This will switch 90-ceph-osd.conf when compiling Crimson builds.
See 36326dc.
Clasical osd packages are adjusting the aio-max-nr value
from the default of 65536 to 1048576 as the default is too low
for some deployments. The same should be applied for Crimson's
packages.
No further changes are applied to ceph.spec.in / debuan/rules since
etc/sysctl/90-ceph-osd.conf will be installed regardless.
For rpm, we package crimson-osd with ceph-osd - this means that
the existing `%post osd` will be applied for crimson-osd packages
as well.
Signed-off-by: Matan Breizman <mbreizma@redhat.com>
For CONFIG_BASE_FULL Linux kernels, the maximum number of proc/thread
IDs is set to 32768 by default. This default limit can be quite easily
hit during recovery on nodes with high OSD counts.
To avoid hitting the pid_max default limit, attempt to configure it to
4194304, which corresponds to the maximum limit possible on 64-bit
CONFIG_BASE_FULL kernels.
Fixes: http://tracker.ceph.com/issues/21929
Signed-off-by: David Disseldorp <ddiss@suse.de>
Specify the nofile ulimit in one standard place, where everyone expects it
to be. Drop it from the ceph-osd unit file.
Leave upstart and sysvinit untouched for the time being to avoid compat
issues.
Signed-off-by: Sage Weil <sage@redhat.com>
Better to have static config like this that needs to be installed in
/etc in a separate subdirectory of the project.
Signed-off-by: Tim Serong <tserong@suse.com>