Otherwise a pre-single-major kernel override is a headache,
particularly with non-standard yaml configs.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
The unmap test uses one remote, so the end result is the same.
However, overriding the most specific role is nicer and allows
scheduling with
kernel:
client:
branch: testing
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Kernel 3.13, which is used in pre-single-major.yaml test, doesn't
support firefly tunables (default in jewel, up from bobtail tunables).
This went unnoticed for a while because of a kernel task regression -
the pre-single-major override was ignored.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Similarly to how single-major-off.yaml and single-major-on.yaml check
the value of /sys/module/rbd/parameters/single_major, assert that it's
not there for pre-single-major.yaml.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Also removes fio-version option from yaml since its redundant and if required can be specified in
overrides
Signed-off-by: Vasu Kulkarni <vasu@redhat.com>
.. for testing various unmap scenarios, mostly unmap by spec, but also
unmap by device and device partition.
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
The tiobench software has been abandoned upstream for years. Fedora and
Debian are no longer shipping the tiobench package, so we've had to
carry the package ourselves in the Ceph project, and we're trying to
slim down our dependencies where it makes sense to do so.
Nuke the tiobench tests.
http://tracker.ceph.com/issues/10152 Refs: #10152
Signed-off-by: Ken Dreyer <kdreyer@redhat.com>
Our fsx fork has recently gained a support for the krbd mode - add it
to the test suite. Disable discard ops and randomized striping, both
of which aren't ready yet.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
In the current xfstests, tests cannot be listed in ranges. Because of
this, and because our distribution of tests between our three clients
was pretty uneven, I've changed this job to run the whole auto group
(with some tests excluded by run_xfstests_krbd.sh) in random order on
two clients in parallel. It takes longer to run, but it also spares
a test box and can potentially create a better test workload.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
libceph.ko support is in testing and should be in 3.15. This commit
effectively reverts commit 66ffaa6565 ("kcephfs, krbd: do not thrash
primary-affinity").
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
This is ignored by old teuthology, but used by newer code to tell us when
to generate a product of all directory items.
Signed-off-by: Sage Weil <sage@inktank.com>
