Commit Graph

2710 Commits

Author SHA1 Message Date
Matthew Ahrens
856d185dc2 Fix use-after-free of vd_path in spa_vdev_remove()
After spa_vdev_remove_aux() is called, the config nvlist is no longer
valid, as it's been replaced by the new one (with the specified device
removed).  Therefore any pointers into the nvlist are no longer valid.
So we can't save the result of
`fnvlist_lookup_string(nv, ZPOOL_CONFIG_PATH)` (in vd_path) across the
call to spa_vdev_remove_aux().

Instead, use spa_strdup() to save a copy of the string before calling
spa_vdev_remove_aux.

Found by AddressSanitizer:

ERROR: AddressSanitizer: heap-use-after-free on address ...
READ of size 34 at 0x608000a1fcd0 thread T686
    #0 0x7fe88b0c166d  (/usr/lib/x86_64-linux-gnu/libasan.so.4+0x5166d)
    #1 0x7fe88a5acd6e in spa_strdup spa_misc.c:1447
    #2 0x7fe88a688034 in spa_vdev_remove vdev_removal.c:2259
    #3 0x55ffbc7748f8 in ztest_vdev_aux_add_remove ztest.c:3229
    #4 0x55ffbc769fba in ztest_execute ztest.c:6714
    #5 0x55ffbc779a90 in ztest_thread ztest.c:6761
    #6 0x7fe889cbc6da in start_thread
    #7 0x7fe8899e588e in __clone

0x608000a1fcd0 is located 48 bytes inside of 88-byte region
freed by thread T686 here:
    #0 0x7fe88b14e7b8 in __interceptor_free
    #1 0x7fe88ae541c5 in nvlist_free nvpair.c:874
    #2 0x7fe88ae543ba in nvpair_free nvpair.c:844
    #3 0x7fe88ae57400 in nvlist_remove_nvpair nvpair.c:978
    #4 0x7fe88a683c81 in spa_vdev_remove_aux vdev_removal.c:185
    #5 0x7fe88a68857c in spa_vdev_remove vdev_removal.c:2221
    #6 0x55ffbc7748f8 in ztest_vdev_aux_add_remove ztest.c:3229
    #7 0x55ffbc769fba in ztest_execute ztest.c:6714
    #8 0x55ffbc779a90 in ztest_thread ztest.c:6761
    #9 0x7fe889cbc6da in start_thread

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@ixsystems.com>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #9706
2020-01-22 13:49:05 -08:00
Paul Zuchowski
4d658bda32 zio_decompress_data always ASSERTs successful decompression
This interferes with zdb_read_block trying all the decompression
algorithms when the 'd' flag is specified, as some are
expected to fail.  Also control the output when guessing
algorithms, try the more common compression types first, allow
specifying lsize/psize, and fix an uninitialized variable.

Reviewed-by: Ryan Moeller <ryan@ixsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Paul Zuchowski <pzuchowski@datto.com>
Closes #9612
Closes #9630
2020-01-22 13:49:05 -08:00
Matthew Macy
d2233a08fa Exclude data from cores unconditionally and metadata conditionally
This change allows us to align the code dump logic across platforms.

Reviewed-by: Jorgen Lundman <lundman@lundman.net>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Don Brady <don.brady@delphix.com>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #9691
2020-01-22 13:49:05 -08:00
Brian Behlendorf
2525b71c68 ZTS: Fix zpool_reopen_001_pos
Update the vdev_disk_open() retry logic to use a specified number
of milliseconds to be more robust.  Additionally, on failure log
both the time waited and requested timeout to the internal log.

The default maximum allowed open retry time has been increased
from 500ms to 1000ms.

Reviewed-by: Kjeld Schouten <kjeld@schouten-lebbing.nl>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #9680
Conflicts:
2020-01-22 13:49:05 -08:00
Alexander Motin
388ef045b2 Fix use-after-free in case of L2ARC prefetch failure
In case L2ARC read failed, l2arc_read_done() creates _different_ ZIO
to read data from the original storage device.  Unfortunately pointer
to the failed ZIO remains in hdr->b_l1hdr.b_acb->acb_zio_head, and if
some other read try to bump the ZIO priority, it will crash.

The problem is reproducible by corrupting L2ARC content and reading
some data with prefetch if l2arc_noprefetch tunable is changed to 0.
With the default setting the issue is probably not reproducible now.

Reviewed-by: Tom Caputi <tcaputi@datto.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Sponsored-By: iXsystems, Inc.
Closes #9648
2020-01-22 13:49:05 -08:00
Brian Behlendorf
9cf46ddedc Increase allowed 'special_small_blocks' maximum value
There may be circumstances where it's desirable that all blocks
in a specified dataset be stored on the special device.  Relax
the artificial 128K limit and allow the special_small_blocks
property to be set up to 1M.  When blocks >1MB have been enabled
via the zfs_max_recordsize module option, this limit is increased
accordingly.

Reviewed-by: Don Brady <don.brady@delphix.com>
Reviewed-by: Kjeld Schouten <kjeld@schouten-lebbing.nl>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #9131
Closes #9355
2020-01-22 13:49:05 -08:00
Michael Niewöhner
85204e30dd Adapt gitignore for modules
Remove the specific gitignore rules for module left-overs and add a
generic one in modules/.

