As part of some internal gang block testing within Delphix
we hit the assertion removed by this patch. The assertion
was triggered by a ZIO that had two copies and was a gang
block making the following expression equal to 3:
```
MIN(zp->zp_copies + BP_IS_GANG(bp), spa_max_replication(spa))
```
and failing when we expected the above to be equal to
`BP_GET_NDVAS(bp)`.
The assertion is no longer valid since the following commit:
```
commit 14872aaa4f
Author: Matthew Ahrens <matthew.ahrens@delphix.com>
Date: Mon Feb 6 09:37:06 2023 -0800
EIO caused by encryption + recursive gang
```
The above commit changed gang block headers so they can't
have more than 2 copies but the assertion in question from
this PR was never updated.
Reviewed-by: George Wilson <george.wilson@delphix.com>
Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Signed-off-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Closes#15180
The previous patch #14841 appeared to have significant flaw, causing
deadlocks if zl_get_data callback got blocked waiting for TXG sync. I
already handled some of such cases in the original patch, but issue
#14982 shown cases that were impossible to solve in that design.
This patch fixes the problem by postponing log blocks allocation till
the very end, just before the zios issue, leaving nothing blocking after
that point to cause deadlocks. Before that point though any sleeps are
now allowed, not causing sync thread blockage. This require slightly
more complicated lwb state machine to allocate blocks and issue zios
in proper order. But with removal of special early issue workarounds
the new code is much cleaner now, and should even be more efficient.
Since this patch uses null zios between write, I've found that null
zios do not wait for logical children ready status in zio_ready(),
that makes parent write to proceed prematurely, producing incorrect
log blocks. Added ZIO_CHILD_LOGICAL_BIT to zio_wait_for_children()
fixes it.
Reviewed-by: Rob Norris <rob.norris@klarasystems.com>
Reviewed-by: Mark Maybee <mark.maybee@delphix.com>
Reviewed-by: George Wilson <george.wilson@delphix.com>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Sponsored by: iXsystems, Inc.
Closes#15122
Fastwrite was introduced many years ago to improve ZIL writes spread
between multiple top-level vdevs by tracking number of allocated but
not written blocks and choosing vdev with smaller count. It suposed
to reduce ZIL knowledge about allocation, but actually made ZIL to
even more actively report allocation code about the allocations,
complicating both ZIL and metaslabs code.
On top of that, it seems ZIO_FLAG_FASTWRITE setting in dmu_sync()
was lost many years ago, that was one of the declared benefits. Plus
introduction of embedded log metaslab class solved another problem
with allocation rotor accounting both normal and log allocations,
since in most cases those are now in different metaslab classes.
After all that, I'd prefer to simplify already too complicated ZIL,
ZIO and metaslab code if the benefit of complexity is not obvious.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: George Wilson <george.wilson@delphix.com>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Sponsored by: iXsystems, Inc.
Closes#15107
Since spa_min_alloc may not be a power of 2, unlike ashifts, in the
case of DRAID, we should not select the minimal value among several
vdevs. Rounding to a multiple of it is unlikely to work for other
vdevs. Instead, using the greatest common divisor produces smaller
yet more reasonable results.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Signed-off-by: Ameer Hamza <ahamza@ixsystems.com>
Closes#15067
- Pack struct zio_prop by 4 bytes from 84 to 80.
- Skip new child ZIO locking while linking to parent. The newly
allocated ZIO is not externally visible yet, so nobody should care.
- Skip io_bp_copy writes when not used (write && non-debug).
Reviewed-by: Brian Atkinson <batkinson@lanl.gov>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Sponsored by: iXsystems, Inc.
Closes#14985
Those callbacks were introduced many years ago as part of a bigger
patch to smoothen the write throttling within a txg. They allow to
account completion of individual physical writes within a logical
one, improving cases when some of physical writes complete much
sooner than others, gradually opening the write throttle.
Few years after that ZFS got allocation throttling, working on a
level of logical writes and limiting number of writes queued to
vdevs at any point, and so limiting latency distribution between
the physical writes and especially writes of multiple copies.
The addition of scheduling deadline I proposed in #14925 should
further reduce the latency distribution. Grown memory sizes over
the past 10 years should also reduce importance of the smoothing.
While the use of physdone callback may still in theory provide
some smoother throttling, there are cases where we simply can not
afford it. Since dirty data accounting is protected by pool-wide
lock, in case of 6-wide RAIDZ, for example, it requires us to take
it 8 times per logical block write, creating huge lock contention.
My tests of this patch show radical reduction of the lock spinning
time on workloads when smaller blocks are written to RAIDZ pools,
when each of the disks receives 8-16KB chunks, but the total rate
reaching 100K+ blocks per second. Same time attempts to measure
any write time fluctuations didn't show anything noticeable.
While there, remove also io_child_count/io_parent_count counters.
