summaryrefslogtreecommitdiff
path: root/fs/nfs/nfs4_fs.h
AgeCommit message (Collapse)Author
2012-01-05NFS: Cache state owners after files are closedChuck Lever
Servers have a finite amount of memory to store NFSv4 open and lock owners. Moreover, servers may have a difficult time determining when they can reap their state owner table, thanks to gray areas in the NFSv4 protocol specification. Thus clients should be careful to reuse state owners when possible. Currently Linux is not too careful. When a user has closed all her files on one mount point, the state owner's reference count goes to zero, and it is released. The next OPEN allocates a new one. A workload that serially opens and closes files can run through a large number of open owners this way. When a state owner's reference count goes to zero, slap it onto a free list for that nfs_server, with an expiry time. Garbage collect before looking for a state owner. This makes state owners for active users available for re-use. Now that there can be unused state owners remaining at umount time, purge the state owner free list when a server is destroyed. Also be sure not to reclaim unused state owners during state recovery. This change has benefits for the client as well. For some workloads, this approach drops the number of OPEN_CONFIRM calls from the same as the number of OPEN calls, down to just one. This reduces wire traffic and thus open(2) latency. Before this patch, untarring a kernel source tarball shows the OPEN_CONFIRM call counter steadily increasing through the test. With the patch, the OPEN_CONFIRM count remains at 1 throughout the entire untar. As long as the expiry time is kept short, I don't think garbage collection should be terribly expensive, although it does bounce the clp->cl_lock around a bit. [ At some point we should rationalize the use of the nfs_server ->destroy method. ] Signed-off-by: Chuck Lever <chuck.lever@oracle.com> [Trond: Fixed a garbage collection race and a few efficiency issues] Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-10-25Merge branch 'for-3.2' of git://linux-nfs.org/~bfields/linuxLinus Torvalds
* 'for-3.2' of git://linux-nfs.org/~bfields/linux: (103 commits) nfs41: implement DESTROY_CLIENTID operation nfsd4: typo logical vs bitwise negate for want_mask nfsd4: allow NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL | NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED nfsd4: seq->status_flags may be used unitialized nfsd41: use SEQ4_STATUS_BACKCHANNEL_FAULT when cb_sequence is invalid nfsd4: implement new 4.1 open reclaim types nfsd4: remove unneeded CLAIM_DELEGATE_CUR workaround nfsd4: warn on open failure after create nfsd4: preallocate open stateid in process_open1() nfsd4: do idr preallocation with stateid allocation nfsd4: preallocate nfs4_file in process_open1() nfsd4: clean up open owners on OPEN failure nfsd4: simplify process_open1 logic nfsd4: make is_open_owner boolean nfsd4: centralize renew_client() calls nfsd4: typo logical vs bitwise negate nfs: fix bug about IPv6 address scope checking nfsd4: more robust ignoring of WANT bits in OPEN nfsd4: move name-length checks to xdr nfsd4: move access/deny validity checks to xdr code ...
2011-08-27nfsd4: cleanup and consolidate seqid_mutating_errJ. Bruce Fields
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
2011-08-24NFSv4: renewd needs to be able to handle the NFS4ERR_CB_PATH_DOWN errorTrond Myklebust
The NFSv4 spec does not specify that the server must repeat that error, so in order to avoid having the delegations revoked, we should handle it immediately. Also note that NFS4ERR_CB_PATH_DOWN does in fact renew the lease... Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-08-24NFSv4: The NFSv4.0 client must send RENEW calls if it holds a delegationTrond Myklebust
RFC3530 states that if the client holds a delegation, then it is obliged to continue to send RENEW calls once every lease period in order to allow the server to return NFS4ERR_CB_PATH_DOWN if the callback path is unreachable. This is not required for NFSv4.1, since the server can at any time set the SEQ4_STATUS_CB_PATH_DOWN_SESSION in any SEQUENCE operation. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-08-24NFSv4: nfs4_proc_renew should be declared staticTrond Myklebust
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-07-31pnfs: ask for layout_blksize and save it in nfs_serverFred Isaman
Block layout needs it to determine IO size. Signed-off-by: Fred Isaman <iisaman@citi.umich.edu> Signed-off-by: Tao Guo <glorioustao@gmail.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Benny Halevy <bhalevy@tonian.com> Signed-off-by: Jim Rees <rees@umich.edu> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-07-25Merge branch 'master' into devel and apply fixup from Stephen Rothwell:Stephen Rothwell
