Currently contexts C_Probe/C_PurgeRange are executed while holding
OSDSession::completion_lock. C_Probe and C_PurgeRange may call
Objecter::stat() and Objecter::remove() respectively, which acquire
Objecter::rwlock. This can cause deadlock because there is intermediate
dependency between Objecter::rwlock and OSDSession::completion_lock:
Objecter::rwlock -> OSDSession::lock -> OSDSession::completion_lock
The fix is exexcute C_Probe/C_PurgeRange in finisher thread.
Fixes: #10229
Signed-off-by: Yan, Zheng <zyan@redhat.com>
The google/ headers location has been deprecated as of gperftools 2.0.
As of gperftools 2.2rc, the google/ headers will now give deprecation
warnings, and they will probably disappear in a future gperftools
update.
Signed-off-by: Ken Dreyer <kdreyer@redhat.com>
This was missing from 17b5fc9a but we didn't notice
because the test wasn't being run by the gitbuilders.
Signed-off-by: John Spray <john.spray@redhat.com>
In the past (e229f8451d) we decided to disable
reset of lossless Pipes, because lossless peers resetting caused trouble and
they can't forget about each other. But they actually can: if mark_down()
is called.
I can't figure out how else we could forget about a remote endpoint, so I think
it's okay if we tell them we reset in order to clean up state. That's desirable
so that we don't get into strange situations with out-of-whack counters.
Fixes: #10080
Backport: giant, firefly, dumpling
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
The func of command perfcounters_dump and 'perf dump' are the same .
But from the print 'ceph --admin-daemon help', it only print 'perf
dump'. So replace.
In order to keep consistent, still keep perfcounters_dump in code for
old user.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
--admin-daemon'
Using this command, we can reset all perfcounters or reset on specified
perfcounter.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
Fedora doesn't have point releases, so it doesn't make sense to talk
about "Fedora 18.0" or "Fedora 19.0" - it's just "Fedora 18" or "Fedora
19".
Signed-off-by: Ken Dreyer <kdreyer@redhat.com>
This was introduced before cuttlefish. We require users to upgrade first
to a newer release, so there is no need to support a mixed cluster with
such old code.
Signed-off-by: Sage Weil <sage@redhat.com>
The ceph-disk man page was added in
a450cab2b8, but this was not added to the
RPM or DEB packaging. Add it here.
Signed-off-by: Ken Dreyer <kdreyer@redhat.com>
We don't exactly do continuous builds on all the platforms marked with
"B", but we have published binary RPMs for them. Adjust the "B"
footnote definition to reflect this.
Signed-off-by: Ken Dreyer <kdreyer@redhat.com>
Using the array notation to list test is error prone and more
complicated to write.
It also fixes a bug : only the first test of each series (MON, OSD, MDS)
was run and the others were ignored.
Signed-off-by: Loic Dachary <loic@dachary.org>
The list of daemons is provided in the $CEPH_START environment variable
but vstart_wrapper.sh incorrectly uses the $VSTART_ARGS empty variable.
As a consequence vstart.sh calls init-ceph stop which kills daemons that
do not belong to the test.
http://tracker.ceph.com/issues/10215Fixes: #10215
Signed-off-by: Loic Dachary <loic@dachary.org>
Let say the ErasureCode::encode function is given a 4096 bytes
bufferlist made of a 1249 bytes bufferptr followed by a 2847 bytes
bufferptr, both properly starting on SIMD_ALIGN address. As a result the
second 2048 had to be reallocated when bufferlist::substr_of gets the
second 2048 buffer, the address starts at 799 bytes after the beginning
of the 2847 buffer ptr and is not SIMD_ALIGN'ed.
The ErasureCode::encode must enforce a size alignment based on the chunk
size in addition to the memory alignment required by SIMD operations,
using the bufferlist::rebuild_aligned_size_and_memory function instead of
bufferlist::rebuild_aligned.
http://tracker.ceph.com/issues/10211Fixes: #10211
Signed-off-by: Loic Dachary <loic@dachary.org>
Do not assume the alignment is a power of two in the is_n_align_sized()
predicate. When used in the context of erasure code it is common
for chunks to not be powers of two.
Signed-off-by: Loic Dachary <loic@dachary.org>
The function bufferlist::rebuild_aligned checks memory and size
alignment with the same variable. It is however useful to separate
memory alignment constraints from size alignment constraints. For
instance rebuild_aligned could be called to allocate an erasure coded
buffer where each 2048 bytes chunk needs to start on a memory address
aligned on 32 bytes.
Signed-off-by: Loic Dachary <loic@dachary.org>
CentOS 7 was missing from the list of recommended OSes for Firefly. Add
it to the list.
Reported-By: Frank Even <lists+ceph.com@elitists.org>
Signed-off-by: Ken Dreyer <kdreyer@redhat.com>
