Commit Graph

9 Commits

Author SHA1 Message Date
Bart Van Assche
d03025aef8 fs/xfs: Use the enum req_op and blk_opf_t types
Improve static type checking by using the enum req_op type for variables
that represent a request operation and the new blk_opf_t type for the
combination of a request operation with request flags.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20220714180729.1065367-63-bvanassche@acm.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-07-14 12:14:33 -06:00
Linus Torvalds
b32e3819a8 Bug fixes for 5.18:
- Fix an incorrect free space calculation in xfs_reserve_blocks that
   could lead to a request for free blocks that will never succeed.
 - Fix a hang in xfs_reserve_blocks caused by an infinite loop and the
   incorrect free space calculation.
 - Fix yet a third problem in xfs_reserve_blocks where multiple racing
   threads can overfill the reserve pool.
 - Fix an accounting error that lead to us reporting reserved space as
   "available".
 - Fix a race condition during abnormal fs shutdown that could cause UAF
   problems when memory reclaim and log shutdown try to clean up inodes.
 - Fix a bug where log shutdown can race with unmount to tear down the
   log, thereby causing UAF errors.
 - Disentangle log and filesystem shutdown to reduce confusion.
 - Fix some confusion in xfs_trans_commit such that a race between
   transaction commit and filesystem shutdown can cause unlogged dirty
   inode metadata to be committed, thereby corrupting the filesystem.
 - Remove a performance optimization in the log as it was discovered that
   certain storage hardware handle async log flushes so poorly as to
   cause serious performance regressions.  Recent restructuring of other
   parts of the logging code mean that no performance benefit is seen on
   hardware that handle it well.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEUzaAxoMeQq6m2jMV+H93GTRKtOsFAmJEjg4ACgkQ+H93GTRK
 tOsUHRAAj5n65L1r80HSuayipWrwyuD2paa3cqtV76Y8n6CBck8CcnWjZ1t88NYO
 rvfRWKlkJAxkafc5dOiEQ4lm0AL2pHuAWeMrVu/EHvwzj9D+F/GXPrgWCJ1spsN/
 Osd8LgMrxrOaaHgPhENKGa4Ktc5dQoRfDD1IvbAyPEt2puLjoRm00STqUFMYuejR
 96yzreL8kLQdnErxKlQzo4ShsdckyBqA62AAQBIVr3B93+plefTXrWlp2HrblP11
 Upd/sdrIdVp/n104fAfaMT5pSamn3NGyV+8FaUjruBv/alC7pWrWrah6KuBl9omy
 ql8wvtO5KTQdESLx2wjYpC5odi9hQfJYDLCMN3B6gxXg26mcZVvOCfSNtrayPkYj
 ShfkT4mn+TFPFqG/NOgg8ebPp94fzXctKZ+ExVg1dGVAR9oz8QlUUmsqIdbq/4tx
 hrkGOKTa/oGBVoakHgGfbfY5Zz4yX5hVjGWN+l54YRKWHZwYDatRT/O4GkQEZqlU
 dgXsZFT0IZpz4WuTCan+VPJ85I+SKuoYsjh0n4rlGgfCcVK81uvtRB+Jn9rO0wHW
 Uzv1S6HrzblvBnUZGVt49z3co+APYwIRKY8mb+YHWmVNQqmZqyUj7KyFvxuTTkOm
 g0b8oK0/3hpC70v91aTFQmpA6R6cQAS2D4JsM4nXxjyluRWAphI=
 =6Vg8
 -----END PGP SIGNATURE-----

Merge tag 'xfs-5.18-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs fixes from Darrick Wong:
 "This fixes multiple problems in the reserve pool sizing functions: an
  incorrect free space calculation, a pointless infinite loop, and even
  more braindamage that could result in the pool being overfilled. The
  pile of patches from Dave fix myriad races and UAF bugs in the log
  recovery code that much to our mutual surprise nobody's tripped over.
  Dave also fixed a performance optimization that had turned into a
  regression.

