The race was introduced in r337669, the large dnode feature import from
ZoL. The problem was debugged by ZoL developers and then,
independently, on FreeBSD.
The fix is an early proposal by Brian Behlendorf:
50f32ed74e
This fix never went into ZoL. A larger change that was committed later
included a different solution because of the re-worked code.
Ideally, we want to revert this fix and re-synchronize FreeBSD large
dnode code with that in illumos (or newer ZoL). illumos has a later
import of the feature from ZoL that does not have the bug.
PR: 236480
Obtained from: Brian Behlendorf <behlendorf1@llnl.gov>
Submitted by: ncrogers@gmail.com (patch adaptation)
Reported by: ncrogers@gmail.com
Tested by: ncrogers@gmail.com,
Dennis Noordsij <dennis.noordsij@alumni.helsinki.fi>,
Julien Cigar <julien@perdition.city>
MFC after: 10 days
We should support removing vdev from boot pool. Update loader zfs reader
to support com.delphix:removing.
Reviewed by: allanjude
MFC after: 2 weeks
Differential Revision: https://reviews.freebsd.org/D18901
with an eventual goal to convert all legacl zlib callers to the new zlib
version:
* Move generic zlib shims that are not specific to zlib 1.0.4 to
sys/dev/zlib.
* Connect new zlib (1.2.11) to the zlib kernel module, currently built
with Z_SOLO.
* Prefix the legacy zlib (1.0.4) with 'zlib104_' namespace.
* Convert sys/opencrypto/cryptodeflate.c to use new zlib.
* Remove bundled zlib 1.2.3 from ZFS and adapt it to new zlib and make
it depend on the zlib module.
* Fix Z_SOLO build of new zlib.
PR: 229763
Submitted by: Yoshihiro Ota <ota j email ne jp>
Reviewed by: markm (sys/dev/zlib/zlib_kmod.c)
Relnotes: yes
Differential Revision: https://reviews.freebsd.org/D19706
This ioctl is used when a breakpoint is encountered while disassembling
a symbol in the target process. Since only one DTrace consumer can
toggle or enumerate fasttrap probes from a given process at time, this
ioctl does not appear to be used in practice.
The hold_count and wire_count fields of struct vm_page are separate
reference counters with similar semantics. The remaining essential
differences are that holds are not counted as a reference with respect
to LRU, and holds have an implicit free-on-last unhold semantic whereas
vm_page_unwire() callers must explicitly determine whether to free the
page once the last reference to the page is released.
This change removes the KPIs which directly manipulate hold_count.
Functions such as vm_fault_quick_hold_pages() now return wired pages
instead. Since r328977 the overhead of maintaining LRU for wired pages
is lower, and in many cases vm_fault_quick_hold_pages() callers would
swap holds for wirings on the returned pages anyway, so with this change
we remove a number of page lock acquisitions.
No functional change is intended. __FreeBSD_version is bumped.
Reviewed by: alc, kib
Discussed with: jeff
Discussed with: jhb, np (cxgbe)
Tested by: pho (previous version)
Sponsored by: Netflix
Differential Revision: https://reviews.freebsd.org/D19247
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.
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).
MFC after: 2 weeks
Sponsored by: iXsystems, Inc.
It is too generous to collect in production debug traces that can only
be read with kernel debugger. Illumos includes special code in their
mdb debugger to read it, we don't.
MFC after: 1 week
Sponsored by: iXsystems, Inc.
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: ahrens, behlendorf, ryao
MFC after: 2 weeks
Sponsored by: iXsystems, Inc.
When ARC size is very small, aggsum_lower_bound(&arc_size) may return
negative values, that due to unsigned comparison caused delays, waiting
for arc_adjust() to "fix" it by calling aggsum_value(&arc_size). Use
of signed comparison there fixes the problem.
MFC after: 2 weeks
Sponsored by: iXsystems, Inc.
While formally it is not necessary, but the sooner it start, the sooner it
finish, and supposedly less disturbing for workload it will be.
MFC after: 2 weeks
Before r305323 (MFV r302991: 6950 ARC should cache compressed data)
arc_read() code did this for access to a ghost buffer:
arc_adapt() (from arc_get_data_buf())
arc_access(hdr, hash_lock)
I.e., we first checked access to the MFU ghost/MRU ghost buffer and
adapt MFU/MRU sizes (in arc_adapt()) and next move buffer from the ghost
state to regular.
After r305323 the sequence is different:
arc_access(hdr, hash_lock);
arc_hdr_alloc_pabd(hdr);
I.e., we first move the buffer from the ghost state in arc_access() and
then we check access to buffer in ghost state (in arc_hdr_alloc_pabd()
-> arc_get_data_abd() -> arc_get_data_impl() -> arc_adapt()). This is
incorrect: arc_adapt() never see access to the ghost buffer because
arc_access() already migrated the buffer from the ghost state to
regular.
So, the fix is to restore a call to arc_adapt() before arc_access() and
to suppress the call to arc_adapt() after arc_access().
