Pulpito :: Results Dashboard

Posted	Started	Updated	Runtime	Duration	In Waiting	Machine	Teuthology Branch	OS Type	OS Version	Nodes	Status
2024-07-26 13:26:50	2024-07-26 20:07:26	2024-07-26 20:14:55	0:07:29			smithi	main	ubuntu	22.04	3	dead

Nodes: smithi052 smithi090 smithi136

Description: rados/cephadm/workunits/{0-distro/ubuntu_22.04 agent/on mon_election/connectivity task/test_monitoring_stack_basic}

Log: http://qa-proxy.ceph.com/teuthology/yuriw-2024-07-26_13:22:04-rados-wip-yuri10-testing-2024-07-25-0747-distro-default-smithi/7819431/teuthology.log

Failure Reason:

Error reimaging machines: This operation would block forever Hub: <Hub '' at 0x7f71c31ffdd0 epoll default pending=0 ref=0 fileno=4 thread_ident=0x7f71c5995740> Handles: []

All Details...

log_href: http://qa-proxy.ceph.com/teuthology/yuriw-2024-07-26_13:22:04-rados-wip-yuri10-testing-2024-07-25-0747-distro-default-smithi/7819431/teuthology.log
archive_path: /home/teuthworker/archive/yuriw-2024-07-26_13:22:04-rados-wip-yuri10-testing-2024-07-25-0747-distro-default-smithi/7819431
description: rados/cephadm/workunits/{0-distro/ubuntu_22.04 agent/on mon_election/connectivity task/test_monitoring_stack_basic}
duration:
email: yweinste@redhat.com
failure_reason: Error reimaging machines: This operation would block forever Hub: Handles: []
flavor:
job_id: 7819431
kernel:
- kdb: 1
- sha1: distro
last_in_suite: False
machine_type: smithi
name: yuriw-2024-07-26_13:22:04-rados-wip-yuri10-testing-2024-07-25-0747-distro-default-smithi
nuke_on_error:
os_type: ubuntu
os_version: 22.04
overrides:
- admin_socket:
  - branch: wip-yuri10-testing-2024-07-25-0747
- ceph:
  - conf:
    - global:
      - mon election default strategy: 3
    - mgr:
      - debug mgr: 20
      - debug ms: 1
      - mgr/cephadm/use_agent: True
    - 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: 387735b04c21d62e21975a50a7f6c06a95b3cf6d
- ceph-deploy:
  - conf:
    - client:
      - log file: /var/log/ceph/ceph-$name.$pid.log
    - mon:
- install:
  - ceph:
    - flavor: default
    - sha1: 387735b04c21d62e21975a50a7f6c06a95b3cf6d
- workunit:
  - branch: wip-yuri10-testing-2024-07-25-0747
  - sha1: 387735b04c21d62e21975a50a7f6c06a95b3cf6d
owner: scheduled_yuriw@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:
status: dead
success:
branch: wip-yuri10-testing-2024-07-25-0747
seed: 7059
sha1: 387735b04c21d62e21975a50a7f6c06a95b3cf6d
subset: 111/120000
suite: rados
suite_branch: wip-yuri10-testing-2024-07-25-0747
suite_path: /home/teuthworker/src/github.com_ceph_ceph-c_387735b04c21d62e21975a50a7f6c06a95b3cf6d/qa
suite_relpath: qa
suite_repo: https://github.com/ceph/ceph-ci.git
suite_sha1: 387735b04c21d62e21975a50a7f6c06a95b3cf6d
targets:
- smithi052.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBHAFj7nDMuik3N0m4O8K/Hmpe+VbmXIBxySV2qkyv9II5rR2+yPTIrUFH/Joc2I7t2gMJdduRPt6XWrjSiGZxNc=
- smithi090.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBNpASyJrji32Ri8xhHwLCd7F7nFNyv+Wu6v+1TPvCXzrrt1tEoCI2b6WDsO2yGUeFMRSEBWIantKnHfopJnTB+Q=
- smithi136.front.sepia.ceph.com: ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBMdQeTJxqNRHgLgQ4sLbdkqSsAhxXSmmeF5aodda/yG0F05TyQRPkcL2WT+AF2LfV4BmNcgDPp99EcB9VYKF+e0=
tasks:
- 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: 99
user: yuriw
queue:
posted: 2024-07-26 13:26:50
started: 2024-07-26 20:07:26
updated: 2024-07-26 20:14:55
status_class: danger
runtime: 0:07:29