They are used only for couple assertions that can be avoided.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Sponsored by: iXsystems, Inc.
Closes#14948
It was a vdev level read cache, designed to aggregate many small
reads by speculatively issuing bigger reads instead and caching
the result. But since it has almost no idea about what is going
on with exception of ZIO_FLAG_DONT_CACHE flag set by higher layers,
it was found to make more harm than good, for which reason it was
disabled for the past 12 years. These days we have much better
instruments to enlarge the I/Os, such as speculative and prescient
prefetches, I/O scheduler, I/O aggregation etc.
Besides just the dead code removal this removes one extra mutex
lock/unlock per write inside vdev_cache_write(), not otherwise
disabled and trying to do some work.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Sponsored by: iXsystems, Inc.
Closes#14953
We only need to know if ZIO has any parent there. We do not care if
it has more than one, but use of zio_unique_parent() == NULL asserts
that.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Sponsored by: iXsystems, Inc.
Closes#14823
If a block pointer is corrupted (but the block containing it checksums
correctly, e.g. due to a bug that overwrites random memory), we can
often detect it before the block is read, with the `zfs_blkptr_verify()`
function, which is used in `arc_read()`, `zio_free()`, etc.
However, such corruption is not typically recoverable. To recover from
it we would need to detect the memory error before the block pointer is
written to disk.
This PR verifies BP's that are contained in indirect blocks and dnodes
before they are written to disk, in `dbuf_write_ready()`. This way,
we'll get a panic before the on-disk data is corrupted. This will help
us to diagnose what's causing the corruption, as well as being much
easier to recover from.
To minimize performance impact, only checks that can be done without
holding the spa_config_lock are performed.
Additionally, when corruption is detected, the raw words of the block
pointer are logged. (Note that `dprintf_bp()` is a no-op by default,
but if enabled it is not safe to use with invalid block pointers.)
Reviewed-by: Rich Ercolani <rincebrain@gmail.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Paul Zuchowski <pzuchowski@datto.com>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes#14817
Address the following bugs in persistent error log:
1) Check nested clones, eg "fs->snap->clone->snap2->clone2".
2) When deleting files containing error blocks in those clones (from
"clone" the example above), do not break the check chain.
3) When deleting files in the originating fs before syncing the errlog
to disk, do not break the check chain. This happens because at the
time of introducing the error block in the error list, we do not have
its birth txg and the head filesystem. If the original file is
deleted before the error list is synced to the error log (which is
when we actually lookup the birth txg and the head filesystem), then
we do not have access to this info anymore and break the check chain.
The most prominent change is related to achieving (3). We expand the
spa_error_entry_t structure to accommodate the newly introduced
zbookmark_err_phys_t structure (containing the birth txg of the error
block).Due to compatibility reasons we cannot remove the
zbookmark_phys_t structure and we also need to place the new structure
after se_avl, so it is not accounted for in avl_find(). Then we modify
spa_log_error() to also provide the birth txg of the error block. With
these changes in place we simplify the previously introduced function
get_head_and_birth_txg() (now named get_head_ds()).
We chose not to follow the same approach for the head filesystem (thus
completely removing get_head_ds()) to avoid introducing new lock
contentions.
The stack sizes of nested functions (as measured by checkstack.pl in the
linux kernel) are:
check_filesystem [zfs]: 272 (was 912)
check_clones [zfs]: 64
We also introduced two new tests covering the above changes.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: George Amanakis <gamanakis@gmail.com>
Closes#14633
Block Cloning allows to manually clone a file (or a subset of its
blocks) into another (or the same) file by just creating additional
references to the data blocks without copying the data itself.
Those references are kept in the Block Reference Tables (BRTs).
The whole design of block cloning is documented in module/zfs/brt.c.
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Christian Schwarz <christian.schwarz@nutanix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Rich Ercolani <rincebrain@gmail.com>
Signed-off-by: Pawel Jakub Dawidek <pawel@dawidek.net>
Closes#13392
Hole detection in the zio compression code allows us to
opportunistically skip compression on holes. We can go a step further
by not doing memory allocations on holes either.
Reviewed-by: Brian Atkinson <batkinson@lanl.gov>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Signed-off-by: Richard Yao <richard.yao@klarasystems.com>
Sponsored-by: Wasabi Technology, Inc.
Closes#14500
Clang's static analyzer correctly identified a NULL pointer dereference
in zio_ready() when ZIO_FLAG_NODATA has been set on a zio that is
missing a block pointer. The NULL pointer dereference occurs because we
have logic intended to disable ZIO_FLAG_NODATA when it has been set on a
gang block.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Brian Atkinson <batkinson@lanl.gov>
Signed-off-by: Richard Yao <richard.yao@alumni.stonybrook.edu>
Closes#14469
Encrypted blocks can not have 3 DVAs, because they use the space of the
3rd DVA for the IV+salt. zio_write_gang_block() takes this into
account, setting `gbh_copies` to no more than 2 in this case. Gang
members BP's do not have the X (encrypted) bit set (nor do they have the
DMU level and type fields set), because encryption is not handled at
this level. The gang block is reassembled, and then encryption (and
compression) are handled.
