Richard Yao [Tue, 13 Aug 2019 13:46:12 +0000 (09:46 -0400)]
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
Introduce getting holds and listing bookmarks through ZCP
Consumers of ZFS Channel Programs can now list bookmarks,
and get holds from datasets. A minor-refactoring was also
applied to distinguish between user and system properties
in ZCP.
Reviewed-by: Paul Dagnelie <pcd@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Matt Ahrens <mahrens@delphix.com> Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com> Ported-by: Serapheim Dimitropoulos <serapheim@delphix.com> Signed-off-by: Dan Kimmel <dan.kimmel@delphix.com>
OpenZFS-issue: https://illumos.org/issues/8862
Closes #7902
Paul Dagnelie [Mon, 5 Aug 2019 21:34:27 +0000 (14:34 -0700)]
Metaslab max_size should be persisted while unloaded
When we unload metaslabs today in ZFS, the cached max_size value is
discarded. We instead use the histogram to determine whether or not we
think we can satisfy an allocation from the metaslab. This can result in
situations where, if we're doing I/Os of a size not aligned to a
histogram bucket, a metaslab is loaded even though it cannot satisfy the
allocation we think it can. For example, a metaslab with 16 entries in
the 16k-32k bucket may have entirely 16kB entries. If we try to allocate
a 24kB buffer, we will load that metaslab because we think it should be
able to handle the allocation. Doing so is expensive in CPU time, disk
reads, and average IO latency. This is exacerbated if the write being
attempted is a sync write.
This change makes ZFS cache the max_size after the metaslab is
unloaded. If we ever get a free (or a coalesced group of frees) larger
than the max_size, we will update it. Otherwise, we leave it as is. When
attempting to allocate, we use the max_size as a lower bound, and
respect it unless we are in try_hard. However, we do age the max_size
out at some point, since we expect the actual max_size to increase as we
do more frees. A more sophisticated algorithm here might be helpful, but
this works reasonably well.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Matt Ahrens <mahrens@delphix.com> Signed-off-by: Paul Dagnelie <pcd@delphix.com>
Closes #9055
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
Channel programs that many users find useful should be included with zfs
in the /contrib directory. This is the first of these contributions. A
channel program to recursively take snapshots of datasets with the
property com.sun:auto-snapshot=true.
9072 handle error of zap_cursor_retrieve() for log spacemap zap
In spa_ld_log_sm_metadata(), it is possible for zap_cursor_retrieve()
to return errors other than the expected ENOENT (e.g. when we are at
the end of the zap). Ensure that these error cases are handled
correctly by the import path.
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed by: Sara Hartse <sara.hartse@delphix.com>
Reviewed by: Matt Ahrens <matt@delphix.com> Signed-off-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Closes #9074
mismerged log spacemap comment for metaslab_verify_weight_and_frag
When the log spacemap commit was merged in ZoL, the
metaslab_verify_unflushed_changes() debugging function
was deleted as the feature was pretty much stable by
then. Unfortunately though there was a reference to
it from a comment in metaslab_verify_weight_and_frag().
This patch deletes the reference and pastes that
comment as is.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Matt Ahrens <mahrens@delphix.com> Reviewed-by: Igor Kozhukhov <igor@dilos.org> Reviewed-by: George Melikov <mail@gmelikov.ru> Signed-off-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Closes #9097
pkconfig files get installed to $datarootdir/pkgconfig but rpm expects
them to be at $datadir. This works when $datarootdir==$datadir which is
the case most of the time but will fail when they differ.
* install: make initramfs-tools path static
Since initramfs-tools' path is nothing we can control as it is an
external package it does not make any sense to install zfs additions
anywhere else. Simply use /usr/share/initramfs-tools as path.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Richard Laager <rlaager@wiktel.com> Signed-off-by: Michael Niewöhner <foss@mniewoehner.de>
Closes #9087
When creating hundreds of clones (for example using containers with
LXD) cloning slows down as the number of clones increases over time.
The reason for this is that the fetching of the clone information
using a small zcmd buffer requires two ioctl calls, one to determine
the size and a second to return the data. However, this requires
gathering the data twice, once to determine the size and again to
populate the zcmd buffer to return it to userspace.
These are expensive ioctl() calls, so instead, make the default buffer
size much larger: 256K.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: George Melikov <mail@gmelikov.ru> Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Michael Niewöhner <foss@mniewoehner.de>
Closes #9084
Matthew Ahrens [Tue, 30 Jul 2019 16:18:30 +0000 (09:18 -0700)]
Improve performance by using dmu_tx_hold_*_by_dnode()
In zfs_write() and dmu_tx_hold_sa(), we can use dmu_tx_hold_*_by_dnode()
instead of dmu_tx_hold_*(), since we already have a dbuf from the target
dnode in hand. This eliminates some calls to dnode_hold(), which can be
expensive. This is especially impactful if several threads are
accessing objects that are in the same block of dnodes, because they
will contend for that dbuf's lock.
We are seeing 10-20% performance wins for the sequential_writes tests in
the performance test suite, when doing >=128K writes to files with
recordsize=8K.
This also removes some unnecessary casts that are in the area.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Tony Nguyen <tony.nguyen@delphix.com> Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #9081
Brian Behlendorf [Mon, 29 Jul 2019 19:46:56 +0000 (12:46 -0700)]
Revert "Develop tests for issues #5866 and #8858"
This reverts commit 693c1fc478cc8118dd0168c4815c0ae3be41c9c3. This
change resulted in a kmem leak being observed in existing code which
needs to be identified and addressed.
Reviewed-by: Paul Zuchowski <pzuchowski@datto.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #8978
Closes #9090
Brian Behlendorf [Mon, 29 Jul 2019 01:15:26 +0000 (18:15 -0700)]
Fix channel programs on s390x
When adapting the original sources for s390x the JMP_BUF_CNT was
mistakenly halved due to an incorrect assumption of the size of
a unsigned long. They are 8 bytes for the s390x architecture.
Increase JMP_BUF_CNT accordingly.
Authored-by: Don Brady <don.brady@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reported-by: Colin Ian King <canonical.com> Tested-by: Colin Ian King <canonical.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #8992
Closes #9080
George Wilson [Mon, 29 Jul 2019 01:13:56 +0000 (21:13 -0400)]
Race between zfs-share and zfs-mount services
When a system boots the zfs-mount.service and the
zfs-share.service can start simultaneously. What may be
unclear is that sharing a filesystem will first mount
the filesystem if it's not already mounted. This means
that both service can race to mount the same fileystem.
This race can result in a SEGFAULT or EBUSY conditions.
