buffer for the last vnode on the mount back to the server, it
returns. At that point, the code continues with the unmount,
including freeing up the nfs specific part of the mount structure.
It is possible that an nfsiod thread will try to check for an
empty I/O queue in the nfs specific part of the mount structure
after it has been free'd by the unmount. This patch avoids this problem by
setting the iodmount entries for the mount back to NULL while holding the
mutex in the unmount and checking the appropriate entry is non-NULL after
acquiring the mutex in the nfsiod thread.
Reported and tested by: pho
Reviewed by: kib
MFC after: 2 weeks
option. This can occur when an nfsiod thread that already holds
a buffer lock attempts to acquire a vnode lock on an entry in
the directory (a LOR) when another thread holding the vnode lock
is waiting on an nfsiod thread. This patch avoids the deadlock by disabling
readahead for this case, so the nfsiod threads never do readdirplus.
Since readaheads for directories need the directory offset cookie
from the previous read, they cannot normally happen in parallel.
As such, testing by jhb@ and myself didn't find any performance
degredation when this patch is applied. If there is a case where
this results in a significant performance degradation, mounting
without the "rdirplus" option can be done to re-enable readahead
for directories.
Reported and tested by: jhb
Reviewed by: jhb
MFC after: 2 weeks
it will work with either the old or new server.
The FHA code keeps a cache of currently active file handles for
NFSv2 and v3 requests, so that read and write requests for the same
file are directed to the same group of threads (reads) or thread
(writes). It does not currently work for NFSv4 requests. They are
more complex, and will take more work to support.
This improves read-ahead performance, especially with ZFS, if the
FHA tuning parameters are configured appropriately. Without the
FHA code, concurrent reads that are part of a sequential read from
a file will be directed to separate NFS threads. This has the
effect of confusing the ZFS zfetch (prefetch) code and makes
sequential reads significantly slower with clients like Linux that
do a lot of prefetching.
The FHA code has also been updated to direct write requests to nearby
file offsets to the same thread in the same way it batches reads,
and the FHA code will now also send writes to multiple threads when
needed.
This improves sequential write performance in ZFS, because writes
to a file are now more ordered. Since NFS writes (generally
less than 64K) are smaller than the typical ZFS record size
(usually 128K), out of order NFS writes to the same block can
trigger a read in ZFS. Sending them down the same thread increases
the odds of their being in order.
In order for multiple write threads per file in the FHA code to be
useful, writes in the NFS server have been changed to use a LK_SHARED
vnode lock, and upgrade that to LK_EXCLUSIVE if the filesystem
doesn't allow multiple writers to a file at once. ZFS is currently
the only filesystem that allows multiple writers to a file, because
it has internal file range locking. This change does not affect the
NFSv4 code.
This improves random write performance to a single file in ZFS, since
we can now have multiple writers inside ZFS at one time.
I have changed the default tuning parameters to a 22 bit (4MB)
window size (from 256K) and unlimited commands per thread as a
result of my benchmarking with ZFS.
The FHA code has been updated to allow configuring the tuning
parameters from loader tunable variables in addition to sysctl
variables. The read offset window calculation has been slightly
modified as well. Instead of having separate bins, each file
handle has a rolling window of bin_shift size. This minimizes
glitches in throughput when shifting from one bin to another.
sys/conf/files:
Add nfs_fha_new.c and nfs_fha_old.c. Compile nfs_fha.c
when either the old or the new NFS server is built.
sys/fs/nfs/nfsport.h,
sys/fs/nfs/nfs_commonport.c:
Bring in changes from Rick Macklem to newnfs_realign that
allow it to operate in blocking (M_WAITOK) or non-blocking
(M_NOWAIT) mode.
sys/fs/nfs/nfs_commonsubs.c,
sys/fs/nfs/nfs_var.h:
Bring in a change from Rick Macklem to allow telling
nfsm_dissect() whether or not to wait for mallocs.
sys/fs/nfs/nfsm_subs.h:
Bring in changes from Rick Macklem to create a new
nfsm_dissect_nonblock() inline function and
NFSM_DISSECT_NONBLOCK() macro.
sys/fs/nfs/nfs_commonkrpc.c,
sys/fs/nfsclient/nfs_clkrpc.c:
Add the malloc wait flag to a newnfs_realign() call.
sys/fs/nfsserver/nfs_nfsdkrpc.c:
Setup the new NFS server's RPC thread pool so that it will
call the FHA code.