To check if this gang block is encrypted, the code in
zio_write_gang_block() checks `pio->io_bp`. This is normally fine,
because the block that's being ganged is typically the encrypted BP.
The problem is that if there is "recursive ganging", where a gang member
is itself a gang block, then when zio_write_gang_block() is called to
create a gang block for a gang member, `pio->io_bp` is the gang member's
BP, which doesn't have the X bit set, so the number of DVA's is not
restricted to 2. It should instead be looking at the the "gang leader",
i.e. the top-level gang block, to determine how many DVA's can be used,
to avoid a "NDVA's inversion" (where a child has more DVA's than its
parent).
gang leader BP: X (encrypted) bit set, 2 DVA's, IV+salt in 3rd DVA's
space:
```
DVA[0]=<1:...:100400> DVA[1]=<0:...:100400> salt=... iv=...
[L0 ZFS plain file] fletcher4 uncompressed encrypted LE
gang unique double size=100000L/100000P birth=... fill=1 cksum=...
```
leader's GBH contains a BP with gang bit set and 3 DVA's:
```
DVA[0]=<1:...:55600> DVA[1]=<0:...:55600>
[L0 unallocated] fletcher4 uncompressed unencrypted LE
contiguous unique double size=55600L/55600P birth=... fill=0 cksum=...
DVA[0]=<1:...:55600> DVA[1]=<0:...:55600>
[L0 unallocated] fletcher4 uncompressed unencrypted LE
contiguous unique double size=55600L/55600P birth=... fill=0 cksum=...
DVA[0]=<1:...:55600> DVA[1]=<0:...:55600> DVA[2]=<1:...:200>
[L0 unallocated] fletcher4 uncompressed unencrypted LE
gang unique double size=55400L/55400P birth=... fill=0 cksum=...
```
On nondebug bits, having the 3rd DVA in the gang block works for the
most part, because it's true that all 3 DVA's are available in the gang
member BP (in the GBH). However, for accounting purposes, gang block
DVA's ASIZE include all the space allocated below them, i.e. the
512-byte gang block header (GBH) as well as the gang members below that.
We see that above where the gang leader BP is 1MB logical (and after
compression: 0x`100000P`), but the ASIZE of each DVA is 2 sectors (1KB)
more than 1MB (0x`100400`).
Since thre are 3 copies of a block below it, we increment the ATIME of
the 3rd DVA of the gang leader by the space used by the 3rd DVA of the
child (1 sector, in this case). But there isn't really a 3rd DVA of the
parent; the salt is stored in place of the 3rd DVA's ASIZE.
So when zio_write_gang_member_ready() increments the parent's BP's
`DVA[2]`'s ASIZE, it's actually incrementing the parent's salt. When we
later try to read the encrypted recursively-ganged block, the salt
doesn't match what we used to write it, so MAC verification fails and we
get an EIO.
```
zio_encrypt(): encrypted 515/2/0/403 salt: 25 25 bb 9d ad d6 cd 89
zio_decrypt(): decrypting 515/2/0/403 salt: 26 25 bb 9d ad d6 cd 89
```
This commit addresses the problem by not increasing the number of copies
of the GBH beyond 2 (even for non-encrypted blocks). This simplifies
the logic while maintaining the ability to traverse all metadata
(including gang blocks) even if one copy is lost. (Note that 3 copies
of the GBH will still be created if requested, e.g. for `copies=3` or
MOS blocks.) Additionally, the code that increments the parent's DVA's
ASIZE is made to check the parent DVA's NDVAS even on nondebug bits. So
if there's a similar bug in the future, it will cause a panic when
trying to write, rather than corrupting the parent BP and causing an
error when reading.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Caused-by: #14356Closes#14440Closes#14413
Encrypted blocks can have up to 2 DVA's, as the third DVA is reserved
for the salt+IV. However, dmu_write_policy() allows non-encrypted
blocks (e.g. DMU_OT_OBJSET) inside encrypted datasets to request and
allocate 3 DVA's, since they don't need a salt+IV (they are merely
authenicated).
However, if such a block becomes a gang block, the gang code incorrectly
limits the gang block header to 2 DVA's. This leads to a "NDVAs
inversion", where a parent block (the gang block header) has less DVA's
than its children (the gang members), causing an assertion failure in
zio_write_gang_member_ready().
This commit addresses the problem by only restricting the gang block
header to 2 DVA's if the block is actually encrypted (and thus its gang
block members can have at most 2 DVA's).
