Disabled resilver_defer feature leads to looping resilvers
When a disk is replaced with another on a pool with the resilver_defer
feature present, but not enabled the resilver activity restarts during
each spa_sync. This patch checks to make sure that the resilver_defer
feature is first enabled before requesting a deferred resilver.
This was originally fixed in illumos-joyent as OS-7982.
Reviewed-by: Chris Dunlop <chris@onthe.net.au> Reviewed-by: George Melikov <mail@gmelikov.ru> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Tom Caputi <tcaputi@datto.com>
Reviewed by: Jerry Jelinek <jerry.jelinek@joyent.com> Signed-off-by: Kody A Kantor <kody@kkantor.com>
External-issue: illumos-joyent OS-7982
Closes #9299
Closes #9338
The was incorrect with respect to swapping dataset IDs both in the
on-disk ZAP object and the in-memory queue.
In both cases, if ds1 was already present, then it would be first
replaced with ds2 and then ds would be replaced back with ds1.
Also, both cases did not properly handle a situation where both ds1 and
ds2 are already queued. A duplicate insertion would be attempted and
its failure would result in a panic.
Reviewed-by: Matt Ahrens <matt@delphix.com> Reviewed-by: Tom Caputi <tcaputi@datto.com> Signed-off-by: Andriy Gapon <avg@FreeBSD.org>
Closes #9140
Closes #9163
Scrubbing root pools may deadlock on kernels without elevator_change() (#9321)
Originally the zfs_vdev_elevator module option was added as a
convenience so the requested elevator would be automatically set
on the underlying block devices. At the time this was simple
because the kernel provided an API function which did exactly this.
This API was then removed in the Linux 4.12 kernel which prompted
us to add compatibly code to set the elevator via a usermodehelper.
Unfortunately changing the evelator via usermodehelper requires reading
some userland binaries, most notably modprobe(8) or sh(1), from a zfs
dataset on systems with root-on-zfs. This can deadlock the system if
used during the following call path because it may need, if the data
is not already cached in the ARC, reading directly from disk while
holding the spa config lock as a writer:
While the usermodehelper waits sh(1), modprobe(8) is blocked in the
ZIO pipeline trying to read from disk:
INFO: task modprobe:2650 blocked for more than 10 seconds.
Tainted: P OE 5.2.14
modprobe D 0 2650 206 0x00000000
Call Trace:
? __schedule+0x244/0x5f0
schedule+0x2f/0xa0
cv_wait_common+0x156/0x290 [spl]
? do_wait_intr_irq+0xb0/0xb0
spa_config_enter+0x13b/0x1e0 [zfs]
zio_vdev_io_start+0x51d/0x590 [zfs]
? tsd_get_by_thread+0x3b/0x80 [spl]
zio_nowait+0x142/0x2f0 [zfs]
arc_read+0xb2d/0x19d0 [zfs]
...
zpl_iter_read+0xfa/0x170 [zfs]
new_sync_read+0x124/0x1b0
vfs_read+0x91/0x140
ksys_read+0x59/0xd0
do_syscall_64+0x4f/0x130
entry_SYSCALL_64_after_hwframe+0x44/0xa9
This commit changes how we use the usermodehelper functionality from
synchronous (UMH_WAIT_PROC) to asynchronous (UMH_NO_WAIT) which prevents
scrubs, and other vdev_elevator_switch() consumers, from triggering the
aforementioned issue.
1. Fix issue: Kernel BUG with QAT during decompression #9276.
Now it is uninterruptible for a specific given QAT request,
but Ctrl-C interrupt still works in user-space process.
2. Copy the digest result to the buffer only when doing encryption,
and vise-versa for decryption.
Reviewed-by: Tom Caputi <tcaputi@datto.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Chengfei Zhu <chengfeix.zhu@intel.com>
Closes #9276
Closes #9303
Brian Behlendorf [Wed, 11 Sep 2019 18:14:50 +0000 (11:14 -0700)]
kmodtool: depmod path
Determine the location of depmod on the system, either /sbin/depmod or
/usr/sbin/depmod. Then use that path when generating the specfile.
