- 07 Jul, 2021 38 commits
-
-
Trond Myklebust authored
When flushing out the unstable file writes as part of a COMMIT call, try to perform most of of the data writes and waits outside the semaphore. This means that if the client is sending the COMMIT as part of a memory reclaim operation, then it can continue performing I/O, with contention for the lock occurring only once the data sync is finished. Fixes: 5011af4c ("nfsd: Fix stable writes") Signed-off-by:
Trond Myklebust <trond.myklebust@hammerspace.com> Tested-by:
Chuck Lever <chuck.lever@oracle.com> Signed-off-by:
J. Bruce Fields <bfields@redhat.com>
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
Chuck Lever authored
Add a .h file containing xdr_stream-based XDR helpers common to both NLMv3 and NLMv4. Signed-off-by:
-
Chuck Lever authored
To enable xdr_stream-based encoding and decoding, create a bespoke RPC dispatch function for the lockd service. Signed-off-by:
-
Chuck Lever authored
Signed-off-by:
-
J. Bruce Fields authored
I'm not even sure cl_xprt can change here, but we're getting "suspicious RCU usage" warnings, and other rpc_peeraddr2str callers are taking the rcu lock. Signed-off-by: -
Colin Ian King authored
The variable status is being initialized with a value that is never read, the assignment is redundant and can be removed. Addresses-Coverity: ("Unused value") Signed-off-by:Colin Ian King <colin.king@canonical.com> Signed-off-by:
-
ChenXiaoSong authored
Fix gcc W=1 warning: fs/nfs_common/grace.c:91: warning: Function parameter or member 'net' not described in 'locks_in_grace' Signed-off-by:
ChenXiaoSong <chenxiaosong2@huawei.com> Signed-off-by:
-
Wei Yongjun authored
'status' has been overwritten to 0 after nfsd4_ssc_setup_dul(), this cause 0 will be return in vfs_kern_mount() error case. Fix to return nfserr_nodev in this error. Fixes: f4e44b39 ("NFSD: delay unmount source's export after inter-server copy completed.") Reported-by:
Hulk Robot <hulkci@huawei.com> Signed-off-by:
Wei Yongjun <weiyongjun1@huawei.com> Signed-off-by:
-
Dai Ngo authored
Fix by initializing pointer nfsd4_ssc_umount_item with NULL instead of 0. Replace return value of nfsd4_ssc_setup_dul with __be32 instead of int. Reported-by:
kernel test robot <lkp@intel.com> Signed-off-by:
Dai Ngo <dai.ngo@oracle.com> Signed-off-by:
-
Dave Wysochanski authored
In addition to the client's address, display the callback channel state and address in the 'info' file. Signed-off-by:
Dave Wysochanski <dwysocha@redhat.com> Signed-off-by:
-
Zheng Yongjun authored
Fix some spelling mistakes in comments: succes ==> success Signed-off-by:
Zheng Yongjun <zhengyongjun3@huawei.com> Signed-off-by:
-
J. Bruce Fields authored
This was causing a "sleeping function called from invalid context" warning. I don't think we need the set_and_test_bit() here; clients move from unconfirmed to confirmed only once, under the client_lock. The (conf == unconf) is a way to check whether we're in that confirming case, hopefully that's not too obscure. Fixes: 472d155a "nfsd: report client confirmation status in "info" file" Signed-off-by:
-
- 25 May, 2021 2 commits
-
-
Dai Ngo authored
Currently the source's export is mounted and unmounted on every inter-server copy operation. This patch is an enhancement to delay the unmount of the source export for a certain period of time to eliminate the mount and unmount overhead on subsequent copy operations. After a copy operation completes, a work entry is added to the delayed unmount list with an expiration time. This list is serviced by the laundromat thread to unmount the export of the expired entries. Each time the export is being used again, its expiration time is extended and the entry is re-inserted to the tail of the list. The unmount task and the mount operation of the copy request are synced to make sure the export is not unmounted while it's being used. Signed-off-by:
-
Olga Kornievskaia authored
Currently, the server does all copies as NFS_UNSTABLE. For synchronous copies linux client will append a COMMIT to the COPY compound but for async copies it does not (because COMMIT needs to be done after all bytes are copied and not as a reply to the COPY operation). However, in order to save the client doing a COMMIT as a separate rpc, the server can reply back with NFS_FILE_SYNC copy. This patch proposed to add vfs_fsync() call at the end of the async copy. Signed-off-by:
Olga Kornievskaia <kolga@netapp.com> Signed-off-by:
-