Reviewed-by: Ryan Moeller <ryan@ixsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Kjeld Schouten <kjeld@schouten-lebbing.nl>
Signed-off-by: Michael Niewöhner <foss@mniewoehner.de>
Closes #9656
2020-01-22 13:49:05 -08:00
Brian Behlendorf
36fe63042c Remove zfs_vdev_elevator module option
As described in commit f81d5ef6 the zfs_vdev_elevator module
option is being removed.  Users who require this functionality
should update their systems to set the disk scheduler using a
udev rule.

Reviewed-by: Richard Laager <rlaager@wiktel.com>
Reviewed-by: loli10K <ezomori.nozomu@gmail.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #8664
Closes #9417
Closes #9609
2020-01-22 13:49:04 -08:00
Mauricio Faria de Oliveira
bc21c56c2d Check for unlinked znodes after igrab()
The changes in commit 41e1aa2a / PR #9583 introduced a regression on
tmpfile_001_pos: fsetxattr() on a O_TMPFILE file descriptor started
to fail with errno ENODATA:

    openat(AT_FDCWD, "/test", O_RDWR|O_TMPFILE, 0666) = 3
    <...>
    fsetxattr(3, "user.test", <...>, 64, 0) = -1 ENODATA

The originally proposed change on PR #9583 is not susceptible to it,
so just move the code/if-checks around back in that way, to fix it.

Reviewed-by: Pavel Snajdr <snajpa@snajpa.net>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Original-patch-by: Heitor Alves de Siqueira <halves@canonical.com>
Signed-off-by: Mauricio Faria de Oliveira <mfo@canonical.com>
Closes #9602
2020-01-22 13:49:04 -08:00
Heitor Alves de Siqueira
20e124dd71 Break out of zfs_zget early if unlinked znode
If zp->z_unlinked is set, we're working with a znode that has been
marked for deletion. If that's the case, we can skip the "goto again"
loop and return ENOENT, as the znode should not be discovered.

Reviewed-by: Richard Yao <ryao@gentoo.org>
Reviewed-by: Matt Ahrens <mahrens@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Heitor Alves de Siqueira <halves@canonical.com>
Closes #9583
2020-01-22 13:49:04 -08:00
loli10K
880a37aa35 Prevent NULL pointer dereference in blkg_tryget() on EL8 kernels
blkg_tryget() as shipped in EL8 kernels does not seem to handle NULL
@blkg as input; this is different from its mainline counterpart where
NULL is accepted.  To prevent dereferencing a NULL pointer when dealing
with block devices which do not set a root_blkg on the request queue
perform the NULL check in vdev_bio_associate_blkg().

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Kjeld Schouten <kjeld@schouten-lebbing.nl>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: loli10K <ezomori.nozomu@gmail.com>
Closes #9546
Closes #9577
2020-01-22 13:49:04 -08:00
Michael Niewöhner
1545f7c59d Add missing documentation for some KMC flags
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Matt Ahrens <matt@delphix.com>
Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Signed-off-by: Michael Niewöhner <foss@mniewoehner.de>
Closes #9034
2020-01-22 13:49:04 -08:00
Alexander Motin
edaec84225 Improve logging of 128KB writes
Before my ZIL space optimization few years ago 128KB writes were logged
as two 64KB+ records in two 128KB log blocks.  After that change it
became ~127KB+/1KB+ in two 128KB log blocks to free space in the second
block for another record.  Unfortunately in case of 128KB only writes,
when space in the second block remained unused, that change increased
write latency by unbalancing checksum computation and write times
between parallel threads.  It also didn't help with SLOG space
efficiency in that case.

This change introduces new 68KB log block size, used for both writes
below 67KB and 128KB-sharp writes.  Writes of 68-127KB are still using
one 128KB block to not increase processing overhead.  Writes above
131KB are still using full 128KB blocks, since possible saving there
is small.  Mixed loads will likely also fall back to previous 128KB,
since code uses maximum of the last 16 requested block sizes.

Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by:  Alexander Motin <mav@FreeBSD.org>
Closes #9409
2020-01-22 13:49:04 -08:00
Matthew Macy
ca0f9b7473 Include prototypes for vdev_initialize
Address two prototype related warnings emitted by clang.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Igor Kozhukhov <igor@dilos.org>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #9535
2020-01-22 13:49:03 -08:00
Tom Caputi
7e1b772edd Fix 'zfs change-key' with unencrypted child
Currently, when you call 'zfs change-key' on an encrypted dataset
that has an unencrypted child, the code will trigger a VERIFY.
This VERIFY is leftover from before we allowed unencrypted
datasets to exist underneath encrypted ones. This patch fixes the
issue by simply replacing the VERIFY with an early return when
recursing through datasets.

Reviewed by: Jason King <jason.brian.king@gmail.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Igor Kozhukhov <igor@dilos.org>
Signed-off-by: Tom Caputi <tcaputi@datto.com>
Closes #9524
2020-01-22 13:49:03 -08:00
Serapheim Dimitropoulos
8c8f84472b Update skc_obj_alloc for spl kmem caches that are backed by Linux
Currently, for certain sizes and classes of allocations we use
SPL caches that are backed by caches in the Linux Slab allocator
to reduce fragmentation and increase utilization of memory. The
way things are implemented for these caches as of now though is
that we don't keep any statistics of the allocations that we
make from these caches.

