Commit Graph

3397 Commits

Author SHA1 Message Date
Brian Behlendorf 1c2358c12a
Linux 5.10 compat: use iov_iter in uio structure
As of the 5.10 kernel the generic splice compatibility code has been
removed.  All filesystems are now responsible for registering a
->splice_read and ->splice_write callback to support this operation.

The good news is the VFS provided generic_file_splice_read() and
iter_file_splice_write() callbacks can be used provided the ->iter_read
and ->iter_write callback support pipes.  However, this is currently
not the case and only iovecs and bvecs (not pipes) are ever attached
to the uio structure.

This commit changes that by allowing full iov_iter structures to be
attached to uios.  Ever since the 4.9 kernel the iov_iter structure
has supported iovecs, kvecs, bvevs, and pipes so it's desirable to
pass the entire thing when possible.  In conjunction with this the
uio helper functions (i.e uiomove(), uiocopy(), etc) have been
updated to understand the new UIO_ITER type.

Note that using the kernel provided uio_iter interfaces allowed the
existing Linux specific uio handling code to be simplified.  When
there's no longer a need to support kernel's older than 4.9, then
it will be possible to remove the iovec and bvec members from the
uio structure and always use a uio_iter.  Until then we need to
maintain all of the existing types for older kernels.

Some additional refactoring and cleanup was included in this change:

- Added checks to configure to detect available iov_iter interfaces.
  Some are available all the way back to the 3.10 kernel and are used
  when available.  In particular, uio_prefaultpages() now always uses
  iov_iter_fault_in_readable() which is available for all supported
  kernels.

- The unused UIO_USERISPACE type has been removed.  It is no longer
  needed now that the uio_seg enum is platform specific.

- Moved zfs_uio.c from the zcommon.ko module to the Linux specific
  platform code for the zfs.ko module.  This gets it out of libzfs
  where it was never needed and keeps this Linux specific code out
  of the common sources.

- Removed unnecessary O_APPEND handling from zfs_iter_write(), this
  is redundant and O_APPEND is already handled in zfs_write();

Reviewed-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #11351
2020-12-18 08:48:26 -08:00
Matthew Ahrens 71e4ce0e52
special device removal space accounting fixes
The space in special devices is not included in spa_dspace (or
dsl_pool_adjustedsize(), or the zfs `available` property).  Therefore
there is always at least as much free space in the normal class, as
there is allocated in the special class(es).  And therefore, there is
always enough free space to remove a special device.

However, the checks for free space when removing special devices did not
take this into account.  This commit corrects that.

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Don Brady <don.brady@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #11329
2020-12-17 12:11:56 -08:00
Ryan Moeller 1531506d23
Avoid extra work updating ARC kstats and tunables
After e357046 it should not be necessary to periodically update ARC
kstats and tunables.  Tunable updates are applied when modified, and
kstats are updated on demand.

Update kstats in `arc_evict_cb_check()` for `ZFS_DEBUG` builds only.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11237
2020-12-17 11:16:42 -08:00
Matthew Ahrens be5c6d9653
Only examine best metaslabs on each vdev
On a system with very high fragmentation, we may need to do lots of gang
allocations (e.g. most indirect block allocations (~50KB) may need to
gang). Before failing a "normal" allocation and resorting to ganging, we
try every metaslab.  This has the impact of loading every metaslab (not
a huge deal since we now typically keep all metaslabs loaded), and also
iterating over every metaslab for every failing allocation. If there are
many metaslabs (more than the typical ~200, e.g. due to vdev expansion
or very large vdevs), the CPU cost of this iteration can be very
impactful.  This iteration is done with the mg_lock held, creating long
hold times and high lock contention for concurrent allocations,
ultimately causing long txg sync times and poor application performance.

To address this, this commit changes the behavior of "normal" (not
try_hard, not ZIL) allocations.  These will now only examine the 100
best metaslabs (as determined by their ms_weight).  If none of these
have a large enough free segment, then the allocation will fail and
we'll fall back on ganging.

To accomplish this, we will now (normally) gang before doing a
`try_hard` allocation.  Non-try_hard allocations will only examine the
100 best metaslabs of each vdev.  In summary, we will first try normal
allocation.  If that fails then we will do a gang allocation.  If that
fails then we will do a "try hard" gang allocation.  If that fails then
we will have a multi-layer gang block.

Reviewed-by: Paul Dagnelie <pcd@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #11327
2020-12-16 14:40:05 -08:00
Alexander Motin f8020c9363
Make metaslab class rotor and aliquot per-allocator.
Metaslab rotor and aliquot are used to distribute workload between
vdevs while keeping some locality for logically adjacent blocks.  Once
multiple allocators were introduced to separate allocation of different
objects it does not make much sense for different allocators to write
into different metaslabs of the same metaslab group (vdev) same time,
competing for its resources.  This change makes each allocator choose
metaslab group independently, colliding with others only sporadically.

Test including simultaneous write into 4 files with recordsize of 4KB
on a striped pool of 30 disks on a system with 40 logical cores show
reduction of vdev queue lock contention from 54 to 27% due to better
load distribution.  Unfortunately it won't help much ZVOLs yet since
only one dataset/ZVOL is synced at a time, and so for the most part
only one allocator is used, but it may improve later.

While there, to reduce the number of pointer dereferences change
per-allocator storage for metaslab classes and groups from several
separate malloc()'s to variable length arrays at the ends of the
original class and group structures.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Closes #11288
2020-12-15 10:55:44 -08:00
Ryan Libby d8a09b3a04
lua: avoid gcc -Wreturn-local-addr bug
Avoid a bug with gcc's -Wreturn-local-addr warning with some
obfuscation.  In buggy versions of gcc, if a return value is an
expression that involves the address of a local variable, and even if
that address is legally converted to a non-pointer type, a warning may
be emitted and the value of the address may be replaced with zero.
Howerver, buggy versions don't emit the warning or replace the value
when simply returning a local variable of non-pointer type.

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90737

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Libby <rlibby@FreeBSD.org>
Closes #11337
2020-12-15 09:20:48 -08:00
Matthew Macy 923d730329
dmu_zfetch: fix memory leak
The last change caused the read completion callback to not be called
if the IO was still in progress. This change restores allocation
of the arc buf callback, but in the callback path checks the new
acb_nobuf field to know to skip buffer allocation.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #11324
2020-12-12 16:00:00 -08:00
George Amanakis c76a40bfda
Fix reporting of CKSUM errors in indirect vdevs
When removing and subsequently reattaching a vdev, CKSUM errors may
occur as vdev_indirect_read_all() reads from all children of a mirror
in case of a resilver.

Fix this by checking whether a child is missing the data and setting a
flag (ic_error) which is then checked in vdev_indirect_repair() and
suppresses incrementing the checksum counter.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: George Amanakis <gamanakis@gmail.com>
Closes #11277
2020-12-11 12:15:37 -08:00
Ryan Moeller 439dc034e9 FreeBSD: Implement sysctl for fletcher4 impl
There is a tunable to select the fletcher 4 checksum implementation on
Linux but it was not present in FreeBSD.

Implement the sysctl handler for FreeBSD and use ZFS_MODULE_PARAM_CALL
to provide the tunable on both platforms.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11270
2020-12-11 10:29:01 -08:00
Matthew Ahrens ba67d82142
Improve zfs receive performance with lightweight write
The performance of `zfs receive` can be bottlenecked on the CPU consumed
by the `receive_writer` thread, especially when receiving streams with
small compressed block sizes.  Much of the CPU is spent creating and
destroying dbuf's and arc buf's, one for each `WRITE` record in the send
stream.

This commit introduces the concept of "lightweight writes", which allows
`zfs receive` to write to the DMU by providing an ABD, and instantiating
only a new type of `dbuf_dirty_record_t`.  The dbuf and arc buf for this
"dirty leaf block" are not instantiated.

Because there is no dbuf with the dirty data, this mechanism doesn't
support reading from "lightweight-dirty" blocks (they would see the
on-disk state rather than the dirty data).  Since the dedup-receive code
has been removed, `zfs receive` is write-only, so this works fine.

Because there are no arc bufs for the received data, the received data
is no longer cached in the ARC.

Testing a receive of a stream with average compressed block size of 4KB,
this commit improves performance by 50%, while also reducing CPU usage
by 50% of a CPU.  On a per-block basis, CPU consumed by receive_writer()
and dbuf_evict() is now 1/7th (14%) of what it was.

Baseline: 450MB/s, CPU in receive_writer() 40% + dbuf_evict() 35%
New: 670MB/s, CPU in receive_writer() 17% + dbuf_evict() 0%

The code is also restructured in a few ways:

Added a `dr_dnode` field to the dbuf_dirty_record_t.  This simplifies
some existing code that no longer needs `DB_DNODE_ENTER()` and related
routines.  The new field is needed by the lightweight-type dirty record.

To ensure that the `dr_dnode` field remains valid until the dirty record
is freed, we have to ensure that the `dnode_move()` doesn't relocate the
dnode_t.  To do this we keep a hold on the dnode until it's zio's have
completed.  This is already done by the user-accounting code
(`userquota_updates_task()`), this commit extends that so that it always
keeps the dnode hold until zio completion (see `dnode_rele_task()`).

`dn_dirty_txg` was previously zeroed when the dnode was synced.  This
was not necessary, since its meaning can be "when was this dnode last
dirtied".  This change simplifies the new `dnode_rele_task()` code.

Removed some dead code related to `DRR_WRITE_BYREF` (dedup receive).

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Paul Dagnelie <pcd@delphix.com>
Reviewed-by: George Wilson <gwilson@delphix.com>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #11105
2020-12-11 10:26:02 -08:00
Paul Dagnelie 7d4b365ce3
Fix kernel panic induced by redacted send
In the redaction list traversal code, there is a bug in the binary search
logic when looking for the resume point. Maxbufid can be decremented to -1,
causing us to read the last possible block of the object instead of the one we
wanted. This can cause incorrect resume behavior, or possibly even a hang in
some cases. In addition, when examining non-last blocks, we can treat the
block as being the same size as the last block, causing us to miss entries in
the redaction list when determining where to resume. Finally, we were ignoring
the case where the resume point was found in the buffer being searched, and
resuming from minbufid. All these issues have been corrected, and the code has
been significantly simplified to make future issues less likely.

Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Signed-off-by: Paul Dagnelie <pcd@delphix.com>
Closes #11297
2020-12-11 10:22:29 -08:00
Ryan Moeller 8c5606ca0b FreeBSD: Fix format of vfs.zfs.arc_no_grow_shift
vfs.zfs.arc_no_grow_shift has an invalid type (15) and this causes
py-sysctl to format it as a bytearray when it should be an integer.

"U" is not a valid format, it should be "I" and the type should match
the variable type, int.  We can return EINVAL if the value is set below
zero.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11318
2020-12-10 15:28:56 -08:00
Brian Behlendorf e5f732edbb
Fix possibly uninitialized 'root_inode' variable warning
Resolve an uninitialized variable warning when compiling.

    In function ‘zfs_domount’:
    warning: ‘root_inode’ may be used uninitialized in this
        function [-Wmaybe-uninitialized]
    sb->s_root = d_make_root(root_inode);

Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #11306
2020-12-10 15:23:26 -08:00
Paul Dagnelie 60a4c7d2a2
Implement memory and CPU hotplug
ZFS currently doesn't react to hotplugging cpu or memory into the 
system in any way. This patch changes that by adding logic to the ARC 
that allows the system to take advantage of new memory that is added 
for caching purposes. It also adds logic to the taskq infrastructure 
to support dynamically expanding the number of threads allocated to a 
taskq.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Co-authored-by: Matthew Ahrens <matthew.ahrens@delphix.com>
Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Paul Dagnelie <pcd@delphix.com>
Closes #11212
2020-12-10 14:09:23 -08:00
Ryan Moeller e0716250bf
FreeBSD: Do zcommon_init sooner to avoid FPU panic
There has been a panic affecting some system configurations where the
thread FPU context is disturbed during the fletcher 4 benchmarks,
leading to a panic at boot.

module_init() registers zcommon_init to run in the last subsystem
(SI_SUB_LAST).  Running it as soon as interrupts have been configured
(SI_SUB_INT_CONFIG_HOOKS) makes sure we have finished the benchmarks
before we start doing other things.

While it's not clear *how* the FPU context was being disturbed, this
does seem to avoid it.

Add a module_init_early() macro to run zcommon_init() at this earlier
point on FreeBSD.  On Linux this is defined as module_init().

Authored by: Konstantin Belousov <kib@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11302
2020-12-09 21:29:00 -08:00
Matthew Macy 1e4732cbda
Decouple arc_read_done callback from arc buf instantiation
Add ARC_FLAG_NO_BUF to indicate that a buffer need not be
instantiated.  This fixes a ~20% performance regression on
cached reads due to zfetch changes.

Reviewed-by: Tony Nguyen <tony.nguyen@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #11220 
Closes #11232
2020-12-09 15:05:06 -08:00
Brian Behlendorf edb20ff3ba
Fix optional "force" arg handing in zfs_ioc_pool_sync()
The fnvlist_lookup_boolean_value() function should not be used
to check the force argument since it's optional.  It may not be
provided or may have been created with the wrong flags.

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #11281
Closes #11284
2020-12-09 14:52:45 -08:00
Brian Behlendorf 83b698dc42
Reduce fletcher4 and raidz benchmark times
During module load time all of the available fetcher4 and raidz
implementations are benchmarked for a fixed amount of time to
determine the fastest available.  Manual testing has shown that this
time can be significantly reduced with negligible effect on the final
results.