Add the malloc flag argument to newnfs_realign().
Unstaticize newnfs_nfsv3_procid[] so that we can use it in
the FHA code.
sys/fs/nfsserver/nfs_nfsdsocket.c:
In nfsrvd_dorpc(), add NFSPROC_WRITE to the list of RPC types
that use the LK_SHARED lock type.
sys/fs/nfsserver/nfs_nfsdport.c:
In nfsd_fhtovp(), if we're starting a write, check to see
whether the underlying filesystem supports shared writes.
If not, upgrade the lock type from LK_SHARED to LK_EXCLUSIVE.
sys/nfsserver/nfs_fha.c:
Remove all code that is specific to the NFS server
implementation. Anything that is server-specific is now
accessed through a callback supplied by that server's FHA
shim in the new softc.
There are now separate sysctls and tunables for the FHA
implementations for the old and new NFS servers. The new
NFS server has its tunables under vfs.nfsd.fha, the old
NFS server's tunables are under vfs.nfsrv.fha as before.
In fha_extract_info(), use callouts for all server-specific
code. Getting file handles and offsets is now done in the
individual server's shim module.
In fha_hash_entry_choose_thread(), change the way we decide
whether two reads are in proximity to each other.
Previously, the calculation was a simple shift operation to
see whether the offsets were in the same power of 2 bucket.
The issue was that there would be a bucket (and therefore
thread) transition, even if the reads were in close
proximity. When there is a thread transition, reads wind
up going somewhat out of order, and ZFS gets confused.
The new calculation simply tries to see whether the offsets
are within 1 << bin_shift of each other. If they are, the
reads will be sent to the same thread.
The effect of this change is that for sequential reads, if
the client doesn't exceed the max_reqs_per_nfsd parameter
and the bin_shift is set to a reasonable value (22, or
4MB works well in my tests), the reads in any sequential
stream will largely be confined to a single thread.
Change fha_assign() so that it takes a softc argument. It
is now called from the individual server's shim code, which
will pass in the softc.
Change fhe_stats_sysctl() so that it takes a softc
parameter. It is now called from the individual server's
shim code. Add the current offset to the list of things
printed out about each active thread.
Change the num_reads and num_writes counters in the
fha_hash_entry structure to 32-bit values, and rename them
num_rw and num_exclusive, respectively, to reflect their
changed usage.
Add an enable sysctl and tunable that allows the user to
disable the FHA code (when vfs.XXX.fha.enable = 0). This
is useful for before/after performance comparisons.
nfs_fha.h:
Move most structure definitions out of nfs_fha.c and into
the header file, so that the individual server shims can
see them.
Change the default bin_shift to 22 (4MB) instead of 18
(256K). Allow unlimited commands per thread.
sys/nfsserver/nfs_fha_old.c,
sys/nfsserver/nfs_fha_old.h,
sys/fs/nfsserver/nfs_fha_new.c,
sys/fs/nfsserver/nfs_fha_new.h:
Add shims for the old and new NFS servers to interface with
the FHA code, and callbacks for the
The shims contain all of the code and definitions that are
specific to the NFS servers.
They setup the server-specific callbacks and set the server
name for the sysctl and loader tunable variables.
sys/nfsserver/nfs_srvkrpc.c:
Configure the RPC code to call fhaold_assign() instead of
fha_assign().
sys/modules/nfsd/Makefile:
Add nfs_fha.c and nfs_fha_new.c.
sys/modules/nfsserver/Makefile:
Add nfs_fha_old.c.
Reviewed by: rmacklem
Sponsored by: Spectra Logic
MFC after: 2 weeks
- Don't insert BKGRDMARKER bufs into the splay or dirty/clean buf lists.
No consumers need to find them there and it complicates the tree.
These flags are all FFS specific and could be moved out of the buf
cache.
- Use pbgetvp() and pbrelvp() to associate the background and journal
bufs with the vp. Not only is this much cheaper it makes more sense
for these transient bufs.
- Fix the assertions in pbget* and pbrel*. It's not safe to check list
pointers which were never initialized. Use the BX flags instead. We
also check B_PAGING in reassignbuf() so this should cover all cases.
