On 6/29/21 11:27 PM, Jeff Layton wrote:
On Tue, 2021-06-29 at 12:42 +0800, xiubli@xxxxxxxxxx wrote:
From: Xiubo Li <xiubli@xxxxxxxxxx>
For the client requests who will have unsafe and safe replies from
MDS daemons, in the MDS side the MDS daemons won't flush the mdlog
(journal log) immediatelly, because they think it's unnecessary.
That's true for most cases but not all, likes the fsync request.
The fsync will wait until all the unsafe replied requests to be
safely replied.
Normally if there have multiple threads or clients are running, the
whole mdlog in MDS daemons could be flushed in time if any request
will trigger the mdlog submit thread. So usually we won't experience
the normal operations will stuck for a long time. But in case there
has only one client with only thread is running, the stuck phenomenon
maybe obvious and the worst case it must wait at most 5 seconds to
wait the mdlog to be flushed by the MDS's tick thread periodically.
This patch will trigger to flush the mdlog in all the MDSes manually
just before waiting the unsafe requests to finish.
This seems a bit heavyweight, given that you may end up sending
FLUSH_MDLOG messages to mds's on which you're not waiting. What might be
best is to scan the list of requests you're waiting on and just send
these messages to those mds's.
Is that possible here?
Yeah, possibly and let me try that.
Thanks.
Xiubo Li (5):
ceph: export ceph_create_session_msg
ceph: export iterate_sessions
ceph: flush mdlog before umounting
ceph: flush the mdlog before waiting on unsafe reqs
ceph: fix ceph feature bits
fs/ceph/caps.c | 35 ++++----------
fs/ceph/mds_client.c | 91 +++++++++++++++++++++++++++---------
fs/ceph/mds_client.h | 9 ++++
include/linux/ceph/ceph_fs.h | 1 +
4 files changed, 88 insertions(+), 48 deletions(-)
