Currently the create code decides the vg_name "ceph-$cluster_fsid" as
the primary vg_name and creates a new name if this already exists.
If this code is run N times in parallel, the script will try to
create N times the vg with the name "ceph-$cluster_fsid" and it
will fail to create the N osds successfully.
Creating vgs with names like "ceph-$uuid4" lets our scripts to run
without any problems.
Signed-off-by: Theofilos Mouratidis <t.mour@cern.ch>
rhel/centos 7.3 comes with tox 1.4.2, which has a bunch of issues related
to environment variable substitution. for instance, see
- https://github.com/tox-dev/tox/issues/515
so, instead of having different coverage files for py3 and py2.7, it
would be simpler to just use the same path for coverage. this approach
works because pytest-cov plugin erases the coverage data file at the
beginning of test[1].
---
[1] https://pypi.org/project/pytest-cov/#coverage-data-file .
Signed-off-by: Kefu Chai <kchai@redhat.com>
This allows all ranks to stop. If the administrator shuts down the cluster then
we should immediately shut down all client's I/O.
Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
MDS deactivation is now handled by the max_mds parameter. Deprecate
ceph mds deactivate and note it to be removed in a future release.
Signed-off-by: Douglas Fuller <dfuller@redhat.com>
As dirfrags are now standard in CephFS, remove the machinery for
tracking and enabling this feature.
ceph fs set <fs> allow_dirfrags is now deprecated and prints a warning
message.
Signed-off-by: Douglas Fuller <dfuller@redhat.com>
With multi-mds now declared stable, allow_multimds now defaults to 1.
Given the max_mds parameter, it is now redundant. Remove it, leaving a
comment placeholder in the features bitmap.
ceph fs set <fs> allow_multimds is now deprecated and prints a warning
message.
Signed-off-by: Douglas Fuller <dfuller@redhat.com>
Setting the cluster_down flag will now set all active MDS
to standby and clearing it will restore the previous max_mds.
Changing max_mds when the cluster_down flag is set will clear the
flag automatically.
Signed-off-by: Douglas Fuller <dfuller@redhat.com>
Issue the HEALTH_WARN MDS_UP_LESS_THAN_MAX whenever an MDS cluster
has fewer than its max_mds online.
Issue the HEALTH_ERR MDS_ALL_DOWN whenever an MDS cluster has no
active MDS.
Signed-off-by: Douglas Fuller <dfuller@redhat.com>
No longer check for commands for deprecated legacy filesystems.
These commands are long since deprecated and this code is no longer
needed.
Signed-off-by: Douglas Fuller <dfuller@redhat.com>
This commit is designed to permanently protect the current epoch FSMap from
accidental changes. Modifications to the pending_fsmap are protected by
checking if the monitor is the leader. Additionally, code must explicitly
request a writeable reference.
Fixes http://tracker.ceph.com/issues/23762
Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
Drop 4.4 -- even though it is an "Extended LTS" release, it predates
the OSD client rewrite and should no longer be recommended.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
