nfsd uses do_readv_writev() to implement fops->read and fops->write.
do_readv_writev() will attempt to read/write using fops->aio_read and
fops->aio_write, but it will fallback to fops->read and fops->write when
AIO is not available. However, the fallback will perform a call for each
individual data page. Since our default recordsize is 128KB, sequential
operations on NFS will generate 32 DMU transactions where only 1
transaction was needed. That was unnecessary overhead and we implement
fops->aio_read and fops->aio_write to eliminate it.
ZFS originated in OpenSolaris, where the AIO API is entirely implemented
in userland's libc by intelligently mapping them to VOP_WRITE, VOP_READ
and VOP_FSYNC. Linux implements AIO inside the kernel itself. Linux
filesystems therefore must implement their own AIO logic and nearly all
of them implement fops->aio_write synchronously. Consequently, they do
not implement aio_fsync(). However, since the ZPL works by mapping
Linux's VFS calls to the functions implementing Illumos' VFS operations,
we instead implement AIO in the kernel by mapping the operations to the
VOP_READ, VOP_WRITE and VOP_FSYNC equivalents. We therefore implement
fops->aio_fsync.
One might be inclined to make our fops->aio_write implementation
synchronous to make software that expects this behavior safe. However,
there are several reasons not to do this:
1. Other platforms do not implement aio_write() synchronously and since
the majority of userland software using AIO should be cross platform,
expectations of synchronous behavior should not be a problem.
2. We would hurt the performance of programs that use POSIX interfaces
properly while simultaneously encouraging the creation of more
non-compliant software.
3. The broader community concluded that userland software should be
patched to properly use POSIX interfaces instead of implementing hacks
in filesystems to cater to broken software. This concept is best
described as the O_PONIES debate.
4. Making an asynchronous write synchronous is non sequitur.
Any software dependent on synchronous aio_write behavior will suffer
data loss on ZFSOnLinux in a kernel panic / system failure of at most
zfs_txg_timeout seconds, which by default is 5 seconds. This seems like
a reasonable consequence of using non-compliant software.
It should be noted that this is also a problem in the kernel itself
where nfsd does not pass O_SYNC on files opened with it and instead
relies on a open()/write()/close() to enforce synchronous behavior when
the flush is only guarenteed on last close.
Exporting any filesystem that does not implement AIO via NFS risks data
loss in the event of a kernel panic / system failure when something else
is also accessing the file. Exporting any file system that implements
AIO the way this patch does bears similar risk. However, it seems
reasonable to forgo crippling our AIO implementation in favor of
developing patches to fix this problem in Linux's nfsd for the reasons
stated earlier. In the interim, the risk will remain. Failing to
implement AIO will not change the problem that nfsd created, so there is
no reason for nfsd's mistake to block our implementation of AIO.
It also should be noted that `aio_cancel()` will always return
`AIO_NOTCANCELED` under this implementation. It is possible to implement
aio_cancel by deferring work to taskqs and use `kiocb_set_cancel_fn()`
to set a callback function for cancelling work sent to taskqs, but the
simpler approach is allowed by the specification:
```
Which operations are cancelable is implementation-defined.
```
http://pubs.opengroup.org/onlinepubs/009695399/functions/aio_cancel.html
The only programs on my system that are capable of using `aio_cancel()`
are QEMU, beecrypt and fio use it according to a recursive grep of my
system's `/usr/src/debug`. That suggests that `aio_cancel()` users are
rare. Implementing aio_cancel() is left to a future date when it is
clear that there are consumers that benefit from its implementation to
justify the work.
Lastly, it is important to know that handling of the iovec updates differs
between Illumos and Linux in the implementation of read/write. On Linux,
it is the VFS' responsibility whle on Illumos, it is the filesystem's
responsibility. We take the intermediate solution of copying the iovec
so that the ZFS code can update it like on Solaris while leaving the
originals alone. This imposes some overhead. We could always revisit
this should profiling show that the allocations are a problem.