Submitted by: Slawa Olhovchenkov <slw@zxy.spb.ru>
MFC after: 2 weeks
Sponsored by: Integros [integros.com]
Differential Revision: https://reviews.freebsd.org/D19094
When disabling the last enabled userspace probe, fasttrap clears the
function pointers which hook in to the breakpoint handler. If a traced
thread hit a fasttrap breakpoint before it was removed, we must ensure
that it is able to call the hook; otherwise fasttrap will not consume
the trap and SIGTRAP will be delievered to the thread. Synchronize
with such threads by ensuring that they load the hook pointer with
interrupts disabled, and by completing an SMP rendezvous after removing
breakpoints and before clearing the pointers.
Reported by: Alexander Alexeev <Alexander.Alexeev@dell.com>
Tested by: Alexander Alexeev (earlier version)
Reviewed by: cem, kib
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D20526
illumos/illumos-gate@6fe4f3002c
Reviewed by: Sara Hartse <sara.hartse@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Approved by: Dan McDonald <danmcd@joyent.com>
Author: Pavel Zakharov <pavel.zakharov@delphix.com>
This is irrelevant to FreeBSD, just to reduce divergence.
illumos/illumos-gate@17fb938fd6
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Serapheim Dimitropoulos <serapheim@delphix.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Approved by: Richard Lowe <richlowe@richlowe.net>
Author: Matthew Ahrens <mahrens@delphix.com>
illumos/illumos-gate@2258ad0b75
Reviewed by: Prakash Surya <prakash.surya@delphix.com>
Reviewed by: Brad Lewis <brad.lewis@delphix.com>
Reviewed by: Matt Ahrens <matt@delphix.com>
Approved by: Dan McDonald <danmcd@joyent.com>
Author: George Wilson <george.wilson@delphix.com>
illumos/illumos-gate@84927f52bd
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Approved by: Robert Mustacchi <rm@joyent.com>
Author: Allan Jude <allanjude@freebsd.org>
illumos/illumos-gate@047c81d31d
Reviewed by: Jerry Jelinek <jerry.jelinek@joyent.com>
Reviewed by: Garrett D'Amore <garrett@damore.org>
Reviewed by: Igor Kozhukhov <igor@dilos.org>
Approved by: Dan McDonald <danmcd@joyent.com>
Author: Saso Kiselkov <saso.kiselkov@nexenta.com>
This is irrelevant to FreeBSD, just a diff reduction.
illumos/illumos-gate@7928f4baf4
Reviewed by: Serapheim Dimitropoulos <serapheim.dimitro@delphix.com>
Reviewed by: Brad Lewis <brad.lewis@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Andrew Stormont <andyjstormont@gmail.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Author: Matthew Ahrens <mahrens@delphix.com>
illumos/illumos-gate@7341a7de4f
Reviewed by: Matt Ahrens <matt@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Prashanth Sreenivasa <pks@delphix.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Author: Brad Lewis <brad.lewis@delphix.com>
Due to an attempt to check two conditions at once in a macro not designed
as such, the assertion would always evaluate to true.
#define VERIFY3_IMPL(LEFT, OP, RIGHT, TYPE) do { \
const TYPE __left = (TYPE)(LEFT); \
const TYPE __right = (TYPE)(RIGHT); \
if (!(__left OP __right)) \
assfail3(#LEFT " " #OP " " #RIGHT, \
(uintmax_t)__left, #OP, (uintmax_t)__right, \
__FILE__, __LINE__); \
_NOTE(CONSTCOND) } while (0)
#define ASSERT3U(x, y, z) VERIFY3_IMPL(x, y, z, uint64_t)
Mean that we compared:
left = (type == ZIO_TYPE_FREE || psize)
OP = "<="
right = (SPA_MAXBLOCKSIZE)
If the type was not FREE, 0 is less than SPA_MAXBLOCKSIZE (16MB)
If the type is ZIO_TYPE_FREE, 1 is less than SPA_MAXBLOCKSIZE
The constraint on psize (physical size of the FREE operation) is never
checked against SPA_MAXBLOCKSIZE
Reported by: Ka Ho Ng <khng300@gmail.com>
Reviewed by: kevans
MFC after: 2 weeks
Sponsored by: Klara Systems
This allows to reduce memory waste by letting UMA to put multiple small
buffers into one memory page slab. The page sharing means that UMA
may not be able to free memory page when some of buffers are freed, but
alternatively memory used by that buffer would just be wasted from the
beginning.
This change follows alike change in ZoL, but unlike Linux (according to
my understanding of it from comments) FreeBSD never shares slabs bigger
then one memory page, so this should be even less invasive then there.
MFC after: 2 weeks
Sponsored by: iXsystems, Inc.
This allows the user to enable, disable, and adjust the I/O deadman at
runtime. This can be especially useful when a pool is backed by remote
storage (such as iscsi, ggated, etc).
PR: 221906
Submitted by: Fabian Keil <fk@fabiankeil.de>
Obtained from: ElectroBSD
MFC after: 1 week
Sponsored by: Klara Systems
Event: Waterloo Hackathon 2019
I believe previous ifdef caused NULL dereference in later zfs_log_create()
on attempt to create file inside directory belonging to ephemeral group
created on illumos, trying to write to log information about GID domain
of the newly created file, inheriting the ephemeral GID.