This commit changes the benchmark time to 1ms which can reduce the
module load time by over a second on x86_64.  On an x86_64 system
with sse3, ssse3, and avx2 instructions the benchmark times are:

    Fletcher4    603ms   -> 15ms
    RAIDZ        1,322ms -> 64ms

Reviewed-by: Matthew Macy <mmacy@freebsd.org>
Reviewed-by: George Melikov <mail@gmelikov.ru>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #11282
2020-12-06 09:57:20 -08:00
Alexander Motin 8136b9d73b
Avoid some spa_has_pending_synctask() calls.
Since 8c4fb36a24 (PR #7795) spa_has_pending_synctask() started to
take two more locks per write inside txg_all_lists_empty().  I am
surprised those pool-wide locks are not contended, but still their
operations are visible in CPU profiles under contended vdev lock.

This commit slightly changes vdev_queue_max_async_writes() flow to
not call the function if we are going to return max_active any way
due to high amount of dirty data.  It allows to save some CPU time
exactly when the pool is busy.

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-By: Tom Caputi <caputit1@tcnj.edu>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Closes #11280
2020-12-06 09:55:02 -08:00
Alexander Motin 6366ef2240
Bring consistency to ABD chunk count types.
With both abd_size and abd_nents being uint_t it makes no sense for
abd_chunkcnt_for_bytes() to return size_t.  Random mix of different
types used to count chunks looks bad and makes compiler more difficult
to optimize the code.

In particular on FreeBSD this change allows compiler to completely
optimize out abd_verify_scatter() when built without debug, removing
pointless 64-bit division and even more pointless empty loop.

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Closes #11279
2020-12-06 09:53:40 -08:00
George Amanakis d1d47691c2
Fix raw sends on encrypted datasets when copying back snapshots
When sending raw encrypted datasets the user space accounting is present
when it's not expected to be. This leads to the subsequent mount failure
due a checksum error when verifying the local mac.
Fix this by clearing the OBJSET_FLAG_USERACCOUNTING_COMPLETE and reset
the local mac. This allows the user accounting to be correctly updated
on first mount using the normal upgrade process.

Reviewed-By: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-By: Tom Caputi <caputit1@tcnj.edu>
Signed-off-by: George Amanakis <gamanakis@gmail.com>
Closes #10523 
Closes #11221
2020-12-04 14:34:29 -08:00
Alexander Motin dcf7044522
Fix for "Reduce latency effects of non-interactive I/O"
It was found that setting min_active tunables for non-interactive I/Os
makes them stuck.  It is caused by zfs_vdev_nia_delay, that can never
be reached if we never issue any I/Os due to min_active set to zero.

Fix this by issuing at least one non-interactive I/O at a time when
there are no interactive I/Os.  When there are interactive I/Os, zero
min_active allows to completely block any non-interactive I/O.  It may
min_active starvation in some scenarios, but who we are to deny foot
shooting?

Reviewed-by: George Melikov <mail@gmelikov.ru>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Closes #11261
2020-12-03 10:02:39 -08:00
Ryan Moeller 0aacde2e9a
FreeBSD: notify userspace when a vdev is removed
This is needed for zfsd to autoreplace vdevs.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11260
2020-12-02 10:20:02 -08:00
Finix1979 ec50cd24ba
Avoid unneccessary zio allocation and wait
In function dmu_buf_hold_array_by_dnode, the usage of zio is only for 
the reading operation. Only create the zio and wait it in the reading 
scenario as a performance optimization.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Finix Yan <yancw@info2soft.com>
Closes #11251 
Closes #11256
2020-12-02 09:28:55 -08:00
Brian Behlendorf 04a82e043d
Remove incorrect assertion
Commit 85703f6 added a new ASSERT to zfs_write() as part of the
cleanup which isn't correct in the case where multiple processes
are concurrently extending a file.  The `zp->z_size` is updated
atomically while holding a range lock on only a portion of the
file.  Therefore, it's possible for the file size to increase
after a same check is performed earlier in the loop causing this
ASSERT to fail.  The code itself handles this case correctly so
only the invalid ASSERT needs to be removed.

Reviewed-by: Brian Atkinson <batkinson@lanl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #11235
2020-11-24 09:28:42 -08:00
Alexander Motin 6f5aac3ca0
Reduce latency effects of non-interactive I/O
Investigating influence of scrub (especially sequential) on random read
latency I've noticed that on some HDDs single 4KB read may take up to 4
seconds!  Deeper investigation shown that many HDDs heavily prioritize
sequential reads even when those are submitted with queue depth of 1.

This patch addresses the latency from two sides:
 - by using _min_active queue depths for non-interactive requests while
   the interactive request(s) are active and few requests after;
 - by throttling it further if no interactive requests has completed
   while configured amount of non-interactive did.

While there, I've also modified vdev_queue_class_to_issue() to give
more chances to schedule at least _min_active requests to the lowest
priorities.  It should reduce starvation if several non-interactive
processes are running same time with some interactive and I think should
make possible setting of zfs_vdev_max_active to as low as 1.

I've benchmarked this change with 4KB random reads from ZVOL with 16KB
block size on newly written non-fragmented pool.  On fragmented pool I
also saw improvements, but not so dramatic.  Below are log2 histograms
of the random read latency in milliseconds for different devices:

4 2x mirror vdevs of SATA HDD WDC WD20EFRX-68EUZN0 before:
0, 0, 2,  1,  12,  21,  19,  18, 10, 15, 17, 21
after:
0, 0, 0, 24, 101, 195, 419, 250, 47,  4,  0,  0
, that means maximum latency reduction from 2s to 500ms.

4 2x mirror vdevs of SATA HDD WDC WD80EFZX-68UW8N0 before:
0, 0,  2,  31,  38,  28,  18,  12, 17, 20, 24, 10, 3
after:
0, 0, 55, 247, 455, 470, 412, 181, 36,  0,  0,  0, 0
, i.e. from 4s to 250ms.

1 SAS HDD SEAGATE ST14000NM0048 before:
0,  0,  29,   70, 107,   45,  27, 1, 0, 0, 1, 4, 19
after:
1, 29, 681, 1261, 676, 1633,  67, 1, 0, 0, 0, 0,  0
, i.e. from 4s to 125ms.

1 SAS SSD SEAGATE XS3840TE70014 before (microseconds):
0, 0, 0, 0, 0, 0, 0, 0,  70, 18343, 82548, 618
after:
0, 0, 0, 0, 0, 0, 0, 0, 283, 92351, 34844,  90

I've also measured scrub time during the test and on idle pools.  On
idle fragmented pool I've measured scrub getting few percent faster
due to use of QD3 instead of QD2 before.  On idle non-fragmented pool
I've measured no difference.  On busy non-fragmented pool I've measured
scrub time increase about 1.5-1.7x, while IOPS increase reached 5-9x.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Sponsored-By: iXsystems, Inc.
Closes #11166
2020-11-24 09:26:42 -08:00
Matthew Macy cd44f5be37
FreeBSD: decouple ZFS_DEBUG from kernel debug settings
Reviewed-by: Martelli Nikola @martellini
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #11213
2020-11-24 09:16:46 -08:00
Brian Behlendorf 0657326f9c
Update dRAID short feature description
The documentation describes dRAID as a distributed spare, not
parity, RAID implementation.  Update the short feature description
to match the rest of the documentation.

Reviewed-by: George Melikov <mail@gmelikov.ru>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #11229
2020-11-23 14:49:17 -08:00
Brian Behlendorf 4d0ba94113
Correct missing zil_claim() DTL updates
Commit a1d477c2 accidentally disabled DTL updates for the zil_claim()
case described at the end of vdev_stat_update() by unconditionally
disabling all DTL updates when loading.  This was done to avoid
a deadlock on the vd_dtl_lock when loading the DTLs from disk.

    vdev_dtl_contains <--- Takes vd->vd_dtl_lock
    vdev_mirror_child_missing
    vdev_mirror_io_start
    zio_vdev_io_start
    __zio_execute
    arc_read
    dbuf_issue_final_prefetch
    dbuf_prefetch_impl
    dbuf_prefetch
    dmu_prefetch
    space_map_iterate
    space_map_load_length
    space_map_load
    vdev_dtl_load <--- Takes vd->vd_dtl_lock
    vdev_load
    spa_ld_load_vdev_metadata
    spa_tryimport

The missing DTL updates can be restored by moving the space_map_load()
call outside the vd_dtl_lock.  A private range tree is populated by
reading the space map and then merged in to the DTL_MISSING tree
under the lock.

Furthermore, the SPA_LOAD_NONE check in vdev_dtl_contains() leads to an
additional problem.  Any resilvering which occurs before SPA_LOAD_NONE
is set will incorrectly determine that there's nothing to repair.  This
can result in full redundancy not being restored for some blocks.

Reviewed-by: Matt Ahrens <matt@delphix.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #11218
2020-11-20 13:14:45 -08:00
Ryan Moeller 85703f616d
Reduce confusion in zfs_write
Is this block when abuf != NULL ever reached? Yes, it is.

Add asserts and comments to prove that when we get here, we have a full
block write at an aligned offset extending past EOF.

Simplify by removing the check that tx_bytes == max_blksz, since we can
assert that it is always true.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11191
2020-11-18 15:06:59 -08:00
Matthew Macy 0ca45cb310
Fix problems in zvol_set_volmode_impl
- Don't leave fstrans set when passed a snapshot
- Don't remove minor if volmode already matches new value
- (FreeBSD) Wait for GEOM ops to complete before trying
  remove (at create time GEOM will be "tasting" in parallel)
- (FreeBSD) Don't leak zvol_state_lock on open if zv == NULL
- (FreeBSD) Don't try to unlock zv->zv_state lock if zv == NULL

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #11199
2020-11-17 09:50:52 -08:00
loli10K 4072f465bc
Fix 'zfs userspace' for received datasets in encrypted root
For encrypted receives, where user accounting is initially disabled on
creation, both 'zfs userspace' and 'zfs groupspace' fails with
EOPNOTSUPP: this is because dmu_objset_id_quota_upgrade_cb() forgets to
set OBJSET_FLAG_USERACCOUNTING_COMPLETE on the objset flags after a
successful dmu_objset_space_upgrade().

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: loli10K <ezomori.nozomu@gmail.com>
Closes #9501 
Closes #9596
2020-11-16 09:10:29 -08:00
George Amanakis 2c210f6818
Fix ASSERT logic in l2arc_evict()
In case of cache device removal it is possible that at the end of
l2arc_evict() we have l2ad_hand = l2ad_evict. This can lead to the
following panic in case of a debug build:

VERIFY3(dev->l2ad_hand < dev->l2ad_evict) failed (321920512 < 321920512)
Call Trace:
 dump_stack+0x66/0x90
 spl_panic+0xef/0x117 [spl]
 l2arc_remove_vdev+0x11d/0x290 [zfs]
 spa_load_l2cache+0x275/0x5b0 [zfs]
 spa_vdev_remove+0x4a5/0x6e0 [zfs]
 zfs_ioc_vdev_remove+0x59/0xa0 [zfs]
 zfsdev_ioctl_common+0x5b3/0x630 [zfs]
 zfsdev_ioctl+0x53/0xe0 [zfs]
 do_vfs_ioctl+0x42e/0x6b0
 ksys_ioctl+0x5e/0x90
 do_syscall_64+0x5b/0x1a0
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

In case of cache device removal it also possible that l2ad_hand +
distance > l2ad_end since we do not iterate l2arc_evict() and l2ad_hand
is not reset. This has no functional consequence however as the cache
device is about to be removed.

Fix this by omitting the ASSERT in case of device removal.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: George Amanakis <gamanakis@gmail.com>
Closes #11205
2020-11-16 09:08:11 -08:00
Brian Behlendorf 4352edaafb
Linux: Fix ZFS_ENTER/ZFS_EXIT/ZFS_VERFY_ZP usage
The ZFS_ENTER/ZFS_EXIT/ZFS_VERFY_ZP macros should not be used
in the Linux zpl_*.c source files.  They return a positive error
value which is correct for the common code, but not for the Linux
specific kernel code which expects a negative return value.  The
ZPL_ENTER/ZPL_EXIT/ZPL_VERFY_ZP macros should be used instead.

Furthermore, the ZPL_EXIT macro has been updated to not call the
zfs_exit_fs() function.  This prevents a possible deadlock which
can occur when a snapshot is automatically unmounted because the
zpl_show_devname() must never wait on in progress automatic
snapshot unmounts.

Reviewed-by: Adam Moss <c@yotes.com>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #11169 
Closes #11201
2020-11-14 10:19:00 -08:00
Matthew Ahrens d66aab7c08
Assertion failure when logging large output of channel program
The output of ZFS channel programs is logged on-disk in the zpool
history, and printed by `zpool history -i`.  Channel programs can use
10MB of memory by default, and up to 100MB by using the `zfs program -m`
flag.  Therefore their output can be up to some fraction of 100MB.

In addition to being somewhat wasteful of the limited space reserved for
the pool history (which for large pools is 1GB), in extreme cases this
can result in a failure of `ASSERT(length <= DMU_MAX_ACCESS);` in
`dmu_buf_hold_array_by_dnode()`.

This commit limits the output size that will be logged to 1MB.  Larger
outputs will not be logged, instead a entry will be logged indicating
the size of the omitted output.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #11194
2020-11-14 10:17:16 -08:00
Ryan Moeller 7e3617de35
Return EFAULT at the end of zfs_write() when set
FreeBSD's VFS expects EFAULT from zfs_write() if we didn't complete
the full write so it can retry the operation.  Add some missing
SET_ERRORs in zfs_write().

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11193
2020-11-14 10:16:26 -08:00
Brian Behlendorf b2255edcc0
Distributed Spare (dRAID) Feature
This patch adds a new top-level vdev type called dRAID, which stands
for Distributed parity RAID.  This pool configuration allows all dRAID
vdevs to participate when rebuilding to a distributed hot spare device.
This can substantially reduce the total time required to restore full
parity to pool with a failed device.