Discussed with: kib, mckusick, attilio
Sponsored by: EMC / Isilon Storage Division
u_long. Before this change it was of type int for syscalls, but prototypes
in sys/stat.h and documentation for chflags(2) and fchflags(2) (but not
for lchflags(2)) stated that it was u_long. Now some related functions
use u_long type for flags (strtofflags(3), fflagstostr(3)).
- Make path argument of type 'const char *' for consistency.
Discussed on: arch
Sponsored by: The FreeBSD Foundation
locked. vnode_pager_setsize() might sleep waiting for the page after
EOF be unbusied.
Call vnode_pager_setsize() both for the regular and directory vnodes.
Reported by: mich
Reviewed by: rmacklem
Discussed with: avg, jhb
MFC after: 2 weeks
In common configurations biosize is a power of two, but is not required to
be so. Thanks to markj@ for spotting an additional case beyond my original
patch.
Reviewed by: rmacklem@
cluster_write() and cluster_wbuild() functions. The flags to be
allowed are a subset of the GB_* flags for getblk().
Sponsored by: The FreeBSD Foundation
Tested by: pho
proper locking. This doesn't prevent in any case reclaim of the vnode.
Avoid this not going over-the-wire in this case and relying on subsequent
smbfs_getattr() call to restore consistency.
While I'm here, change a couple of SMBVDEBUG() in MPASS().
sbmfs_smb_lookup() doesn't and shouldn't know about '.' and '..'
Reported by: pho's stress2 suite
from the tree since few months (please note that the userland bits
were already disconnected since a long time, thus there is no need
to update the OLD* entries).
This is not targeted for MFC.
Include some flags of the nullfs mount itself:
MNT_RDONLY, MNT_NOEXEC, MNT_NOSUID, MNT_UNION, MNT_NOSYMFOLLOW.
This allows userland code calling statfs() or fstatfs() to see these flags.
In particular, this allows opendir() to detect that a -t nullfs -o union
mount needs deduplication (otherwise at least . and .. are returned twice)
and allows rtld to detect a -t nullfs -o noexec mount as noexec.
Turn off the MNT_ROOTFS flag from the underlying filesystem because the
nullfs mount is definitely not the root filesystem.
Reviewed by: kib
MFC after: 1 week
- Capability is no longer separate descriptor type. Now every descriptor
has set of its own capability rights.
- The cap_new(2) system call is left, but it is no longer documented and
should not be used in new code.
- The new syscall cap_rights_limit(2) should be used instead of
cap_new(2), which limits capability rights of the given descriptor
without creating a new one.
- The cap_getrights(2) syscall is renamed to cap_rights_get(2).
- If CAP_IOCTL capability right is present we can further reduce allowed
ioctls list with the new cap_ioctls_limit(2) syscall. List of allowed
ioctls can be retrived with cap_ioctls_get(2) syscall.
- If CAP_FCNTL capability right is present we can further reduce fcntls
that can be used with the new cap_fcntls_limit(2) syscall and retrive
them with cap_fcntls_get(2).
- To support ioctl and fcntl white-listing the filedesc structure was
heavly modified.
- The audit subsystem, kdump and procstat tools were updated to
recognize new syscalls.
- Capability rights were revised and eventhough I tried hard to provide
backward API and ABI compatibility there are some incompatible changes
that are described in detail below:
CAP_CREATE old behaviour:
- Allow for openat(2)+O_CREAT.
- Allow for linkat(2).
- Allow for symlinkat(2).
CAP_CREATE new behaviour:
- Allow for openat(2)+O_CREAT.
Added CAP_LINKAT:
- Allow for linkat(2). ABI: Reuses CAP_RMDIR bit.
- Allow to be target for renameat(2).
Added CAP_SYMLINKAT:
- Allow for symlinkat(2).
Removed CAP_DELETE. Old behaviour:
- Allow for unlinkat(2) when removing non-directory object.
- Allow to be source for renameat(2).
Removed CAP_RMDIR. Old behaviour:
- Allow for unlinkat(2) when removing directory.
Added CAP_RENAMEAT:
- Required for source directory for the renameat(2) syscall.