This change explicitly defines the start ordering between the
two services such that the zfs-mount.service is solely
responsible for mounting filesystems eliminating the race
between "zfs mount -a" and "zfs share -a" commands.
Reviewed-by: Sebastien Roy <sebastien.roy@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: George Wilson <george.wilson@delphix.com>
Closes #9083
Paul Zuchowski [Sat, 27 Jul 2019 00:52:13 +0000 (20:52 -0400)]
Develop tests for issues #5866 and #8858
Provide zfstest coverage for these two issues which
were a panic accessing extended attributes and
a problem comparing 64 bit and 32 bit generation
numbers.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Paul Zuchowski <pzuchowski@datto.com>
Issue #5866
Issue #8858
Closes #8978
Don't unconditionally return 0 (i.e. retain SUID/SGID).
Test CAP_FSETID capability.
https://github.com/pjd/pjdfstest/blob/master/tests/chmod/12.t
which expects SUID/SGID to be dropped on write(2) by non-owner fails
without this. Most filesystems make this decision within VFS by using
a generic file write for fops.
Matthew Ahrens [Fri, 26 Jul 2019 19:07:48 +0000 (12:07 -0700)]
zed crashes when devid not present
zed core dumps due to a NULL pointer in zfs_agent_iter_vdev(). The
gs_devid is NULL, but the nvl has a "devid" entry.
zfs_agent_post_event() checks that ZFS_EV_VDEV_GUID or DEV_IDENTIFIER is
present in nvl, but then later it and zfs_agent_iter_vdev() assume that
DEV_IDENTIFIER is present and thus gs_devid is set.
Typically this is not a problem because usually either all vdevs have
devid's, or none of them do. Since zfs_agent_iter_vdev() first checks if
the vdev has devid before dereferencing gs_devid, the problem isn't
typically encountered. However, if some vdevs have devid's and some do
not, then the problem is easily reproduced. This can happen if the pool
has been moved from a system that has devid's to one that does not.
The fix is for zfs_agent_iter_vdev() to only try to match the devid's if
both nvl and gsp have devid's present.
Reviewed-by: Prashanth Sreenivasa <pks@delphix.com> Reviewed-by: Don Brady <don.brady@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: loli10K <ezomori.nozomu@gmail.com> Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
External-issue: DLPX-65090
Closes #9054
Closes #9060
Sara Hartse [Fri, 26 Jul 2019 17:54:14 +0000 (10:54 -0700)]
Fast Clone Deletion
Deleting a clone requires finding blocks are clone-only, not shared
with the snapshot. This was done by traversing the entire block tree
which results in a large performance penalty for sparsely
written clones.
This is new method keeps track of clone blocks when they are
modified in a "Livelist" so that, when it’s time to delete,
the clone-specific blocks are already at hand.
We see performance improvements because now deletion work is
proportional to the number of clone-modified blocks, not the size
of the original dataset.
Reviewed-by: Sean Eric Fagan <sef@ixsystems.com> Reviewed-by: Matt Ahrens <matt@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com> Signed-off-by: Sara Hartse <sara.hartse@delphix.com>
Closes #8416
Matthew Ahrens [Thu, 25 Jul 2019 18:57:58 +0000 (11:57 -0700)]
Replace zf_rwlock with a mutex
The rwlock implementation on linux does not perform as well as mutexes.
We can realize a performance benefit by replacing the zf_rwlock with a
mutex. Local microbenchmarks show ~50% improvement, and over NFS we see
~5% improvement on several of the ZFS Performance Tests cases,
especially randwrite and seq_write.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Tony Nguyen <tony.nguyen@delphix.com> Reviewed-by: Olaf Faaland <faaland1@llnl.gov> Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #9062
Tony Hutter [Fri, 19 Jul 2019 18:21:54 +0000 (11:21 -0700)]
Move some tests to cli_user/zpool_status
The tests in tests/functional/cli_root/zpool_status should all require
root. However, linux.run has "user =" specified for those tests, which
means they run as a normal user. When I removed that line to run them
as root, the following tests did not pass:
These tests need to be run as a normal user. To fix this, move these
tests to a new tests/functional/cli_user/zpool_status directory.
Reviewed-by: George Melikov <mail@gmelikov.ru> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Giuseppe Di Natale <guss80@gmail.com> Signed-off-by: Tony Hutter <hutter2@llnl.gov>
Closes #9057
Tricky semantics of ms_max_size in metaslab_should_allocate()
metaslab_should_allocate() is used in two places:
[1] When trying to select a metaslab to allocate from
[2] When trying to allocate from a metaslab
In [2] we always expect the metaslab to be loaded, and after
the refactoring of the log spacemap changes, whenever we load
a metaslab we set ms_max_size to the biggest range in the
ms_allocatable tree. Thus, when it is used in [2], if that
field is 0, it means that the metaslab doesn't have any
segments that can be used for allocations now (though it may
have some free space but that space can be in the freeing,
freed, or deferred trees).
In [1] a metaslab can be loaded or unloaded at which point 0
can either mean the metaslab doesn't have any space or the
metaslab is just not loaded thus we go ahead and try to make
an estimation based on its weight.
The issue here is when we call the above function for [2] and
the metaslab doesn't have any allocatable space, we still go
ahead and check its ms_weight which may be out of date because
we haven't ran metaslab_sync_done() yet. At that point we are
allowing an allocation to be attempted even though we know
there is no range that is allocatable.
This patch fixes this issue by explicitly checking if the
metaslab is loaded and if it is, the ms_max_size is used.
Reviewed-by: Matt Ahrens <mahrens@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Closes #9045
Race condition between spa async threads and export
In the past we've seen multiple race conditions that have
to do with open-context threads async threads and concurrent
calls to spa_export()/spa_destroy() (including the one
referenced in issue #9015).
This patch ensures that only one thread can execute the
main body of spa_export_common() at a time, with subsequent
threads returning with a new error code created just for
this situation, eliminating this way any race condition
bugs introduced by concurrent calls to this function.
Reviewed by: Matt Ahrens <matt@delphix.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Closes #9015
Closes #9044
There exists a race condition were hdr_recl() calls
zthr_wakeup() on a destroyed zthr. The timeline is the
following:
[1] hdr_recl() runs first and goes intro zthr_wakeup()
because arc_initialized is set.
[2] arc_fini() is called by another thread, zeroes
that flag, destroying the zthr, and goes into
buf_init().
[3] hdr_recl() tries to enter the destroyed mutex
and we blow up.
This patch ensures that the ARC's zthrs are not offloaded
any new work once arc_initialized is set and then destroys
them after all of the ARC state has been deleted.