A dRAID pool can be created using the new top-level `draid` type.
Like `raidz`, the desired redundancy is specified after the type:
`draid[1,2,3]`.  No additional information is required to create the
pool and reasonable default values will be chosen based on the number
of child vdevs in the dRAID vdev.

    zpool create <pool> draid[1,2,3] <vdevs...>

Unlike raidz, additional optional dRAID configuration values can be
provided as part of the draid type as colon separated values. This
allows administrators to fully specify a layout for either performance
or capacity reasons.  The supported options include:

    zpool create <pool> \
        draid[<parity>][:<data>d][:<children>c][:<spares>s] \
        <vdevs...>

    - draid[parity]       - Parity level (default 1)
    - draid[:<data>d]     - Data devices per group (default 8)
    - draid[:<children>c] - Expected number of child vdevs
    - draid[:<spares>s]   - Distributed hot spares (default 0)

Abbreviated example `zpool status` output for a 68 disk dRAID pool
with two distributed spares using special allocation classes.

```
  pool: tank
 state: ONLINE
config:

    NAME                  STATE     READ WRITE CKSUM
    slag7                 ONLINE       0     0     0
      draid2:8d:68c:2s-0  ONLINE       0     0     0
        L0                ONLINE       0     0     0
        L1                ONLINE       0     0     0
        ...
        U25               ONLINE       0     0     0
        U26               ONLINE       0     0     0
        spare-53          ONLINE       0     0     0
          U27             ONLINE       0     0     0
          draid2-0-0      ONLINE       0     0     0
        U28               ONLINE       0     0     0
        U29               ONLINE       0     0     0
        ...
        U42               ONLINE       0     0     0
        U43               ONLINE       0     0     0
    special
      mirror-1            ONLINE       0     0     0
        L5                ONLINE       0     0     0
        U5                ONLINE       0     0     0
      mirror-2            ONLINE       0     0     0
        L6                ONLINE       0     0     0
        U6                ONLINE       0     0     0
    spares
      draid2-0-0          INUSE     currently in use
      draid2-0-1          AVAIL
```

When adding test coverage for the new dRAID vdev type the following
options were added to the ztest command.  These options are leverages
by zloop.sh to test a wide range of dRAID configurations.

    -K draid|raidz|random - kind of RAID to test
    -D <value>            - dRAID data drives per group
    -S <value>            - dRAID distributed hot spares
    -R <value>            - RAID parity (raidz or dRAID)

The zpool_create, zpool_import, redundancy, replacement and fault
test groups have all been updated provide test coverage for the
dRAID feature.

Co-authored-by: Isaac Huang <he.huang@intel.com>
Co-authored-by: Mark Maybee <mmaybee@cray.com>
Co-authored-by: Don Brady <don.brady@delphix.com>
Co-authored-by: Matthew Ahrens <mahrens@delphix.com>
Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Mark Maybee <mmaybee@cray.com>
Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #10102
2020-11-13 13:51:51 -08:00
Matthew Ahrens a724db0374
Channel program may spuriously fail with "memory limit exhausted"
ZFS channel programs (invoked by `zfs program`) are executed in a LUA
sandbox with a limit on the amount of memory they can consume.  The
limit is 10MB by default, and can be raised to 100MB with the `-m` flag.
If the memory limit is exceeded, the LUA program exits and the command
fails with a message like `Channel program execution failed: Memory
limit exhausted.`

The LUA sandbox allocates memory with `vmem_alloc(KM_NOSLEEP)`, which
will fail if the requested memory is not immediately available.  In this
case, the program fails with the same message, `Memory limit exhausted`.
However, in this case the specified memory limit has not been reached,
and the memory may only be temporarily unavailable.

This commit changes the LUA memory allocator `zcp_lua_alloc()` to use
`vmem_alloc(KM_SLEEP)`, so that we won't spuriously fail when memory is
temporarily low.  Instead, we rely on the system to be able to free up
memory (e.g. by evicting from the ARC), and we assume that even at the
highest memory limit of 100MB, the channel program will not truly
exhaust the system's memory.

External-issue: DLPX-71924
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #11190
2020-11-11 17:16:15 -08:00
Brian Behlendorf c08d442e45
Linux: Fix mount/unmount when dataset name has a space
The custom zpl_show_devname() helper should translate spaces in
to the octal escape sequence \040.  The getmntent(2) function
is aware of this convention and properly translates the escape
character back to a space when reading the fsname.

Without this change the `zfs mount` and `zfs unmount` commands
incorrectly detect when a dataset with a name containing spaces
is mounted.

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #11182 
Closes #11187
2020-11-11 17:14:24 -08:00
Mateusz Guzik 18ca574f0a
G/C data_alloc_arena
It is a leftover from illumos always set to NULL and introducing a
spurious difference between zio_buf and zio_data_buf.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Closes #11188
2020-11-11 17:11:32 -08:00
Tony Perkins 9bd14b8724 Start snapdir_iterate traversals to begin wtih the value of zero.
The microzap hash can sometimes be zero for single digit snapnames.
The zap cursor can then have a serialized value of two (for . and ..),
and skip the first entry in the avl tree for the .zfs/snapshot directory
listing, and therefore does not return all snapshots.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Cedric Berger <cedric@precidata.com>
Signed-off-by: Tony Perkins <tperkins@datto.com>
Closes #11039
2020-11-11 17:06:16 -08:00
Mateusz Guzik 1a0b4f566c
G/C struct znode -> z_moved
The field is yet another leftover from unsupported zfs_znode_move.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Closes #11186
2020-11-10 12:42:47 -08:00
Ryan Moeller 7b42f09049 FreeBSD: Simplify zvol_geom_open and zvol_cdev_open
We can consolidate the unlocking procedure into one place by starting
with drop_suspend set to B_FALSE and moving the open count check up.

While here, a little code cleanup. Match the out labels between
zvol_geom_open and zvol_cdev_open, and add a missing period in some
comments.

Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11175
2020-11-10 11:08:10 -08:00
Ryan Moeller 2186ed33f1 FreeBSD: Avoid spurious EINTR in zvol_cdev_open
zvol_first_open can fail with EINTR if spa_namespace_lock is not held
and cannot be taken without waiting.

Apply the same logic that was done for zvol_geom_open to take
spa_namespace_lock if not already held on first open in zvol_cdev_open.

Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11175
2020-11-10 11:07:25 -08:00
Ryan Moeller d1dd72a2c5 Simplify offset and length limit in zfs_write
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11176
2020-11-10 10:58:59 -08:00
Ryan Moeller 9a764716fc Const some unchanging variables in zfs_write
Show that these values will not be changing later.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11176
2020-11-10 10:58:59 -08:00
Ryan Moeller 8a9634e2f3 Remove redundant oid parameter to update_pages
The oid comes from the znode we are already passing.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11176
2020-11-10 10:54:30 -08:00
Ryan Moeller eec6646ea9 Factor uid, gid, and projid out of loop in zfs_write
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11176
2020-11-10 10:53:19 -08:00
Alexander Motin daabddaac1
Fix dmu_tx_dirty_throttle after arc_c reduction
After initial arc_c was reduced to arc_c_min it became possible that
on datasets with primarycache=metadata or none dirty data make up most
of ARC capacity and easily more than configured 50% of initial arc_c,
that causes forced txg commits by arc_tempreserve_space() and periodic
very long write delays.

This patch makes arc_tempreserve_space() to use arc_c only after ARC
warmed up once and arc_c really means something, but use arc_c_max
before that.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Sponsored-By: iXsystems, Inc.
Closes #11178
2020-11-10 10:39:26 -08:00
Matthew Macy 570d7038d0
Fix dnode refcount tracking
Fix a couple of places where the wrong tag is passed
to dnode_{hold, rele}

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #11184
2020-11-10 10:37:10 -08:00
Mariusz Zaborski ae37ceadaa
FreeBSD: Prevent a NULL reference in zvol_cdev_open
Check if the ZVOL has been written before calling zil_async_to_sync.
The ZIL will be opened on the first write, not earlier.

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Mariusz Zaborski <oshogbo@vexillium.org>
Closes #11152
2020-11-05 17:02:19 -08:00
khng300 a4246bce50
FreeBSD: Prevent NULL pointer dereference of resid
spa_config_load() passes NULL into resid when doing zfs_file_read().
This would trip over when vfs.zfs.autoimport_disable=0.

Sponsored by: The FreeBSD Foundation
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Allan Jude <allan@klarasystems.com>
Signed-off-by: Ka Ho Ng <khng@freebsdfoundation.org>
Closes #11149
2020-11-04 16:50:08 -08:00
Ryan Moeller 181b2adc2a
FreeBSD: zvol_os: Use SET_ERROR more judiciously
SET_ERROR is useful to trace errors, so use it where the errors occur
rather than factored out to the end of a function.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11146
2020-11-03 09:21:09 -08:00
Coleman Kane 59b6872327 Linux 5.10 compat: revalidate_disk_size() added
A new function was added named revalidate_disk_size() and the old
revalidate_disk() appears to have been deprecated. As the only ZFS
code that calls this function is zvol_update_volsize, swapping the
old function call out for the new one should be all that is required.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Coleman Kane <ckane@colemankane.org>
Closes #11085
2020-11-02 22:01:19 +00:00
Coleman Kane ae15f1c1d8 Linux 5.10 compat: check_disk_change() removed
Kernel 5.10 removed check_disk_change() in favor of callers using
the faster bdev_check_media_change() instead, and explicitly forcing
bdev revalidation when they desire that behavior. To preserve prior
behavior, I have wrapped this into a zfs_check_media_change() macro
that calls an inline function for the new API that mimics the old
behavior when check_disk_change() doesn't exist, and just calls
check_disk_change() if it exists.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Coleman Kane <ckane@colemankane.org>
Closes #11085
2020-11-02 22:01:19 +00:00
Coleman Kane 838a249012 Linux 5.10 compat: percpu_ref added data member
Kernel commit 2b0d3d3e4fcfb brought in some changes to the struct
percpu_ref structure that moves most of its fields into a member
struct named "data" of type struct percpu_ref_data. This includes
the "count" member which is updated by vdev_blkg_tryget(), so update
this function to chase the API change, and detect it via configure.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Coleman Kane <ckane@colemankane.org>
Closes #11085
2020-11-02 22:01:19 +00:00
Sebastian Gottschall 7eefaf0ca0
Optimize locking checks in mempool allocator
Avoid checking the whole array of objects each time by removing the self
organized memory reaping. this can be managed by the global memory reap
callback which is called every 60 seconds. this will reduce the use if
locking operations significant.

Reviewed-by: Kjeld Schouten <kjeld@schouten-lebbing.nl>
Reviewed-by: Mateusz Guzik <mjguzik@gmail.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Closes #11126
2020-11-02 12:10:07 -08:00
Christian Schwarz ab8c935ea6
zfs_vnops: make zfs_get_data OS-independent
Move zfs_get_data() in to platform-independent code. The only
platform-specific aspect of it is the way we release an inode 
(Linux) / vnode_t (FreeBSD). I am not aware of a platform that
could be supported by ZFS that couldn't implement zfs_rele_async 
itself. It's sibling zvol_get_data already is platform-independent.

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Christian Schwarz <me@cschwarz.com>
Closes #10979
2020-11-02 12:07:07 -08:00
Mateusz Guzik 09eb36ce3d
Introduce CPU_SEQID_UNSTABLE
Current CPU_SEQID users don't care about possibly changing CPU ID, but
enclose it within kpreempt disable/enable in order to fend off warnings
from Linux's CONFIG_DEBUG_PREEMPT.

There is no need to do it. The expected way to get CPU ID while allowing
for migration is to use raw_smp_processor_id.

In order to make this future-proof this patch keeps CPU_SEQID as is and
introduces CPU_SEQID_UNSTABLE instead, to make it clear that consumers
explicitly want this behavior.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Closes #11142
2020-11-02 11:51:12 -08:00
Matthew Macy 8583540c6e
Consolidate zfs_holey and zfs_access
The zfs_holey() and zfs_access() functions can be made common
to both FreeBSD and Linux.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #11125
2020-10-31 09:40:08 -07:00
Ryan Moeller 65a343bbd3 zvol_os: Fix handling of zvol private data
zvol private data is supposed to be nulled by zvol_clear_private before
zvol_free is called as an indicator that the zvol is going away.

Implement zvol_clear_private for volmode=dev.

Assert that zvol_clear_private has been called before zvol_free.

Check that zvol_clear_private has not been called when updating
volsize.  If it has, fail with ENXIO.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11117
2020-10-30 15:34:49 -07:00
Ryan Moeller 277884ab42 zvol_os: Don't leak doi in cdev error path
Make sure to free doi in zvol_create_minor impl when make_dev_s fails.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11117
2020-10-30 15:34:43 -07:00
Ryan Moeller 9a0ef216e5 zvol_os: Properly ignore error in volmode lookup
We fall back to a default volmode and continue when looking up a zvol's
volmode property fails.  After this we should set the error to 0 to
ensure we take the success paths in the out section.

While here, make sure we only log that the zvol was created on success.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11117
2020-10-30 15:34:36 -07:00
Ryan Moeller 1a6a75ac07 zvol_os: Code cleanup in zvol_create_minor_impl
Nonfunctional changes for readability and consistency.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11117
2020-10-30 15:34:30 -07:00
Ryan Moeller 260f6a28af zvol_os: Keep better track of open count in close
zvol_geom_close gets a count of the number of close operations to do.

Make sure we're always using this count to check if this will be the
last close operation performed on the zvol.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11117
2020-10-30 15:34:23 -07:00
Ryan Moeller 0b32d81783 zvol_os: Tidy up asserts
Using more specific assert variants gives better messages on failure.

No functional change.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11117
2020-10-30 15:34:15 -07:00
Mateusz Guzik c4ede65bdf
zstd: track allocator statistics
Note that this only tracks sizes as requested by the caller.
Actual allocated space will almost always be bigger (e.g., rounded up to
the next power of 2 or page size). Additionally the allocated buffer may
be holding other areas hostage. Nonetheless, this is a starting point
for tracking memory usage in zstd.