Additionally, update the Requires lines to reference the package which
provides depmod rather than the binary itself. For CentOS/RHEL 7+8
and all supported Fedora releases this is the kmod package, and for
CentOS/RHEL 6 it is the module-init-tools package.
Reviewed-by: Minh Diep <mdiep@whamcloud.com> Signed-off-by: Olaf Faaland <faaland1@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #8724
Closes #9310
Brian Behlendorf [Tue, 10 Sep 2019 20:42:30 +0000 (13:42 -0700)]
Fix /etc/hostid on root pool deadlock
Accidentally introduced by dc04a8c which now takes the SCL_VDEV lock
as a reader in zfs_blkptr_verify(). A deadlock can occur if the
/etc/hostid file resides on a dataset in the same pool. This is
because reading the /etc/hostid file may occur while the caller is
holding the SCL_VDEV lock as a writer. For example, to perform a
`zpool attach` as shown in the abbreviated stack below.
To resolve the issue we cache the system's hostid when initializing
the spa_t, or when modifying the multihost property. The cached
value is then relied upon for subsequent accesses.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: George Melikov <mail@gmelikov.ru> Signed-off-by: Olaf Faaland <faaland1@llnl.gov>
Closes #9289
Debian zfs-dkms package generated by alien doesn't call the prerm script
(rpm's %preun) with an integer as first parameter, which results in the
following warning when the package is uninstalled:
"zfs-dkms.prerm: line 3: [: remove: integer expression expected"
Modify the if-condition to avoid the warning.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: loli10K <ezomori.nozomu@gmail.com>
Closes #9271
Pavel Zakharov [Tue, 3 Sep 2019 18:29:52 +0000 (14:29 -0400)]
zvol_wait script should ignore partially received zvols
Partially received zvols won't have links in /dev/zvol.
Reviewed-by: Sebastien Roy <sebastien.roy@delphix.com> Reviewed-by: Paul Dagnelie <pcd@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Pavel Zakharov <pavel.zakharov@delphix.com>
Closes #9260
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
Always refuse receving non-resume stream when resume state exists
This fixes a hole in the situation where the resume state is left from
receiving a new dataset and, so, the state is set on the dataset itself
(as opposed to %recv child).
Additionally, distinguish incremental and resume streams in error
messages.
Reviewed-by: Matt Ahrens <matt@delphix.com> Reviewed-by: Tom Caputi <tcaputi@datto.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Andriy Gapon <avg@FreeBSD.org>
Closes #9252
Pavel Zakharov [Wed, 28 Aug 2019 22:02:58 +0000 (18:02 -0400)]
zfs_handle used after being closed/freed in change_one callback
This is a typical case of use after free. We would call zfs_close(zhp)
which would free the handle, and then call zfs_iter_children() on that
handle later. This change ensures that the zfs_handle is only closed
when we are ready to return.
Running `zfs inherit -r sharenfs pool` was failing with an error
code without any error messages. After some debugging I've pinpointed
the issue to be memory corruption, which would cause zfs to try to
issue an ioctl to the wrong device and receive ENOTTY.
Reviewed-by: Paul Dagnelie <pcd@delphix.com> Reviewed-by: George Wilson <gwilson@delphix.com> Reviewed-by: Sebastien Roy <sebastien.roy@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Alek Pinchuk <apinchuk@datto.com> Signed-off-by: Pavel Zakharov <pavel.zakharov@delphix.com>
Issue #7967
Closes #9165
Chunwei Chen [Wed, 28 Aug 2019 17:42:02 +0000 (10:42 -0700)]
Fix zil replay panic when TX_REMOVE followed by TX_CREATE
If TX_REMOVE is followed by TX_CREATE on the same object id, we need to
make sure the object removal is completely finished before creation. The
current implementation relies on dnode_hold_impl with
DNODE_MUST_BE_ALLOCATED returning ENOENT. While this check seems to work
fine before, in current version it does not guarantee the object removal
is completed.