Reviewed by: Matt Ahrens <matt@delphix.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Closes #9047
Pavel Zakharov [Wed, 17 Jul 2019 22:33:05 +0000 (18:33 -0400)]
New service that waits on zvol links to be created
The zfs-volume-wait.service scans existing zvols and waits for their
links under /dev to be created. Any service that depends on zvol
links to be there should add a dependency on zfs-volumes.target.
By default, this target is not enabled.
Reviewed-by: Fabian Grünbichler <f.gruenbichler@proxmox.com> Reviewed-by: Antonio Russo <antonio.e.russo@gmail.com> Reviewed-by: Richard Laager <rlaager@wiktel.com> Reviewed-by: loli10K <ezomori.nozomu@gmail.com> Reviewed-by: John Gallagher <john.gallagher@delphix.com> Reviewed-by: George Wilson <gwilson@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Pavel Zakharov <pzakharov@delphix.com>
Closes #8975
Brian Behlendorf [Fri, 12 Jul 2019 21:06:36 +0000 (14:06 -0700)]
Linux 5.3 compat: retire rw_tryupgrade()
The Linux kernel's rwsem's have never provided an interface to
allow a reader to be upgraded to a writer. Historically, this
functionality has been implemented by a SPL wrapper function.
However, this approach depends on internal knowledge of the
rw_semaphore and is therefore rather brittle.
Since the ZFS code must always be able to fallback to rw_exit()
and rw_enter() when an rw_tryupgrade() fails; this functionality
isn't critical. Furthermore, the only potentially performance
sensitive consumer is dmu_zfetch() and no decrease in performance
was observed with this change applied. See the PR comments for
additional testing details.
Therefore, it is being retired to make the build more robust and
to simplify the rwlock implementation.
Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: Tomohiro Kusumi <kusumi.tomohiro@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #9029
Brian Behlendorf [Fri, 12 Jul 2019 20:27:24 +0000 (13:27 -0700)]
Linux 5.3 compat: rw_semaphore owner
Commit https://github.com/torvalds/linux/commit/94a9717b updated the
rwsem's owner field to contain additional flags describing the rwsem's
state. Rather then update the wrappers to mask out these bits, the
code no longer relies on the owner stored by the kernel. This does
increase the size of a krwlock_t but it makes the implementation
less sensitive to future kernel changes.
Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: Tomohiro Kusumi <kusumi.tomohiro@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #9029
Fix lockdep recursive locking false positive in dbuf_destroy
lockdep reports a possible recursive lock in dbuf_destroy.
It is true that dbuf_destroy is acquiring the dn_dbufs_mtx
on one dnode while holding it on another dnode. However,
it is impossible for these to be the same dnode because,
among other things,dbuf_destroy checks MUTEX_HELD before
acquiring the mutex.
This fix defines a class NESTED_SINGLE == 1 and changes
that lock to call mutex_enter_nested with a subclass of
NESTED_SINGLE.
In order to make the userspace code compile,
include/sys/zfs_context.h now defines mutex_enter_nested and
NESTED_SINGLE.
This is the lockdep report:
[ 122.950921] ============================================
[ 122.950921] WARNING: possible recursive locking detected
[ 122.950921] 4.19.29-4.19.0-debug-d69edad5368c1166 #1 Tainted: G O
[ 122.950921] --------------------------------------------
[ 122.950921] dbu_evict/1457 is trying to acquire lock:
[ 122.950921] 0000000083e9cbcf (&dn->dn_dbufs_mtx){+.+.}, at: dbuf_destroy+0x3c0/0xdb0 [zfs]
[ 122.950921]
but task is already holding lock:
[ 122.950921] 0000000055523987 (&dn->dn_dbufs_mtx){+.+.}, at: dnode_evict_dbufs+0x90/0x740 [zfs]
[ 122.950921]
other info that might help us debug this:
[ 122.950921] Possible unsafe locking scenario:
Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Jeff Dike <jdike@akamai.com>
Closes #8984
Brian Behlendorf [Wed, 17 Jul 2019 16:14:36 +0000 (09:14 -0700)]
Fix CONFIG_X86_DEBUG_FPU build failure
When CONFIG_X86_DEBUG_FPU is defined the alternatives_patched symbol
is pulled in as a dependency which results in a build failure. To
prevent this undefine CONFIG_X86_DEBUG_FPU to disable the WARN_ON_FPU()
macro and rely on WARN_ON_ONCE debugging checks which were previously
added.
Reviewed-by: Tony Hutter <hutter2@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #9041
Closes #9049
Make use of __GFP_HIGHMEM flag in vmem_alloc, which is required for
some 32-bit systems to make use of full available memory.
While kernel versions >=4.12-rc1 add this flag implicitly, older
kernels do not.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Sebastian Gottschall <s.gottschall@dd-wrt.com> Signed-off-by: Michael Niewöhner <foss@mniewoehner.de>
Closes #9031
Brian Behlendorf [Wed, 17 Jul 2019 00:22:31 +0000 (17:22 -0700)]
Minor style cleanup
Resolve an assortment of style inconsistencies including
use of white space, typos, capitalization, and line wrapping.
There is no functional change.
Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: George Melikov <mail@gmelikov.ru> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #9030
Brian Behlendorf [Tue, 16 Jul 2019 21:14:12 +0000 (14:14 -0700)]
Fix get_special_prop() build failure
The cast of the size_t returned by strlcpy() to a uint64_t by the
VERIFY3U can result in a build failure when CONFIG_FORTIFY_SOURCE
is set. This is due to the additional hardening. Since the token
is expected to always fit in strval the VERIFY3U has been removed.
If somehow it doesn't, it will still be safely truncated.
Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: Don Brady <don.brady@delphix.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #8999
Closes #9020
Mike Gerdts [Tue, 16 Jul 2019 18:19:24 +0000 (13:19 -0500)]
Add zfs create dryrun
Adds the ability to sanity check zfs create arguments and to see the
value of any additional properties that will local to the dataset. For
example, automation that may need to adjust quota on a parent filesystem
before creating a volume may call `zfs create -nP -V <size> <volume>` to
obtain the value of refreservation. This adds the following options to
zfs create:
Reviewed-by: Ryan Moeller <ryan@ixsystems.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Matt Ahrens <matt@delphix.com> Reviewed-by: Jerry Jelinek <jerry.jelinek@joyent.com> Signed-off-by: Mike Gerdts <mike.gerdts@joyent.com>
Closes #8974
At Delphix we've seen a lot of customer systems where fragmentation
is over 75% and random writes take a performance hit because a lot
of time is spend on I/Os that update on-disk space accounting metadata.
