Andrew Turner [Sun, 4 Sep 2016 17:50:23 +0000 (17:50 +0000)]
Enable superpages on arm64 by default. These seem to be stable, having
survived multiple world and kernel builds, and of poudriere building full
package sets.
I have observed a 3% reduction in buildworld times with superpages enabled,
however further testing is needed to see if this is observed in other
workloads.
Obtained from: ABT Systems Ltd
MFC after: 1 month
Sponsored by: The FreeBSD Foundation
With clang 3.9.0, compiling sys/netinet/igmp.c results in the following
warning:
sys/netinet/igmp.c:546:21: error: implicit conversion from 'int' to 'char' changes value from 148 to -108 [-Werror,-Wconstant-conversion]
p->ipopt_list[0] = IPOPT_RA; /* Router Alert Option */
~ ^~~~~~~~
sys/netinet/ip.h:153:19: note: expanded from macro 'IPOPT_RA'
#define IPOPT_RA 148 /* router alert */
^~~
This is because ipopt_list is an array of char, so IPOPT_RA is wrapped
to a negative value. It would be nice to change ipopt_list to an array
of u_char, but it changes the signature of the public struct ipoption,
so add an explicit cast to suppress the warning.
Reviewed by: imp
MFC after: 3 days
Differential Revision: https://reviews.freebsd.org/D7777
Bruce Evans [Sun, 4 Sep 2016 14:12:19 +0000 (14:12 +0000)]
Disconnect the "optimized" asm variants of cos(), sin() and tan() from
the build on i386. Leave them in the source tree for regression tests.
The asm functions were always much less accurate (by a factor of more
than 10**18 in the worst case). They were faster on old CPUs. But
with each new generation of CPUs they get relatively slower. The
double precision C version's average advantage is about a factor of 2
on Haswell.
The asm functions were already intentionally avoided in float and long
double precision on i386 and in all precisions on amd64. Float
precision and amd64 give larger advantages to the C version. The long
double precision C code and compilers' understanding of long double
precision are not so good, so the i387 is still slightly faster for
long double precision, except for the unimportant subcase of huge args
where the sub-optimal C code now somehow beats the i387 by about a
factor of 2.
Bruce Evans [Sun, 4 Sep 2016 12:22:14 +0000 (12:22 +0000)]
Add asm versions of fmod(), fmodf() and fmodl() on amd64. Add asm
versions of fmodf() amd fmodl() on i387.
fmod is similar to remainder, and the C versions are 3 to 9 times
slower than the asm versions on x86 for both, but we had the strange
mixture of all 6 variants of remainder in asm and only 1 of 6
variants of fmod in asm.
bhndb(4): Fix probing of bhndb-attached bhnd_nvram devices.
This fixes bhnd(4) nvram handling on devices that map SPROM CSRs via PCI
configuration space.
The probe method previously required that a bhnd(4) device be attached to the
parent bridge; now that the bhnd_nvram device is always attached first, this
unnecessary sanity check always failed.
bhndb(4): Skip disabled cores when performing bridge configuration probing.
On BCM4321 chipsets, both PCI and PCIe cores are included, with one of
the cores potentially left floating.
Since the PCI core appears first in the device table, and the PCI
profiles appear first in the resource configuration tables, this resulted in
incorrectly matching and using the PCI/v1 resource configuration on PCIe
devices, rather than the correct PCIe/v1 profile.
Adds support for probing and initializing bhndb(4) bridge state using
the bhnd_erom API, ensuring that full bridge configuration is available
*prior* to actually attaching and enumerating the bhnd(4) child device,
allowing us to safely allocate bus-level agent/device resources during
bhnd(4) bus enumeration.
- Add a bhnd_erom_probe() method usable by bhndb(4). This is an analogue
to the existing bhnd_erom_probe_static() method, and allows the bhndb
bridge to discover the best available erom parser class prior to newbus
probing of its children.
- Add support for supplying identification hints when probing erom
devices. This is required on early EXTIF-only chipsets, where chip
identification registers are not available.
- Migrate bhndb over to the new bhnd_erom API, using bhnd_core_info
records rather than bridged bhnd(4) device_t references to determine
the bridged chipsets' capability/bridge configuration.
- The bhndb parent (e.g. if_bwn) is now required to supply a hardware
priority table to the bridge. The default table is currently sufficient
for our supported devices.
- Drop the two-pass attach approach we used for compatibility with bhndb(4) in
the bhnd(4) bus drivers, and instead perform bus enumeration immediately,
and allocate bridged per-child bus-level resources during that enumeration.
Approved by: adrian (mentor)
Differential Revision: https://reviews.freebsd.org/D7768
Mark Johnston [Sun, 4 Sep 2016 00:25:49 +0000 (00:25 +0000)]
Respect the caller's hints when performing swap readahead.
The pager getpages interface allows the caller to bound the number of
readahead and readbehind pages, and vm_fault_hold() makes use of this
feature. These bounds were ignored after r305056, causing the swap pager
to potentially page in more than the specified number of pages.
Implement a generic bhnd(4) device enumeration table API.
This defines a new bhnd_erom_if API, providing a common interface to device
enumeration on siba(4) and bcma(4) devices, for use both in the bhndb bridge
and SoC early boot contexts, and migrates mips/broadcom over to the new API.