Reviewed-by: Allan Jude <allan@klarasystems.com>
Reviewed-by: Ryan Moeller <ryan@ixsystems.com>
Reviewed-by: Kjeld Schouten <kjeld@schouten-lebbing.nl>
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Closes #11129
2020-10-30 15:26:10 -07:00
Attila Fülöp e8beeaa111
ICP: gcm: Allocate hash subkey table separately
While evaluating other assembler implementations it turns out that
the precomputed hash subkey tables vary in size, from 8*16 bytes
(avx2/avx512) up to 48*16 bytes (avx512-vaes), depending on the
implementation.

To be able to handle the size differences later, allocate
`gcm_Htable` dynamically rather then having a fixed size array, and
adapt consumers.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Attila Fülöp <attila@fueloep.org>
Closes #11102
2020-10-30 15:24:21 -07:00
Attila Fülöp d9655c5b37
Add some missing cfi frame info in aesni-gcm-x86_64.S
While preparing #9749 some .cfi_{start,end}proc directives
were missed. Add the missing ones.

See upstream https://github.com/openssl/openssl/commit/275a048f

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Attila Fülöp <attila@fueloep.org>
Closes #11101
2020-10-30 15:23:18 -07:00
Mateusz Guzik 115216cc92
FreeBSD: catch up with 1300124 version bump
- use cache_vop_mkdir
- cache_rename -> cache_vop_rename

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Allan Jude <allan@klarasystems.com>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Closes #11136
2020-10-30 15:22:04 -07:00
Ryan Moeller d1e4ded7bc
FreeBSD: Fix 12.2-STABLE after AT_BENEATH MFC
AT_BENEATH was merged to stable/12, where kern_unlinkat takes a 
non-const path.  DECONST the path passed to kern_unlinkat in the 
case where AT_BENEATH is defined.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11139
2020-10-30 15:19:02 -07:00
Matthew Macy 5fa356ea44
Remove UIO_ZEROCOPY functions structures
The original xuio zero copy functionality has always been unused 
on Linux and FreeBSD.  Remove this disabled code to avoid any
confusion and improve readability.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #11124
2020-10-30 10:00:33 -07:00
Alexander Motin 1199c3e8fb
Yield periodically when rebuilding L2ARC
L2ARC devices of several terabytes filled with 4KB blocks may take 15
minutes to rebuild.  Due to the way L2ARC log reading is implemented
it is quite likely that for all that time rebuild thread will never
sleep.  At least on FreeBSD kernel threads have absolute priority and
can not be preempted by threads with lower priorities.  If some thread
is also bound to that specific CPU it may not get any CPU time for all
the 15 minutes.

Reviewed-by: Cedric Berger <cedric@precidata.com>
Reviewed-by: Ryan Moeller <freqlabs@FreeBSD.org>
Reviewed-by: George Amanakis <gamanakis@gmail.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Closes #11116
2020-10-30 08:57:54 -07:00
Ryan Moeller 76d04993a6
Update references to nonexistent man pages in code
Refer to the correct section or alternative for FreeBSD and Linux.

Reviewed-by: George Melikov <mail@gmelikov.ru>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11132
2020-10-30 08:55:59 -07:00
Alexander Motin e3a6ac8d06
FreeBSD: Remove BIO_ORDERED flag from BIO_FLUSH
ZFS always waits for the write completion before flushing the cache.
That is why it does not require explicit ordering fences around it,
which are pretty difficult to implement for NVMe, since one has no
internal concept of strict request ordering.

This was already removed from FreeBSD once, but got resurrected
by mistake during OpenZFS merge.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Closes #11130
2020-10-30 08:50:57 -07:00
Mateusz Guzik 973ba682f5
Linux: g/c leftover fence in zfs_znode_alloc
The port removed provisions for zfs_znode_move but the cleanup missed
this bit. To quote the original:

[snip]
    list_insert_tail(&zfsvfs->z_all_znodes, zp);
    membar_producer();
    /*
     * Everything else must be valid before assigning z_zfsvfs makes the
     * znode eligible for zfs_znode_move().
     */
    zp->z_zfsvfs = zfsvfs;
[/snip]

In the current code it is immediately followed by unlock which issues
the same fence, thus plays no role in correctness.

Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Closes #11115
2020-10-29 09:54:20 -07:00
Mateusz Guzik 082ff328f2
FreeBSD: g/c unused zfs_znode_move support
The allocator does not provide the functionality to begin with.

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Closes #11114
2020-10-29 09:52:50 -07:00
Brian Behlendorf 4ce728d028
Use known license string for zlua
The Linux kernel MODULE_LICENSE macro only recognizes a handful of
license strings and "MIT" is not one of the them.  Update the macro
to use "Dual MIT/GPL" which is recognized and what the kernel expects
MIT licensed modules to use.

Reviewed-by: George Melikov <mail@gmelikov.ru>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #11112
Closes #11113
2020-10-27 09:43:36 -07:00
Ryan Moeller 5c810ac499
FreeBSD: Skip RAW kstat sysctls by default
These kstats are often expensive to compute so we want to avoid them
unless specifically requested.

The following kstats are affected by this change:

kstat.zfs.${pool}.multihost
kstat.zfs.${pool}.misc.state
kstat.zfs.${pool}.txgs
kstat.zfs.misc.fletcher_4_bench
kstat.zfs.misc.vdev_raidz_bench
kstat.zfs.misc.dbufs
kstat.zfs.misc.dbgmsg

In FreeBSD 13, sysctl(8) has been updated to still list the
names/description/type of skipped sysctls so they are still
discoverable.

Reviewed-by: Allan Jude <allan@klarasystems.com>
Reviewed-by: Mateusz Guzik <mjguzik@gmail.com>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11099
2020-10-26 14:34:28 -07:00
Mateusz Guzik 01a65c5861
FreeBSD: catch up with 1300123 version bump
- removed thread argument from VOP_INACTIVE
- removed cred argument from VOP_VPTOCNP

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Closes #11104
2020-10-26 14:32:17 -07:00
Ryan Moeller eb02a4c6fb
Add missing zfs_arc_evict_batch_limit tunable
It's even documented already.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11094
2020-10-22 10:18:26 -07:00
Matthew Macy e53d678d4a
Share zfs_fsync, zfs_read, zfs_write, et al between Linux and FreeBSD
The zfs_fsync, zfs_read, and zfs_write function are almost identical
between Linux and FreeBSD.  With a little refactoring they can be
moved to the common code which is what is done by this commit.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #11078
2020-10-21 14:08:06 -07:00
Adam D. Moss 666aa69f32
Non-l2arc pool reads shouldn't be l2arc misses
The current l2_misses accounting behavior treats all reads to pools 
without a configured l2arc as an l2arc miss, IFF there is at least 
one other pool on the system which does have an l2arc configured.

This makes it extremely hard to tune for an improved l2arc hit/miss 
ratio because this ratio will be modulated by reads from pools which 
do not (and should not) have l2arc devices; its upper limit will 
depend on the ratio of reads from l2arc'd pools and non-l2arc'd pools.

This PR prevents ARC reads affecting l2arc stats (n.b. l2_misses is 
the only relevant one) where the target spa doesn't have an l2arc.

Includes new test - l2arc_l2miss_pos.ksh

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: George Amanakis <gamanakis@gmail.com>
Signed-off-by: Adam Moss <c@yotes.com>
Closes #10921
2020-10-20 11:39:52 -07:00
Kyle Evans 241c62bdd7
Makefile.bsd: remove directory that no longer exists
This was removed in a reorganization of directories preparing for the
merge of FreeBSD support, 006e9a4088 by mmacy. While llvm is perfectly
happy with the nonexistent -I directory, the gcc6 and gcc9 we can elect
to use as cross-toolchains both trip over it.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Kyle Evans <kevans@FreeBSD.org>
Closes #11077
2020-10-20 11:34:59 -07:00
Matthew Macy ff2f54246d
FreeBSD: delete unreferenced file
zfs_onexit_os.c was not deleted when it was removed from the build

Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #11079
2020-10-20 08:53:16 -07:00
Mateusz Guzik 41e2b3de13 FreeBSD: add missing fplookup_vexec handler to special vop vectors
Otherwise lookup can fail with EOPNOTSUPP or panic.

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Closes #11066
2020-10-15 14:49:06 -07:00
Mateusz Guzik 34cda44af6 FreeBSD: g/c unused vop vector zfsctl_ops_shares_dir
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Closes #11066
2020-10-15 14:48:20 -07:00
Don Brady dff71c7936
Ignore special vdev ashift for spa ashift min/max
The removal of a vdev in the normal class would fail if there was a 
special or deup vdev that had a different ashift than the vdevs in 
the normal class.

Moved the initialization of spa_min_ashift / spa_max_ashift from 
vdev_open so that it occurs after the vdev allocation bias was 
initialized (i.e. after vdev_load).

Caveat -- In order to remove a special/dedup vdev it must have the 
same ashift as the normal pool vdevs.  This could perhaps be lifted 
in the future (i.e. for the case where there is ample space in any 
surviving special class vdevs)

Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Don Brady <don.brady@delphix.com>
Closes #9363
Closes #9364
Closes #11053
2020-10-15 14:45:16 -07:00
Christian Schwarz 15a4ca4620
Fix crash caused by invalid snapshot names in redactnvl
This is a follow up fix for commit 0fdd6106bb.  The VERIFY is
only true when we haven't hit an error code path.  See added
test case for a reproducer.

Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Christian Schwarz <me@cschwarz.com>
Closes #11048
2020-10-14 14:04:19 -07:00
Paul Dagnelie 6a60ef80e2
Fix incorrect deletion order in range_tree_add_impl gap case
After a side-effectful call like add or remove, references to range 
segs stored in btrees can no longer be used safely.  We move the 
remove call to just before the reinsertion call so that the seg 
remains valid for as long as we need it.

Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Paul Dagnelie <pcd@delphix.com>
Closes #11044 
Closes #11056
2020-10-14 08:59:54 -07:00
Mateusz Guzik 47a7e99939
FreeBSD: fix panic due to tqid overflow
The 32-bit counter eventually wraps to 0 which is a sentinel for invalid
id.

Make it 64-bit on LP64 platforms and 0-check otherwise.

Note: Linux counterpart uses id stored per queue instead of a global.
I did not check going that way is feasible with the goal being the
minimal fix doing the job.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Closes #11059
2020-10-14 08:57:03 -07:00
Ryan Moeller 485b50bb9e
Cross-platform acltype
The acltype property is currently hidden on FreeBSD and does not
reflect the NFSv4 style ZFS ACLs used on the platform.  This makes it
difficult to observe that a pool imported from FreeBSD on Linux has a
different type of ACL that is being ignored, and vice versa.

Add an nfsv4 acltype and expose the property on FreeBSD.

Make the default acltype nfsv4 on FreeBSD.

Setting acltype to an unhanded style is treated the same as setting
it to off.  The ACLs will not be removed, but they will be ignored.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10520
2020-10-13 21:25:48 -07:00
Warner Losh b302185a92
FreeBSD: make adjustments for the standalone environment
In FreeBSD, there are three compile environments that are supported:
user land, the kernel and the bootloader / standalone. Adjust the
headers to compile in the standalone environment. Limit kernel-only
items from view when _STANDALONE is defined.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Warner Losh <imp@FreeBSD.org>
Closes #10998
2020-10-13 21:05:49 -07:00
Matthew Macy 57dc5d42b1
dmu_zfetch: don't leak unreferenced stream when zfetch is freed
Currently streams are only freed when:
  - They have no referencing zfetch and and their I/O references
    go to zero.
  - They are more than 2s old and a new I/O request comes in on
    the same zfetch.

This means that we will leak unreferenced streams when their zfetch
structure is freed.

This change checks the reference count on a stream at zfetch free
time. If it is zero we free it immediately. If it has remaining
references we allow the prefetch callback to free it at I/O
completion time.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Adam Moss <c@yotes.com>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #11052
2020-10-13 21:03:36 -07:00
Warner Losh 6ba2e72b78
aarch64: Use proper guards for NEON instructions
The zstd code assumes that if you are on aarch64, you have NEON
instructions. This is not necessarily true. In a boot loader, where
you might not have the VFP properly initialized, these instructions
may not be available. It's also an error to include arm_neon.h when
the NEON insturctions aren't enabled. Change the guards for using the
NEON instructions from __aarch64__ to __ARM_NEON which is the standard
symbol for knowing if they are available.

__ARM_NEON is the proper symbol, defined in ARM C Language Extensions
Release 2.1 (https://developer.arm.com/documentation/ihi0053/d/). Some
sources suggest __ARM_NEON__, but that's the obsolete spelling from
prior versions of the standard.

Updated based on zstd pull request https://github.com/facebook/zstd/pull/2356

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Warner Losh <imp@bsdimp.com>
Closes #11055
2020-10-13 21:01:40 -07:00
Mateusz Guzik 2ce14cdf68
FreeBSD: use cache_rename if available
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Closes #11045
2020-10-13 16:41:26 -07:00
Ryan Moeller 7dfc56d866
Expose zfetch_max_idistance tunable
FreeBSD had this value tunable before the switch to the new OpenZFS.
The tunable name has changed, breaking legacy compat.

Restore legacy compat for this tunable, properly expose the tunable
with the new name on all platforms, and document it in
zfs-module-parameters(5).

While here, clean up the documentation for zfetch_max_distance a bit.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11038
2020-10-13 09:32:34 -07:00
Christian Schwarz 61868bb14d
zil_parse: make callback parameters const
Code cleanup, a follow up commit to 4d55ea81.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Co-authored-by: Ryan Moeller <ryan@freqlabs.com>
Signed-off-by: Christian Schwarz <me@cschwarz.com>
Closes #11020
2020-10-09 09:34:54 -07:00
Ryan Moeller b7ab7ae241
Linux: Initialize zp in zfs_setattr_dir
The value of zp is used without having been initialized under some
conditions.  Initialize the pointer to NULL.