Specifically, we seen cases where 20% to 40% of sync time is spend
after sync pass 1 and ~30% of the I/Os on the system is spent updating
spacemaps.
The problem is that these pools have existed long enough that we've
touched almost every metaslab at least once, and random writes
scatter frees across all metaslabs every TXG, thus appending to
their spacemaps and resulting in many I/Os. To give an example,
assuming that every VDEV has 200 metaslabs and our writes fit within
a single spacemap block (generally 4K) we have 200 I/Os. Then if we
assume 2 levels of indirection, we need 400 additional I/Os and
since we are talking about metadata for which we keep 2 extra copies
for redundancy we need to triple that number, leading to a total of
1800 I/Os per VDEV every TXG.
We could try and decrease the number of metaslabs so we have less
I/Os per TXG but then each metaslab would cover a wider range on
disk and thus would take more time to be loaded in memory from disk.
In addition, after it's loaded, it's range tree would consume more
memory.
Another idea would be to just increase the spacemap block size
which would allow us to fit more entries within an I/O block
resulting in fewer I/Os per metaslab and a speedup in loading time.
The problem is still that we don't deal with the number of I/Os
going up as the number of metaslabs is increasing and the fact
is that we generally write a lot to a few metaslabs and a little
to the rest of them. Thus, just increasing the block size would
actually waste bandwidth because we won't be utilizing our bigger
block size.
= About this patch
This patch introduces the Log Spacemap project which provides the
solution to the above problem while taking into account all the
aforementioned tradeoffs. The details on how it achieves that can
be found in the references sections below and in the code (see
Big Theory Statement in spa_log_spacemap.c).
Even though the change is fairly constraint within the metaslab
and lower-level SPA codepaths, there is a side-change that is
user-facing. The change is that VDEV IDs from VDEV holes will no
longer be reused. To give some background and reasoning for this,
when a log device is removed and its VDEV structure was replaced
with a hole (or was compacted; if at the end of the vdev array),
its vdev_id could be reused by devices added after that. Now
with the pool-wide space maps recording the vdev ID, this behavior
can cause problems (e.g. is this entry referring to a segment in
the new vdev or the removed log?). Thus, to simplify things the
ID reuse behavior is gone and now vdev IDs for top-level vdevs
are truly unique within a pool.
= Testing
The illumos implementation of this feature has been used internally
for a year and has been in production for ~6 months. For this patch
specifically there don't seem to be any regressions introduced to
ZTS and I have been running zloop for a week without any related
problems.
= Performance Analysis (Linux Specific)
All performance results and analysis for illumos can be found in
the links of the references. Redoing the same experiments in Linux
gave similar results. Below are the specifics of the Linux run.
After the pool reached stable state the percentage of the time
spent in pass 1 per TXG was 64% on average for the stock bits
while the log spacemap bits stayed at 95% during the experiment
(graph: sdimitro.github.io/img/linux-lsm/PercOfSyncInPassOne.png).
Sync times per TXG were 37.6 seconds on average for the stock
bits and 22.7 seconds for the log spacemap bits (related graph:
sdimitro.github.io/img/linux-lsm/SyncTimePerTXG.png). As a result
the log spacemap bits were able to push more TXGs, which is also
the reason why all graphs quantified per TXG have more entries for
the log spacemap bits.
Another interesting aspect in terms of txg syncs is that the stock
bits had 22% of their TXGs reach sync pass 7, 55% reach sync pass 8,
and 20% reach 9. The log space map bits reached sync pass 4 in 79%
of their TXGs, sync pass 7 in 19%, and sync pass 8 at 1%. This
emphasizes the fact that not only we spend less time on metadata
but we also iterate less times to convergence in spa_sync() dirtying
objects.
[related graphs:
stock- sdimitro.github.io/img/linux-lsm/NumberOfPassesPerTXGStock.png
lsm- sdimitro.github.io/img/linux-lsm/NumberOfPassesPerTXGLSM.png]
Finally, the improvement in IOPs that the userland gains from the
change is approximately 40%. There is a consistent win in IOPS as
you can see from the graphs below but the absolute amount of
improvement that the log spacemap gives varies within each minute
interval.
sdimitro.github.io/img/linux-lsm/StockVsLog3Days.png
sdimitro.github.io/img/linux-lsm/StockVsLog10Hours.png
= Porting to Other Platforms
For people that want to port this commit to other platforms below
is a list of ZoL commits that this patch depends on:
Background, Motivation, and Internals of the Feature
- OpenZFS 2017 Presentation:
youtu.be/jj2IxRkl5bQ
- Slides:
slideshare.net/SerapheimNikolaosDim/zfs-log-spacemaps-project
Reviewed-by: Sean Eric Fagan <sef@ixsystems.com> Reviewed-by: Matt Ahrens <matt@delphix.com> Reviewed-by: George Wilson <gwilson@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Closes #8442
Antonio Russo [Sun, 2 Jun 2019 12:57:10 +0000 (08:57 -0400)]
systemd encryption key support
Modify zfs-mount-generator to produce a dependency on new
zfs-import-key-*.service units, dynamically created at boot to call
zfs load-key for the encryption root, before attempting to mount any
encrypted datasets.
These units are created by zfs-mount-generator, and RequiresMountsFor on
the keyfile, if present, or call systemd-ask-password if a passphrase is
requested.
This patch includes suggestions from @Fabian-Gruenbichler, @ryanjaeb and
@rlaager, as well an adaptation of @rlaager's script to retry on
incorrect password entry.
Reviewed-by: Richard Laager <rlaager@wiktel.com> Reviewed-by: Fabian Grünbichler <f.gruenbichler@proxmox.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Antonio Russo <antonio.e.russo@gmail.com>
Closes #8750
Closes #8848
Brian Behlendorf [Mon, 15 Jul 2019 23:11:55 +0000 (16:11 -0700)]
Export dnode symbols
External consumers such as Lustre require access to the dnode
interfaces in order to correctly manipulate dnodes.
Reviewed-by: James Simmons <uja.ornl@yahoo.com> Reviewed-by: Olaf Faaland <faaland1@llnl.gov> Reviewed-by: George Melikov <mail@gmelikov.ru> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #8994
Closes #9027
Tom Caputi [Mon, 15 Jul 2019 23:08:42 +0000 (16:08 -0700)]
Ensure dsl_destroy_head() decrypts objsets
This patch corrects a small issue where the dsl_destroy_head()
code that runs when the async_destroy feature is disabled would
not properly decrypt the dataset before beginning processing.