This patch reuses original illumos SGID code with exception that due to
lack of ID mapping code on FreeBSD ephemeral GID will turn into GID_NOBODY
by another ifdef inside zfs_fuid_map_id().
MFC after: 1 month
Sponsored by: iXsystems, Inc.
I overlooked the fact that that VOP_FSYNC() call is not a FreeBSD VFS
call, but a macro that provides an illumos-compatible wrapper for the
FreeBSD operation.
PR: 236475
Reported by: lwhsu
Pointyhat to: avg
`arc_reclaim_thread()` calls `arc_adjust()` after calling
`arc_kmem_reap_now()`; `arc_adjust()` signals `arc_get_data_buf()` to
indicate that we may no longer be `arc_is_overflowing()`.
The problem is, `arc_kmem_reap_now()` can take several seconds to
complete, has no impact on `arc_is_overflowing()`, but due to how the
code is structured, can impact how long the ARC will remain in the
`arc_is_overflowing()` state.
The fix is to use seperate threads to:
1. keep `arc_size` under `arc_c`, by calling `arc_adjust()`, which
improves `arc_is_overflowing()`
2. keep enough free memory in the system, by calling
`arc_kmem_reap_now()` plus `arc_shrink()`, which improves
`arc_available_memory()`.
illumos/illumos-gate@de753e34f9
Reviewed by: Matt Ahrens <mahrens@delphix.com>
Reviewed by: Serapheim Dimitropoulos <serapheim@delphix.com>
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed by: Dan Kimmel <dan.kimmel@delphix.com>
Reviewed by: Paul Dagnelie <pcd@delphix.com>
Reviewed by: Dan McDonald <danmcd@joyent.com>
Reviewed by: Tim Kordas <tim.kordas@joyent.com>
Approved by: Garrett D'Amore <garrett@damore.org>
Author: Brad Lewis <brad.lewis@delphix.com>
I tried to save some CPU time on hopeless aggregation attempts, but it seems
the condition I added is overly strict, blocking also aggregation of optional
I/Os in cases which previously were possible. Revert just to be safe.
MFC after: 1 month
The LBA weighting makes sense on rotational media where the outer tracks
have twice the bandwidth of the inner tracks. However, it is detrimental
on nonrotational media such as solid state disks, where the only effect
is to ensure that metaslabs enter the best-fit allocation behavior
sooner, which is detrimental to performance. It also makes no sense on
files where the underlying filesystem can arrange things however it
wants.
Author: Richard Yao <ryao@gentoo.org>
Signed-off-by: Richard Yao <ryao@gentoo.org>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#3712zfsonlinux/zfs@fb40095f5f
To reduce code divergence this merge replaces equivalent but different
FreeBSD code detecting non-rotating medium vdevs.
MFC after: 1 month
Before sequential scrub patches ZFS never aggregated I/Os above 128KB.
Sequential scrub bumped that to 1MB, which motivation I understand for
spinning disks, since it should reduce number of head seeks. But for
SSDs it makes much less sense to me, especially on FreeBSD, where due
to MAXPHYS limitation device will likely still see bunch of 128KB I/Os
instead of one large. Having more strict aggregation limit allows to
avoid allocation of large memory buffer and memcpy to/from it, that is
a serious problem when bandwidth reaches few GB/s.
MFC after: 1 month
Sponsored by: iXsystems, Inc.
Update the bounds checking for zfs_vdev_aggregation_limit so that
it has a floor of zero and a maximum value of the supported block
size for the pool.
Additionally add an early return when zfs_vdev_aggregation_limit
equals zero to disable aggregation. For very fast solid state or
memory devices it may be more expensive to perform the aggregation
than to issue the IO immediately.
Author: Brian Behlendorf <behlendorf1@llnl.gov>
zfsonlinux/zfs@a58df6f536
MFV/ZoL: Cap maximum aggregate IO size
Commit 8542ef8 allowed optional IOs to be aggregated beyond
the specified aggregation limit. Since the aggregation limit
was also used to enforce the maximum block size, setting
`zfs_vdev_aggregation_limit=16777216` could result in an
attempt to allocate an ABD larger than 16M.
Author: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: George Melikov <mail@gmelikov.ru>
Reviewed-by: Giuseppe Di Natale <dinatale2@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes#6259Closes#6270zfsonlinux/zfs@2d678f779a
I just found that at least on Skylake CPUs cpu_ticks() never returns odd
values, only even, and possibly has even bigger step (176/2?), that makes
its lower bits very bad entropy source, leaving half of taskqueues unused.
Switch to sbinuptime(), closer to upstreams, mitigates the problem by the
rate conversion working as kind of hash function. In case that is somehow
not enough (timer rate is too low or too divisible) mix in curcpu.
MFC after: 1 week
- Don't leak the ksiginfo structure.
- Hold the proc lock when sending a signal in fasttrap_sigsegv().
MFC after: 1 week
Sponsored by: The FreeBSD Foundation
