This was kind of easy to miss, and if users
just paste in the command as given then their
first few OSDs will work, and from their
4th OSD onwards things will get weird.
Signed-off-by: John Spray <john.spray@redhat.com>
* nodelete - pool can't be deleted
* nopgchange - pool's pg and pgp num can't be changed
* nosizechange - pool's size and min size can't be changed
This is intended to help some poor admin to avoid a very bad day.
Fixes: #9792 (but in a different way than it was proposed there)
Signed-off-by: Mykola Golub <mgolub@mirantis.com>
Add a new section to the PG troubleshooting section that covers the most
common problems reported when an erasure coded pool fails to properly
map PGs to enough OSDs.
http://tracker.ceph.com/issues/10350Fixes: #10350
Signed-off-by: Loic Dachary <ldachary@redhat.com>
undersized not valid: undersized not in inactive|unclean|stale
undersized not valid: undersized doesn't represent an int
Invalid command: unused arguments: ['undersized']
pg dump_stuck {inactive|unclean|stale [inactive|unclean|stale...]} {<int>} : show information about stuck pgs
Signed-off-by: xinxin shu <xinxin.shu@intel.com>
Remove the reference to "Ubuntu 12.10" since this is EOL.
Clarify that we only recommend Ubuntu LTS releases.
(Since this information has a tendancy to become stale, perhaps this
whole paragraph should be removed here and we should simply point at the
main OS Recommendations page.)
Signed-off-by: Ken Dreyer <kdreyer@redhat.com>
A short introduction to the first time user of an erasure coded pool.
It includes a reminder of how it relates to cache tiering and links to
define new profiles with an example.
There was examples in the developer documentation but the operator
expects to find such a guide in the rados operations chapter.
http://tracker.ceph.com/issues/9970Fixes: #9970
Signed-off-by: Loic Dachary <ldachary@redhat.com>
LRC now uses Jerasure as the default EC backend. But it is actually
possible to switch to other backend like Isa using the low level
configuration. This commits Adds documents on how to specify the EC
backend in each LRC layer:
Signed-off-by: Yuan Zhou <yuan.zhou@intel.com>
Add release note
New librados interface
New pg_nls_response_t over the wire protocol
Ignore internal namespace (.ceph_internal)
Enhance ObjListCtx to keep independent IoCtxImpl so nspace won't change out from under listing code
Add ListObject with private implementation ListObjectImpl to return from iterator
Add EINVAL error for old librados interface when LIBRADOS_ALL_NSPACES set
Add throw to old librados c++ interface when all_nspaces set
Fixes: #9031
Signed-off-by: David Zafman <dzafman@redhat.com>
* Update the ceph tell from ceph daemon tell id to the new
ceph tell deamon.id form
* Add usages examples for easier copy / paste
* Add MON to the list of daemons that can be profiled
* Document CEPH_HEAP_PROFILER_INIT=true
* Remove trailing empty lines
Signed-off-by: Loic Dachary <loic-201408@dachary.org>
When a cluster has few OSDs (less than 50) propose a preselection of
values: as long as the number of placement groups is not too small nor
too large, it won't make much of a difference anyway.
Users of small clusters tend to blindly apply the (OSD*100)/(pool size)
formula and worry about chosing a wrong value because they do not
understand the tradeoffs. The preselection will hopefully save them from
this uncertainty.
Add an explanation of how placement groups relate to OSDs, CRUSH and
pools to help understand the tradeoffs. Explain the
tradeoffs (durability, distribution and resource usages) with examples.
Signed-off-by: Loic Dachary <loic-201408@dachary.org>
Reviewed-by: Gerben Meijer <infernix@gmail.com>
Reviewed-by: Laurent Guerby <laurent@guerby.net>