If the dataset is not able to be decrypted, the optimization
code now simply does not run and the dataset is completely
destroyed in the DSL sync task.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Tom Caputi <tcaputi@datto.com>
Closes #9021
Disable unused pathname::pn_path* (unneeded in Linux)
struct pathname is originally from Solaris VFS, and it has been used
in ZoL to merely call VOP from Linux VFS interface without API change,
therefore pathname::pn_path* are unused and unneeded. Technically,
struct pathname is a wrapper for C string in ZoL.
Saves stack a bit on lookup and unlink.
(#if0'd members instead of removing since comments refer to them.)
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Richard Elling <Richard.Elling@RichardElling.com> Reviewed-by: George Melikov <mail@gmelikov.ru> Signed-off-by: Tomohiro Kusumi <kusumi.tomohiro@gmail.com>
Closes #9025
Brian Behlendorf [Fri, 12 Jul 2019 16:31:20 +0000 (09:31 -0700)]
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 is accomplished by leveraging
the fact that by definition dedicated kernel threads never need
to concern themselves with saving and restoring the user FPU state.
Therefore, they may use the FPU as long as we can guarantee user
tasks always restore their FPU state before context switching back
to user space.
For the 5.0 and 5.1 kernels disabling preemption and local
interrupts is sufficient to allow the FPU to be used. All non-kernel
threads will restore the preserved user FPU state.
For 5.2 and latter kernels the user FPU state restoration will be
skipped if the kernel determines the registers have not changed.
Therefore, for these kernels we need to perform the additional
step of saving and restoring the FPU registers. Invalidating the
per-cpu global tracking the FPU state would force a restore but
that functionality is private to the core x86 FPU implementation
and unavailable.
In practice, restricting SIMD to kernel threads is not a major
restriction for ZFS. The vast majority of SIMD operations are
already performed by the IO pipeline. The remaining cases are
relatively infrequent and can be handled by the generic code
without significant impact. The two most noteworthy cases are:
1) Decrypting the wrapping key for an encrypted dataset,
i.e. `zfs load-key`. All other encryption and decryption
operations will use the SIMD optimized implementations.
2) Generating the payload checksums for a `zfs send` stream.
In order to avoid making any changes to the higher layers of ZFS
all of the `*_get_ops()` functions were updated to take in to
consideration the calling context. This allows for the fastest
implementation to be used as appropriate (see kfpu_allowed()).
The only other notable instance of SIMD operations being used
outside a kernel thread was at module load time. This code
was moved in to a taskq in order to accommodate the new kernel
thread restriction.
Finally, a few other modifications were made in order to further
harden this code and facilitate testing. They include updating
each implementations operations structure to be declared as a
constant. And allowing "cycle" to be set when selecting the
preferred ops in the kernel as well as user space.
Reviewed-by: Tony Hutter <hutter2@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #8754
Closes #8793
Closes #8965
Nick Mattis [Wed, 10 Jul 2019 22:54:49 +0000 (18:54 -0400)]
Fixes: #8934 Large kmem_alloc
Large allocation over the spl_kmem_alloc_warn value was being performed.
Switched to vmem_alloc interface as specified for large allocations.
Changed the subsequent frees to match.
Reviewed-by: Tom Caputi <tcaputi@datto.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: nmattis <nickm970@gmail.com>
Closes #8934
Closes #9011
Attila Fülöp [Wed, 10 Jul 2019 18:44:52 +0000 (20:44 +0200)]
Fix ZTS killed processes detection
log_neg_expect was using the wrong exit status to detect if a process
got killed by SIGSEGV or SIGBUS, resulting in false positives.
Reviewed-by: loli10K <ezomori.nozomu@gmail.com>
Reviewed by: John Kennedy <john.kennedy@delphix.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Attila Fülöp <attila@fueloep.org>
Closes #9003
Fix race in parallel mount's thread dispatching algorithm
Strategy of parallel mount is as follows.
1) Initial thread dispatching is to select sets of mount points that
don't have dependencies on other sets, hence threads can/should run
lock-less and shouldn't race with other threads for other sets. Each
thread dispatched corresponds to top level directory which may or may
not have datasets to be mounted on sub directories.
2) Subsequent recursive thread dispatching for each thread from 1)
is to mount datasets for each set of mount points. The mount points
within each set have dependencies (i.e. child directories), so child
directories are processed only after parent directory completes.
The problem is that the initial thread dispatching in
zfs_foreach_mountpoint() can be multi-threaded when it needs to be
single-threaded, and this puts threads under race condition. This race
appeared as mount/unmount issues on ZoL for ZoL having different
timing regarding mount(2) execution due to fork(2)/exec(2) of mount(8).
`zfs unmount -a` which expects proper mount order can't unmount if the
mounts were reordered by the race condition.
There are currently two known patterns of input list `handles` in
`zfs_foreach_mountpoint(..,handles,..)` which cause the race condition.
1) #8833 case where input is `/a /a /a/b` after sorting.
The problem is that libzfs_path_contains() can't correctly handle an
input list with two same top level directories.
There is a race between two POSIX threads A and B,
* ThreadA for "/a" for test1 and "/a/b"
* ThreadB for "/a" for test0/a
and in case of #8833, ThreadA won the race. Two threads were created
because "/a" wasn't considered as `"/a" contains "/a"`.
2) #8450 case where input is `/ /var/data /var/data/test` after sorting.
The problem is that libzfs_path_contains() can't correctly handle an
input list containing "/".
There is a race between two POSIX threads A and B,
* ThreadA for "/" and "/var/data/test"
* ThreadB for "/var/data"
and in case of #8450, ThreadA won the race. Two threads were created
because "/var/data" wasn't considered as `"/" contains "/var/data"`.
In other words, if there is (at least one) "/" in the input list,
the initial thread dispatching must be single-threaded since every
directory is a child of "/", meaning they all directly or indirectly
depend on "/".
In both cases, the first non_descendant_idx() call fails to correctly
determine "path1-contains-path2", and as a result the initial thread
dispatching creates another thread when it needs to be single-threaded.
Fix a conditional in libzfs_path_contains() to consider above two.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed by: Sebastien Roy <sebastien.roy@delphix.com> Signed-off-by: Tomohiro Kusumi <kusumi.tomohiro@gmail.com>
Closes #8450
Closes #8833
Closes #8878
This commit ensures make(1) targets that build .deb packages fail if
alien(1) can't convert all .rpm files; additionally it also updates
the zfs-dracut package name which was changed to "noarch" in ca4e5a7.
