mirror of
https://github.com/ceph/ceph
synced 2024-12-22 11:31:55 +00:00
d88c834ea4
Ceph AIO installation with single/multiple node is not friendly for
loopback mount, especially always get deadlock issue during graceful
system reboot.
We already have `rbdmap.service` with graceful system reboot friendly as
below:
[Unit]
After=network-online.target
Before=remote-fs-pre.target
Wants=network-online.target remote-fs-pre.target
[Service]
ExecStart=/usr/bin/rbdmap map
ExecReload=/usr/bin/rbdmap map
ExecStop=/usr/bin/rbdmap unmap-all
This PR introduce:
- `ceph-mon.target`: Ensure startup after `network-online.target` and
before `remote-fs-pre.target`
- `ceph-*.target`: Ensure startup after `ceph-mon.target` and before
`remote-fs-pre.target`
- `rbdmap.service`: Once all `_netdev` get unmount by
`remote-fs.target`, ensure unmap all RBD BEFORE any Ceph components
under `ceph.target` get stopped during shutdown
The logic is concept proof by
<https://github.com/alvistack/ansible-role-ceph_common/tree/develop>;
also works as expected with Ceph + Kubernetes deployment by
<https://github.com/alvistack/ansible-collection-kubernetes/tree/develop>.
No more deadlock happened during graceful system reboot, both AIO
single/multiple no de with loopback mount.
Also see:
- <https://github.com/ceph/ceph/pull/36776>
- <https://github.com/etcd-io/etcd/pull/12259>
- <https://github.com/cri-o/cri-o/pull/4128>
- <https://github.com/kubernetes/release/pull/1504>
Fixes: https://tracker.ceph.com/issues/47528
Signed-off-by: Wong Hoi Sing Edison <hswong3i@gmail.com>
38 lines
1.0 KiB
SYSTEMD
38 lines
1.0 KiB
SYSTEMD
[Unit]
|
|
Description=Ceph cluster manager daemon
|
|
PartOf=ceph-mgr.target
|
|
After=network-online.target local-fs.target time-sync.target
|
|
Before=remote-fs-pre.target ceph-mgr.target
|
|
Wants=network-online.target local-fs.target time-sync.target remote-fs-pre.target ceph-mgr.target
|
|
|
|
[Service]
|
|
Environment=CLUSTER=ceph
|
|
EnvironmentFile=-@SYSTEMD_ENV_FILE@
|
|
ExecReload=/bin/kill -HUP $MAINPID
|
|
ExecStart=/usr/bin/ceph-mgr -f --cluster ${CLUSTER} --id %i --setuser ceph --setgroup ceph
|
|
LimitNOFILE=1048576
|
|
LimitNPROC=1048576
|
|
LockPersonality=true
|
|
NoNewPrivileges=true
|
|
PrivateDevices=yes
|
|
PrivateTmp=true
|
|
ProtectClock=true
|
|
ProtectControlGroups=true
|
|
ProtectHome=true
|
|
ProtectHostname=true
|
|
ProtectKernelLogs=true
|
|
ProtectKernelModules=true
|
|
ProtectKernelTunables=true
|
|
ProtectSystem=full
|
|
Restart=on-failure
|
|
RestartSec=10
|
|
RestrictSUIDSGID=true
|
|
StartLimitBurst=3
|
|
StartLimitInterval=30min
|
|
# We need to disable this protection as some python libraries generate
|
|
# dynamic code, like python-cffi, and require mmap calls to succeed
|
|
MemoryDenyWriteExecute=false
|
|
|
|
[Install]
|
|
WantedBy=ceph-mgr.target
|