This PR makes the "Ceph OSDs" and "MDSs" bullet points
parallel by naming "object storage daemon" before referring
to the (admittedly more common and colloquial, but surely
unknown to people who genuinely require a document called
'Intro') acronym "OSD".
Signed-off-by: Zac Dover <zac.dover@gmail.com>
This PR supersedes https://github.com/ceph/ceph/pull/46584
and makes changes suggested by Anthony D'Atri that improve
the coherence and consistency of the paragraph that explains
the basics of the CRUSH algorithm.
Signed-off-by: Zac Dover <zac.dover@gmail.com>
The 'size' shown in the output of snapshot info command relies on
rstats which is incorrect snapshot size. It tracks size of the
subvolume from the snapshot has been taken instead of the snapshot
itself. Hence having the 'size' field in the output of 'snapshot info'
doesn't make sense until the rstats is fixed.
Fixes: https://tracker.ceph.com/issues/55822
Signed-off-by: Nikhilkumar Shelke <nshelke@redhat.com>
The 'size' shown in the output of snapshot info command relies on
rstats which is incorrect snapshot size. It tracks size of the
subvolume from the snapshot has been taken instead of the snapshot
itself. Hence having the 'size' field in the output of 'snapshot info'
doesn't make sense until the rstats is fixed.
Fixes: https://tracker.ceph.com/issues/55822
Signed-off-by: Nikhilkumar Shelke <nshelke@redhat.com>
The 'size' shown in the output of snapshot info command relies on
rstats which is incorrect snapshot size. It tracks size of the
subvolume from the snapshot has been taken instead of the snapshot
itself. Hence having the 'size' field in the output of 'snapshot info'
doesn't make sense until the rstats is fixed.
Fixes: https://tracker.ceph.com/issues/55822
Signed-off-by: Nikhilkumar Shelke <nshelke@redhat.com>
pool should not be shared between multiple file system.
Hence adding check to verify pool is already not in use.
Fixes: https://tracker.ceph.com/issues/54111
Signed-off-by: Nikhilkumar Shelke <nshelke@redhat.com>
This reverts commit 9fb7ec61ba.
Although the chunking in off-line `dups` trimming (via COT) seems
fine, the `ceph-objectstore-tool` is a client of `trim()` of
`PGLog::IndexedLog` which means than a partial revert is not
possible without extensive changes. Moreover, trimming pg log
is not enough without modifying pg_info_t accordingly which
the reverted patch lacks.
Fixes: https://tracker.ceph.com/issues/53729
Signed-off-by: Radosław Zarzyński <rzarzyns@redhat.com>
This reverts commit 0d253bcc09.
which is the in-OSD part of the fix for accumulation of `dup`
entries in a PG Log. Brainstorming it has brought questions
on the OSD's behaviour during an upgrade if there are tons of
dups in the log. What must be double-checked before bringing
it back is ensuring we chunk the deletions properly to not
impose OOMs / stalls in, to exemplify, RocksDB.
Fixes: https://tracker.ceph.com/issues/53729
Signed-off-by: Radosław Zarzyński <rzarzyns@redhat.com>
Change Cache::get_(del)_backrefs_in_range's return from extents in [start,end] to extents in
[start, end); this is because BackrefManager::get_mappings return extents in [start,end), and
Cache's related methods have to be consistent with BackrefManager::get_mappings
Signed-off-by: Xuehan Xu <xxhdx1985126@gmail.com>
* refs/pull/46421/head:
doc/dev: move option -R to a different section of doc
Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
Reviewed-by: Anthony D Atri <anthony.datri@gmail.com>
We really want to have the ability to know how many
entries `PGLog::IndexedLog::dups` has inside.
The current ways are either invasive (stopping an OSD)
or indirect (examination of `dump_mempools`).
The code comes from Nitzan Mordechai (part of
ede37edd79a9d5560dfb417ec176327edfc0e4a3).
Fixes: https://tracker.ceph.com/issues/55982
Signed-off-by: Radoslaw Zarzynski <rzarzyns@redhat.com>
The unit type for `client_mount_timeout` was changed from "float" to "secs" in
983b10506d. To make this test comply with the new
seconds unit change, we need to change the value to an integer, as seconds
does not accept float values.
Fixes: https://tracker.ceph.com/issues/55971
Signed-off-by: Laura Flores <lflores@redhat.com>
lua integer is "long long int" which works with GCC 11.2.1 (fedora 36)
but fails to compile on centos8 and ubuntu focal
Signed-off-by: yuval Lifshitz <ylifshit@redhat.com>
It's hitting pacific with a nuisance -Werror=array-parameter= const
char * vs const char[37] mismatch. Follow commit 91a616b26e ("cmake:
pass RTE_DEVEL_BUILD=n when building dpdk") and just disable -Werror.
Fixes: https://tracker.ceph.com/issues/55977
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Building with jaeger by default pulls in opentelemetry, and
cmake/modules/BuildOpentelemetry.cmake tries to go get
https://github.com/ideepika/opentelemetry-cpp.git at build
time, which doesn't work on SUSE's build service (no internet
access at build time). Also, since WITH_JAEGER now defaults
to ON in CMakeLists.txt, we need to flip the logic when
setting -DWITH_JAEGER.
Fixes: 644c99826d
Fixes: 7be8be6350
Signed-off-by: Tim Serong <tserong@suse.com>
if goest into do_osd_ops, will set osd_op.rval, but it
is not reuqired in some tests, this follow classic ceph do_op logic.
Signed-off-by: chunmei-liu <chunmei.liu@intel.com>
https://github.com/ceph/teuthology/pull/999 never got overridden in ceph.git. We've been using a years-old checkout of teuthology for the `teuthology` user.
With the master->main change, that checkout needed to go. Then when trying to schedule new nightlies, teuthology-suite was defaulting to ceph-ci.git which either has very old versions of the release branches (octopus, pacific, etc.) or they don't exist at all.
Signed-off-by: David Galloway <dgallowa@redhat.com>
It's incorrect to pass option "-R fail" to the teuthology-suite command
meant for triggering tests for first time. teuthology-suite command will
fail if "-R" is passed without "-r". Therefore, move this option and its
description from the section meant for triggering tests for first time
to the section dedicated to re-running of tests.
Signed-off-by: Rishabh Dave <ridave@redhat.com>