vfs/nfs: fixup for nfs_open_context change Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-07-20nfs4_closedata doesn't need to mess with struct pathAl Viro
instead of path_get()/path_put(), we can just use nfs_sb_{,de}active() to pin the superblock down. Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-07-12NFS: Add SECINFO_NO_NAME procedureBryan Schumaker
If the client is using NFS v4.1, then we can use SECINFO_NO_NAME to find the secflavor for the initial mount. If the server doesn't support SECINFO_NO_NAME then I fall back on the "guess and check" method used for v4.0 mounts. Signed-off-by: Bryan Schumaker <bjschuma@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-07-12NFS: use scope from exchange_id to skip reclaimWeston Andros Adamson
can be skipped if the "eir_server_scope" from the exchange_id proc differs from previous calls. Also, in the future server_scope will be useful for determining whether client trunking is available Signed-off-by: Weston Andros Adamson <dros@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-04-24NFSv4.1: Don't loop forever in nfs4_proc_create_sessionTrond Myklebust
If a server for some reason keeps sending NFS4ERR_DELAY errors, we can end up looping forever inside nfs4_proc_create_session, and so the usual mechanisms for detecting if the nfs_client is dead don't work. Fix this by ensuring that we loop inside the nfs4_state_manager thread instead. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-03-24Merge branch 'nfs-for-2.6.39' into nfs-for-nextTrond Myklebust
2011-03-24NFSv4.1 convert layoutcommit sync to booleanAndy Adamson
Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-03-24NFS: lookup supports alternate clientBryan Schumaker
A later patch will need to perform a lookup using an alternate client with a different security flavor. This patch adds support for doing that on NFS v4. Signed-off-by: Bryan Schumaker <bjschuma@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-03-23NFSv4.1: layoutcommitAndy Adamson
The filelayout driver sends LAYOUTCOMMIT only when COMMIT goes to the data server (as opposed to the MDS) and the data server WRITE is not NFS_FILE_SYNC. Only whole file layout support means that there is only one IOMODE_RW layout segment. Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Dean Hildebrand <dhildeb@us.ibm.com> Signed-off-by: Fred Isaman <iisaman@citi.umich.edu> Signed-off-by: Mingyang Guo <guomingyang@nrchpc.ac.cn> Signed-off-by: Tao Guo <guotao@nrchpc.ac.cn> Signed-off-by: Zhang Jingwang <zhangjingwang@nrchpc.ac.cn> Tested-by: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Fred Isaman <iisaman@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-03-11NFSv4.1: filelayout readAndy Adamson
Attempt a pNFS file layout read by setting up the nfs_read_data struct and calling nfs_initiate_read with the data server rpc client and the filelayout rpc call ops. Error handling is implemented in a subsequent patch. Signed-off-by: Andy Adamson <andros@citi.umich.edu> Signed-off-by: Dean Hildebrand <dhildeb@us.ibm.com> Signed-off-by: Fred Isaman <iisaman@citi.umich.edu> Signed-off-by: Fred Isaman <iisaman@netapp.com> Signed-off-by: Mingyang Guo <guomingyang@nrchpc.ac.cn> Signed-off-by: Oleg Drokin <green@linuxhacker.ru> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Tested-by: Guo Mingyang <guomingyang@nrchpc.ac.cn> Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-03-11NFSv4.1: data server connectionAndy Adamson
Introduce a data server set_client and init session following the nfs4_set_client and nfs4_init_session convention. Once a new nfs_client is on the nfs_client_list, the nfs_client cl_cons_state serializes access to creating an nfs_client struct with matching properties. Use the new nfs_get_client() that initializes new clients. Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-03-11NFSv4.1: add MDS mount DS only checkAndy Adamson
The DS only role cannot be used to mount. Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-03-11NFSv4: nfs4_state_mark_reclaim_nograce() should be staticTrond Myklebust
There are no more external users of nfs4_state_mark_reclaim_nograce() or nfs4_state_mark_reclaim_reboot(), so mark them as static. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-03-11NFSv4/4.1: Fix nfs4_schedule_state_recovery abusesTrond Myklebust
nfs4_schedule_state_recovery() should only be used when we need to force the state manager to check the lease. If we just want to start the state manager in order to handle a state recovery situation, we should be using nfs4_schedule_state_manager(). This patch fixes the abuses of nfs4_schedule_state_recovery() by replacing its use with a set of helper functions that do the right thing. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-01-06NFS: Move cl_state_owners and related fields to the nfs_server structChuck Lever