Signed-off-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#223Closes#2373
3598 want to dtrace when errors are generated in zfs
Reviewed by: Dan Kimmel <dan.kimmel@delphix.com>
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Approved by: Garrett D'Amore <garrett@damore.org>
References:
https://www.illumos.org/issues/3598illumos/illumos-gate@be6fd75a69
Ported-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #1775
Porting notes:
1. include/sys/zfs_context.h has been modified to render some new
macros inert until dtrace is available on Linux.
2. Linux-specific changes have been adapted to use SET_ERROR().
3. I'm NOT happy about this change. It does nothing but ugly
up the code under Linux. Unfortunately we need to take it to
avoid more merge conflicts in the future. -Brian
The PaX team modified the kernel's modpost to report writeable function
pointers as section mismatches because they are potential exploit
targets. We could ignore the warnings, but their presence can obscure
actual issues. Proper const correctness can also catch programming
mistakes.
Building the kernel modules against a PaX/GrSecurity patched Linux 3.4.2
kernel reports 133 section mismatches prior to this patch. This patch
eliminates 130 of them. The quantity of writeable function pointers
eliminated by constifying each structure is as follows:
vdev_opts_t 52
zil_replay_func_t 24
zio_compress_info_t 24
zio_checksum_info_t 9
space_map_ops_t 7
arc_byteswap_func_t 5
The remaining 3 writeable function pointers cannot be addressed by this
patch. 2 of them are in zpl_fs_type. The kernel's sget function requires
that this be non-const. The final writeable function pointer is created
by SPL_SHRINKER_DECLARE. The kernel's set_shrinker() and
remove_shrinker() functions also require that this be non-const.
Signed-off-by: Richard Yao <ryao@cs.stonybrook.edu>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#1300
When zfs_replay_write() replays TX_WRITE records from ZIL
it calls zpl_write_common() to perform the actual write.
zpl_write_common() returns the number of bytes written
(similar to write() system call) or an (negative) error.
However, the code expects the positive return value to be
a residual counter. Thus when zpl_write_common() successfully
completes it is mistakenly considered to be a partial write and
the error code delivered further. At this point the ZIL processing
is aborted with famous "ZFS replay transaction error 5" error
message given to the message buffer.
The fix is to compare the zpl_write_commmon() return value with
the buffer size and flag error only when they disagree.
Signed-off-by: Cyril Plisko <cyril.plisko@mountall.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#933
The AT_ versions of these macros are used on Solaris and while they
map to their Linux equivilants the code has been updated to use the
ATTR_ versions.
When I began work on the Posix layer it immediately became clear to
me that to integrate cleanly with the Linux VFS certain Solaris
specific things would have to go. One of these things was to elimate
as many Solaris specific types from the ZPL layer as possible. They
would be replaced with their Linux equivalents. This would not only
be good for performance, but for the general readability and health of
the code. The Solaris and Linux VFS are different beasts and should
be treated as such. Most of the code remains common for constructing
transactions and such, but there are subtle and important differenced
which need to be repsected.
This policy went quite for for certain types such as the vnode_t,
and it initially seemed to be working out well for the vattr_t. There
was a relatively small amount of related xvattr_t code I was forced to
comment out with HAVE_XVATTR. But it didn't look that hard to come
back soon and replace it all with a native Linux type.
However, after going doing this path with xvattr some distance it
clear that this code was woven in the ZPL more deeply than I thought.
In particular its hooks went very deep in to the ZPL replay code
and replacing it would not be as easy as I originally thought.
Rather than continue persuing replacing and removing this code I've
taken a step back and reevaluted things. This commit reverts many of
my previous commits which removed xvattr related code. It restores
much of the code to its original upstream state and now relies on
improved xvattr_t support in the zfs package itself.
The result of this is that much of the code which I had commented
out, which accidentally broke things like replay, is now back in
place and working. However, there may be a small performance
impact for getattr/setattr operations because they now require
a translation from native Linux to Solaris types. For now that's
a price I'm willing to pay. Once everything is completely functional
we can revisting the issue of removing the vattr_t/xvattr_t types.
Closes#111
For the moment exactly how to handle xvattr is not clear. This
change largely consists of the code to comment out the offending
bits until something reasonable can be done.