This patch enables the tracking of allocated objects in those
SPL caches by making the trade-off of grabbing the cache lock
at every object allocation and free to update the respective
counter.

Additionally, this patch makes those caches visible in the
/proc/spl/kmem/slab special file.

As a side note, enabling the specific counter for those caches
enables SDB to create a more user-friendly interface than
/proc/spl/kmem/slab that can also cross-reference data from
slabinfo. Here is for example the output of one of those
caches in SDB that outputs the name of the underlying Linux
cache, the memory of SPL objects allocated in that cache,
and the percentage of those objects compared to all the
objects in it:
```
> spl_kmem_caches | filter obj.skc_name == "zio_buf_512" | pp
name        ...            source total_memory util
----------- ... ----------------- ------------ ----
zio_buf_512 ... kmalloc-512[SLUB]       16.9MB    8
```

Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Closes #9474
2020-01-22 13:49:03 -08:00
loli10K
f1ba5478a3 Fix pool creation with feature@allocation_classes disabled
When "feature@allocation_classes" is not enabled on the pool no vdev
with "special" or "dedup" allocation type should be allowed to exist in
the vdev tree.

Reviewed-by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: loli10K <ezomori.nozomu@gmail.com>
Closes #9427
Closes #9429
2020-01-22 13:49:02 -08:00
George Melikov
8139355dce module/Makefile.in: don't run xargs if empty
If stdin if empty - don't run xargs command,
otherwise we can get `cp: missing file operand`
error.

Reviewed-by: Ryan Moeller <ryan@ixsystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: George Melikov <mail@gmelikov.ru>
Closes #9418
2020-01-22 13:49:02 -08:00
Brian Behlendorf
5a1bf9e8b1 Fix automount for root filesystems
Commit 093bb64 resolved an automount failures for chroot'd processes
but inadvertently broke automounting for root filesystems where the
vfs_mntpoint is NULL.  Resolve the issue by checking for NULL in order
to generate the correct path.

Reviewed-by: Tom Caputi <tcaputi@datto.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #9381
Closes #9384
2020-01-22 13:49:02 -08:00
Matthew Macy
b43893de86 Rename rangelock_ functions to zfs_rangelock_
A rangelock KPI already exists on FreeBSD.  Add a zfs_ prefix as
per our convention to prevent any conflict with existing symbols.

Reviewed-by: Igor Kozhukhov <igor@dilos.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matt Macy <mmacy@FreeBSD.org>
Closes #9402
2020-01-22 13:49:02 -08:00
Brian Behlendorf
62c034f6d4 Linux 5.0 compat: SIMD compatibility
Restore the SIMD optimization for 4.19.38 LTS, 4.14.120 LTS,
and 5.0 and newer kernels.

This commit squashes the following commits from master in to
a single commit which can be applied to 0.8.2.

10fa2545 - Linux 4.14, 4.19, 5.0+ compat: SIMD save/restore
b88ca2ac - Enable SIMD for encryption
095b5412 - Fix CONFIG_X86_DEBUG_FPU build failure
e5db3134 - Linux 5.0 compat: SIMD compatibility

Reviewed-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
TEST_ZIMPORT_SKIP="yes"
2020-01-22 13:49:01 -08:00
Brian Behlendorf
055238d2eb Add warning for zfs_vdev_elevator option removal
Originally the zfs_vdev_elevator module option was added as a
convenience so the requested elevator would be automatically set
on the underlying block devices.  At the time this was simple
because the kernel provided an API function which did exactly this.

This API was then removed in the Linux 4.12 kernel which prompted
us to add compatibly code to set the elevator via a usermodehelper.
While well intentioned this introduced a bug which could cause a
system hang, that issue was subsequently fixed by commit 2a0d4188.

In order to avoid future bugs in this area, and to simplify the code,
this functionality is being deprecated.  A console warning has been
added to notify any existing consumers and the documentation updated
accordingly.  This option will remain for the lifetime of the 0.8.x
series for compatibility but if planned to be phased out of master.

Reviewed-by: Richard Laager <rlaager@wiktel.com>
Reviewed-by: loli10K <ezomori.nozomu@gmail.com>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #8664
Closes #9317
2020-01-22 13:49:01 -08:00
loli10K
ec5d76e853 diff_cb() does not handle large dnodes
Trying to 'zfs diff' a snapshot with large dnodes will incorrectly try
to access its interior slots when dnodesize > sizeof(dnode_phys_t).
This is normally not an issue because the interior slots are
zero-filled, which report_dnode() handles calling
report_free_dnode_range(). However this is not the case for encrypted
large dnodes or filesystem using many SA based xattrs where the extra
data past the legacy dnode size boundary is interpreted as a
dnode_phys_t.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Tom Caputi <tcaputi@datto.com>
Reviewed-by: Ryan Moeller <ryan@ixsystems.com>
Signed-off-by: loli10K <ezomori.nozomu@gmail.com>
Closes #7678
Closes #8931
Closes #9343
2020-01-22 13:49:01 -08:00
loli10K
444df1051c Device removal of indirect vdev panics the kernel
This commit fixes a NULL pointer dereference triggered in
spa_vdev_remove_top_check() by trying to "zpool remove" an indirect
vdev.

Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: loli10K <ezomori.nozomu@gmail.com>
Closes #9327
2020-01-22 13:49:01 -08:00
Tom Caputi
5986c5c687 Fix clone handling with encryption roots
Currently, spa_keystore_change_key_sync_impl() does not recurse
into clones when updating encryption roots for either a call to
'zfs promote' or 'zfs change-key'. This can cause children of
these clones to end up in a state where they point to the wrong
dataset as the encryption root. It can also trigger ASSERTs in
some cases where the code checks reference counts on wrapping
keys. This patch fixes this issue by ensuring that this function
properly recurses into clones during processing.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Alek Pinchuk <apinchuk@datto.com>
Signed-off-by: Tom Caputi <tcaputi@datto.com>
Closes #9267
Closes #9294
2020-01-22 13:49:00 -08:00
Tom Caputi
8747ee4513 Fix stalled txg with repeated noop scans
Currently, the DSL scan code figures out when it should suspend
processing and allow a txg to continue by calling the function
dsl_scan_check_suspend(). Unfortunately, this function only
allows the scan to suspend at a level 0 block. In the event that
the system is scanning a bunch of empty snapshots or a resilver
is running with a high enough scn_cur_min_txg, the scan will
stop processing each dataset at the root level, deciding it
has nothing left to do. This means that the check_suspend
function is never called and the txg remains stuck until a
dataset is found that has data to scan.

This patch fixes the problem by allowing scans to suspend at
the root level of the objset. For backwards compatibility, we
use the bookmark <objsetid, 0, 0, 0> when we suspend here so
that older versions of the code will work as intended.

Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Tom Caputi <tcaputi@datto.com>
Closes #9300
2020-01-22 13:49:00 -08:00
Igor K
5cb46afcf1 Fix panic on DilOS with kstat per dataset statistics
Account for ZFS_MAX_DATASET_NAME_LEN in kstat data size.  This value
is ignored in the Linux kstat code but resolves the issue for other
platforms.

Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Igor Kozhukhov <igor@dilos.org>
Closes #9254
Closes #9151
2020-01-22 13:49:00 -08:00
George Wilson
7e93917309 maxinflight can overflow in spa_load_verify_cb()
When running on larger memory systems, we can overflow the value of
maxinflight. This can result in maxinflight having a value of 0 causing
the system to hang.

Reviewed-by: Igor Kozhukhov <igor@dilos.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: George Wilson <george.wilson@delphix.com>
Closes #9272
2020-01-22 13:49:00 -08:00
Andrea Gelmini
5097eb6ac9 Fix typos in module/zfs/
Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed-by: Ryan Moeller <ryan@ixsystems.com>
Reviewed-by: Richard Laager <rlaager@wiktel.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Andrea Gelmini <andrea.gelmini@gelma.net>
Closes #9240
2020-01-22 13:48:59 -08:00
Andrea Gelmini
48d8b249c9 Fix typos in module/
Reviewed-by: Ryan Moeller <ryan@ixsystems.com>
Reviewed-by: Richard Laager <rlaager@wiktel.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Andrea Gelmini <andrea.gelmini@gelma.net>
Closes #9241
2020-01-22 13:48:59 -08:00
Andrea Gelmini
8c01eb1c4a Fix typos in modules/icp/
Reviewed-by: Ryan Moeller <ryan@ixsystems.com>
Reviewed-by: Richard Laager <rlaager@wiktel.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Andrea Gelmini <andrea.gelmini@gelma.net>
Closes #9239
2020-01-22 13:48:59 -08:00
Paul Dagnelie
ebdb770554 Prevent metaslab_sync panic due to spa_final_dirty_txg
If a pool enables the SPACEMAP_HISTOGRAM feature shortly before being
exported, we can enter a situation that causes a kernel panic. Any metaslabs
that are loaded during the final dirty txg and haven't already been condensed
will cause metaslab_sync to proceed after the final dirty txg so that the
condense can be performed, which there are assertions to prevent. Because of
the nature of this issue, there are a number of ways we can enter this
state. Rather than try to prevent each of them one by one, potentially missing
some edge cases, we instead cut it off at the point of intersection; by
preventing metaslab_sync from proceeding if it would only do so to perform a
condense and we're past the final dirty txg, we preserve the utility of the
existing asserts while preventing this particular issue.

Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Paul Dagnelie <pcd@delphix.com>
Closes #9185
Closes #9186
Closes #9231
Closes #9253
2020-01-22 13:48:58 -08:00
Tony Nguyen
16f42e1b6d Use smaller default slack/delta value for schedule_hrtimeout_range()
For interrupt coalescing, cv_timedwait_hires() uses a 100us slack/delta
for calls to schedule_hrtimeout_range(). This 100us slack can be costly
for small writes.

This change improves small write performance by passing resolution `res`
parameter to schedule_hrtimeout_range() to be used as delta/slack. A new
tunable `spl_schedule_hrtimeout_slack_us` is added to preserve old
behavior when desired.

Performance observations on 8K recordsize filesystem:
- 8K random writes at 1-64 threads, up to 60% improvement for one thread
  and smaller gains as thread count increases. At >64 threads, 2-5%
  decrease in performance was observed.
- 8K sequential writes, similar 60% improvement for one thread and
  leveling out around 64 threads. At >64 threads, 5-10% decrease in
  performance was observed.
- 128K sequential write sees 1-5 for the 128K. No observed regression at
  high thread count.