Reviewed-by: Richard Yao <richard.yao@alumni.stonybrook.edu>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes#14250Closes#14356
When doing a device removal on a pool with gang blocks, the zio pipeline
can deadlock when trying to free blocks from a device which is being
removed with a stack similar to this:
0xffff8ab9a13a1740 UNINTERRUPTIBLE 4
__schedule+0x2e5
__schedule+0x2e5
schedule+0x33
schedule_preempt_disabled+0xe
__mutex_lock.isra.12+0x2a7
__mutex_lock.isra.12+0x2a7
__mutex_lock_slowpath+0x13
mutex_lock+0x2c
free_from_removing_vdev+0x61
metaslab_free_impl+0xd6
metaslab_free_dva+0x5e
metaslab_free+0x196
zio_free_sync+0xe4
zio_free_gang+0x38
zio_gang_tree_issue+0x42
zio_gang_tree_issue+0xa2
zio_gang_issue+0x6d
zio_execute+0x94
zio_execute+0x94
taskq_thread+0x23b
kthread+0x120
ret_from_fork+0x1f
Since there are gang blocks we have to read the gang members as part of
the free. This can be seen with a zio dependency tree that looks like
this:
sdb> echo 0xffff900c24f8a700 | zio -rc | zio
ADDRESS TYPE STAGE WAITER
0xffff900c24f8a700 NULL CHECKSUM_VERIFY 0xffff900ddfd31740
0xffff900c24f8c920 FREE GANG_ASSEMBLE -
0xffff900d93d435a0 READ DONE
In the illustration above we are processing frees but because of gang
block we have to read the constituents blocks. Once we finish the READ
in the zio pipeline we will execute the parent. In this case the parent
is a FREE but the zio taskq is a READ and we continue to process the
pipeline leading to the stack above. In the stack above, we are blocked
waiting for the svr_lock so as a result a READ interrupt taskq thread
is now consumed. Eventually, all of the READ taskq threads end up
blocked and we're unable to complete any read requests.
In zio_notify_parent there is an optimization to continue to use
the taskq thread to exectue the parent's pipeline. To resolve the
deadlock above, we only allow this optimization if the parent's
zio type matches the child which just completed.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Signed-off-by: George Wilson <gwilson@delphix.com>
External-issue: DLPX-80130
Closes#14236
After a device has been removed, any nopwrites for blocks on that
indirect vdev should be ignored and a new block should be allocated. The
original code attempted to handle this but used the wrong block pointer
when checking for indirect vdevs and failed to check all DVAs.
This change corrects both of these issues and modifies the test case
to ensure that it properly tests nopwrites with device removal.
Reviewed-by: Prakash Surya <prakash.surya@delphix.com>
Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Richard Yao <richard.yao@alumni.stonybrook.edu>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: George Wilson <gwilson@delphix.com>
Closes#14235
The checksum error counter is incremented after reporting to ZED. This
leads ZED to receiving a checksum error report with 0 checksum errors.
To avoid this, bump the checksum error counter before reporting to ZED.
Sponsored-by: Seagate Technology LLC
Reviewed-by: Richard Yao <richard.yao@alumni.stonybrook.edu>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Rob Wing <rob.wing@klarasystems.com>
Closes#14190
We ran out of space in enum zio_flag for additional flags. Rather than
introduce enum zio_flag2 and then modify a bunch of functions to take a
second flags variable, we expand the type to 64 bits via `typedef
uint64_t zio_flag_t`.
Reviewed-by: Allan Jude <allan@klarasystems.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Richard Yao <richard.yao@klarasystems.com>
Signed-off-by: Allan Jude <allan@klarasystems.com>
Co-authored-by: Richard Yao <richard.yao@klarasystems.com>
Closes#14086
This patch inserts the `static` keyword to non-global variables,
which where found by the analysis tool smatch.
Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Tino Reichardt <milky-zfs@mcmilk.de>
Closes#13970
The metaslab_check_free() function only needs to be called in the
GANG|DEDUP|etc case because zio_free_sync() will internally call
metaslab_check_free().
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Richard Yao <richard.yao@alumni.stonybrook.edu>
Signed-off-by: Finix1979 <yancw@info2soft.com>
Closes#13977
ZED does not take any action for disk removal events if there is no
spare VDEV available. Added zpool_vdev_remove_wanted() in libzfs
and vdev_remove_wanted() in vdev.c to remove the VDEV through ZED
on removal event. This means that if you are running zed and
remove a disk, it will be properly marked as REMOVED.
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Ameer Hamza <ahamza@ixsystems.com>
Closes#13797
In #13871, zfs_vdev_aggregation_limit_non_rotating and
zfs_vdev_aggregation_limit being signed was pointed out as a possible
reason not to eliminate an unnecessary MAX(unsigned, 0) since the
unsigned value was assigned from them.