Reviewed-by: Neal Gompa <ngompa@datto.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Olaf Faaland <faaland1@llnl.gov> Signed-off-by: loli10K <ezomori.nozomu@gmail.com>
Closes #8990
Closes #8991
Due to some changes introduced in 30af21b 'zfs send' can crash when
provided with invalid inputs: this change attempts to add more checks
to the affected code paths.
Reviewed-by: Attila Fülöp <attila@fueloep.org> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Signed-off-by: loli10K <ezomori.nozomu@gmail.com>
Closes #9001
Paul Dagnelie [Mon, 8 Jul 2019 20:18:50 +0000 (13:18 -0700)]
Decrease contention on dn_struct_rwlock
Currently, sequential async write workloads spend a lot of time
contending on the dn_struct_rwlock. This lock is responsible for
protecting the entire block tree below it; this naturally results
in some serialization during heavy write workloads. This can be
resolved by having per-dbuf locking, which will allow multiple
writers in the same object at the same time.
We introduce a new rwlock, the db_rwlock. This lock is responsible
for protecting the contents of the dbuf that it is a part of; when
reading a block pointer from a dbuf, you hold the lock as a reader.
When writing data to a dbuf, you hold it as a writer. This allows
multiple threads to write to different parts of a file at the same
time.
Reviewed by: Brad Lewis <brad.lewis@delphix.com>
Reviewed by: Matt Ahrens matt@delphix.com
Reviewed by: George Wilson george.wilson@delphix.com Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Paul Dagnelie <pcd@delphix.com>
External-issue: DLPX-52564
External-issue: DLPX-53085
External-issue: DLPX-57384
Closes #8946
Brad Lewis [Mon, 8 Jul 2019 18:20:53 +0000 (12:20 -0600)]
8659 static dtrace probes unavailable on non-GPL modules
ZFS tracing efforts are hampered by the inability to access zfs static
probes(probes using DTRACE_PROBE macros). The probes are available via
tracepoints for GPL modules only. The build could be modified to
generate a function for each unique DTRACE_PROBE invocation. These could
be then accessed via kprobes.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Matt Ahrens <matt@delphix.com> Reviewed-by: Richard Elling <Richard.Elling@RichardElling.com> Signed-off-by: Brad Lewis <brad.lewis@delphix.com>
Closes #8659
Closes #8663
Revert "Fail early on bio corruption confirmed on 5.2-rc1"
This reverts commit aa7aab6c457f106d2b794b9adf3fe5aa451ad8e.
The change is not compatible with CentOS 6's 2.6.32 based kernel
due to differnces in the bio layer.
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #8961
Tom Caputi [Fri, 5 Jul 2019 23:53:14 +0000 (19:53 -0400)]
Remove VERIFY from dsl_dataset_crypt_stats()
This patch fixes an issue where dsl_dataset_crypt_stats() would
VERIFY that it was able to hold the encryption root. This function
should instead silently continue without populating the related
field in the nvlist, as is the convention for this code.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Tom Caputi <tcaputi@datto.com>
Closes #8976
Paul Dagnelie [Fri, 5 Jul 2019 23:45:20 +0000 (16:45 -0700)]
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
* zfs redact error messages do not end with newline character
* 30af21b0 inadvertently removed some ZFS_PROP comments
* man/zfs: zfs redact <redaction_snapshot> is not optional
Reviewed-by: Giuseppe Di Natale <guss80@gmail.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: George Melikov <mail@gmelikov.ru> Signed-off-by: loli10K <ezomori.nozomu@gmail.com>
Closes #8988
Mike Gerdts [Sun, 30 Jun 2019 23:38:07 +0000 (23:38 +0000)]
OpenZFS 9318 - vol_volsize_to_reservation does not account for raidz skip blocks
When a volume is created in a pool with raidz vdevs and
volblocksize != 128k, the volume can reference more space than is
reserved with the automatically calculated refreservation. There
are two deficiencies in vol_volsize_to_reservation that contribute
to this:
1) Skip blocks may be added to keep each allocation a multiple
of parity + 1. This is the dominating factor when volblocksize
is close to 2^ashift.
2) raidz deflation for 128 KB blocks is different for most other
block sizes.
See "The theory of raidz space accounting" comment in
libzfs_dataset.c for a full explanation.
Authored by: Mike Gerdts <mike.gerdts@joyent.com>
Reviewed by: Richard Elling <Richard.Elling@RichardElling.com>
Reviewed by: Sanjay Nadkarni <sanjay.nadkarni@nexenta.com>
Reviewed by: Jerry Jelinek <jerry.jelinek@joyent.com>
Reviewed by: Matt Ahrens <matt@delphix.com>
Reviewed by: Kody Kantor <kody.kantor@joyent.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Approved by: Dan McDonald <danmcd@joyent.com> Ported-by: Mike Gerdts <mike.gerdts@joyent.com>
Porting Notes:
* ZTS: wait for zvols to exist before writing
* ZTS: use log_must_busy with {zpool|zfs} destroy
Paul Zuchowski [Wed, 3 Jul 2019 20:05:02 +0000 (16:05 -0400)]
Improve "Unable to automount" error message.
Having the mountpoint and dataset name both in the message made it
confusing to read. Additionally, convert this to a zfs_dbgmsg rather than
sending it to the console.
Reviewed-by: Tom Caputi <tcaputi@datto.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Paul Zuchowski <pzuchowski@datto.com>
Closes #8959
Check b_freeze_cksum under ZFS_DEBUG_MODIFY conditional
The b_freeze_cksum field can only have data when ZFS_DEBUG_MODIFY
is set. Therefore, the EQUIV check must be wrapped accordingly.
For the same reason the ASSERT in arc_buf_fill() in unsafe.
However, since it's largely redundant it has simply been removed.
Reviewed-by: George Wilson <gwilson@delphix.com> Reviewed-by: Allan Jude <allanjude@freebsd.org> Reviewed-by: Igor Kozhukhov <igor@dilos.org> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #8979
Matthew Ahrens [Wed, 3 Jul 2019 19:57:05 +0000 (12:57 -0700)]
Fix typo in zpool-features.5, section bookmark_written
The full property name includes "delphix", not "delphxi".
Reviewed-by: Richard Laager <rlaager@wiktel.com> Reviewed-by: George Melikov <mail@gmelikov.ru> Reviewed-by: Igor Kozhukhov <igor@dilos.org> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #8985
Tom Caputi [Wed, 3 Jul 2019 00:30:00 +0000 (20:30 -0400)]
Fix error text for EINVAL in zfs_receive_one()
This small patch fixes the EINVAL case for zfs_receive_one(). A
missing 'else' has been added to the two possible cases, which
will ensure the intended error message is printed.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: loli10K <ezomori.nozomu@gmail.com> Signed-off-by: Tom Caputi <tcaputi@datto.com>
Closes #8977
Don't use d_path() for automount mount point for chroot'd process
Chroot'd process fails to automount snapshots due to realpath(3)
failure in mount.zfs(8).