Testing done on Ubuntu 18.04 with 4.15 kernel, 8vCPUs and SSD storage on
VMware ESX.

Reviewed-by: Richard Elling <Richard.Elling@RichardElling.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Matt Ahrens <mahrens@delphix.com>
Signed-off-by: Tony Nguyen <tony.nguyen@delphix.com>
Closes #9217
2020-01-22 13:48:58 -08:00
jdike
db58aa717b Fix lockdep circular locking false positive involving sa_lock
There are two different deadlock scenarios, but they share a common
link, which is
thread 1 holding sa_lock and trying to get zap->zap_rwlock:
    zap_lockdir_impl+0x858/0x16c0 [zfs]
    zap_lockdir+0xd2/0x100 [zfs]
    zap_lookup_norm+0x7f/0x100 [zfs]
    zap_lookup+0x12/0x20 [zfs]
    sa_setup+0x902/0x1380 [zfs]
    zfsvfs_init+0x3d6/0xb20 [zfs]
    zfsvfs_create+0x5dd/0x900 [zfs]
    zfs_domount+0xa3/0xe20 [zfs]

and thread 2 trying to get sa_lock, either in sa_setup:
   sa_setup+0x742/0x1380 [zfs]
   zfsvfs_init+0x3d6/0xb20 [zfs]
   zfsvfs_create+0x5dd/0x900 [zfs]
   zfs_domount+0xa3/0xe20 [zfs]
or in sa_build_index:
   sa_build_index+0x13d/0x790 [zfs]
   sa_handle_get_from_db+0x368/0x500 [zfs]
   zfs_znode_sa_init.isra.0+0x24b/0x330 [zfs]
   zfs_znode_alloc+0x3da/0x1a40 [zfs]
   zfs_zget+0x39a/0x6e0 [zfs]
   zfs_root+0x101/0x160 [zfs]
   zfs_domount+0x91f/0xea0 [zfs]

From there, there are different locking paths back to something
holding zap->zap_rwlock.

The deadlock scenarios involve multiple different ZFS filesystems
being mounted.  sa_lock is common to these scenarios, and the sa
struct involved is private to a mount.  Therefore, these must be
referring to different sa_lock instances and these deadlocks can't
occur in practice.

The fix, from Brian Behlendorf, is to remove sa_lock from lockdep
coverage by initializing it with MUTEX_NOLOCKDEP.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Jeff Dike <jdike@akamai.com>
Closes #9110
2020-01-22 13:48:57 -08:00
Serapheim Dimitropoulos
dfa4d3d986 dmu_tx_wait() hang likely due to cv_signal() in dsl_pool_dirty_delta()
Even though the bug's writeup (Github issue #9136) is very detailed,
we still don't know exactly how we got to that state, thus I wasn't
able to reproduce the bug. That said, we can make an educated guess
combining the information on filled issue with the code.

From the fact that `dp_dirty_total` was 0 (which is less than
`zfs_dirty_data_max`) we know that there was one thread that set it to
0 and then signaled one of the waiters of `dp_spaceavail_cv` [see
`dsl_pool_dirty_delta()` which is also the only place that
`dp_dirty_total` is changed].  Thus, the only logical explaination
then for the bug being hit is that the waiter that just got awaken
didn't go through `dsl_pool_dirty_data()`. Given that this function
is only called by `dsl_pool_dirty_space()` or `dsl_pool_undirty_space()`
I can only think of two possible ways of the above scenario happening:

[1] The waiter didn't call into any of the two functions - which I
    find highly unlikely (i.e. why wait on `dp_spaceavail_cv` to begin
    with?).
[2] The waiter did call in one of the above function but it passed 0 as
    the space/delta to be dirtied (or undirtied) and then the callee
    returned immediately (e.g both `dsl_pool_dirty_space()` and
    `dsl_pool_undirty_space()` return immediately when space is 0).

In any case and no matter how we got there, the easy fix would be to
just broadcast to all waiters whenever `dp_dirty_total` hits 0. That
said and given that we've never hit this before, it would make sense
to think more on why the above situation occured.

Attempting to mimic what Prakash was doing in the issue filed, I
created a dataset with `sync=always` and started doing contiguous
writes in a file within that dataset. I observed with DTrace that even
though we update the pool's dirty data accounting when we would dirty
stuff, the accounting wouldn't be decremented incrementally as we were
done with the ZIOs of those writes (the reason being that
`dbuf_write_physdone()` isn't be called as we go through the override
code paths, and thus `dsl_pool_undirty_space()` is never called). As a
result we'd have to wait until we get to `dsl_pool_sync()` where we
zero out all dirty data accounting for the pool and the current TXG's
metadata.

In addition, as Matt noted and I later verified, the same issue would
arise when using dedup.

In both cases (sync & dedup) we shouldn't have to wait until
`dsl_pool_sync()` zeros out the accounting data. According to the
comment in that part of the code, the reasons why we do the zeroing,
have nothing to do with what we observe:
````
/*
 * We have written all of the accounted dirty data, so our
 * dp_space_towrite should now be zero.  However, some seldom-used
 * code paths do not adhere to this (e.g. dbuf_undirty(), also
 * rounding error in dbuf_write_physdone).
 * Shore up the accounting of any dirtied space now.
 */
dsl_pool_undirty_space(dp, dp->dp_dirty_pertxg[txg & TXG_MASK], txg);
````

Ideally what we want to do is to undirty in the accounting exactly what
we dirty (I use the word ideally as we can still have rounding errors).
This would make the behavior of the system more clear and predictable.