We fix this by checking if DNODE_MUST_BE_FREE returns successful
instead. Also add test and remove dead code in dnode_hold_impl.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Tom Caputi <tcaputi@datto.com> Signed-off-by: Chunwei Chen <david.chen@nutanix.com>
Closes #7151
Closes #8910
Closes #9123
Closes #9145
Andriy Gapon [Tue, 27 Aug 2019 20:45:53 +0000 (23:45 +0300)]
zfs_ioc_snapshot: check user-prop permissions on snapshotted datasets
Previously, the permissions were checked on the pool which was obviously
incorrect.
After this change, zfs_check_userprops() only validates the properties
without any permission checks. The permissions are checked individually
for each snapshotted dataset.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Matt Ahrens <mahrens@delphix.com> Signed-off-by: Andriy Gapon <avg@FreeBSD.org>
Closes #9179
Closes #9180
Richard Allen [Tue, 27 Aug 2019 20:44:02 +0000 (21:44 +0100)]
Fix Plymouth passphrase prompt in initramfs script
Entering the ZFS encryption passphrase under Plymouth wasn't working
because in the ZFS initrd script, Plymouth was calling zfs via
"--command", which wasn't passing through the filesystem argument to
zfs load-key properly (it was passing through the single quotes around
the filesystem name intended to handle spaces literally,
which zfs load-key couldn't understand).
Reviewed-by: Richard Laager <rlaager@wiktel.com> Reviewed-by: Garrett Fields <ghfields@gmail.com> Signed-off-by: Richard Allen <belperite@gmail.com>
Issue #9193
Closes #9202
Tom Caputi [Tue, 27 Aug 2019 16:55:51 +0000 (12:55 -0400)]
Fix deadlock in 'zfs rollback'
Currently, the 'zfs rollback' code can end up deadlocked due to
the way the kernel handles unreferenced inodes on a suspended fs.
Essentially, the zfs_resume_fs() code path may cause zfs to spawn
new threads as it reinstantiates the suspended fs's zil. When a
new thread is spawned, the kernel may attempt to free memory for
that thread by freeing some unreferenced inodes. If it happens to
select inodes that are a a part of the suspended fs a deadlock
will occur because freeing inodes requires holding the fs's
z_teardown_inactive_lock which is still held from the suspend.
This patch corrects this issue by adding an additional reference
to all inodes that are still present when a suspend is initiated.
This prevents them from being freed by the kernel for any reason.
Reviewed-by: Alek Pinchuk <apinchuk@datto.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Tom Caputi <tcaputi@datto.com>
Closes #9203
Ryan Moeller [Fri, 23 Aug 2019 00:26:51 +0000 (20:26 -0400)]
Make slog test setup more robust
The slog tests fail when attempting to create pools using file vdevs
that already exist from previous test runs. Remove these files in the
setup for the test.
Reviewed-by: Igor Kozhukhov <igor@dilos.org> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: John Kennedy <john.kennedy@delphix.com> Signed-off-by: Ryan Moeller <ryan@ixsystems.com>
Closes #9194
Chunwei Chen [Wed, 14 Aug 2019 03:21:27 +0000 (20:21 -0700)]
Fix out-of-order ZIL txtype lost on hardlinked files
We should only call zil_remove_async when an object is removed. However,
in current implementation, it is called whenever TX_REMOVE is called. In
the case of hardlinked file, every unlink will generate TX_REMOVE and
causing operations to be dropped even when the object is not removed.
We fix this by only calling zil_remove_async when the file is fully
unlinked.
Reviewed-by: George Wilson <gwilson@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Prakash Surya <prakash.surya@delphix.com> Signed-off-by: Chunwei Chen <david.chen@nutanix.com>
Closes #8769
Closes #9061
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 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
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
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
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
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
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
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
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
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 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
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.
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
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
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
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.
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
Brian Behlendorf [Wed, 19 Jun 2019 17:39:28 +0000 (10:39 -0700)]
ZTS: Fix mmp_interval failure
The mmp_interval test case was failing on Fedora 30 due to the built-in
'echo' command terminating the script when it was unable to write to
the sysfs module parameter. This change in behavior was observed with
ksh-2020.0.0-alpha1. Resolve the issue by using the external cat
command which fails gracefully as expected.