Construct a mount point path from sb of the ctldir inode and dirent
name, instead of from d_path(), so that chroot'd process doesn't get
affected by its view of fs.
mandoc: ./man/man8/zfs.8: ERROR: skipping item outside list: It Ar filesystem Ns | Ns Ar mountpoint
mandoc: ./man/man8/zfs.8: ERROR: skipping item outside list: It Xo
mandoc: ./man/man8/zfs.8: ERROR: skipping end of block that is not open: Xc
mandoc: ./man/man8/zfs.8: ERROR: skipping item outside list: It Xo
mandoc: ./man/man8/zfs.8: ERROR: skipping end of block that is not open: Xc
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: George Melikov <mail@gmelikov.ru> Signed-off-by: loli10K <ezomori.nozomu@gmail.com>
Closes #8980
George Wilson [Fri, 28 Jun 2019 19:40:24 +0000 (15:40 -0400)]
nopwrites on dmu_sync-ed blocks can result in a panic
After device removal, performing nopwrites on a dmu_sync-ed block
will result in a panic. This panic can show up in two ways:
1. an attempt to issue an IOCTL in vdev_indirect_io_start()
2. a failed comparison of zio->io_bp and zio->io_bp_orig in
zio_done()
To resolve both of these panics, nopwrites of blocks on indirect
vdevs should be ignored and new allocations should be performed on
concrete vdevs.
Reviewed-by: Igor Kozhukhov <igor@dilos.org> Reviewed-by: Pavel Zakharov <pavel.zakharov@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Don Brady <don.brady@delphix.com> Signed-off-by: George Wilson <gwilson@delphix.com>
Closes #8957
Paul Dagnelie [Wed, 26 Jun 2019 18:00:12 +0000 (11:00 -0700)]
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
Paul Dagnelie [Tue, 25 Jun 2019 19:50:38 +0000 (12:50 -0700)]
zdb -vvvvv on ztest pool dies with "out of memory"
ztest creates some extremely large files as part of its
operation. When zdb tries to dump a large enough file, it
can run out of memory or spend an extremely long time
attempting to print millions or billions of uint64_ts.
We cap the amount of data from a uint64 object that we
are willing to read and print.
Reviewed-by: Don Brady <don.brady@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Paul Dagnelie <pcd@delphix.com>
External-issue: DLPX-53814
Closes #8947
Alexander Motin [Tue, 25 Jun 2019 19:03:38 +0000 (15:03 -0400)]
Avoid extra taskq_dispatch() calls by DMU
DMU sync code calls taskq_dispatch() for each sublist of os_dirty_dnodes
and os_synced_dnodes. Since the number of sublists by default is equal
to number of CPUs, it will dispatch equal, potentially large, number of
tasks, waking up many CPUs to handle them, even if only one or few of
sublists actually have any work to do.
This change adds check for empty sublists to avoid this.
Reviewed by: Sean Eric Fagan <sef@ixsystems.com>
Reviewed by: Matt Ahrens <matt@delphix.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Closes #8909
Igor K [Tue, 25 Jun 2019 00:58:12 +0000 (03:58 +0300)]
-Y option for zdb is valid
The -Y option was added for ztest to test split block reconstruction.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Richard Elling <Richard.Elling@RichardElling.com> Signed-off-by: Igor Kozhukhov <igor@dilos.org>
Closes #8926
Matthew Ahrens [Mon, 24 Jun 2019 23:44:01 +0000 (16:44 -0700)]
Remove code for zfs remap
The "zfs remap" command was disabled by 6e91a72fe3ff8bb282490773bd687632f3e8c79d, because it has little utility
and introduced some tricky bugs. This commit removes the code for it,
the associated ZFS_IOC_REMAP ioctl, and tests.
Note that the ioctl and property will remain, but have no functionality.
This allows older software to fail gracefully if it attempts to use
these, and avoids a backwards incompatibility that would be introduced if
we renumbered the later ioctls/props.
Reviewed-by: Tom Caputi <tcaputi@datto.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #8944
Brian Behlendorf [Mon, 24 Jun 2019 16:32:47 +0000 (09:32 -0700)]
Fix out-of-tree build failures
Resolve the incorrect use of srcdir and builddir references for
various files in the build system. These have crept in over time
and went unnoticed because when building in the top level directory
srcdir and builddir are identical.
With this change it's again possible to build in a subdirectory.
$ mkdir obj
$ cd obj
$ ../configure
$ make
Reviewed-by: loli10K <ezomori.nozomu@gmail.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: Don Brady <don.brady@delphix.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #8921
Closes #8943
Don Brady [Sat, 22 Jun 2019 23:51:46 +0000 (16:51 -0700)]
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
Matthew Ahrens [Sat, 22 Jun 2019 23:48:54 +0000 (16:48 -0700)]
dn_struct_rwlock can not be held in dmu_tx_try_assign()
The thread calling dmu_tx_try_assign() can't hold the dn_struct_rwlock
while assigning the tx, because this can lead to deadlock. Specifically,
if this dnode is already assigned to an earlier txg, this thread may
need to wait for that txg to sync (the ERESTART case below). The other
thread that has assigned this dnode to an earlier txg prevents this txg
from syncing until its tx can complete (calling dmu_tx_commit()), but it
may need to acquire the dn_struct_rwlock to do so (e.g. via
dmu_buf_hold*()).
This commit adds an assertion to dmu_tx_try_assign() to ensure that this
deadlock is not inadvertently introduced.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
Closes #8929
Don Brady [Sat, 22 Jun 2019 23:41:21 +0000 (16:41 -0700)]
Let zfs mount all tolerate in-progress mounts
The zfs-mount service can unexpectedly fail to start when zfs
encounters a mount that is in progress. This service uses
zfs mount -a, which has a window between the time it checks if
the dataset was mounted and when the actual mount (via mount.zfs
binary) occurs.