There is no reason for these module parameters to be signed and upon
inspection, it was found that there are a number of other module
parameters that are signed, but should not be, so we make them unsigned.
Making them unsigned made it clear that some other variables in the code
should also be unsigned, so we also make those unsigned. This prevents
users from setting negative values that could potentially cause bad
behaviors. It also makes the code slightly easier to understand.
Mostly module parameters that deal with timeouts, limits, bitshifts and
percentages are made unsigned by this. Any that are boolean are left
signed, since whether booleans should be considered signed or unsigned
does not matter.
Making zfs_arc_lotsfree_percent unsigned caused a
`zfs_arc_lotsfree_percent >= 0` check to become redundant, so it was
removed. Removing the check was also necessary to prevent a compiler
error from -Werror=type-limits.
Several end of line comments had to be moved to their own lines because
replacing int with uint_t caused us to exceed the 80 character limit
enforced by cstyle.pl.
The following were kept signed because they are passed to
taskq_create(), which expects signed values and modifying the
OpenSolaris/Illumos DDI is out of scope of this patch:
* metaslab_load_pct
* zfs_sync_taskq_batch_pct
* zfs_zil_clean_taskq_nthr_pct
* zfs_zil_clean_taskq_minalloc
* zfs_zil_clean_taskq_maxalloc
* zfs_arc_prune_task_threads
Also, negative values in those parameters was found to be harmless.
The following were left signed because either negative values make
sense, or more analysis was needed to determine whether negative values
should be disallowed:
* zfs_metaslab_switch_threshold
* zfs_pd_bytes_max
* zfs_livelist_min_percent_shared
zfs_multihost_history was made static to be consistent with other
parameters.
A number of module parameters were marked as signed, but in reality
referenced unsigned variables. upgrade_errlog_limit is one of the
numerous examples. In the case of zfs_vdev_async_read_max_active, it was
already uint32_t, but zdb had an extern int declaration for it.
Interestingly, the documentation in zfs.4 was right for
upgrade_errlog_limit despite the module parameter being wrongly marked,
while the documentation for zfs_vdev_async_read_max_active (and friends)
was wrong. It was also wrong for zstd_abort_size, which was unsigned,
but was documented as signed.
Also, the documentation in zfs.4 incorrectly described the following
parameters as ulong when they were int:
* zfs_arc_meta_adjust_restarts
* zfs_override_estimate_recordsize
They are now uint_t as of this patch and thus the man page has been
updated to describe them as uint.
dbuf_state_index was left alone since it does nothing and perhaps should
be removed in another patch.
If any module parameters were missed, they were not found by `grep -r
'ZFS_MODULE_PARAM' | grep ', INT'`. I did find a few that grep missed,
but only because they were in files that had hits.
This patch intentionally did not attempt to address whether some of
these module parameters should be elevated to 64-bit parameters, because
the length of a long on 32-bit is 32-bit.
Lastly, it was pointed out during review that uint_t is a better match
for these variables than uint32_t because FreeBSD kernel parameter
definitions are designed for uint_t, whose bit width can change in
future memory models. As a result, we change the existing parameters
that are uint32_t to use uint_t.
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Neal Gompa <ngompa@datto.com>
Signed-off-by: Richard Yao <richard.yao@alumni.stonybrook.edu>
Closes#13875
This type of recv is used to heal corrupted data when a replica
of the data already exists (in the form of a send file for example).
With the provided send stream, corrective receive will read from
disk blocks described by the WRITE records. When any of the reads
come back with ECKSUM we use the data from the corresponding WRITE
record to rewrite the corrupted block.
Reviewed-by: Paul Dagnelie <pcd@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Paul Zuchowski <pzuchowski@datto.com>
Signed-off-by: Alek Pinchuk <apinchuk@axcient.com>
Closes#9372
It may happen that scan bookmark points to a block that was turned
into a part of a big hole. In such case dsl_scan_visitbp() may skip
it and dsl_scan_check_resume() will not be called for it. As result
new scan suspend won't be possible until the end of the object, that
may take hours if the object is a multi-terabyte ZVOL on a slow HDD
pool, stretching TXG to all that time, creating all sorts of problems.
This patch changes the resume condition to any greater or equal block,
so even if we miss the bookmarked block, the next one we find will
delete the bookmark, allowing new suspend.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Sponsored-By: iXsystems, Inc.
Closes#13643
We want `zpool import` to be highly robust and never panic, even
when encountering corrupt metadata. This is already handled in the
arc_read() code path, which covers most cases, but spa_load_verify_cb()
relies on zio_read() and is responsible for verifying the block pointer.
During import it is also possible to encounter blocks pointers which
contain ZIO_COMPRESS_INHERIT and ZIO_CHECKSUM_INHERIT values. Relax
the verification function slightly to allow this.