Additionally, remove some incorrect quotes around the $? return values.
Reviewed-by: Giuseppe Di Natale <guss80@gmail.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: Olaf Faaland <faaland1@llnl.gov> Reviewed-by: Richard Elling <Richard.Elling@RichardElling.com> Reviewed-by: George Melikov <mail@gmelikov.ru> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #8906
Alexander Motin [Fri, 14 Jun 2019 21:07:34 +0000 (17:07 -0400)]
Minimize aggsum_compare(&arc_size, arc_c) calls.
For busy ARC situation when arc_size close to arc_c is desired. But
then it is quite likely that aggsum_compare(&arc_size, arc_c) will need
to flush per-CPU buckets to find exact comparison result. Doing that
often in a hot path penalizes whole idea of aggsum usage there, since it
replaces few simple atomic additions with dozens of lock acquisitions.
Replacing aggsum_compare() with aggsum_upper_bound() in code increasing
arc_p when ARC is growing (arc_size < arc_c) according to PMC profiles
allows to save ~5% of CPU time in aggsum code during sequential write
to 12 ZVOLs with 16KB block size on large dual-socket system.
I suppose there some minor arc_p behavior change due to lower precision
of the new code, but I don't think it is a big deal, since it should
affect only very small window in time (aggsum buckets are flushed every
second) and in ARC size (buckets are limited to 10 average ARC blocks
per CPU).
Reviewed-by: Chris Dunlop <chris@onthe.net.au> Reviewed-by: Richard Elling <Richard.Elling@RichardElling.com> Reviewed-by: George Melikov <mail@gmelikov.ru> Reviewed-by: Allan Jude <allanjude@freebsd.org> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Closes #8901
Ryan Moeller [Thu, 13 Jun 2019 20:15:46 +0000 (13:15 -0700)]
Python config cleanup
Don't require Python at configure/build unless building pyzfs.
Move ZFS_AC_PYTHON_MODULE to always-pyzfs.m4 where it is used.
Make test syntax more consistent.
Sponsored by: iXsystems, Inc. Reviewed-by: Neal Gompa <ngompa@datto.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Ryan Moeller <ryan@ixsystems.com>
Closes #8895
Matthew Ahrens [Thu, 13 Jun 2019 20:12:39 +0000 (13:12 -0700)]
panic in removal_remap test on 4K devices
If the zfs_remove_max_segment tunable is changed to be not a multiple of
the sector size, then the device removal code will malfunction and try
to create mappings that are smaller than one sector, leading to a panic.
On debug bits this assertion will fail in spa_vdev_copy_segment():
ASSERT3U(DVA_GET_ASIZE(&dst), ==, size);
On nondebug, the system panics with a stack like:
metaslab_free_concrete()
metaslab_free_impl()
metaslab_free_impl_cb()
vdev_indirect_remap()
free_from_removing_vdev()
metaslab_free_impl()
metaslab_free_dva()
metaslab_free()
Fortunately, the default for zfs_remove_max_segment is 1MB, so this
can't occur by default. We hit it during this test because
removal_remap.ksh changes zfs_remove_max_segment to 1KB. When testing on
4KB-sector disks, we hit the bug.
This change makes the zfs_remove_max_segment tunable more robust,
automatically rounding it up to a multiple of the sector size. We also
turn some key assertions into VERIFY's so that similar bugs would be
caught before they are encoded on disk (and thus avoid a
panic-reboot-loop).
Reviewed-by: Sean Eric Fagan <sef@ixsystems.com> Reviewed-by: Pavel Zakharov <pavel.zakharov@delphix.com> Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com> Reviewed-by: Sebastien Roy <sebastien.roy@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
External-issue: DLPX-61342
Closes #8893
Matthew Ahrens [Thu, 13 Jun 2019 20:10:19 +0000 (13:10 -0700)]
compress metadata in later sync passes
Starting in sync pass 5 (zfs_sync_pass_dont_compress), we disable
compression (including of metadata). Ostensibly this helps the sync
passes to converge (i.e. for a sync pass to not need to allocate
anything because it is 100% overwrites).