Another interesting issue that I observed with DTrace was that we
wouldn't update any of the pool's dirty data accounting whenever we
would dirty and/or undirty MOS data. In addition, every time we would
change the size of a dbuf through `dbuf_new_size()` we wouldn't update
the accounted space dirtied in the appropriate dirty record, so when
ZIOs are done we would undirty less that we dirtied from the pool's
accounting point of view.

For the first two issues observed (sync & dedup) this patch ensures
that we still update the pool's accounting when we undirty data,
regardless of the write being physical or not.

For changes in the MOS, we first ensure to zero out the pool's dirty
data accounting in `dsl_pool_sync()` after we synced the MOS. Then we
can go ahead and enable the update of the pool's dirty data accounting
wheneve we change MOS data.

Another fix is that we now update the accounting explicitly for
counting errors in `dbuf_write_done()`.

Finally, `dbuf_new_size()` updates the accounted space of the
appropriate dirty record correctly now.

The problem is that we still don't know how the bug came up in the
issue filled. That said the issues fixed seem to be very relevant, so
instead of going with the broadcasting solution right away,
I decided to leave this patch as is.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Prakash Surya <prakash.surya@delphix.com>
Signed-off-by: Serapheim Dimitropoulos <serapheim@delphix.com>
External-issue: DLPX-47285
Closes #9137
2020-01-22 13:48:57 -08:00
Tony Nguyen
b78d32cc25 Improve write performance by using dmu_read_by_dnode()
In zfs_log_write(), we can use dmu_read_by_dnode() rather than
dmu_read() thus avoiding unnecessary dnode_hold() calls.

We get a 2-5% performance gain for large sequential_writes tests, >=128K
writes to files with recordsize=8K.

Testing done on Ubuntu 18.04 with 4.15 kernel, 8vCPUs and SSD storage on
VMware ESX.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Tony Nguyen <tony.nguyen@delphix.com>
Closes #9156
2020-01-22 13:48:57 -08:00
Serapheim Dimitropoulos
dd6d0bdbb3 Assert that a dnode's bonuslen never exceeds its recorded size
This patch introduces an assertion that can catch pitfalls in
development where there is a mismatch between the size of
reads and writes between a *_phys structure and its respective
in-core structure when bonus buffers are used.

This debugging-aid should be complementary to the verification
done by ztest in ztest_verify_dnode_bt().

A side to this patch is that we now clear out any extra bytes
past a bonus buffer's new size when the buffer is shrinking.

Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Tom Caputi <tcaputi@datto.com>
Signed-off-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Closes #8348
2020-01-22 13:48:57 -08:00
Paul Zuchowski
9d4ca81b6f Make txg_wait_synced conditional in zfsvfs_teardown
The call to txg_wait_synced in zfsvfs_teardown should
be made conditional on the objset having dirty data.
This can prevent unnecessary txg_wait_synced during
some unmount operations.

Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Paul Zuchowski <pzuchowski@datto.com>
Closes #9115
2020-01-22 13:48:57 -08:00
Paul Dagnelie
93fd9101c9 Prevent race in blkptr_verify against device removal
When we check the vdev of the blkptr in zfs_blkptr_verify, we can run
into a race condition where that vdev is temporarily unavailable. This
happens when a device removal operation and the old vdev_t has been
removed from the array, but the new indirect vdev has not yet been
inserted.

We hold the spa_config_lock while doing our sensitive verification.
To ensure that we don't deadlock, we only grab the lock if we don't
have config_writer held. In addition, I had to const the tags of the
refcounts and the spa_config_lock arguments.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Signed-off-by: Paul Dagnelie <pcd@delphix.com>
Closes #9112
2020-01-22 13:48:57 -08:00
George Wilson
628fd31d26 spa_load_verify() may consume too much memory
When a pool is imported it will scan the pool to verify the integrity
of the data and metadata. The amount it scans will depend on the
import flags provided. On systems with small amounts of memory or
when importing a pool from the crash kernel, it's possible for
spa_load_verify to issue too many I/Os that it consumes all the memory
of the system resulting in an OOM message or a hang.

To prevent this, we limit the amount of memory that the initial pool
scan can consume. This change will, by default, use 1/16th of the ARC
for scan I/Os to prevent running the system out of memory during import.

Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Signed-off-by: George Wilson george.wilson@delphix.com
External-issue: DLPX-65237
External-issue: DLPX-65238
Closes #9146
2020-01-22 13:48:57 -08:00
Tomohiro Kusumi
d38e4ee142 Change boolean-like uint8_t fields in znode_t to boolean_t
Given znode_t is an in-core structure, it's more readable to have
them as boolean. Also co-locate existing boolean fields with them
for space efficiency (expecting 8 booleans to be packed/aligned).