Added CAP_UNLINKAT (effectively it replaces CAP_DELETE and CAP_RMDIR):
- Allow for unlinkat(2) on any object.
- Required if target of renameat(2) exists and will be removed by this
call.
Removed CAP_MAPEXEC.
CAP_MMAP old behaviour:
- Allow for mmap(2) with any combination of PROT_NONE, PROT_READ and
PROT_WRITE.
CAP_MMAP new behaviour:
- Allow for mmap(2)+PROT_NONE.
Added CAP_MMAP_R:
- Allow for mmap(PROT_READ).
Added CAP_MMAP_W:
- Allow for mmap(PROT_WRITE).
Added CAP_MMAP_X:
- Allow for mmap(PROT_EXEC).
Added CAP_MMAP_RW:
- Allow for mmap(PROT_READ | PROT_WRITE).
Added CAP_MMAP_RX:
- Allow for mmap(PROT_READ | PROT_EXEC).
Added CAP_MMAP_WX:
- Allow for mmap(PROT_WRITE | PROT_EXEC).
Added CAP_MMAP_RWX:
- Allow for mmap(PROT_READ | PROT_WRITE | PROT_EXEC).
Renamed CAP_MKDIR to CAP_MKDIRAT.
Renamed CAP_MKFIFO to CAP_MKFIFOAT.
Renamed CAP_MKNODE to CAP_MKNODEAT.
CAP_READ old behaviour:
- Allow pread(2).
- Disallow read(2), readv(2) (if there is no CAP_SEEK).
CAP_READ new behaviour:
- Allow read(2), readv(2).
- Disallow pread(2) (CAP_SEEK was also required).
CAP_WRITE old behaviour:
- Allow pwrite(2).
- Disallow write(2), writev(2) (if there is no CAP_SEEK).
CAP_WRITE new behaviour:
- Allow write(2), writev(2).
- Disallow pwrite(2) (CAP_SEEK was also required).
Added convinient defines:
#define CAP_PREAD (CAP_SEEK | CAP_READ)
#define CAP_PWRITE (CAP_SEEK | CAP_WRITE)
#define CAP_MMAP_R (CAP_MMAP | CAP_SEEK | CAP_READ)
#define CAP_MMAP_W (CAP_MMAP | CAP_SEEK | CAP_WRITE)
#define CAP_MMAP_X (CAP_MMAP | CAP_SEEK | 0x0000000000000008ULL)
#define CAP_MMAP_RW (CAP_MMAP_R | CAP_MMAP_W)
#define CAP_MMAP_RX (CAP_MMAP_R | CAP_MMAP_X)
#define CAP_MMAP_WX (CAP_MMAP_W | CAP_MMAP_X)
#define CAP_MMAP_RWX (CAP_MMAP_R | CAP_MMAP_W | CAP_MMAP_X)
#define CAP_RECV CAP_READ
#define CAP_SEND CAP_WRITE
#define CAP_SOCK_CLIENT \
(CAP_CONNECT | CAP_GETPEERNAME | CAP_GETSOCKNAME | CAP_GETSOCKOPT | \
CAP_PEELOFF | CAP_RECV | CAP_SEND | CAP_SETSOCKOPT | CAP_SHUTDOWN)
#define CAP_SOCK_SERVER \
(CAP_ACCEPT | CAP_BIND | CAP_GETPEERNAME | CAP_GETSOCKNAME | \
CAP_GETSOCKOPT | CAP_LISTEN | CAP_PEELOFF | CAP_RECV | CAP_SEND | \
CAP_SETSOCKOPT | CAP_SHUTDOWN)
Added defines for backward API compatibility:
#define CAP_MAPEXEC CAP_MMAP_X
#define CAP_DELETE CAP_UNLINKAT
#define CAP_MKDIR CAP_MKDIRAT
#define CAP_RMDIR CAP_UNLINKAT
#define CAP_MKFIFO CAP_MKFIFOAT
#define CAP_MKNOD CAP_MKNODAT
#define CAP_SOCK_ALL (CAP_SOCK_CLIENT | CAP_SOCK_SERVER)
Sponsored by: The FreeBSD Foundation
Reviewed by: Christoph Mallon <christoph.mallon@gmx.de>
Many aspects discussed with: rwatson, benl, jonathan
ABI compatibility discussed with: kib
changes in r246417 were incomplete as they did not add explicit calls to
sigdeferstop() around all the places that previously passed SBDRY to
_sleep(). In addition, nfs_getcacheblk() could trigger a write RPC from
getblk() resulting in sigdeferstop() recursing. Rather than manually
deferring stop signals in specific places, change the VFS_*() and VOP_*()
methods to defer stop signals for filesystems which request this behavior
via a new VFCF_SBDRY flag. Note that this has to be a VFC flag rather than
a MNTK flag so that it works properly with VFS_MOUNT() when the mount is
not yet fully constructed. For now, only the NFS clients are set this new
flag in VFS_SET().