The reason for the racing mounts is that both zfs-mount.target
and zfs-share.target are allowed to execute concurrently after
the import. This is more of an issue with the relatively recent
addition of parallel mounting, and we should consider serializing
the mount and share targets.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed by: John Kennedy <john.kennedy@delphix.com> Reviewed-by: Allan Jude <allanjude@freebsd.org> Signed-off-by: Don Brady <don.brady@delphix.com>
Closes #8881
Allan Jude [Sat, 22 Jun 2019 23:33:44 +0000 (19:33 -0400)]
zstreamdump: add per-record-type counters and an overhead counter
Count the bytes of payload for each replication record type
Count the bytes of overhead (replication records themselves)
Include these counters in the output summary at the end of the run.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Matt Ahrens <mahrens@delphix.com> Signed-off-by: Allan Jude <allanjude@freebsd.org> Sponsored-By: Klara Systems and Catalogic
Closes #8432
Paul Dagnelie [Sat, 22 Jun 2019 23:32:26 +0000 (16:32 -0700)]
Fix comments on zfs_bookmark_phys
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Matt Ahrens <mahrens@delphix.com> Reviewed-by: George Melikov <mail@gmelikov.ru> Signed-off-by: Paul Dagnelie <pcd@delphix.com>
Closes #8945
Paul Dagnelie [Fri, 21 Jun 2019 16:40:56 +0000 (09:40 -0700)]
Add SCSI_PASSTHROUGH to zvols to enable UNMAP support
When exporting ZVOLs as SCSI LUNs, by default Windows will not
issue them UNMAP commands. This reduces storage efficiency in
many cases.
We add the SCSI_PASSTHROUGH flag to the zvol's device queue,
which lets the SCSI target logic know that it can handle SCSI
commands.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: George Melikov <mail@gmelikov.ru> Reviewed-by: John Gallagher <john.gallagher@delphix.com> Signed-off-by: Paul Dagnelie <pcd@delphix.com>
Closes #8933
Tomohiro Kusumi [Fri, 21 Jun 2019 01:31:53 +0000 (10:31 +0900)]
Prevent pointer to an out-of-scope local variable
`show_str` could be a pointer to a local variable in stack
which is out-of-scope by the time
`return (snprintf(buf, buflen, "%s\n", show_str));`
is called.
Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Tomohiro Kusumi <kusumi.tomohiro@gmail.com>
Closes #8924
Closes #8940
Matthew Ahrens [Fri, 21 Jun 2019 01:30:40 +0000 (18:30 -0700)]
dedup=verify doesn't clear the blkptr's dedup flag
The logic to handle strong checksum collisions where the data doesn't
match is incorrect. It is not clearing the dedup bit of the blkptr,
which can cause a panic later in zio_ddt_free() due to the dedup table
not matching what is in the blkptr.
Reviewed-by: Tom Caputi <tcaputi@datto.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
External-issue: DLPX-48097
Closes #8936
Igor K [Fri, 21 Jun 2019 01:29:02 +0000 (04:29 +0300)]
Update vdev_ops_t from illumos
Align vdev_ops_t from illumos for better compatibility.
Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Igor Kozhukhov <igor@dilos.org>
Closes #8925
Tom Caputi [Thu, 20 Jun 2019 19:29:51 +0000 (15:29 -0400)]
Allow unencrypted children of encrypted datasets
When encryption was first added to ZFS, we made a decision to
prevent users from creating unencrypted children of encrypted
datasets. The idea was to prevent users from inadvertently
leaving some of their data unencrypted. However, since the
release of 0.8.0, some legitimate reasons have been brought up
for this behavior to be allowed. This patch simply removes this
limitation from all code paths that had checks for it and updates
the tests accordingly.
Reviewed-by: Jason King <jason.king@joyent.com> Reviewed-by: Sean Eric Fagan <sef@ixsystems.com> Reviewed-by: Richard Laager <rlaager@wiktel.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Tom Caputi <tcaputi@datto.com>
Closes #8737
Closes #8870
dacianstremtan [Thu, 20 Jun 2019 19:27:14 +0000 (15:27 -0400)]
Replace whereis with type in zfs-lib.sh
The whereis command should not be used since it may not exist
in the initramfs. The dracut plymouth module also uses the type
command instead of whereis.
Matthew Ahrens [Wed, 19 Jun 2019 21:54:02 +0000 (14:54 -0700)]
Remove dedupditto functionality
If dedup is in use, the `dedupditto` property can be set, causing ZFS to
keep an extra copy of data that is referenced many times (>100x). The
idea was that this data is more important than other data and thus we
want to be really sure that it is not lost if the disk experiences a
small amount of random corruption.
ZFS (and system administrators) rely on the pool-level redundancy to
protect their data (e.g. mirroring or RAIDZ). Since the user/sysadmin
doesn't have control over what data will be offered extra redundancy by
dedupditto, this extra redundancy is not very useful. The bulk of the
data is still vulnerable to loss based on the pool-level redundancy.
For example, if particle strikes corrupt 0.1% of blocks, you will either
be saved by mirror/raidz, or you will be sad. This is true even if
dedupditto saved another 0.01% of blocks from being corrupted.
Therefore, the dedupditto functionality is rarely enabled (i.e. the
property is rarely set), and it fulfills its promise of increased
redundancy even more rarely.
Additionally, this feature does not work as advertised (on existing
releases), because scrub/resilver did not repair the extra (dedupditto)
copy (see https://github.com/zfsonlinux/zfs/pull/8270).
In summary, this seldom-used feature doesn't work, and even if it did it
wouldn't provide useful data protection. It has a non-trivial
maintenance burden (again see https://github.com/zfsonlinux/zfs/pull/8270).
We should remove the dedupditto functionality. For backwards
compatibility with the existing CLI, "zpool set dedupditto" will still
"succeed" (exit code zero), but won't have any effect. For backwards
compatibility with existing pools that had dedupditto enabled at some
point, the code will still be able to understand dedupditto blocks and
free them when appropriate. However, ZFS won't write any new dedupditto
blocks.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Igor Kozhukhov <igor@dilos.org> Reviewed-by: Alek Pinchuk <apinchuk@datto.com>
Issue #8270
Closes #8310
Reviewed-by: Allan Jude <allanjude@freebsd.org> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: Richard Elling <Richard.Elling@RichardElling.com> Signed-off-by: Michael Niewöhner <foss@mniewoehner.de>
Closes #8897
Closes #8911
Olaf Faaland [Wed, 19 Jun 2019 18:44:44 +0000 (11:44 -0700)]
kmod-zfs-devel rpm should provide kmod-spl-devel
When configure is run with --with-spec=redhat, and rpms are built, the
kmod-zfs-devel package is missing
Provides: kmod-spl-devel = %{version}
which is required by software such as Lustre which builds against zfs
kmods. Adding it makes it easier for such software to build against
both zfs-0.7 (where SPL is separate and may be missing) and zfs-0.8.
Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Olaf Faaland <faaland1@llnl.gov>
Closes #8930
projects / zfs / log