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Tomohiro Kusumi <kusumi.tomohiro@gmail.com>
Closes #9092
Conflicts:
	include/sys/zfs_znode.h
	module/zfs/zfs_znode.c
2020-01-22 13:48:57 -08:00
Richard Yao
0b96952eef Drop KMC_NOEMERGENCY
This is not implemented. If it were implemented, using it would risk
deadlocks on pre-3.18 kernels. Lets just drop it.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Michael Niewöhner <foss@mniewoehner.de>
Signed-off-by: Richard Yao <ryao@gentoo.org>
Closes #9119
2020-01-22 13:48:57 -08:00
DeHackEd
376ca4649b Don't wakeup unnecessarily in 'zpool events -f'
ZED can prevent CPU's from properly sleeping.

Rather than periodically waking up in the zevents code, just go to sleep and wait for a wakeup.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: DHE <git@dehacked.net>
Closes #9091
2020-01-22 13:48:57 -08:00
jdike
77d59a6d63 lockdep false positive - move txg_kick() outside of ->dp_lock
This fixes a lockdep warning by breaking a link between ->tx_sync_lock
and ->dp_lock.

The deadlock envisioned by lockdep is this:
    thread 1 holds db->db_mtx and tries to get dp->dp_lock:
	dsl_pool_dirty_space+0x70/0x2d0 [zfs]
	dbuf_dirty+0x778/0x31d0 [zfs]

    thread 2 holds bpo->bpo_lock and tries to get db->db_mtx:
        dmu_buf_will_dirty_impl
        dmu_buf_will_dirty+0x6b/0x6c0 [zfs]
        bpobj_iterate_impl+0xbe6/0x1410 [zfs]

    thread 3 holds tx->tx_sync_lock and tries to get bpo->bpo_lock:
        bpobj_space+0x63/0x470 [zfs]
        dsl_scan_active+0x340/0x3d0 [zfs]
        txg_sync_thread+0x3f2/0x1370 [zfs]

    thread 4 holds dp->dp_lock and tries to get tx->tx_sync_lock
       txg_kick+0x61/0x420 [zfs]
       dsl_pool_need_dirty_delay+0x1c7/0x3f0 [zfs]

This patch is orginally from Brian Behlendorf and slightly simplified
by me.

It breaks this cycle in thread 4 by moving the call from
dsl_pool_need_dirty_delay to txg_kick outside the section controlled
by dp->dp_lock.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Matt Ahrens <mahrens@delphix.com>
Signed-off-by: Jeff Dike <jdike@akamai.com>
Closes #9094
2020-01-22 13:48:57 -08:00
Paul Dagnelie
66c8b2f65a Don't activate metaslabs with weight 0
We return ENOSPC in metaslab_activate if the metaslab has weight 0,
to avoid activating a metaslab with no space available.  For sanity
checking, we also assert that there is no free space in the range
tree in that case.

Reviewed-by: Igor Kozhukhov <igor@dilos.org>
Reviewed by: Matt Ahrens <matt@delphix.com>
Reviewed by: Serapheim Dimitropoulos <serapheim.dimitro@delphix.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Paul Dagnelie <pcd@delphix.com>
Closes #8968
2020-01-22 13:48:57 -08:00
Paul Dagnelie
350646563f Concurrent small allocation defeats large allocation
With the new parallel allocators scheme, there is a possibility for
a problem where two threads, allocating from the same allocator at
the same time, conflict with each other. There are two primary cases
to worry about. First, another thread working on another allocator
activates the same metaslab that the first thread was trying to
activate. This results in the first thread needing to go back and
reselect a new metaslab, even though it may have waited a long time
for this metaslab to load. Second, another thread working on the same
allocator may have activated a different metaslab while the first
thread was waiting for its metaslab to load. Both of these cases
can cause the first thread to be significantly delayed in issuing
its IOs. The second case can also cause metaslab load/unload churn;
because the metaslab is loaded but not fully activated, we never set
the selected_txg, which results in the metaslab being immediately
unloaded again. This process can repeat many times, wasting disk and
cpu resources. This is more likely to happen when the IO of the first
thread is a larger one (like a ZIL write) and the other thread is
doing a smaller write, because it is more likely to find an
acceptable metaslab quickly.

There are two primary changes. The first is to always proceed with
the allocation when returning from metaslab_activate if we were
preempted in either of the ways described in the previous section.
The second change is to set the selected_txg before we do the call
to activate so that even if the metaslab is not used for an
allocation, we won't immediately attempt to unload it.

Reviewed by: Jerry Jelinek <jerry.jelinek@joyent.com>
Reviewed by: Matt Ahrens <matt@delphix.com>
Reviewed by: Serapheim Dimitropoulos <serapheim.dimitro@delphix.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Paul Dagnelie <pcd@delphix.com>
External-issue: DLPX-61314
Closes #8843
2020-01-22 13:48:56 -08:00
loli10K
d47ee5ad1c Fix bp_embedded_type enum definition
With the addition of BP_EMBEDDED_TYPE_REDACTED in 30af21b0 a couple of
codepaths make wrong assumptions and could potentially result in errors.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Chris Dunlop <chris@onthe.net.au>
Reviewed-by: Paul Dagnelie <pcd@delphix.com>
Signed-off-by: loli10K <ezomori.nozomu@gmail.com>
Closes #8951
Conflicts:
	include/sys/spa.h
2020-01-22 13:48:56 -08:00
Don Brady
e625030c11 OpenZFS 9425 - channel programs can be interrupted
Problem Statement
=================
ZFS Channel program scripts currently require a timeout, so that hung or
long-running scripts return a timeout error instead of causing ZFS to get
wedged. This limit can currently be set up to 100 million Lua instructions.
Even with a limit in place, it would be desirable to have a sys admin
(support engineer) be able to cancel a script that is taking a long time.