  Dave Chinner is taking over as XFS maintainer starting Sunday and
  lasting until 5.19-rc1 is tagged so that I can focus on starting a
  massive design review for the (feature complete after five years)
  online repair feature. From then on, he and I will be moving XFS to a
  co-maintainership model by trading duties every other release.

  NOTE: I hope very strongly that the other pieces of the (X)FS
  ecosystem (fstests and xfsprogs) will make similar changes to spread
  their maintenance load.

  Summary:

   - Fix an incorrect free space calculation in xfs_reserve_blocks that
     could lead to a request for free blocks that will never succeed.

   - Fix a hang in xfs_reserve_blocks caused by an infinite loop and the
     incorrect free space calculation.

   - Fix yet a third problem in xfs_reserve_blocks where multiple racing
     threads can overfill the reserve pool.

   - Fix an accounting error that lead to us reporting reserved space as
     "available".

   - Fix a race condition during abnormal fs shutdown that could cause
     UAF problems when memory reclaim and log shutdown try to clean up
     inodes.

   - Fix a bug where log shutdown can race with unmount to tear down the
     log, thereby causing UAF errors.

   - Disentangle log and filesystem shutdown to reduce confusion.

   - Fix some confusion in xfs_trans_commit such that a race between
     transaction commit and filesystem shutdown can cause unlogged dirty
     inode metadata to be committed, thereby corrupting the filesystem.

   - Remove a performance optimization in the log as it was discovered
     that certain storage hardware handle async log flushes so poorly as
     to cause serious performance regressions. Recent restructuring of
     other parts of the logging code mean that no performance benefit is
     seen on hardware that handle it well"

* tag 'xfs-5.18-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  xfs: drop async cache flushes from CIL commits.
  xfs: shutdown during log recovery needs to mark the log shutdown
  xfs: xfs_trans_commit() path must check for log shutdown
  xfs: xfs_do_force_shutdown needs to block racing shutdowns
  xfs: log shutdown triggers should only shut down the log
  xfs: run callbacks before waking waiters in xlog_state_shutdown_callbacks
  xfs: shutdown in intent recovery has non-intent items in the AIL
  xfs: aborting inodes on shutdown may need buffer lock
  xfs: don't report reserved bnobt space as available
  xfs: fix overfilling of reserve pool
  xfs: always succeed at setting the reserve pool size
  xfs: remove infinite loop when reserving free block pool
  xfs: don't include bnobt blocks when reserving free block pool
  xfs: document the XFS_ALLOC_AGFL_RESERVE constant
2022-04-01 19:30:44 -07:00
Dave Chinner
919edbadeb xfs: drop async cache flushes from CIL commits.
Jan Kara reported a performance regression in dbench that he
bisected down to commit bad77c375e ("xfs: CIL checkpoint
flushes caches unconditionally").

Whilst developing the journal flush/fua optimisations this cache was
part of, it appeared to made a significant difference to
performance. However, now that this patchset has settled and all the
correctness issues fixed, there does not appear to be any
significant performance benefit to asynchronous cache flushes.

In fact, the opposite is true on some storage types and workloads,
where additional cache flushes that can occur from fsync heavy
workloads have measurable and significant impact on overall
throughput.

Local dbench testing shows little difference on dbench runs with
sync vs async cache flushes on either fast or slow SSD storage, and
no difference in streaming concurrent async transaction workloads
like fs-mark.

Fast NVME storage.

From `dbench -t 30`, CIL scale:

clients		async			sync
		BW	Latency		BW	Latency
1		 935.18   0.855		 915.64   0.903
8		2404.51   6.873		2341.77   6.511
16		3003.42   6.460		2931.57   6.529
32		3697.23   7.939		3596.28   7.894
128		7237.43  15.495		7217.74  11.588
512		5079.24  90.587		5167.08  95.822

fsmark, 32 threads, create w/ 64 byte xattr w/32k logbsize

	create		chown		unlink
async   1m41s		1m16s		2m03s
sync	1m40s		1m19s		1m54s

Slower SATA SSD storage:

From `dbench -t 30`, CIL scale:

clients		async			sync
		BW	Latency		BW	Latency
1		  78.59  15.792		  83.78  10.729
8		 367.88  92.067		 404.63  59.943
16		 564.51  72.524		 602.71  76.089
32		 831.66 105.984		 870.26 110.482
128		1659.76 102.969		1624.73  91.356
512		2135.91 223.054		2603.07 161.160

fsmark, 16 threads, create w/32k logbsize

	create		unlink
async   5m06s		4m15s
sync	5m00s		4m22s

And on Jan's test machine:

                   5.18-rc8-vanilla       5.18-rc8-patched
Amean     1        71.22 (   0.00%)       64.94 *   8.81%*
Amean     2        93.03 (   0.00%)       84.80 *   8.85%*
Amean     4       150.54 (   0.00%)      137.51 *   8.66%*
Amean     8       252.53 (   0.00%)      242.24 *   4.08%*
Amean     16      454.13 (   0.00%)      439.08 *   3.31%*
Amean     32      835.24 (   0.00%)      829.74 *   0.66%*
Amean     64     1740.59 (   0.00%)     1686.73 *   3.09%*

Performance and cache flush behaviour is restored to pre-regression
levels.

As such, we can now consider the async cache flush mechanism an
unnecessary exercise in premature optimisation and hence we can
now remove it and the infrastructure it requires completely.

Fixes: bad77c375e ("xfs: CIL checkpoint flushes caches unconditionally")
Reported-and-tested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
2022-03-29 18:22:02 -07:00
Christoph Hellwig
49add4966d block: pass a block_device and opf to bio_init
Pass the block_device that we plan to use this bio for and the
operation to bio_init to optimize the assignment.  A NULL block_device
can be passed, both for the passthrough case on a raw request_queue and
to temporarily avoid refactoring some nasty code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20220124091107.642561-19-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-02-02 07:49:59 -07:00
Christoph Hellwig
07888c665b block: pass a block_device and opf to bio_alloc
Pass the block_device and operation that we plan to use this bio for to
bio_alloc to optimize the assignment.  NULL/0 can be passed, both for the
passthrough case on a raw request_queue and to temporarily avoid
refactoring some nasty code.

Also move the gfp_mask argument after the nr_vecs argument for a much
more logical calling convention matching what most of the kernel does.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20220124091107.642561-18-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-02-02 07:49:59 -07:00
Dave Chinner
0431d926b3 xfs: async blkdev cache flush
The new checkpoint cache flush mechanism requires us to issue an
unconditional cache flush before we start a new checkpoint. We don't
want to block for this if we can help it, and we have a fair chunk
of CPU work to do between starting the checkpoint and issuing the
first journal IO.

Hence it makes sense to amortise the latency cost of the cache flush
by issuing it asynchronously and then waiting for it only when we
need to issue the first IO in the transaction.

To do this, we need async cache flush primitives to submit the cache
flush bio and to wait on it. The block layer has no such primitives
for filesystems, so roll our own for the moment.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Allison Henderson <allison.henderson@oracle.com>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
2021-06-21 10:05:51 -07:00
Matthew Wilcox (Oracle)
5f7136db82 block: Add bio_max_segs
It's often inconvenient to use BIO_MAX_PAGES due to min() requiring the
sign to be the same.  Introduce bio_max_segs() and change BIO_MAX_PAGES to
be unsigned to make it easier for the users.

Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-02-26 15:49:51 -07:00
Christoph Hellwig
488ca3d8d0 xfs: chain bios the right way around in xfs_rw_bdev
We need to chain the earlier bios to the later ones, so that
submit_bio_wait waits on the bio that all the completions are
dispatched to.

Fixes: 6ad5b3255b ("xfs: use bios directly to read and write the log recovery buffers")
Reported-by: Dave Chinner <david@fromorbit.com>
Tested-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2019-07-10 10:04:16 -07:00
Christoph Hellwig
6ad5b3255b xfs: use bios directly to read and write the log recovery buffers
The xfs_buf structure is basically used as a glorified container for
a memory allocation in the log recovery code.  Replace it with a
call to kmem_alloc_large and a simple abstraction to read into or
write from it synchronously using chained bios.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2019-06-28 19:27:26 -07:00