NFSv4 migration needs to reassociate state owners from the source to the destination nfs_server data structures. To make that easier, move the cl_state_owners field to the nfs_server struct. cl_openowner_id and cl_lockowner_id accompany this move, as they are used in conjunction with cl_state_owners. The cl_lock field in the parent nfs_client continues to protect all three of these fields. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-01-06pnfs: layout roc codeFred Isaman
A layout can request return-on-close. How this interacts with the forgetful model of never sending LAYOUTRETURNS is a bit ambiguous. We forget any layouts marked roc, and wait for them to be completely forgotten before continuing with the close. In addition, to compensate for races with any inflight LAYOUTGETs, and the fact that we do not get any layout stateid back from the server, we set the barrier to the worst case scenario of current_seqid + number of outstanding LAYOUTGETS. Signed-off-by: Fred Isaman <iisaman@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-01-06pnfs: add CB_LAYOUTRECALL handlingFred Isaman
This is the heart of the wave 2 submission. Add the code to trigger drain and forget of any afected layouts. In addition, we set a "barrier", below which any LAYOUTGET reply is ignored. This is to compensate for the fact that we do not wait for outstanding LAYOUTGETs to complete as per section 12.5.5.2.1 of RFC 5661. Signed-off-by: Fred Isaman <iisaman@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2011-01-04nfsv4: Switch to generic xattr handling codeAneesh Kumar K.V
This patch make nfsv4 use the generic xattr handling code to get the nfsv4 acl. This will help us to add richacl support to nfsv4 in later patches Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-12-16NFS: Simplify ->decode_dirent() calling sequenceChuck Lever
Clean up. The pointer returned by ->decode_dirent() is no longer used as a pointer. The only call site (xdr_decode() in fs/nfs/dir.c) simply extracts the errno value encoded in the pointer. Replace the returned pointer with a standard integer errno return value. Also, pass the "server" argument as part of the nfs_entry instead of as a separate parameter. It's faster to derive "server" in nfs_readdir_xdr_to_array() since we already have the directory's inode handy. "server" ought to be invariant for a set of entries in the same directory, right? The legacy versions of decode_dirent() don't use "server" anyway, so it's wasted work for them to derive and pass "server" for each entry. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Tested-by: J. Bruce Fields <bfields@redhat.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-10-23NFS: Readdir plus in v4Bryan Schumaker
By requsting more attributes during a readdir, we can mimic the readdir plus operation that was in NFSv3. To test, I ran the command `ls -lU --color=none` on directories with various numbers of files. Without readdir plus, I see this: n files | 100 | 1,000 | 10,000 | 100,000 | 1,000,000 --------+-----------+-----------+-----------+-----------+---------- real | 0m00.153s | 0m00.589s | 0m05.601s | 0m56.691s | 9m59.128s user | 0m00.007s | 0m00.007s | 0m00.077s | 0m00.703s | 0m06.800s sys | 0m00.010s | 0m00.070s | 0m00.633s | 0m06.423s | 1m10.005s access | 3 | 1 | 1 | 4 | 31 getattr | 2 | 1 | 1 | 1 | 1 lookup | 104 | 1,003 | 10,003 | 100,003 | 1,000,003 readdir | 2 | 16 | 158 | 1,575 | 15,749 total | 111 | 1,021 | 10,163 | 101,583 | 1,015,784 With readdir plus enabled, I see this: n files | 100 | 1,000 | 10,000 | 100,000 | 1,000,000 --------+-----------+-----------+-----------+-----------+---------- real | 0m00.115s | 0m00.206s | 0m01.079s | 0m12.521s | 2m07.528s user | 0m00.003s | 0m00.003s | 0m00.040s | 0m00.290s | 0m03.296s sys | 0m00.007s | 0m00.020s | 0m00.120s | 0m01.357s | 0m17.556s access | 3 | 1 | 1 | 1 | 7 getattr | 2 | 1 | 1 | 1 | 1 lookup | 4 | 3 | 3 | 3 | 3 readdir | 6 | 62 | 630 | 6,300 | 62,993 total | 15 | 67 | 635 | 6,305 | 63,004 Readdir plus disabled has about a 16x increase in the number of rpc calls and is 4 - 5 times slower on large directories. Signed-off-by: Bryan Schumaker <bjschuma@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-10-23NFS: decode_dirent should use an xdr_streamBryan Schumaker
Convert nfs*xdr.c to use an xdr stream in decode_dirent. This will prevent a kernel oops that has been occuring when reading a vmapped page. Signed-off-by: Bryan Schumaker <bjschuma@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-17NFS: Add an 'open_context' element to struct nfs_rpc_opsTrond Myklebust
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-17NFSv4: Further cleanups for nfs4_open_revalidate()Trond Myklebust
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-17NFSv4: Clean up nfs4_open_revalidateTrond Myklebust