Proposed Solution
=================
Make it possible to abort a channel program by sending an interrupt signal.In
the underlying txg_wait_sync function, switch the cv_wait to a cv_wait_sig to
catch the signal. Once a signal is encountered, the dsl_sync_task function can
install a Lua hook that will get called before the Lua interpreter executes a
new line of code. The dsl_sync_task can resume with a standard txg_wait_sync
call and wait for the txg to complete.  Meanwhile, the hook will abort the
script and indicate that the channel program was canceled. The kernel returns
a EINTR to indicate that the channel program run was canceled.

Porting notes: Added missing return value from cv_wait_sig()

Authored by: Don Brady <don.brady@delphix.com>
Reviewed by: Sebastien Roy <sebastien.roy@delphix.com>
Reviewed by: Serapheim Dimitropoulos <serapheim.dimitro@delphix.com>
Reviewed by: Matt Ahrens <matt@delphix.com>
Reviewed by: Sara Hartse <sara.hartse@delphix.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Approved by: Robert Mustacchi <rm@joyent.com>
Ported-by: Don Brady <don.brady@delphix.com>
Signed-off-by: Don Brady <don.brady@delphix.com>

OpenZFS-issue: https://www.illumos.org/issues/9425
OpenZFS-commit: https://github.com/illumos/illumos-gate/commit/d0cb1fb926
Closes #8904
2020-01-22 13:48:56 -08:00
Matthew Ahrens
cbb9154958 looping in metaslab_block_picker impacts performance on fragmented pools
On fragmented pools with high-performance storage, the looping in
metaslab_block_picker() can become the performance-limiting bottleneck.
When looking for a larger block (e.g. a 128K block for the ZIL), we may
search through many free segments (up to hundreds of thousands) to find
one that is large enough to satisfy the allocation. This can take a long
time (up to dozens of ms), and is done while holding the ms_lock, which
other threads may spin waiting for.

When this performance problem is encountered, profiling will show
high CPU time in metaslab_block_picker, as well as in mutex_enter from
various callers.

The problem is very evident on a test system with a sync write workload
with 8K writes to a recordsize=8k filesystem, with 4TB of SSD storage,
84% full and 88% fragmented. It has also been observed on production
systems with 90TB of storage, 76% full and 87% fragmented.

The fix is to change metaslab_df_alloc() to search only up to 16MB from
the previous allocation (of this alignment). After that, we will pick a
segment that is of the exact size requested (or larger). This reduces
the number of iterations to a few hundred on fragmented pools (a ~100x
improvement).

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Paul Dagnelie <pcd@delphix.com>
Reviewed-by: Tony Nguyen <tony.nguyen@delphix.com>
Reviewed-by: George Wilson <george.wilson@delphix.com>
Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
External-issue: DLPX-62324
Closes #8877
2020-01-22 13:48:56 -08:00
Matthew Ahrens
8805abb8fc single-chunk scatter ABDs can be treated as linear
Scatter ABD's are allocated from a number of pages.  In contrast to
linear ABD's, these pages are disjoint in the kernel's virtual address
space, so they can't be accessed as a contiguous buffer.  Therefore
routines that need a linear buffer (e.g. abd_borrow_buf() and friends)
must allocate a separate linear buffer (with zio_buf_alloc()), and copy
the contents of the pages to/from the linear buffer.  This can have a
measurable performance overhead on some workloads.

https://github.com/zfsonlinux/zfs/commit/87c25d567fb7969b44c7d8af63990e
("abd_alloc should use scatter for >1K allocations") increased the use
of scatter ABD's, specifically switching 1.5K through 4K (inclusive)
buffers from linear to scatter.  For workloads that access blocks whose
compressed sizes are in this range, that commit introduced an additional
copy into the read code path.  For example, the
sequential_reads_arc_cached tests in the test suite were reduced by
around 5% (this is doing reads of 8K-logical blocks, compressed to 3K,
which are cached in the ARC).

This commit treats single-chunk scattered buffers as linear buffers,
because they are contiguous in the kernel's virtual address space.

All single-page (4K) ABD's can be represented this way.  Some multi-page
ABD's can also be represented this way, if we were able to allocate a
single "chunk" (higher-order "page" which represents a power-of-2 series
of physically-contiguous pages).  This is often the case for 2-page (8K)
ABD's.

Representing a single-entry scatter ABD as a linear ABD has the
performance advantage of avoiding the copy (and allocation) in
abd_borrow_buf_copy / abd_return_buf_copy.  A performance increase of
around 5% has been observed for ARC-cached reads (of small blocks which
can take advantage of this), fixing the regression introduced by
87c25d567.

Note that this optimization is only possible because all physical memory
is always mapped into the kernel's address space.  This is not the case
for HIGHMEM pages, so the optimization can not be made on 32-bit
systems.

Reviewed-by: Chunwei Chen <tuxoko@gmail.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #8580
2020-01-22 13:48:56 -08:00