Futhermore, extend dsl_scan_recurse() to verify the block pointer
contents of level zero blocks which are not of type DMU_OT_DNODE or
DMU_OT_OBJSET. This is handled by arc_read() in the other cases.
Reviewed-by: Paul Dagnelie <pcd@delphix.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#13124Closes#13360
Increase the default allowed maximum recordsize from 1M to 16M.
As described in the zfs(4) man page, there are significant costs
which need to be considered before using very large blocks.
However, there are scenarios where they make good sense and
it should no longer be necessary to artificially restrict their
use behind a module option.
Note that for 32-bit platforms we continue to leave this
restriction in place due to the limited virtual address space
available (256-512MB). On these systems only a handful
of blocks could be cached at any one time severely impacting
performance and potentially stability.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Signed-off-by: Rich Ercolani <rincebrain@gmail.com>
Closes#12830Closes#13302
bcopy() has a confusing argument order and is actually a move, not a
copy; they're all deprecated since POSIX.1-2001 and removed in -2008,
and we shim them out to mem*() on Linux anyway
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ahelenia Ziemiańska <nabijaczleweli@nabijaczleweli.xyz>
Closes#12996
Raw sending from pool1/encrypted with ashift=9 to pool2/encrypted with
ashift=12 results to failure when mounting pool2/encrypted (Input/Output
error). Notably, the opposite, raw sending from a greater ashift to a
lower one does not fail.
This happens because zio_compress_write() falsely checks only
ZIO_FLAG_RAW_COMPRESS and not ZIO_FLAG_RAW_ENCRYPT which is also set in
encrypted raw send streams. In this case it rounds up the psize and if
not equal to the zio->io_size it modifies the block by zeroing out
the extra bytes. Because this happens in a SA attr. registration object
(type=46), the decryption fails upon mounting the filesystem, and zpool
status falsely reports an error.
Fix this by checking both ZIO_FLAG_RAW_COMPRESS and ZIO_FLAG_RAW_ENCRYPT
before deciding whether to zero-pad a block.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: George Amanakis <gamanakis@gmail.com>
Closes#13067Closes#13074
69 CSTYLED BEGINs remain, appx. 30 of which can be removed if cstyle(1)
had a useful policy regarding
CALL(ARG1,
ARG2,
ARG3);
above 2 lines. As it stands, it spits out *both*
sysctl_os.c: 385: continuation line should be indented by 4 spaces
sysctl_os.c: 385: indent by spaces instead of tabs
which is very cool
Another >10 could be fixed by removing "ulong" &al. handling.
I don't foresee anyone actually using it intentionally
(does it even exist in modern headers? why did it in the first place?).
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ahelenia Ziemiańska <nabijaczleweli@nabijaczleweli.xyz>
Closes#12993
Evaluated every variable that lives in .data (and globals in .rodata)
in the kernel modules, and constified/eliminated/localised them
appropriately. This means that all read-only data is now actually
read-only data, and, if possible, at file scope. A lot of previously-
global-symbols became inlinable (and inlined!) constants. Probably
not in a big Wowee Performance Moment, but hey.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ahelenia Ziemiańska <nabijaczleweli@nabijaczleweli.xyz>
Closes#12899
Add properties, similar to pool properties, to each vdev.
This makes use of the existing per-vdev ZAP that was added as
part of device evacuation/removal.
A large number of read-only properties are exposed,
many of the members of struct vdev_t, that provide useful
statistics.
Adds support for read-only "removing" vdev property.
Adds the "allocating" property that defaults to "on" and
can be set to "off" to prevent future allocations from that
top-level vdev.
Supports user-defined vdev properties.
Includes support for properties.vdev in SYSFS.
Co-authored-by: Allan Jude <allan@klarasystems.com>
Co-authored-by: Mark Maybee <mark.maybee@delphix.com>
Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Mark Maybee <mark.maybee@delphix.com>
Signed-off-by: Allan Jude <allan@klarasystems.com>
Closes#11711
The block pointer verification check in arc_read() should also
cover embedded block pointers. While highly unlikely, accessing
a damaged block pointer can result in panic. To further harden
the code extend the existing check to include embedded block
pointers and add a comment explaining the rational for this
sanity check. Lastly, correct a flaw in zfs_blkptr_verify()
so the error count is checked even when checking a untrusted
config to verify the non-pool-specific portions of a block
pointer.
Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Tony Nguyen <tony.nguyen@delphix.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#12535
We round up the psize to the nearest multiple of the asize or to the
lsize, whichever is smaller. Once that's done, we allocate a new
buffer of the appropriate size, zero the tail, and copy the data
into it. This adds a small performance cost to these kinds of writes,
but fixes the bookkeeping problems.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Co-authored-by: Matthew Ahrens <matthew.ahrens@delphix.com>
Signed-off-by: Paul Dagnelie <pcd@delphix.com>
Closes#12522Closes#8462
Remove mc_lock use from metaslab_class_throttle_*(). The math there
is based on refcounts and so atomic, so the only race possible there
is between zfs_refcount_count() and zfs_refcount_add(). But in most
cases metaslab_class_throttle_reserve() is called with the allocator
lock held, which covers the race. In cases where the lock is not
held, GANG_ALLOCATION() or METASLAB_MUST_RESERVE are set, and so we
do not use zfs_refcount_count(). And even if we assume some other
non-existing scenario, the worst that may happen from this race is
few more I/Os get to allocation earlier, that is not a problem.
Move locks and data of different allocators into different cache
lines to avoid false sharing. Group spa_alloc_* arrays together
into single array of aligned struct spa_alloc spa_allocs. Align
struct metaslab_class_allocator.
Reviewed-by: Paul Dagnelie <pcd@delphix.com>
Reviewed-by: Ryan Moeller <ryan@iXsystems.com>
Reviewed-by: Don Brady <don.brady@delphix.com>
Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Sponsored-By: iXsystems, Inc.
Closes#12314
* zio: avoid callback typecasting
* zil: avoid zil_itxg_clean() callback typecasting
* zpl: decouple zpl_readpage() into two separate callbacks
* nvpair: explicitly declare callbacks for xdr_array()
* linux/zfs_nvops: don't use external iput() as a callback
* zcp_synctask: don't use fnvlist_free() as a callback
* zvol: don't use ops->zv_free() as a callback for taskq_dispatch()
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Mark Maybee <mark.maybee@delphix.com>
Signed-off-by: Alexander Lobakin <alobakin@pm.me>
Closes#12260
ZFS loves using %llu for uint64_t, but that requires a cast to not
be noisy - which is even done in many, though not all, places.
Also a couple places used %u for uint64_t, which were promoted
to %llu.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Rich Ercolani <rincebrain@gmail.com>
Closes#12233
In case we have I/O and try to remove an L2ARC device a deadlock might
occur. arc_read()->zio_read()->zfs_blkptr_verify() waits for SCL_VDEV
to be dropped while holding the hash_lock. However, spa_l2cache_load()
holds SCL_ALL and waits for the hash_lock in l2arc_evict().
Fix this by moving zfs_blkptr_verify() to the top top arc_read() before
the hash_lock is taken. Verify the block pointer and return a checksum
error if damaged rather than halting the system, by using
BLK_VERIFY_LOG instead of BLK_VERIFY_HALT.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Mark Maybee <mark.maybee@delphix.com>
Signed-off-by: George Amanakis <gamanakis@gmail.com>
Closes#12054
This deduplicates 2 sets of caches which use the same allocation size.
Memory savings fluctuate a lot, one sample result is FreeBSD running
"make buildworld" saving ~180MB RAM in reduced page count associated
with zio caches.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Closes#11877
Fix NULL pointer dereference when reporting
checksum error for gang block in zio_done.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Paul Zuchowski <pzuchowski@datto.com>
Closes#11872Closes#11896
For gang blocks, `DVA_GET_ASIZE()` is the total space allocated for the
gang DVA including its children BP's. The space allocated at each DVA's
vdev/offset is `vdev_psize_to_asize(vd, SPA_GANGBLOCKSIZE)`.
This commit makes this relationship more clear by using a helper
function, `vdev_gang_header_asize()`, for the space allocated at the
gang block's vdev/offset.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes#11744
The RAIDZ and DRAID code is responsible for reporting checksum errors on
their child vdevs. Checksum errors represent events where a disk
returned data or parity that should have been correct, but was not. In
other words, these are instances of silent data corruption. The
checksum errors show up in the vdev stats (and thus `zpool status`'s
CKSUM column), and in the event log (`zpool events`).
Note, this is in contrast with the more common "noisy" errors where a
disk goes offline, in which case ZFS knows that the disk is bad and
doesn't try to read it, or the device returns an error on the requested
read or write operation.
RAIDZ/DRAID generate checksum errors via three code paths:
1. When RAIDZ/DRAID reconstructs a damaged block, checksum errors are
reported on any children whose data was not used during the
reconstruction. This is handled in `raidz_reconstruct()`. This is the
most common type of RAIDZ/DRAID checksum error.
2. When RAIDZ/DRAID is not able to reconstruct a damaged block, that
means that the data has been lost. The zio fails and an error is
returned to the consumer (e.g. the read(2) system call). This would
happen if, for example, three different disks in a RAIDZ2 group are
silently damaged. Since the damage is silent, it isn't possible to know
which three disks are damaged, so a checksum error is reported against
every child that returned data or parity for this read. (For DRAID,
typically only one "group" of children is involved in each io.) This
case is handled in `vdev_raidz_cksum_finish()`. This is the next most
common type of RAIDZ/DRAID checksum error.