Remove references to 'struct nameidata' from the low-level open_revalidate code, and replace them with a struct nfs_open_context which will be correctly initialised upon success. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-17NFSv4: Further minor cleanups for nfs4_atomic_open()Trond Myklebust
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-09-17NFSv4: Clean up nfs4_atomic_openTrond Myklebust
Start moving the 'struct nameidata' dependent code out of the lower level NFS code in preparation for the removal of open intents. Instead of the struct nameidata, we pass down a partially initialised struct nfs_open_context that will be fully initialised by the atomic open upon success. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-07-30NFSv4: Ensure the lockowners are labelled using the fl_owner and/or fl_pidTrond Myklebust
flock locks want to be labelled using the process pid, while posix locks want to be labelled using the fl_owner. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-07-30NFSv4: Add support for the RELEASE_LOCKOWNER operationTrond Myklebust
This is needed by NFSv4.0 servers in order to keep the number of locking stateids at a manageable level. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-06-24NFSv4: Clean up struct nfs4_state_ownerTrond Myklebust
The 'so_delegations' list appears to be unused. Also eliminate so_client. If we already have so_server, we can get to the nfs_client structure. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-06-22NFSv4.1: There is no need to init the session more than once...Trond Myklebust
Set up a flag to ensure that is indeed the case. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-06-22NFSv41: Fix nfs_async_inode_return_delegation() uglinessTrond Myklebust
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-06-22NFSv41: Convert the various reboot recovery ops etc to minor version opsTrond Myklebust
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-06-22NFSv41: Clean up the NFSv4.1 minor version specific operationsTrond Myklebust
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-06-22NFSv41: Don't store session state in the nfs_client->cl_stateTrond Myklebust
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-06-22NFSv4.1: Make nfs4_setup_sequence take a nfs_server argumentTrond Myklebust
In anticipation of the day when we have per-filesystem sessions, and also in order to allow the session to change in the event of a filesystem migration event. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-05-14NFSv4: Don't use GFP_KERNEL allocations in state recoveryTrond Myklebust
We do not want to have the state recovery thread kick off and wait for a memory reclaim, since that may deadlock when the writebacks end up waiting for the state recovery thread to complete. The safe thing is therefore to use GFP_NOFS in all open, close, delegation return, lock, etc. operations that may be called by the state recovery thread. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-05-14NFSv4: Clean up the NFSv4 setclientid operationTrond Myklebust
Reviewed-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-02-10nfs41: implement cb_recall_slotAndy Adamson
Drain the fore channel and reset the max_slots to the new value. Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2010-01-26NFS: Ensure that we handle NFS4ERR_STALE_STATEID correctlyTrond Myklebust
Even if the server is crazy, we should be able to mark the stateid as being bad, to ensure it gets recovered. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
2010-01-26NFSv4: Don't allow posix locking against servers that don't support itTrond Myklebust
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: stable@kernel.org Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
2009-12-15NFSv4: Release the sequence id before restarting a CLOSE rpc callTrond Myklebust
If the CLOSE or OPEN_DOWNGRADE call triggers a state recovery, and has to be resent, then we must release the seqid. Otherwise the open recovery will wait for the close to finish, which causes a deadlock. This is mainly a NFSv4.1 problem, although it can theoretically happen with NFSv4.0 too, in a OPEN_DOWNGRADE situation. Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-12-15nfs: change nfs4_do_setlk params to identify recovery typeAlexandros Batsakis
Signed-off-by: Alexandros Batsakis <batsakis@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2009-12-06nfs41: nfs41_setup_state_renewalRicardo Labiaga
Move call to get the lease time and the setup of the state renewal out of nfs4_create_session so that it can be called after clearing the DRAINING flag. We use the getattr RPC to obtain the lease time, which requires a sequence slot. Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>