Add a regression test case using chown in acl/posix.  However, this is
not enough because the setup sets xattr=sa, which means zfs_setattr_dir
will not be called.  Create a second group of acl tests in acl/posix-sa
duplicating the acl/posix tests with symlinks, and remove xattr=sa from
the original acl/posix tests.  This provides more coverage for the
default xattr=on code.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10043
Closes #11025
2020-10-09 09:27:14 -07:00
Brian Behlendorf d0249a4bd0
Replace ZFS on Linux references with OpenZFS
This change updates the documentation to refer to the project
as OpenZFS instead ZFS on Linux.  Web links have been updated
to refer to https://github.com/openzfs/zfs.  The extraneous
zfsonlinux.org web links in the ZED and SPL sources have been
dropped.

Reviewed-by: George Melikov <mail@gmelikov.ru>
Reviewed-by: Richard Laager <rlaager@wiktel.com>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #11007
2020-10-08 20:10:13 -07:00
Jacob Adams 07f5d4d663
Fix Linux modules uninstall
A missing semicolon between kmoddir variable declaration and the
uninstall for loop caused modules_uninstall-Linux to fail with:

    Syntax error: "do" unexpected

Reviewed-by: Kjeld Schouten <kjeld@schouten-lebbing.nl>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Jacob Adams <jacob@tookmund.com>
Closes #11032
2020-10-08 20:07:10 -07:00
Chuck Tuffli a8fc1b8743
Fix ubsan: shift exponent is too large
When running libzpool with the Undefined Behavior Sanitizer (ubsan)
enabled, a zpool create causes a run-time error:

    module/zfs/vdev_label.c:600:14: runtime error: shift exponent 64 is
    too large for 64-bit type 'long long unsigned int'`

in vdev_config_generate()

Fix is to convert vdev_removal_max_span to its base-2 logarithm, using
highbit64(), and then compare the "shifts".

Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Chuck Tuffli <ctuffli@gmail.com>
Closes #9744
Closes #11024
2020-10-08 16:37:27 -07:00
Ryan Moeller 73989f4b9e
Make dbufstat work on FreeBSD
With procfs_list kstats implemented for FreeBSD, dbufs are now exposed
as kstat.zfs.misc.dbufs.

On FreeBSD, dbufstats can use the sysctl instead of procfs when no
input file has been given.

Enable the dbufstats tests on FreeBSD.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <freqlabs@FreeBSD.org>
Closes #11008
2020-10-08 09:40:23 -07:00
Ryan Moeller 82b81a2acd
FreeBSD: Sort and dedup includes in kmod_core
Code cleanup. Sort includes, remove duplicates, and drop
some extra blank lines in kmod_core.c.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <freqlabs@FreeBSD.org>
Closes #11000
2020-10-08 09:37:56 -07:00
George Amanakis a76e4e6761
Make L2ARC tests more robust
Instead of relying on arbitrary timers after pool export/import or cache
device off/online rely on arcstats. This makes the L2ARC tests more
robust. Also cleanup some functions related to persistent L2ARC.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Adam Moss <c@yotes.com>
Signed-off-by: George Amanakis <gamanakis@gmail.com>
Closes #10983
2020-10-05 15:29:05 -07:00
Ryan Moeller 79f0935fab
FreeBSD: Sort out kernel FPU headers for 12.1-REL
We were missing an include for kernel FPU functions, breaking the build
on FreeBSD 12.1-RELEASE.  This was apparently being pulled in from
elsewhere on stable/12 and head.

Sorted the other includes in these files while here.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #11005
2020-10-02 17:48:45 -07:00
Ryan Moeller 4d55ea811d
Throw const on some strings
In C, const indicates to the reader that mutation will not occur.
It can also serve as a hint about ownership.

Add const in a few places where it makes sense.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <freqlabs@FreeBSD.org>
Closes #10997
2020-10-02 17:44:10 -07:00
John Poduska 5b525165e9
Mismatched nvlist names in zfs_keys_send_space
This causes "zfs send -vt ..." to fail with:

    cannot resume send: Unknown error 1030

It turns out that some of the name/value pairs in the verification
list for zfs_ioc_send_space(), zfs_keys_send_space, had the wrong
name, so the ioctl got kicked out in zfs_check_input_nvpairs().
Update the names accordingly.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: John Poduska <jpoduska@datto.com>
Closes #10978
2020-10-02 17:40:46 -07:00
Brian Behlendorf 266d1121c3
Fix buggy procfs_list_seq_next warning
The kernel seq_read() helper function expects ->next() to update
the passed position even there are no more entries.  Failure to
do so results in the following warning being logged.

    seq_file: buggy .next function procfs_list_seq_next [spl]
    did not update position index

Functionally there is no issue with the way procfs_list_seq_next()
is implemented and the warning is harmless.  However, we want to
silence this some what scary incorrect warning.  This commit
updates the Linux procfs code to advance the position even for
the last entry.

Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #10984 
Closes #10996
2020-09-30 13:27:51 -07:00
Ryan Moeller d688beb191
FreeBSD: Fix legacy compat for platform IOCs
The request number is out of bounds of the platform table.

Subtract the starting offset to get the correct subscript.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10994
2020-09-30 13:25:50 -07:00
Matthew Macy 1cb8202b1b
Eliminate gratuitous bzeroing in dbuf_stats_hash_table_data
`dbuf_stats_hash_table_data` can take much longer than it needs to
by repeatedly bzeroing its buffer when in fact the buffer only needs
to be NULL terminated.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10993
2020-09-30 13:24:38 -07:00
Sebastian Gottschall 8a171ccd92
do a cyclic seek for unused memory objects in pool
In non regular use cases allocated memory might stay persistent in memory
pool. This small patch checks every minute if there are old objects which
can be released from memory pool.

Right now with regular use, the pool is checked for old objects on each
allocation attempt from this pool. so basically polling by its use. Now
consider what happens if someone writes a lot of files and stops use of
the volume or even unmounts it. So the code will no longer check if
objects can be released from the pool. Already allocated objects will
still stay in pool cache. this is no big issue for common use. But
someone discovered this issue while doing tests. personally i know this
behavior and I'm aware of it. Its no big issue. just a enhancement

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl>
Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Closes #10938 
Closes #10969
2020-09-30 13:22:34 -07:00
Ryan Moeller c0bd2e0fe2
Drop references when skipping dmu_send due to EXDEV
When an invalid incremental send is requested where the "to" ds is
before the "from" ds, make sure to drop the reference to the pool
and the dataset before returning the error.

Add an assert on FreeBSD to make sure we don't hold any locks after
returning from an ioctl.

Add some test coverage.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10919
2020-09-30 13:19:49 -07:00
Brian Behlendorf 5aa3e3d3be
Use known license string for zzstd
The Linux kernel MODULE_LICENSE macro only recognizes a handful of
license strings and "BSD" is not one of the them.  Update the macro
to use "Dual BSD/GPL" which is recognized and what the kernel expects
BSD licensed module to use.

Reviewed-by: Kjeld Schouten <kjeld@schouten-lebbing.nl>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #10982
Closes #10992
2020-09-28 18:43:27 -07:00
Matthew Macy af20b97078
zfetch: Don't issue new streams when old have not completed
The current dmu_zfetch code implicitly assumes that I/Os complete
within min_sec_reap seconds. With async dmu and a readonly workload
(and thus no exponential backoff in operations from the "write
throttle") such as L2ARC rebuild it is possible to saturate the drives
with I/O requests. These are then effectively compounded with prefetch
requests.

This change reference counts streams and prevents them from being
recycled after their min_sec_reap timeout if they still have
outstanding I/Os.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10900
2020-09-27 17:08:38 -07:00
Adam D. Moss acfd2d4641
Add DB_RF_NOPREFETCH to dbuf_read()s in dnode.c
Prefetching of dnodes in dbuf_read() can cause significant mutex 
contention for some workloads and isn't very helpful.  This is  
because we already get 32 dnodes for each block read, and when 
iterating over a directory we prefetch the dnodes in the directory.
Disable this prefetching to prevent the lock contention.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Submitted-by: Adam Moss <c@yotes.com>
Submitted-by: Matthew Ahrens <mahrens@delphix.com>
Signed-off-by: Adam Moss <c@yotes.com>
Closes #10877 
Closes #10953
2020-09-25 13:49:22 -07:00
Brian Behlendorf 2e407941a2
Fix PREEMPTION=y and BLK_CGROUP=y config on arm64
With PREEMPTION=y and BLK_CGROUP=y preempt_schedule_notrace() is being
used on arm64 which is a GPL-only function and hence the build of the
DKMS kernel module fails.

Fix that by redefining preempt_schedule_notrace() to preempt_schedule()
which should be safe as long as tracing is not used.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Juerg Haefliger <juergh@canonical.com>
Closes #8545 
Closes #9948 
Closes #10416 
Closes #10973
2020-09-25 13:28:35 -07:00
Mateusz Guzik f6bb7c029c
FreeBSD: update cache_purgevfs usage after 1300117 version bump
Reviewed-by: Ryan Moeller <freqlabs@FreeBSD.org>
Reviewed-by: Nick Wolff <darkfiberiru@gmail.com>
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Closes #10970
2020-09-25 13:23:43 -07:00
Ryan Moeller fa1912e80f FreeBSD: Code cleanup in zio_crypt
Address some unused value and control flow issues flagged by Coverity.

Unreachable code is pruned and unused values are avoided.
Some scattered sections are reordered for coherence.

We can assume kmem_alloc(n, KM_SLEEP) doesn't fail, so there is no need
to check if it returned NULL.  The allocated memory doesn't need to be
zeroed, other than the last iovec (the MAC).

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10884
2020-09-25 13:12:35 -07:00
Ryan Moeller 863e38453e Prune dead branch reported by Coverity
wkey is NULL at every `goto error;`.
dcp is never NULL.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10884
2020-09-25 13:11:53 -07:00
Christian Schwarz a5c77dc4d5
zfs_log_write: simplify data copying code for WR_COPIED records
lr_write_t records that are WR_COPIED have the record data directly
appended to them (see lr_write_t type definition).

The data is copied from the debuf using dmu_read_by_dnode.

This function was called, only for WR_COPIED records, as part of a
short-circuiting if-statement's if-expression.

I found this side-effectful call to dmu_read_by_dnode pretty
hard to spot.
This patch improves readability by moving the call to its own line.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: George Wilson <gwilson@delphix.com>
Signed-off-by: Christian Schwarz <me@cschwarz.com>
Closes #10956
2020-09-25 13:06:34 -07:00
Matthew Macy 7b8363d7f0
FreeBSD: Add support for procfs_list
The procfs_list interface is required by several kstats. Implement
this functionality for FreeBSD to provide access to these kstats.
                           
Reviewed-by: Allan Jude <allan@klarasystems.com>
Reviewed-by: Ryan Moeller <ryan@ixsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10890
2020-09-23 16:43:51 -07:00
Matthew Macy 3dad29fb4b
FreeBSD: Don't save user FPU context in kernel threads
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Ryan Moeller <freqlabs@FreeBSD.org>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10899
2020-09-23 11:09:48 -07:00
Paul Dagnelie 20dfe8cd3b
Don't set numobjs to UINT64_MAX or near it
Resolves an issue with `zfs send` streams from 0.8.4 which
prevents them from being received by versions < 0.7.

Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Paul Zuchowski <pzuchowski@datto.com>
Signed-off-by: Paul Dagnelie <pcd@delphix.com>
Closes #10911 
Closes #10916
2020-09-22 16:16:07 -07:00
George Amanakis c6f5e9d92f
Restore clearing of L2CACHE flag in arc_read_done()
Commit 45152dc removed clearing of L2CACHE flag in arc_read_done() and
moved related code in l2arc_write_eligible(). After careful code
inspection arc_read_done() is not bypassed in the case of prefetches.
Thus restore the old behavior.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: adam moss <c@yotes.com>
Signed-off-by: George Amanakis <gamanakis@gmail.com>
Closes #10951
2020-09-22 16:08:05 -07:00
Mark Johnston 0daa0320e9
Fix a logic bug in the FreeBSD getpages VOP
In commit cd32b4f5b7 ("Fix a deadlock in the FreeBSD getpages VOP") I
introduced a bug while porting the patch originally committed to
FreeBSD: the rangelock pointer may be NULL if the try operation failed,
so we must avoid calling zfs_rangelock_unlock() in that case.

Reviewed-by: Allan Jude <allan@klarasystems.com>
Reviewed-by: Ryan Moeller <ryan@ixsystems.com>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Reported-by: Steve Wills <swills@FreeBSD.org>
Signed-off-by: Mark Johnston <markj@FreeBSD.org>
Closes #10519 
Closes #10960
2020-09-22 16:05:52 -07:00
Ryan Moeller 5f8a9e6a02
FreeBSD: Reduce stack usage of Lua
Use the same reduced buffer size for lauxlib that is used on Linux.

Fixes panic on HEAD in lua gsub test designed to exhaust stack space.

With this we can remove the special case to reserve more stack space
on FreeBSD.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Kyle Evans <kevans@FreeBSD.org>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10959
2020-09-22 16:03:11 -07:00
Mark Johnston 6bdb09510b Annontate FreeBSD sysctls with CTLFLAG_MPSAFE
Without this, the sysctl system calls will acquire a global lock before
invoking the handler.  This is noticeable in some situations when
running top(1).  The global lock is mostly vestigal but continues to see
some use and so contention is still a problem; until the default sense
of the MPSAFE flag changes, we have to annotate each and every handler.

Reviewed-by: Allan Jude <allan@klarasystems.com>
Reviewed-by: Ryan Moeller <ryan@ixsystems.com>
Signed-off-by: Mark Johnston <markj@FreeBSD.org>
Closes #10836
2020-09-21 09:49:50 -07:00
Mark Johnston c50f3c902f Fix switch statement indentation in the FreeBSD kstat code
This is in preparation for some functional changes.