3. If RAIDZ/DRAID is not able to reconstruct a damaged block (like in
case 2), but there happens to be additional copies of this block due to
"ditto blocks" (i.e. multiple DVA's in this blkptr_t), and one of those
copies is good, then RAIDZ/DRAID compares each sector of the data or
parity that it retrieved with the good data from the other DVA, and if
they differ then it reports a checksum error on this child. This
differs from case 2 in that the checksum error is reported on only the
subset of children that actually have bad data or parity. This case
happens very rarely, since normally only metadata has ditto blocks. If
the silent damage is extensive, there will be many instances of case 2,
and the pool will likely be unrecoverable.
The code for handling case 3 is considerably more complicated than the
other cases, for two reasons:
1. It needs to run after the main raidz read logic has completed. The
data RAIDZ read needs to be preserved until after the alternate DVA has
been read, which necessitates refcounts and callbacks managed by the
non-raidz-specific zio layer.
2. It's nontrivial to map the sections of data read by RAIDZ to the
correct data. For example, the correct data does not include the parity
information, so the parity must be recalculated based on the correct
data, and then compared to the parity that was read from the RAIDZ
children.
Due to the complexity of case 3, the rareness of hitting it, and the
minimal benefit it provides above case 2, this commit removes the code
for case 3. These types of errors will now be handled the same as case
2, i.e. the checksum error will be reported against all children that
returned data or parity.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes#11735
Fix regression seen in issue #11545 where checksum errors
where not being counted or showing up in a zpool event.
Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Don Brady <don.brady@delphix.com>
Closes#11609
Mixing ZIL and normal allocations has several problems:
1. The ZIL allocations are allocated, written to disk, and then a few
seconds later freed. This leaves behind holes (free segments) where the
ZIL blocks used to be, which increases fragmentation, which negatively
impacts performance.
2. When under moderate load, ZIL allocations are of 128KB. If the pool
is fairly fragmented, there may not be many free chunks of that size.
This causes ZFS to load more metaslabs to locate free segments of 128KB
or more. The loading happens synchronously (from zil_commit()), and can
take around a second even if the metaslab's spacemap is cached in the
ARC. All concurrent synchronous operations on this filesystem must wait
while the metaslab is loading. This can cause a significant performance
impact.
3. If the pool is very fragmented, there may be zero free chunks of
128KB or more. In this case, the ZIL falls back to txg_wait_synced(),
which has an enormous performance impact.
These problems can be eliminated by using a dedicated log device
("slog"), even one with the same performance characteristics as the
normal devices.
This change sets aside one metaslab from each top-level vdev that is
preferentially used for ZIL allocations (vdev_log_mg,
spa_embedded_log_class). From an allocation perspective, this is
similar to having a dedicated log device, and it eliminates the
above-mentioned performance problems.
Log (ZIL) blocks can be allocated from the following locations. Each
one is tried in order until the allocation succeeds:
1. dedicated log vdevs, aka "slog" (spa_log_class)
2. embedded slog metaslabs (spa_embedded_log_class)
3. other metaslabs in normal vdevs (spa_normal_class)
The space required for the embedded slog metaslabs is usually between
0.5% and 1.0% of the pool, and comes out of the existing 3.2% of "slop"
space that is not available for user data.
On an all-ssd system with 4TB storage, 87% fragmentation, 60% capacity,
and recordsize=8k, testing shows a ~50% performance increase on random
8k sync writes. On even more fragmented systems (which hit problem #3
above and call txg_wait_synced()), the performance improvement can be
arbitrarily large (>100x).
Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Reviewed-by: George Wilson <gwilson@delphix.com>
Reviewed-by: Don Brady <don.brady@delphix.com>
Reviewed-by: Mark Maybee <mark.maybee@delphix.com>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes#11389
The `abd_get_offset_*()` routines create an abd_t that references
another abd_t, and doesn't allocate any pages/buffers of its own. In
some workloads, these routines may be called frequently, to create many
abd_t's representing small pieces of a single large abd_t. In
particular, the upcoming RAIDZ Expansion project makes heavy use of
these routines.
This commit adds the ability for the caller to allocate and provide the
abd_t struct to a variant of `abd_get_offset_*()`. This eliminates the
cost of allocating the abd_t and performing the accounting associated
with it (`abdstat_struct_size`). The RAIDZ/DRAID code uses this for
the `rc_abd`, which references the zio's abd. The upcoming RAIDZ
Expansion project will leverage this infrastructure to increase
performance of reads post-expansion by around 50%.
Additionally, some of the interfaces around creating and destroying
abd_t's are cleaned up. Most significantly, the distinction between
`abd_put()` and `abd_free()` is eliminated; all types of abd_t's are
now disposed of with `abd_free()`.
Reviewed-by: Brian Atkinson <batkinson@lanl.gov>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Issue #8853Closes#11439
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
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
