Hi Ilya,
I put my patches in a single branch to make it easier for review.
[1/9] is about to show rbd options in sysfs.
[2/9] - [3/9] is about mark rbd device to readonly when we enable unsupported feature by rbd cli.
[4/9] is about to show the client_options of ceph client
[5/9] - [9/9] is about to return -ENOSPC when cluster is full, rather than block the IO.
Any comments are welcome.
Thanx
Yang
Dongsheng Yang (9):
rbd: show the rbd options in sysfs
rbd: return the features to caller even if there is unsupported bits
rbd: refresh features and set the disk to readonly if there is
unsupported bit
ceph: show all options in client_options even if option is equal with
default value
rbd: protect flag bit of RBD_DEV_FLAG_BLACKLISTED with lock_rwsem
rbd: wake up waiter in rbd_acquire_lock if we got -EBLACKLISTED
ceph: set the req->r_abort_on_full in ceph_osdc_call when we are
writing
rbd: set req->r_abort_on_full in writing
rbd: try to acquire lock once before going waiting
drivers/block/rbd.c | 109 ++++++++++++++++++++++++++++++++++---------
fs/ceph/super.c | 2 +-
include/linux/ceph/libceph.h | 2 +-
net/ceph/ceph_common.c | 10 ++--
net/ceph/debugfs.c | 2 +-
net/ceph/osd_client.c | 2 +
6 files changed, 98 insertions(+), 29 deletions(-)
--
1.8.3.1
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