Reviewed-by: Allan Jude <allan@klarasystems.com>
Reviewed-by: Ryan Moeller <ryan@ixsystems.com>
Signed-off-by: Mark Johnston <markj@FreeBSD.org>
Closes #10950
2020-09-21 09:49:12 -07:00
George Wilson c494aa7f57
vdev_ashift should only be set once
== Motivation and Context

The new vdev ashift optimization prevents the removal of devices when
a zfs configuration is comprised of disks which have different logical
and physical block sizes. This is caused because we set 'spa_min_ashift'
in vdev_open and then later call 'vdev_ashift_optimize'. This would
result in an inconsistency between spa's ashift calculations and that
of the top-level vdev.

In addition, the optimization logical ignores the overridden ashift
value that would be provided by '-o ashift=<val>'.

== Description

This change reworks the vdev ashift optimization so that it's only
set the first time the device is configured. It still allows the
physical and logical ahsift values to be set every time the device
is opened but those values are only consulted on first open.

Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Cedric Berger <cedric@precidata.com>
Signed-off-by: George Wilson <gwilson@delphix.com>
External-Issue: DLPX-71831
Closes #10932
2020-09-18 12:13:47 -07:00
George Wilson 8e82ffba7b
pool may become suspended during device expansion
When expanding a device zfs needs to rescan the partition table to
get the correct size. This can only happen when we're in the kernel
and requires the device to be closed. As part of the rescan, udev is
notified and the device links are removed and recreated. This leave a
window where the vdev code may try to reopen the device before udev
has recreated the link. If that happens, then the pool may end up in
a suspended state.

To correct this, we leverage the BLKPG_RESIZE_PARTITION ioctl which
allows the partition information to be modified even while it's in use.
This ioctl also does not remove the device link associated with the zfs
data partition so it eliminates the race condition that can occur in
the kernel.

Reviewed-by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: George Wilson <gwilson@delphix.com>
Closes #10897
2020-09-17 20:03:10 -07:00
Ryan Moeller 3c7566cb0d
FreeBSD: Do not copy vp into f_data for DTYPE_VNODE files
https://reviews.freebsd.org/D26346

Do not copy vp into f_data for DTYPE_VNODE files.  The vnode pointer is
already stored in f_vnode.  Use that so f_data can be reused.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10929
2020-09-17 10:54:14 -07:00
John Poduska 5bed68bdc4
Need a long hold in zpl_mount_impl
In zpl_mount_impl, there is:
    dmu_objset_hold	; returns with pool & ds held
    dsl_pool_rele

    sget

    dsl_dataset_rele

As spelled out in the "DSL Pool Configuration Lock" in dsl_pool.c,
this requires a long hold.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Paul Zuchowski <pzuchowski@datto.com>
Signed-off-by: John Poduska <jpoduska@datto.com>
Closes #10936
2020-09-17 10:53:02 -07:00
Ryan Moeller 7ead2be3d2
Rename acltype=posixacl to acltype=posix
Prefer acltype=off|posix, retaining the old names as aliases.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10918
2020-09-16 12:26:06 -07:00
Pavel Snajdr 9569c31161 Fix stack frame size: dnode_dirty_l1range()
Reviewed-by: Ryan Moeller <freqlabs@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Pavel Snajdr <snajpa@snajpa.net>
Closes #10879
2020-09-15 15:55:55 -07:00
Pavel Snajdr a1c5578ce0 dmu_redact_snap: fix possible memleak
Reviewed-by: Ryan Moeller <freqlabs@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Pavel Snajdr <snajpa@snajpa.net>
Closes #10879
2020-09-15 15:55:45 -07:00
Pavel Snajdr 8c0b16e6e9 Fix stack frame size: dmu_redact_snap()
Reviewed-by: Ryan Moeller <freqlabs@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Pavel Snajdr <snajpa@snajpa.net>
Closes #10879
2020-09-15 15:55:35 -07:00
Pavel Snajdr c95625769d Fix stack frame size: spa_livelist_delete_cb()
Reviewed-by: Ryan Moeller <freqlabs@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Pavel Snajdr <snajpa@snajpa.net>
Closes #10879
2020-09-15 15:55:03 -07:00
Toomas Soome 1db9e6e4e4
zfs label bootenv should store data as nvlist
nvlist does allow us to support different data types and systems.

To encapsulate user data to/from nvlist, the libzfsbootenv library is
provided.

Reviewed-by: Arvind Sankar <nivedita@alum.mit.edu>
Reviewed-by: Allan Jude <allan@klarasystems.com>
Reviewed-by: Paul Dagnelie <pcd@delphix.com>
Reviewed-by: Igor Kozhukhov <igor@dilos.org>
Signed-off-by: Toomas Soome <tsoome@me.com>
Closes #10774
2020-09-15 15:42:27 -07:00
Ryan Moeller 37325e4749
Linux: Prevent destruction while showing mount devname
Use ZFS_ENTER and ZFS_EXIT to protect datasets while their mount
devname is being retrieved.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10892
Closes #10927
2020-09-15 15:40:03 -07:00
George Amanakis 085321621e
Add L2ARC arcstats for MFU/MRU buffers and buffer content type
Currently the ARC state (MFU/MRU) of cached L2ARC buffer and their
content type is unknown. Knowing this information may prove beneficial
in adjusting the L2ARC caching policy.

This commit adds L2ARC arcstats that display the aligned size
(in bytes) of L2ARC buffers according to their content type
(data/metadata) and according to their ARC state (MRU/MFU or
prefetch). It also expands the existing evict_l2_eligible arcstat to
differentiate between MFU and MRU buffers.

L2ARC caches buffers from the MRU and MFU lists of ARC. Upon caching a
buffer, its ARC state (MRU/MFU) is stored in the L2 header
(b_arcs_state). The l2_m{f,r}u_asize arcstats reflect the aligned size
(in bytes) of L2ARC buffers according to their ARC state (based on
b_arcs_state). We also account for the case where an L2ARC and ARC
cached MRU or MRU_ghost buffer transitions to MFU. The l2_prefetch_asize
reflects the alinged size (in bytes) of L2ARC buffers that were cached
while they had the prefetch flag set in ARC. This is dynamically updated
as the prefetch flag of L2ARC buffers changes.

When buffers are evicted from ARC, if they are determined to be L2ARC
eligible then their logical size is recorded in
evict_l2_eligible_m{r,f}u arcstats according to their ARC state upon
eviction.

Persistent L2ARC:
When committing an L2ARC buffer to a log block (L2ARC metadata) its
b_arcs_state and prefetch flag is also stored. If the buffer changes
its arcstate or prefetch flag this is reflected in the above arcstats.
However, the L2ARC metadata cannot currently be updated to reflect this
change.
Example: L2ARC caches an MRU buffer. L2ARC metadata and arcstats count
this as an MRU buffer. The buffer transitions to MFU. The arcstats are
updated to reflect this. Upon pool re-import or on/offlining the L2ARC
device the arcstats are cleared and the buffer will now be counted as an
MRU buffer, as the L2ARC metadata were not updated.

Bug fix:
- If l2arc_noprefetch is set, arc_read_done clears the L2CACHE flag of
  an ARC buffer. However, prefetches may be issued in a way that
  arc_read_done() is bypassed. Instead, move the related code in
  l2arc_write_eligible() to account for those cases too.

Also add a test and update manpages for l2arc_mfuonly module parameter,
and update the manpages and code comments for l2arc_noprefetch.
Move persist_l2arc tests to l2arc.

Reviewed-by: Ryan Moeller <freqlabs@FreeBSD.org>
Reviewed-by: Richard Elling <Richard.Elling@RichardElling.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: George Amanakis <gamanakis@gmail.com>
Closes #10743
2020-09-14 10:10:44 -07:00
Mateusz Guzik 8e7fe49b25
FreeBSD: convert teardown inactive lock to a read-mostly sleepable lock
The lock is taken all the time and as a regular read-write lock
avoidably serves as a mount point-wide contention point.

This forward ports FreeBSD revision r357322.

To quote aforementioned commit:

Sample result doing an incremental -j 40 build:
before: 173.30s user 458.97s system 2595% cpu 24.358 total
after:  168.58s user 254.92s system 2211% cpu 19.147 total

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Ryan Moeller <freqlabs@FreeBSD.org>
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Closes #10896
2020-09-09 10:15:52 -07:00
Olaf Faaland a74259cea0
Initialize mmp_last_write when the mmp thread starts
A great deal of time may go by between when mmp_init() is called and
the MMP thread starts, particularly if there are bad devices, because
there is I/O checking configs etc.  If this time is too long,

    (gethrtime() - mmp_last_write) > mmp_fail_ns

at the time the MMP thread starts.  If MMP is configured to suspend
the pool, the pool will be suspended immediately.

This can be seen in issue #10838

The value of mmp_last_write doesn't matter before the mmp thread
starts.  To give the MMP thread time to issue and land MMP writes,
initialize mmp_last_write when the MMP thread starts.

Reviewed-by: Giuseppe Di Natale <guss80@gmail.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Olaf Faaland <faaland1@llnl.gov>
Closes #10873
2020-09-09 10:12:54 -07:00
Ryan Moeller cba6d86638
FreeBSD: drop dependency on cryptodev module
We only need the kernel interfaces in crypto, not the device node in
cryptodev.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10901
2020-09-09 10:10:32 -07:00
George Amanakis feb3a7eef1
Introduce ZFS module parameter l2arc_mfuonly
In certain workloads it may be beneficial to reduce wear of L2ARC
devices by not caching MRU metadata and data into L2ARC. This commit
introduces a new tunable l2arc_mfuonly for this purpose.

Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Richard Elling <Richard.Elling@RichardElling.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: George Amanakis <gamanakis@gmail.com>
Closes #10710
2020-09-08 11:44:37 -07:00
Toomas Soome 189272f78a
dnode_special_open() error: unchecked function return 'zrl_tryenter'
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Toomas Soome <tsoome@me.com>
Closes #10876
2020-09-08 11:36:52 -07:00
Matthew Macy 7432d29760
FreeBSD: reduce priority of ZIO_TASKQ_ISSUE writes by a larger value
On FreeBSD, if priorities divided by four (RQ_PPQ) are equal then
a difference between them is insignificant. In other words,
incrementing pri by only one as on Linux is insufficient.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10872
2020-09-04 11:13:27 -07:00
Brian Behlendorf dce63135ae Sequential scrub and resilver updated comments
Commit d4a72f2 which introduced multi-phase scrubs and resilvers
continued the work presented by Nexenta at the 2016 ZFS developer
summit.  Update the source to reflect their contribution.

Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
2020-09-04 10:51:51 -07:00
Don Brady 4f07282786
Avoid posting duplicate zpool events
Duplicate io and checksum ereport events can misrepresent that 
things are worse than they seem. Ideally the zpool events and the 
corresponding vdev stat error counts in a zpool status should be 
for unique errors -- not the same error being counted over and over. 
This can be demonstrated in a simple example. With a single bad 
block in a datafile and just 5 reads of the file we end up with a 
degraded vdev, even though there is only one unique error in the pool.

The proposed solution to the above issue, is to eliminate duplicates 
when posting events and when updating vdev error stats. We now save 
recent error events of interest when posting events so that we can 
easily check for duplicates when posting an error. 

Reviewed by: Brad Lewis <brad.lewis@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Don Brady <don.brady@delphix.com>
Closes #10861
2020-09-04 10:34:28 -07:00
Matthew Ahrens 3808032489
nowait synctask must succeed
If a `zfs_space_check_t` other than `ZFS_SPACE_CHECK_NONE` is used with
`dsl_sync_task_nowait()`, the sync task may fail due to ENOSPC.
However, there is no way to notice or communicate this failure, so it's
extremely difficult to use this functionality correctly, and in fact
almost all callers use `ZFS_SPACE_CHECK_NONE`.

This commit removes the `zfs_space_check_t` argument from
`dsl_sync_task_nowait()`, and always uses `ZFS_SPACE_CHECK_NONE`.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #10855
2020-09-04 10:29:39 -07:00
Ryan Moeller cd80273909
Retain thread name when resuming a zthr
When created, a zthr is given a name to identify it by.  This name is
lost when a cancelled zthr is resumed.

Retain the name of a zthr so it can be used when resuming.

Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10881
2020-09-03 20:09:52 -07:00
Matthew Macy ac6e5fb202
Replace cv_{timed}wait_sig with cv_{timed}wait_idle where appropriate
There are a number of places where cv_?_sig is used simply for
accounting purposes but the surrounding code has no ability to
cope with actually receiving a signal. On FreeBSD it is possible
to send signals to individual kernel threads so this could
enable undesirable behavior.

This patch adds routines on Linux that will do the same idle
accounting as _sig without making the task interruptible. On
FreeBSD cv_*_idle  are all aliases for cv_*

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10843
2020-09-03 20:04:09 -07:00
Spencer Kinny 6fffc88bf3
Links in Source Files
Added comments in following files
with links to Illumos manual pages:

./module/avl/avl.c
./module/nvpair/nvpair.c
./module/os/linux/spl/spl-kstat.c
./module/os/freebsd/spl/spl_kstat.c

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Spencer Kinny <spencerkinny1995@gmail.com>
Closes #5113 
Closes #10859
2020-09-02 09:42:12 -07:00
Toomas Soome 0db1b84a6d
zvol: unsigned off can not be less than zero
Reviewed-by: Richard Elling <Richard.Elling@RichardElling.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Toomas Soome <tsoome@me.com>
Closes #10867
2020-09-02 09:30:29 -07:00
Ryan Moeller 964791acdc
Make spa_stats.c tunables visible on FreeBSD
Use ZFS_MODULE_PARAM for cross-platform tunables in spa_stats.c, and
add update tunables.cfg in tests for the newly supported ones.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10858
2020-09-01 16:19:19 -07:00
Matthew Macy e84e49218f
FreeBSD: Fix up after spa_stats.c move
Moving spa_stats added the additional burden of supporting
KSTAT_TYPE_IO.

spa_state_addr will always return a valid value regardless of
the value of 'n'. On FreeBSD this will cause an infinite loop
as it relies on the raw ops addr routine to indicate that there
is no more data.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <freqlabs@FreeBSD.org>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10860
2020-09-01 16:16:56 -07:00
Ryan Moeller 7b4e27232d
Add 'zfs rename -u' to rename without remounting
Allow to rename file systems without remounting if it is possible.
It is possible for file systems with 'mountpoint' property set to
'legacy' or 'none' - we don't have to change mount directory for them.
Currently such file systems are unmounted on rename and not even
mounted back.