A few other related changes:
- Add an assertion to ensure that TDF_SBDRY doesn't leak to userland.
- When a lookup request uses VOP_READLINK() to follow a symlink, mark
the request as being on behalf of the thread performing the lookup
(cnp_thread) rather than using a NULL thread pointer. This causes
NFS to properly handle signals during this VOP on an interruptible
mount.
PR: kern/176179
Reported by: Russell Cattelan (sigdeferstop() recursion)
Reviewed by: kib
MFC after: 1 month
* VM_OBJECT_LOCK and VM_OBJECT_UNLOCK are mapped to write operations
* VM_OBJECT_SLEEP() is introduced as a general purpose primitve to
get a sleep operation using a VM_OBJECT_LOCK() as protection
* The approach must bear with vm_pager.h namespace pollution so many
files require including directly rwlock.h
is excessive. Postpone the flush of the fsinfo to VFS_SYNC(),
remembering the need for update with the flag MSDOSFS_FSIMOD, stored
in pm_flags.
FAT32 specification describes both FSI_Free_Count and FSI_Nxt_Free as
the advisory hints, not requiring them to be correct.
Based on the patch from bde, modified by me.
Reviewed by: bde
MFC after: 2 weeks
tmpfs_mapped{read, write}() functions:
- tmpfs_mapped{read, write}() are only called within VOP_{READ, WRITE}(),
which check before-hand to work only on valid VREG vnodes. Also the
vnode is locked for the duration of the work, making vnode reclaiming
impossible, during the operation. Hence, vobj can never be NULL.
- Currently check on resident pages and cached pages without vm object
lock held is racy and can do even more harm than good, as a page could
be transitioning between these 2 pools and then be skipped entirely.
Skip the checks as lookups on empty splay trees are very cheap.
Discussed with: alc
Tested by: flo
MFC after: 2 weeks
e2fs_maxcontig was modelled after UFS when bringing the
"Orlov allocator" to ext2. On UFS fs_maxcontig is kept in the
superblock and is used by userland tools (fsck and growfs),
In ext2 this information is volatile so it is not available
for userland tools, so in this case it doesn't have sense
to carry it in the in-memory superblock.
Also remove a pointless check for MAX(1, x) > 0.
Submitted by: Christoph Mallon
MFC after: 2 weeks
Posix requires that open(2) is restartable for SA_RESTART.
For non-posix objects, in particular, devfs nodes, still disable
automatic restart of the opens. The open call to a driver could have
significant side effects for the hardware.
Noted and reviewed by: jilles
Discussed with: bde
MFC after: 2 weeks
195702, 195703, and 195821 prevented a thread from suspending while holding
locks inside of NFS by forcing the thread to fail sleeps with EINTR or
ERESTART but defer the thread suspension to the user boundary. However,
this had the effect that stopping a process during an NFS request could
abort the request and trigger EINTR errors that were visible to userland
processes (previously the thread would have suspended and completed the
request once it was resumed).
This change instead effectively masks stop signals while in the NFS client.
It uses the existing TDF_SBDRY flag to effect this since SIGSTOP cannot
be masked directly. Also, instead of setting PBDRY on individual sleeps,
the NFS client now sets the TDF_SBDRY flag around each NFS request and
stop signals are masked for all sleeps during that region (the previous
change missed sleeps in lockmgr locks). The end result is that stop
signals sent to threads performing an NFS request are completely
ignored until after the NFS request has finished processing and the
thread prepares to return to userland. This restores the behavior of
stop signals being transparent to userland processes while still
preventing threads from suspending while holding NFS locks.
Reviewed by: kib
MFC after: 1 month
