Pulpito :: Results Dashboard

Posted	Started	Updated	Runtime	Duration	In Waiting	Machine	Teuthology Branch	OS Type	OS Version	Nodes	Status
2024-08-09 12:47:19	2024-08-09 14:05:12	2024-08-09 14:37:27	0:32:15	0:18:26	0:13:49	smithi	main	centos	9.stream	3	fail

Nodes: smithi037 smithi052 smithi167

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

Log: http://qa-proxy.ceph.com/teuthology/gabrioux-2024-08-09_12:45:09-orch:cephadm-wip-guits-main-2024-08-09-0834-distro-default-smithi/7845490/teuthology.log

Sentry event: https://sentry.ceph.com/organizations/ceph/?query=1909354b8e434983bea87a7b70434c83

Failure Reason:

Command failed on smithi037 with status 5: 'sudo /home/ubuntu/cephtest/cephadm --image quay-quay-quay.apps.os.sepia.ceph.com/ceph-ci/ceph:7b00023a6c268030a3ca35430bfc61e75afd447f shell -c /etc/ceph/ceph.conf -k /etc/ceph/ceph.client.admin.keyring --fsid 1e19e6a8-565b-11ef-bccd-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/gabrioux-2024-08-09_12:45:09-orch:cephadm-wip-guits-main-2024-08-09-0834-distro-default-smithi/7845490/teuthology.log
archive_path: /home/teuthworker/archive/gabrioux-2024-08-09_12:45:09-orch:cephadm-wip-guits-main-2024-08-09-0834-distro-default-smithi/7845490
description: orch:cephadm/workunits/{0-distro/centos_9.stream_runc agent/off mon_election/classic task/test_monitoring_stack_basic}
duration: 0:18:26
email: gabrioux@ibm.com
failure_reason: Command failed on smithi037 with status 5: 'sudo /home/ubuntu/cephtest/cephadm --image quay-quay-quay.apps.os.sepia.ceph.com/ceph-ci/ceph:7b00023a6c268030a3ca35430bfc61e75afd447f shell -c /etc/ceph/ceph.conf -k /etc/ceph/ceph.client.admin.keyring --fsid 1e19e6a8-565b-11ef-bccd-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: 7845490
kernel:
- kdb: 1
- sha1: distro
last_in_suite: False
machine_type: smithi
name: gabrioux-2024-08-09_12:45:09-orch:cephadm-wip-guits-main-2024-08-09-0834-distro-default-smithi
nuke_on_error:
os_type: centos
os_version: 9.stream
overrides:
- admin_socket:
  - branch: wip-guits-main-2024-08-09-0834
- ceph:
  - conf:
    - global:
      - mon election default strategy: 1
    - 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: 7b00023a6c268030a3ca35430bfc61e75afd447f
- ceph-deploy:
  - conf:
    - client:
      - log file: /var/log/ceph/ceph-$name.$pid.log
    - mon:
- install:
  - ceph:
    - flavor: default
    - sha1: 7b00023a6c268030a3ca35430bfc61e75afd447f
- selinux:
  - allowlist:
    - scontext=system_u:system_r:logrotate_t:s0
- workunit:
  - branch: wip-guits-main-2024-08-09-0834
  - sha1: 7b00023a6c268030a3ca35430bfc61e75afd447f
owner: scheduled_gabrioux@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=1909354b8e434983bea87a7b70434c83
status: fail
success: False
branch: wip-guits-main-2024-08-09-0834
seed: 5062
sha1: 7b00023a6c268030a3ca35430bfc61e75afd447f
subset: 1/8
suite: orch:cephadm
suite_branch: wip-guits-main-2024-08-09-0834
suite_path: /home/teuthworker/src/git.ceph.com_ceph-c_7b00023a6c268030a3ca35430bfc61e75afd447f/qa
suite_relpath: qa
suite_repo: https://git.ceph.com/ceph-ci.git
suite_sha1: 7b00023a6c268030a3ca35430bfc61e75afd447f
targets:
- smithi037.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBBAjeHtNErVnbGujMo7cy8lkt59mbF6pEoa/BMhQ3LWdebG+XtCLYRYaPfGcDNrSSzImimT/Nggcw3RShfIF8Yc=
- smithi052.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBCRcdwRkmgpxhbpPb9P2MBGRoxKhll5dGW8HJv5xMD9eISRnqNit/o6yIZ94EgVpywz052Z3yEGHpoRJCVwU+Ek=
- smithi167.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBD8GHdSYi219YJtwzL4NEvhl+d4379AIo2toE+ORspiLkpxWmw9Ry6zvzJ5si4UA4sdlyGq11WHalYQUoSZdw+Q=
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 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: True
pcp_grafana_url:
priority: 70
user: gabrioux
queue:
posted: 2024-08-09 12:47:19
started: 2024-08-09 14:05:12
updated: 2024-08-09 14:37:27
status_class: danger
runtime: 0:32:15
wait_time: 0:13:49