This introduces layering violation, as we need to update
'f_mntfromname' field in statfs structure related to mountpoint (for
the dataset we are renaming and all its children).

In my opinion it is worth it, as it allow to update FreeBSD in even
cleaner way - in ZFS-only configuration root file system is ZFS file
system with 'mountpoint' property set to 'legacy'. If root dataset is
named system/rootfs, we can snapshot it (system/rootfs@upgrade), clone
it (system/oldrootfs), update FreeBSD and if it doesn't boot we can
boot back from system/oldrootfs and rename it back to system/rootfs
while it is mounted as /. Before it was not possible, because
unmounting / was not possible.

Authored by: Pawel Jakub Dawidek <pjd@FreeBSD.org>
Reviewed-by: Allan Jude <allan@klarasystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Ported by: Matt Macy <mmacy@freebsd.org>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10839
2020-09-01 16:14:16 -07:00
Ryan Moeller 88d19d7cc2
FreeBSD: Remove unused SECLABEL code
SECLABEL is undefined on FreeBSD and should be pruned.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <freqlabs@FreeBSD.org>
Closes #10847
2020-08-31 19:52:46 -07:00
Ryan Moeller eff621071f FreeBSD: Simplify INGLOBALZONE
FreeBSD's previous ZFS implemented INGLOBALZONE(thread) as
(!jailed((thread)->td_ucred)) and passed curthread to INGLOBALZONE.

We pass curproc instead of curthread, so we can achieve the same effect
with (!jailed((proc)->p_ucred)).  The implementation is trivial enough
to fit on a single line in a define.  We don't really need a whole
separate function for something that's already macros all the way down.

Eliminate in_globalzone.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <freqlabs@FreeBSD.org>
Closes #10851
2020-08-31 19:43:08 -07:00
Toomas Soome 1144586b57
zio_ereport_post() and zio_ereport_start() return values are ignored
use (void) to silence analyzers.

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Toomas Soome <tsoome@me.com>
Closes #10857
2020-08-31 19:35:11 -07:00
Matthew Macy 7bb18b94c7
Move spa_stats.c to common code
Initially it was considered simplest to stub out all
of the functions on FreeBSD. Now that FreeBSD supports
KSTAT_TYPE_RAW at least some of the functionality should
be made available.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Richard Elling <Richard.Elling@RichardElling.com>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10842
2020-08-30 14:12:46 -07:00
Matthew Macy cd23154a8c
FreeBSD: Fix spurious failure in zvol_geom_open
In zvol_geom_open on first open we need to guarantee
that the namespace lock is held to avoid spurious
failures in zvol_first_open.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <freqlabs@FreeBSD.org>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10841
2020-08-30 14:11:33 -07:00
Matthew Macy d436de6389
FreeBSD: add support for KSTAT_TYPE_RAW
A few kstats use KSTAT_TYPE_RAW to provide a string generated on
demand.  Implementing these as sysctls was punted until now.

Reviewed by: Toomas Soome <tsoome@me.com>
Reviewed-by: Allan Jude <allan@klarasystems.com>
Reviewed-by: Ryan Moeller <ryan@ixsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10836
2020-08-29 20:59:50 -07:00
Brian Behlendorf 3e29e1971b
Linux 5.9 compat: NR_SLAB_RECLAIMABLE
Commit dcdc12e added compatibility code to treat NR_SLAB_RECLAIMABLE_B
as if it were the same as NR_SLAB_RECLAIMABLE.  However, the new value
is in bytes while the old value was in pages which means they are not
interchangeable.

The only place the reclaimable slab size is used is as a component of
the calculation done by arc_free_memory().  This function returns the
amount of memory the ARC considers to be free or reclaimable at little
cost.  Rather than switch to a new interface to get this value it has
been removed it from the calculation.  It is normally a minor component
compared to the number of inactive or free pages, and removing it
aligns the behavior with the FreeBSD version of arc_free_memory().

Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Coleman Kane <ckane@colemankane.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #10834
2020-08-29 20:57:45 -07:00
Georgy Yakovlev 735ba76104
module/zstd: pass -U__BMI__
If kernel is compiled with -march=znver1 or -march=znver2 zstd module 
compilation will fail due to SSE register return with SSE disabled.
What's interesting, is that -march=skylake also implies -mbmi which 
defines __BMI__ but compilation succeeds.  It is probably due to 
different BMI implementations on AMD and INTEL processors and the 
way compiler uses instructions.

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Georgy Yakovlev <gyakovlev@gentoo.org>
Closes #10758 
Closes #10829
2020-08-27 15:50:13 -07:00
Patrick Mooney 8d42c98d95
dnode_sync is careless with range tree
Because dnode_sync_free_range() must drop dn_mtx during its processing,
using it as a callback to range_tree_vacate() is not safe.  No other
operations (besides destroy) are allowed once range_tree_vacate() has
begun, and dropping dn_mtx would leave a window open for another thread
to observe that invalid (and unsafe) state via dnode_block_freed().

Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Igor Kozhukhov <igor@dilos.org>
Signed-off-by: Patrick Mooney <pmooney@oxide.computer>
Closes #10708 
Closes #10823
2020-08-26 21:48:29 -07:00
Ryan Moeller a2f944a140
zpool: Change base URL for ZFS messages to openzfs-docs
Reviewed-by: George Melikov <mail@gmelikov.ru>
Reviewed-by: Kjeld Schouten <kjeld@schouten-lebbing.nl>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10820
2020-08-26 21:43:06 -07:00
Brian Behlendorf 03f5d2fd6a
Remove duplicate dnode.h include
The zfs/sa.c source file accidentally includes sys/dnode.h twice.
Remove the second occurrence.

Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #10816 
Closes #10819
2020-08-26 21:41:09 -07:00
Paul Dagnelie 4aa3b3bd47
Always track temporary fses and snapshots for accounting
The root cause of the issue is that we only occasionally do as the 
comments in the code suggest and actually ignore the %recv dataset when 
it comes to filesystem limit tracking. Specifically, the only time we 
ignore it is when initializing the filesystem and snapshot limit values; 
when creating a new %recv dataset or deleting one, we always update 
the bookkeeping. This causes a problem if you init the fs count on a 
filesystem that already has a %recv dataset, since the bookmarking 
will be decremented but not incremented. This is resolved in this 
patch by simply always tracking the %recv dataset as a child.

Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed by: Jerry Jelinek <jerry.jelinek@joyent.com>
Signed-off-by: Paul Dagnelie <pcd@delphix.com>
Closes #10791
2020-08-26 21:38:27 -07:00
Toomas Soome ec0c480c14
Remove pragma ident lines
The #pragma ident is a historical relic and not needed any more, this
pragma is actually unknown for common compilers and is only causing
trouble.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Signed-off-by: Toomas Soome <tsoome@me.com>
Closes #10810
2020-08-26 10:35:50 -07:00
Matthew Macy 2dbad44710
FreeBSD: disable neon usage
The neon support code does not build on FreeBSD,
ifdef out references to fix linker issues on arm64.

Reviewed-by: George Melikov <mail@gmelikov.ru>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10809
2020-08-26 09:54:37 -07:00
Alexander Motin 523e1295fe
Introduce limit on size of L2ARC headers
Since L2ARC buffers are not evicted on memory pressure, too large
amount of headers on system with irrationally large L2ARC can render
it slow or even unusable.  This change limits L2ARC writes and
rebuild if unevictable L2ARC-only headers reach dangerous level.

While there, call arc_adapt() on L2ARC rebuild, so that it could
properly grow arc_c, reflecting potentially significant ARC size
increase and avoiding slow growth with hopeless eviction attempts
later when "overflow" is detected.

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reported-by: Richard Elling <Richard.Elling@RichardElling.com>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Closes #10765
2020-08-25 14:33:36 -07:00
sterlingjensen 87688b686b
Mark lua setjmp/longjmp for powerpc weak
Linux already defines setjmp/longjmp for powerpc, which leads to
duplicate symbols in a statically linked build.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Sterlng Jensen <sterlingjensen@users.noreply.github.com>
Closes #10795
2020-08-25 10:32:49 -07:00
Brian Behlendorf 94dac3e880
Export dmu_offset_next() symbol
Export the dmu_offset_next() symbol for use by Lustre.

Reviewed-by: George Melikov <mail@gmelikov.ru>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #10796
2020-08-25 08:34:41 -07:00
youzhongyang b900799768
Fix inability to destroy snapshot used over NFS
The cache of struct svc_export and struct svc_expkey by nfsd and
rpc.mountd for the snapshot holds references to the mount point.
We need to flush them out before unmounting, otherwise umount
would fail with EBUSY.

Reviewed-by: Don Brady <don.brady@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Youzhong Yang <yyang@mathworks.com>
Closes #6000 
Closes #10783
2020-08-24 17:33:02 -07:00
Sebastian Gottschall 184df27eef
Avoid symbol collision with in-kernel zstdlib
For Linux, when zfs is compiled as an in kernel static variant
and the in kernel zstd library is compiled statically into the kernel
a symbol collision will occur.  This wrapper header renames all
of the relevant zstd functions to avoid this problem.

Reviewed-by: Kjeld Schouten <kjeld@schouten-lebbing.nl>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Closes #10775
2020-08-24 12:20:41 -07:00
Andrew a741b386d3
Prevent zfs_acl_chmod() if aclmode restricted and ACL inherited
In absence of inheriting entry for owner@, group@, or everyone@,
zfs_acl_chmod() is called to set these. This can cause confusion for Samba
admins who do not expect these entries to appear on newly created files and
directories once they have been stripped from from the parent directory.

When aclmode is set to "restricted", chmod is prevented on non-trivial ACLs.
It is not a stretch to assume that in this case the administrator does not want
ZFS to add the missing special entries. Add check for this aclmode, and if an
inherited entry is present skip zfs_acl_chmod().

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Andrew Walker <awalker@ixsystems.com>
Closes #10748
2020-08-22 21:49:25 -07:00
Clint Armstrong 1ddd7cdb92
Make formatting of dedup values string consistent
All other prop values return options separated by ` | `,
dedup values do not, they are separated by `, `. This change
makes the dedup value formatting consistent with other properties.

Reviewed-by: George Melikov <mail@gmelikov.ru>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Clint Armstrong <clint@clintarmstrong.net>
Closes #10761
2020-08-22 10:58:07 -07:00
Ryan Moeller 6fe3498ca3
Import vdev ashift optimization from FreeBSD
Many modern devices use physical allocation units that are much
larger than the minimum logical allocation size accessible by
external commands. Two prevalent examples of this are 512e disk
drives (512b logical sector, 4K physical sector) and flash devices
(512b logical sector, 4K or larger allocation block size, and 128k
or larger erase block size). Operations that modify less than the
physical sector size result in a costly read-modify-write or garbage
collection sequence on these devices.

Simply exporting the true physical sector of the device to ZFS would
yield optimal performance, but has two serious drawbacks:

 1. Existing pools created with devices that have different logical
    and physical block sizes, but were configured to use the logical
    block size (e.g. because the OS version used for pool construction
    reported the logical block size instead of the physical block
    size) will suddenly find that the vdev allocation size has
    increased. This can be easily tolerated for active members of
    the array, but ZFS would prevent replacement of a vdev with
    another identical device because it now appears that the smaller
    allocation size required by the pool is not supported by the new
    device.

 2. The device's physical block size may be too large to be supported
    by ZFS. The optimal allocation size for the vdev may be quite
    large. For example, a RAID controller may export a vdev that
    requires read-modify-write cycles unless accessed using 64k
    aligned/sized requests. ZFS currently has an 8k minimum block
    size limit.

Reporting both the logical and physical allocation sizes for vdevs
solves these problems. A device may be used so long as the logical
block size is compatible with the configuration. By comparing the
logical and physical block sizes, new configurations can be optimized
and administrators can be notified of any existing pools that are
sub-optimal.

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Co-authored-by: Matthew Macy <mmacy@freebsd.org>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10619
2020-08-21 12:53:17 -07:00
Matthew Ahrens 3dc18995bd
Fix indentation in dnode_free_range()
Reviewed-by: George Melikov <mail@gmelikov.ru>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #10744
2020-08-20 11:45:20 -07:00
Matthew Macy 1c2725a157
FreeBSD: 11.x arc_stats compatibility
Removing other_size from arc_stats breaks top in 11.x jails
running on HEAD.

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10745
2020-08-20 10:55:02 -07:00
Michael Niewöhner 10b3c7f5e4 Add zstd support to zfs
This PR adds two new compression types, based on ZStandard:

- zstd: A basic ZStandard compression algorithm Available compression.
  Levels for zstd are zstd-1 through zstd-19, where the compression
  increases with every level, but speed decreases.

- zstd-fast: A faster version of the ZStandard compression algorithm
  zstd-fast is basically a "negative" level of zstd. The compression
  decreases with every level, but speed increases.

  Available compression levels for zstd-fast:
   - zstd-fast-1 through zstd-fast-10
   - zstd-fast-20 through zstd-fast-100 (in increments of 10)
   - zstd-fast-500 and zstd-fast-1000

For more information check the man page.