However, in practice it increases the average number of sync passes,
because when we turn compression off, a lot of block's size will change
and thus we have to re-allocate (not overwrite) them. It also increases
the number of 128KB allocations (e.g. for indirect blocks and spacemaps)
because these will not be compressed. The 128K allocations are
especially detrimental to performance on highly fragmented systems,
which may have very few free segments of this size, and may need to load
new metaslabs to satisfy 128K allocations.
We should increase zfs_sync_pass_dont_compress. In practice on a highly
fragmented system we see a few 5-pass txg's, a tiny number of 6-pass
txg's, and no txg's with more than 6 passes.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Richard Elling <Richard.Elling@RichardElling.com>
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com> Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com> Reviewed-by: George Wilson <george.wilson@delphix.com> Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
External-issue: DLPX-63431
Closes #8892
Alexander Motin [Thu, 13 Jun 2019 20:08:24 +0000 (16:08 -0400)]
Move write aggregation memory copy out of vq_lock
Memory copy is too heavy operation to do under the congested lock.
Moving it out reduces congestion by many times to almost invisible.
Since the original zio removed from the queue, and the child zio is
not executed yet, I don't see why would the copy need protection.
My guess it just remained like this from the time when lock was not
dropped here, which was added later to fix lock ordering issue.
Multi-threaded sequential write tests with both HDD and SSD pools
with ZVOL block sizes of 4KB, 16KB, 64KB and 128KB all show major
reduction of lock congestion, saving from 15% to 35% of CPU time
and increasing throughput from 10% to 40%.
Reviewed-by: Richard Yao <ryao@gentoo.org> Reviewed-by: Matt Ahrens <mahrens@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Alexander Motin <mav@FreeBSD.org>
Closes #8890
Matthew Ahrens [Thu, 13 Jun 2019 15:48:43 +0000 (08:48 -0700)]
ztest: dmu_tx_assign() gets ENOSPC in spa_vdev_remove_thread()
When running zloop, we occasionally see the following crash:
dmu_tx_assign(tx, TXG_WAIT) == 0 (0x1c == 0)
ASSERT at ../../module/zfs/vdev_removal.c:1507:spa_vdev_remove_thread()/sbin/ztest(+0x89c3)[0x55faf567b9c3]
The error value 0x1c is ENOSPC.
The transaction used by spa_vdev_remove_thread() should not be able to
fail due to being out of space. i.e. we should not call
dmu_tx_hold_space(). This will allow the removal thread to schedule its
work even when the pool is low on space. The "slop space" will provide
enough free space to sync out the txg.
Reviewed-by: Igor Kozhukhov <igor@dilos.org> Reviewed-by: Paul Dagnelie <pcd@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
External-issue: DLPX-37853
Closes #8889
Matthew Ahrens [Wed, 12 Jun 2019 20:13:09 +0000 (13:13 -0700)]
fat zap should prefetch when iterating
When iterating over a ZAP object, we're almost always certain to iterate
over the entire object. If there are multiple leaf blocks, we can
realize a performance win by issuing reads for all the leaf blocks in
parallel when the iteration begins.
For example, if we have 10,000 snapshots, "zfs destroy -nv
pool/fs@1%9999" can take 30 minutes when the cache is cold. This change
provides a >3x performance improvement, by issuing the reads for all ~64
blocks of each ZAP object in parallel.
Reviewed-by: Andreas Dilger <andreas.dilger@whamcloud.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
External-issue: DLPX-58347
Closes #8862
Matthew Ahrens [Wed, 12 Jun 2019 20:06:55 +0000 (13:06 -0700)]
Target ARC size can get reduced to arc_c_min
Sometimes the target ARC size is reduced to arc_c_min, which impacts
performance. We've seen this happen as part of the random_reads
performance regression test, where the ARC size is reduced before the
reads test starts which impacts how long it takes for system to reach
good IOPS performance.
