mirror of https://github.com/ceph/ceph
systemd: Support Graceful Reboot for AIO Node
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>
This commit is contained in:
Wong Hoi Sing Edison
parent
ff16f5d67c
commit
d88c834ea4
|
|
@ -2,5 +2,6 @@
|
|||
Description=ceph target allowing to start/stop all ceph-fuse@.service instances at once
|
||||
PartOf=ceph.target
|
||||
Before=ceph.target
|
||||
|
||||
[Install]
|
||||
WantedBy=remote-fs.target ceph.target
|
||||
|
|
|
|||
|
|
@ -2,5 +2,6 @@
|
|||
Description=ceph target allowing to start/stop all ceph-immutable-object-cache@.service instances at once
|
||||
PartOf=ceph.target
|
||||
Before=ceph.target
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target ceph.target
|
||||
|
|
|
|||
|
|
@ -1,6 +1,9 @@
|
|||
[Unit]
|
||||
Description=ceph target allowing to start/stop all ceph-mds@.service instances at once
|
||||
PartOf=ceph.target
|
||||
After=ceph-mon.target
|
||||
Before=ceph.target
|
||||
Wants=ceph.target ceph-mon.target
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target ceph.target
|
||||
|
|
|
|||
|
|
@ -1,8 +1,9 @@
|
|||
[Unit]
|
||||
Description=Ceph metadata server daemon
|
||||
After=network-online.target local-fs.target time-sync.target
|
||||
Wants=network-online.target local-fs.target time-sync.target
|
||||
PartOf=ceph-mds.target
|
||||
After=network-online.target local-fs.target time-sync.target
|
||||
Before=remote-fs-pre.target ceph-mds.target
|
||||
Wants=network-online.target local-fs.target time-sync.target remote-fs-pre.target ceph-mds.target
|
||||
|
||||
[Service]
|
||||
Environment=CLUSTER=ceph
|
||||
|
|
|
|||
|
|
@ -1,6 +1,9 @@
|
|||
[Unit]
|
||||
Description=ceph target allowing to start/stop all ceph-mgr@.service instances at once
|
||||
PartOf=ceph.target
|
||||
After=ceph-mon.target
|
||||
Before=ceph.target
|
||||
Wants=ceph.target ceph-mon.target
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target ceph.target
|
||||
|
|
|
|||
|
|
@ -1,8 +1,9 @@
|
|||
[Unit]
|
||||
Description=Ceph cluster manager daemon
|
||||
After=network-online.target local-fs.target time-sync.target
|
||||
Wants=network-online.target local-fs.target time-sync.target
|
||||
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
|
||||
|
|
@ -28,11 +29,9 @@ 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
|
||||
|
|
|
|||
|
|
@ -2,5 +2,7 @@
|
|||
Description=ceph target allowing to start/stop all ceph-mon@.service instances at once
|
||||
PartOf=ceph.target
|
||||
Before=ceph.target
|
||||
Wants=ceph.target
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target ceph.target
|
||||
|
|
|
|||
|
|
@ -1,13 +1,13 @@
|
|||
[Unit]
|
||||
Description=Ceph cluster monitor daemon
|
||||
|
||||
PartOf=ceph-mon.target
|
||||
# According to:
|
||||
# http://www.freedesktop.org/wiki/Software/systemd/NetworkTarget
|
||||
# these can be removed once ceph-mon will dynamically change network
|
||||
# configuration.
|
||||
After=network-online.target local-fs.target time-sync.target
|
||||
Wants=network-online.target local-fs.target time-sync.target
|
||||
PartOf=ceph-mon.target
|
||||
Before=remote-fs-pre.target ceph-mon.target
|
||||
Wants=network-online.target local-fs.target time-sync.target remote-fs-pre.target ceph-mon.target
|
||||
|
||||
[Service]
|
||||
Environment=CLUSTER=ceph
|
||||
|
|
|
|||
|
|
@ -1,6 +1,9 @@
|
|||
[Unit]
|
||||
Description=ceph target allowing to start/stop all ceph-osd@.service instances at once
|
||||
PartOf=ceph.target
|
||||
After=ceph-mon.target
|
||||
Before=ceph.target
|
||||
Wants=ceph.target ceph-mon.target
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target ceph.target
|
||||
|
|
|
|||
|
|
@ -1,8 +1,9 @@
|
|||
[Unit]
|
||||
Description=Ceph object storage daemon osd.%i
|
||||
After=network-online.target local-fs.target time-sync.target ceph-mon.target
|
||||
Wants=network-online.target local-fs.target time-sync.target
|
||||
PartOf=ceph-osd.target
|
||||
After=network-online.target local-fs.target time-sync.target
|
||||
Before=remote-fs-pre.target ceph-osd.target
|
||||
Wants=network-online.target local-fs.target time-sync.target remote-fs-pre.target ceph-osd.target
|
||||
|
||||
[Service]
|
||||
Environment=CLUSTER=ceph
|
||||
|
|
|
|||
|
|
@ -1,6 +1,9 @@
|
|||
[Unit]
|
||||
Description=ceph target allowing to start/stop all ceph-radosgw@.service instances at once
|
||||
PartOf=ceph.target
|
||||
After=ceph-mon.target
|
||||
Before=ceph.target
|
||||
Wants=ceph.target ceph-mon.target
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target ceph.target
|
||||
|
|
|
|||
|
|
@ -1,8 +1,9 @@
|
|||
[Unit]
|
||||
Description=Ceph rados gateway
|
||||
After=network-online.target local-fs.target time-sync.target
|
||||
Wants=network-online.target local-fs.target time-sync.target
|
||||
PartOf=ceph-radosgw.target
|
||||
After=network-online.target local-fs.target time-sync.target
|
||||
Before=remote-fs-pre.target ceph-radosgw.target
|
||||
Wants=network-online.target local-fs.target time-sync.target remote-fs-pre.target ceph-radosgw.target
|
||||
|
||||
[Service]
|
||||
Environment=CLUSTER=ceph
|
||||
|
|
|
|||
|
|
@ -2,5 +2,6 @@
|
|||
Description=ceph target allowing to start/stop all ceph-rbd-mirror@.service instances at once
|
||||
PartOf=ceph.target
|
||||
Before=ceph.target
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target ceph.target
|
||||
|
|
|
|||
|
|
@ -1,4 +1,5 @@
|
|||
[Unit]
|
||||
Description=ceph target allowing to start/stop all ceph*@.service instances at once
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
|
|
|
|||
|
|
@ -1,9 +1,8 @@
|
|||
[Unit]
|
||||
Description=Map RBD devices
|
||||
|
||||
After=network-online.target
|
||||
After=network-online.target ceph.target
|
||||
Before=remote-fs-pre.target
|
||||
Wants=network-online.target remote-fs-pre.target
|
||||
Wants=network-online.target remote-fs-pre.target ceph.target
|
||||
|
||||
[Service]
|
||||
EnvironmentFile=-@SYSTEMD_ENV_FILE@
|
||||
|
|
|
|||
Loading…
Reference in New Issue