Implementation details:

Rather than treat each level of zstd as a different algorithm (as was
done historically with gzip), the block pointer `enum zio_compress`
value is simply zstd for all levels, including zstd-fast, since they all
use the same decompression function.

The compress= property (a 64bit unsigned integer) uses the lower 7 bits
to store the compression algorithm (matching the number of bits used in
a block pointer, as the 8th bit was borrowed for embedded block
pointers).  The upper bits are used to store the compression level.

It is necessary to be able to determine what compression level was used
when later reading a block back, so the concept used in LZ4, where the
first 32bits of the on-disk value are the size of the compressed data
(since the allocation is rounded up to the nearest ashift), was
extended, and we store the version of ZSTD and the level as well as the
compressed size. This value is returned when decompressing a block, so
that if the block needs to be recompressed (L2ARC, nop-write, etc), that
the same parameters will be used to result in the matching checksum.

All of the internal ZFS code ( `arc_buf_hdr_t`, `objset_t`,
`zio_prop_t`, etc.) uses the separated _compress and _complevel
variables.  Only the properties ZAP contains the combined/bit-shifted
value. The combined value is split when the compression_changed_cb()
callback is called, and sets both objset members (os_compress and
os_complevel).

The userspace tools all use the combined/bit-shifted value.

Additional notes:

zdb can now also decode the ZSTD compression header (flag -Z) and
inspect the size, version and compression level saved in that header.
For each record, if it is ZSTD compressed, the parameters of the decoded
compression header get printed.

ZSTD is included with all current tests and new tests are added
as-needed.

Per-dataset feature flags now get activated when the property is set.
If a compression algorithm requires a feature flag, zfs activates the
feature when the property is set, rather than waiting for the first
block to be born.  This is currently only used by zstd but can be
extended as needed.

Portions-Sponsored-By: The FreeBSD Foundation
Co-authored-by: Allan Jude <allanjude@freebsd.org>
Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov>
Co-authored-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Co-authored-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl>
Co-authored-by: Michael Niewöhner <foss@mniewoehner.de>
Signed-off-by: Allan Jude <allan@klarasystems.com>
Signed-off-by: Allan Jude <allanjude@freebsd.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Signed-off-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl>
Signed-off-by: Michael Niewöhner <foss@mniewoehner.de>
Closes #6247
Closes #9024
Closes #10277
Closes #10278
2020-08-20 10:30:06 -07:00
Michael Niewöhner dc544aba15 Import ZStandard v1.4.5
ZStandard is a modern, high performance, general compression algorithm.
It provides similar or better compression levels to GZIP, but with much
better performance. ZStandard provides a large selection of compression
levels to allow a storage administrator to select the preferred
performance/compression trade-off.

This commit imports the unmodified ZStandard single-file library which
will be used by ZFS.

The implementation of this new library is done with future updates of
zstd in mind. For this reason we integrated the code in a way, that does
not require modifications to the library. For more details, see
`module/zstd/README.md`.

The library is excluded from codecov calculation and cppcheck as
unaltered dependencies do not need full codecov or cppcheck.

Co-authored-by: Allan Jude <allanjude@freebsd.org>
Co-authored-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl>
Co-authored-by: Michael Niewöhner <foss@mniewoehner.de>
Signed-off-by: Allan Jude <allanjude@freebsd.org>
Signed-off-by: Kjeld Schouten-Lebbing <kjeld@schouten-lebbing.nl>
Signed-off-by: Michael Niewöhner <foss@mniewoehner.de>
2020-08-20 10:30:06 -07:00
Mariusz Zaborski f2c027bd6a
FreeBSD: Add option to rewind checkpoint while importing root pool
This option is used by FreeBSD boot loader.

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Mariusz Zaborski <oshogbo@vexillium.org>
Closes #10738
2020-08-19 17:19:42 -07:00
Brian Behlendorf cfd59f904b
Fix ARC aggsum access after arc_state_fini()
Commit 85ec5cbae updated abd_update_scatter_stats() such that it
calls arc_space_consume() and arc_space_return() when updating the
scatter stats.  This requires that the global aggsum value for the
ARC be initialized.  Normally this is not an issue, however during
module unload the l2arc_do_free_on_write() function was called in
l2arc_cleanup() after arc_state_fini() destroyed the aggsum values.
We can resolve this issue by performing l2arc_do_free_on_write()
slightly earlier in arc_fini().

Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #10739
2020-08-18 22:11:34 -07:00
Matthew Macy 716b53d0a1
FreeBSD: Fix UNIX permissions checking
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10727
2020-08-18 09:57:07 -07:00
Matthew Macy 5e7eaf8fbd
Add define to enable autotrim to default to on
In FreeBSD trim has defaulted to on for several
years. In order to minimize POLA violations on
import it's important to maintain this default
when importing vendored openzfs in to FreeBSD
base.

Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10719
2020-08-18 09:52:30 -07:00
Ryan Moeller 009cc8e884
Make zc_nvlist_src_size limit tunable
We limit the size of nvlists passed to the kernel so a user cannot make
the kernel do an unreasonably large allocation.  On FreeBSD this limit
was 128 kiB, which turns out to be a bit too small when doing some
operations involving a large number of datasets or snapshots, for
example replication.

Make this limit tunable, with a platform-specific auto default.
Linux keeps its limit at KMALLOC_MAX_SIZE. FreeBSD uses 1/4 of the
system limit on user wired memory, which allows it to scale depending
on system configuration.

Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <freqlabs@FreeBSD.org>
Issue #6572 
Closes #10706
2020-08-18 09:33:55 -07:00
Richard Laager eaa25f1a8e
Remove GRUB restrictions
The GRUB restrictions are based around the pool's bootfs property.
Given the current situation where GRUB is not staying current with
OpenZFS pool features, having either a non-ZFS /boot or a separate
pool with limited features are pretty much the only long-term answers
for GRUB support.  Only the second case matters in this context.  For
the restrictions to be useful, the bootfs property would have to be set
on the boot pool, because that is where we need the restrictions, as
that is the pool that GRUB reads from. The documentation for bootfs
describes it as pointing to the root pool. That's also how it's used in
the initramfs. ZFS does not allow setting bootfs to point to a dataset
in another pool. (If it did, it'd be difficult-to-impossible to enforce
these restrictions cross-pool). Accordingly, bootfs is pretty much
useless for GRUB scenarios moving forward.

Even for users who have only one pool, the existing restrictions for
GRUB are incomplete. They don't prevent you from enabling the
unsupported checksums, for example. For that reason, I have ripped out
all the GRUB restrictions.

A little longer-term, I think extending the proposed features=portable
system to define a features=grub is a much more useful approach. The
user could set that on the boot pool at creation, and things would
Just Work.

Reviewed-by: Paul Dagnelie <pcd@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Richard Laager <rlaager@wiktel.com>
Closes #8627
2020-08-17 23:12:39 -07:00
Matthew Ahrens 85ec5cbae2
Include scatter_chunk_waste in arc_size
The ARC caches data in scatter ABD's, which are collections of pages,
which are typically 4K.  Therefore, the space used to cache each block
is rounded up to a multiple of 4K.  The ABD subsystem tracks this wasted
memory in the `scatter_chunk_waste` kstat.  However, the ARC's `size` is
not aware of the memory used by this round-up, it only accounts for the
size that it requested from the ABD subsystem.

Therefore, the ARC is effectively using more memory than it is aware of,
due to the `scatter_chunk_waste`.  This impacts observability, e.g.
`arcstat` will show that the ARC is using less memory than it
effectively is.  It also impacts how the ARC responds to memory
pressure.  As the amount of `scatter_chunk_waste` changes, it appears to
the ARC as memory pressure, so it needs to resize `arc_c`.

If the sector size (`1<<ashift`) is the same as the page size (or
larger), there won't be any waste.  If the (compressed) block size is
relatively large compared to the page size, the amount of
`scatter_chunk_waste` will be small, so the problematic effects are
minimal.

However, if using 512B sectors (`ashift=9`), and the (compressed) block
size is small (e.g. `compression=on` with the default `volblocksize=8k`
or a decreased `recordsize`), the amount of `scatter_chunk_waste` can be
very large.  On a production system, with `arc_size` at a constant 50%
of memory, `scatter_chunk_waste` has been been observed to be 10-30% of
memory.

This commit adds `scatter_chunk_waste` to `arc_size`, and adds a new
`waste` field to `arcstat`.  As a result, the ARC's memory usage is more
observable, and `arc_c` does not need to be adjusted as frequently.

Reviewed-by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: George Wilson <gwilson@delphix.com>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #10701
2020-08-17 20:04:04 -07:00
Matthew Ahrens 994de7e4b7
Remove KMC_KMEM and KMC_VMEM
`KMC_KMEM` and `KMC_VMEM` are now unused since all SPL-implemented
caches are `KMC_KVMEM`.

KMC_KMEM: Given the default value of `spl_kmem_cache_kmem_limit`, we
don't use kmalloc to back the SPL caches, instead we use kvmalloc
(KMC_KVMEM).  The flag, module parameter, /proc entries, and associated
code are removed.

KMC_VMEM: This flag is not used, and kvmalloc() is always preferable to
vmalloc().  The flag, /proc entries, and associated code are removed.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #10673
2020-08-17 16:04:28 -07:00
Ryan Moeller 3df0c2fa32
FreeBSD: fix the build with Clang 11
* Cast void * to uintptr_t before casting to boolean_t.

* Avoid clashing definition of __asm when not on Linux to
  prevent duplicate __volatile__. This was already done in
  some places but not all.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Matt Macy <mmacy@FreeBSD.org>
Signed-off-by: Ryan Moeller <freqlabs@FreeBSD.org>
Closes #10723
2020-08-17 15:40:17 -07:00
Matthew Macy cfdc432e64
FreeBSD: fix merge error in zfs_acl_ids_create
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10721
2020-08-17 15:28:03 -07:00
Serapheim Dimitropoulos b0099072df
Fix typo in btree.c
Reviewed-by: George Melikov <mail@gmelikov.ru>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Signed-off-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Closes #10725
2020-08-17 15:25:37 -07:00
Matthew Macy 5f1984f2f8
FreeBSD: fallback to /boot/ to look for zpool.cache
Up until now zpool.cache has always lived in /boot on FreeBSD.
For the sake of compatibility fallback to /boot if zpool.cache
isn't found in /etc/zfs.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #10720
2020-08-17 14:43:47 -07:00
Ryan Moeller 3eaf76a8d2
Fix l2arc_dev_rebuild_start thread name
`thread_create` on FreeBSD stringifies the argument passed as the
thread function to create a name for the thread. The thread name for
`l2arc_dev_rebuild_start` ended up with `(void (*)(void *))` in it.

Change the type signature so the function does not need to be cast
when creating the thread.  Rename the function to
`l2arc_dev_rebuild_thread` for clarity and consistency, as well.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: George Amanakis <gamanakis@gmail.com>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10716
2020-08-17 11:02:32 -07:00
Ryan Moeller 3c3d7c8a57
FreeBSD: Create taskq threads in appropriate proc
Stepping stone toward re-enabling spa_thread on FreeBSD.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ryan Moeller <ryan@iXsystems.com>
Closes #10715
2020-08-17 11:01:19 -07:00
Allan Jude fc34dfba8e
Fix L2ARC reads when compressed ARC disabled
When reading compressed blocks from the L2ARC, with
compressed ARC disabled, arc_hdr_size() returns
LSIZE rather than PSIZE, but the actual read is PSIZE.
This causes l2arc_read_done() to compare the checksum
against the wrong size, resulting in checksum failure.

This manifests as an increase in the kstat l2_cksum_bad
and the read being retried from the main pool, making the
L2ARC ineffective.

Add new L2ARC tests with Compressed ARC enabled/disabled

Blocks are handled differently depending on the state of the
zfs_compressed_arc_enabled tunable.

If a block is compressed on-disk, and compressed_arc is enabled:
- the block is read from disk
- It is NOT decompressed
- It is added to the ARC in its compressed form
- l2arc_write_buffers() may write it to the L2ARC (as is)
- l2arc_read_done() compares the checksum to the BP (compressed)

However, if compressed_arc is disabled:
- the block is read from disk
- It is decompressed
- It is added to the ARC (uncompressed)
- l2arc_write_buffers() will use l2arc_apply_transforms() to
  recompress the block, before writing it to the L2ARC
- l2arc_read_done() compares the checksum to the BP (compressed)
- l2arc_read_done() will use l2arc_untransform() to uncompress it

This test writes out a test file to a pool consisting of one disk
and one cache device, then randomly reads from it. Since the arc_max
in the tests is low, this will feed the L2ARC, and result in reads
from the L2ARC.

We compare the value of the kstat l2_cksum_bad before and after
to determine if any blocks failed to survive the trip through the
L2ARC.

Sponsored-by: The FreeBSD Foundation
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Allan Jude <allanjude@freebsd.org>
Closes #10693
2020-08-13 23:31:20 -07:00
Jorgen Lundman faa296c73c
Release onexit/events with any missed zfsdev_state
Linux and FreeBSD will most likely never see this issue.
On macOS when kext is unloaded, but zed is still connected, zed
will be issued ENODEV. As the cdevsw is released, the kernel
will not have zfsdev_release() called to release minor/onexit/events,
and it "leaks". This ensures it is cleaned up before unload.

Changed the for loop from zsprev, to zsnext style, for less
code duplication.

Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Jorgen Lundman <lundman@lundman.net>
Closes #10700
2020-08-13 15:03:23 -07:00
Matthew Ahrens d64c6a2eee
Use zfs_dbgmsg to log metaslab_load/unload
Metaslabs are now (usually) loaded and unloaded infrequently, but when
that is not the case, it is useful to have a log of when and why these
events happened.

This commit enables the zfs_dbgmsg() in metaslab_load(), and adds a
zfs_dbgmsg() in metaslab_unload().

Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #10683
2020-08-12 10:10:50 -07:00