We call arc_reduce_target_size when arc_reap_cb_check() returns TRUE,
and arc_available_memory() is less than arc_c>>arc_shrink_shift.
However, arc_available_memory() could easily be low, even when arc_c is
low, because we can have tons of unused bufs in the abd kmem cache. This
would be especially true just after the DMU requests a bunch of stuff be
evicted from the ARC (e.g. due to "zpool export").
To fix this, the ARC should reduce arc_c by the requested amount, not
all the way down to arc_size (or arc_c_min), which can be very small.
Reviewed-by: Tim Chase <tim@chase2k.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: George Melikov <mail@gmelikov.ru> Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
External-issue: DLPX-59431
Closes #8864
Richard Elling [Thu, 30 May 2019 23:38:51 +0000 (16:38 -0700)]
Improve ZTS block_device_wait debugging
The udevadm settle timeout can be 120 or 180 seconds by default
for some distributions. If a long delay is experienced, it could
be due to some strangeness in a malfunctioning device that isn't
related to the devices under test. To help debug this condition,
a notice is given if settle takes too long.
Arguments can now be passed to block_device_wait. The expected
arguments are block device pathnames.
Reviewed by: John Kennedy <john.kennedy@delphix.com> Reviewed-by: Giuseppe Di Natale <guss80@gmail.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Richard Elling <Richard.Elling@RichardElling.com>
Closes #8839
Richard Elling [Fri, 7 Jun 2019 17:12:42 +0000 (10:12 -0700)]
Block_device_wait does not return an error code
Reviewed by: John Kennedy <john.kennedy@delphix.com> Reviewed-by: Giuseppe Di Natale <guss80@gmail.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Richard Elling <Richard.Elling@RichardElling.com>
Closes #8839
Richard Elling [Wed, 5 Jun 2019 23:22:04 +0000 (16:22 -0700)]
Remove redundant redundant remove
Reviewed by: John Kennedy <john.kennedy@delphix.com> Reviewed-by: Giuseppe Di Natale <guss80@gmail.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Richard Elling <Richard.Elling@RichardElling.com>
Closes #8839
Richard Elling [Wed, 5 Jun 2019 23:13:57 +0000 (16:13 -0700)]
Fix logic error in setpartition function
Reviewed by: John Kennedy <john.kennedy@delphix.com> Reviewed-by: Giuseppe Di Natale <guss80@gmail.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Richard Elling <Richard.Elling@RichardElling.com>
Closes #8839
Paul Dagnelie [Fri, 7 Jun 2019 02:10:43 +0000 (19:10 -0700)]
Allow metaslab to be unloaded even when not freed from
On large systems, the memory used by loaded metaslabs can become
a concern. While range trees are a fairly efficient data structure,
on heavily fragmented pools they can still consume a significant
amount of memory. This problem is amplified when we fail to unload
metaslabs that we aren't using. Currently, we only unload a metaslab
during metaslab_sync_done; in order for that function to be called
on a given metaslab in a given txg, we have to have dirtied that
metaslab in that txg. If the dirtying was the result of an allocation,
we wouldn't be unloading it (since it wouldn't be 8 txgs since it
was selected), so in effect we only unload a metaslab during txgs
where it's being freed from.
We move the unload logic from sync_done to a new function, and
call that function on all metaslabs in a given vdev during
vdev_sync_done().
Reviewed-by: Richard Elling <Richard.Elling@RichardElling.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Paul Dagnelie <pcd@delphix.com>
Closes #8837
Allan Jude [Thu, 6 Jun 2019 20:14:48 +0000 (16:14 -0400)]
l2arc_apply_transforms: Fix typo in comment
Reviewed-by: Chris Dunlop <chris@onthe.net.au> Reviewed-by: Matt Ahrens <mahrens@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: George Melikov <mail@gmelikov.ru> Reviewed-by: Richard Laager <rlaager@wiktel.com> Signed-off-by: Allan Jude <allanjude@freebsd.org>
Closes #8822