e '.[]' | jq -r '.hostname') PROM_HOST=$(ceph orch ps --daemon-type prometheus -f json | jq -e '.[]' | jq -r '.hostname') ALERTM_HOST=$(ceph orch ps --daemon-type alertmanager -f json | jq -e '.[]' | jq -r '.hostname') GRAFANA_IP=$(ceph orch host ls -f json | jq -r --arg GRAFANA_HOST "$GRAFANA_HOST" '.[] | select(.hostname==$GRAFANA_HOST) | .addr') PROM_IP=$(ceph orch host ls -f json | jq -r --arg PROM_HOST "$PROM_HOST" '.[] | select(.hostname==$PROM_HOST) | .addr') ALERTM_IP=$(ceph orch host ls -f json | jq -r --arg ALERTM_HOST "$ALERTM_HOST" '.[] | select(.hostname==$ALERTM_HOST) | .addr') # check each host node-exporter metrics endpoint is responsive ALL_HOST_IPS=$(ceph orch host ls -f json | jq -r '.[] | .addr') for ip in $ALL_HOST_IPS; do curl -s http://${ip}:9100/metric done # check grafana endpoints are responsive and database health is okay curl -k -s https://${GRAFANA_IP}:3000/api/health curl -k -s https://${GRAFANA_IP}:3000/api/health | jq -e '.database == "ok"' # stop mon daemon in order to trigger an alert ceph orch daemon stop $MON_DAEMON sleep 120 # check prometheus endpoints are responsive and mon down alert is firing curl -s http://${PROM_IP}:9095/api/v1/status/config curl -s http://${PROM_IP}:9095/api/v1/status/config | jq -e '.status == "success"' curl -s http://${PROM_IP}:9095/api/v1/alerts curl -s http://${PROM_IP}:9095/api/v1/alerts | jq -e '.data | .alerts | .[] | select(.labels | .alertname == "CephMonDown") | .state == "firing"' # check alertmanager endpoints are responsive and mon down alert is active curl -s http://${ALERTM_IP}:9093/api/v1/status curl -s http://${ALERTM_IP}:9093/api/v1/alerts curl -s http://${ALERTM_IP}:9093/api/v1/alerts | jq -e '.data | .[] | select(.labels | .alertname == "CephMonDown") | .status | .state == "active"'
teuthology_branch: main
verbose: False
pcp_grafana_url:
priority: 101
user: teuthology
queue:
posted: 2024-09-01 20:08:34
started: 2024-09-02 06:28:15
updated: 2024-09-02 06:51:51
status_class: danger
runtime: 0:23:36
wait_time: 0:07:57