This also replaces the previous adhoc device enumeration support implemented
for mips/broadcom.
Migration of bhndb to the new API will be implemented in a follow-up commit.
- Defined new bhnd_erom_if interface for bhnd(4) device enumeration, along
with bcma(4) and siba(4)-specific implementations.
- Fixed a minor bug in bhndb that logged an error when we attempted to map the
full siba(4) bus space (18000000-17FFFFFF) in the siba EROM parser.
- Reverted use of the resource's start address as the ChipCommon enum_addr in
bhnd_read_chipid(). When called from bhndb, this address is found within the
host address space, resulting in an invalid bridged enum_addr.
- Added support for falling back on standard bus_activate_resource() in
bhnd_bus_generic_activate_resource(), enabling allocation of the bhnd_erom's
bhnd_resource directly from a nexus-attached bhnd(4) device.
- Removed BHND_BUS_GET_CORE_TABLE(); it has been replaced by the erom API.
- Added support for statically initializing bhnd_erom instances, for use prior
to malloc availability. The statically allocated buffer size is verified both
at runtime, and via a compile-time assertion (see BHND_EROM_STATIC_BYTES).
- bhnd_erom classes are registered within a module via a linker set, allowing
mips/broadcom to probe available EROM parser instances without creating a
strong reference to bcma/siba-specific symbols.
- Migrated mips/broadcom to bhnd_erom_if, replacing the previous MIPS-specific
device enumeration implementation.
Approved by: adrian (mentor)
Differential Revision: https://reviews.freebsd.org/D7748
Mark Johnston [Sat, 3 Sep 2016 20:43:59 +0000 (20:43 +0000)]
Remove redefinitions of some kernel types from mbuf.d.
These override the kernel's definitions and do not match in some cases,
which can break scripts that use these types. With r305055, dtrace is able
to trace fields of struct mbuf's anonymous structs and unions, so there is
no need to redefine types already defined in CTF.
Mark Johnston [Sat, 3 Sep 2016 20:38:13 +0000 (20:38 +0000)]
Remove support for idle page zeroing.
Idle page zeroing has been disabled by default on all architectures since
r170816 and has some bugs that make it seemingly unusable. Specifically,
the idle-priority pagezero thread exacerbates contention for the free page
lock, and yields the CPU without releasing it in non-preemptive kernels. The
pagezero thread also does not behave correctly when superpage reservations
are enabled: its target is a function of v_free_count, which includes
reserved-but-free pages, but it is only able to zero pages belonging to the
physical memory allocator.
With clang 3.9.0, compiling cxgb results in the following warning:
sys/dev/cxgb/cxgb_sge.c:2873:44: error: implicit conversion from 'int'
to 'char' changes value from 128 to -128 [-Werror,-Wconstant-conversion]
*mtod(m, char *) = CPL_ASYNC_NOTIF;
~ ^~~~~~~~~~~~~~~
This is because CPL_ASYNC_NOTIF is 0x80, so the plain char argument is
wrapped to a negative value. Fix this by using uint8_t instead.
Reviewed by: np
MFC after: 3 days
Differential Revision: https://reviews.freebsd.org/D7772
lib/libc/tests/stdio/open_memstream_test.c was moved to
lib/libc/tests/stdio/open_memstream2_test.c to accomodate
the new open_memstream test from NetBSD.
MFC after: 2 months
Tested on: amd64 (VMware fusion VM; various bare metal platforms); i386 (VMware fusion VM); make tinderbox
Sponsored by: EMC / Isilon Storage Division
Andrew Turner [Sat, 3 Sep 2016 17:23:24 +0000 (17:23 +0000)]
Explicitly include all .rodata.* sections in the kernel .rodata. This
helps link the kernel with lld as it will then put all these into a single
.rodata section.
Warner Losh [Sat, 3 Sep 2016 15:26:28 +0000 (15:26 +0000)]
Don't use -N to set the OMAGIC with data and text writeable and data
not page aligned. To do this, use the ld script gnu ld installs on my
system.
This is imperfect: LDFLAGS_BIN and LD_FLAGS_BIN describe different
things. The loader script could be better named and take into account
other architectures. And having two different mechanisms to do
basically the same thing needs study. However, it's blocking forward
progress on lld, so I'll work in parallel to sort these out.
With clang 3.9.0, compiling ppbus(4) results in the following warnings:
sys/dev/ppbus/ppb_1284.c:296:46: error: implicit conversion from 'int'
to 'char' changes value from 144 to -112 [-Werror,-Wconstant-conversion]
if ((error = do_peripheral_wait(bus, SELECT | nBUSY, 0))) {
~~~~~~~~~~~~~~~~~~ ~~~~~~~^~~~~~~
sys/dev/ppbus/ppb_1284.c:785:48: error: implicit conversion from 'int'
to 'char' changes value from 240 to -16 [-Werror,-Wconstant-conversion]
if (do_1284_wait(bus, nACK | SELECT | PERROR | nBUSY,
~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~
sys/dev/ppbus/ppb_1284.c:786:29: error: implicit conversion from 'int'
to 'char' changes value from 240 to -16 [-Werror,-Wconstant-conversion]
nACK | SELECT | PERROR | nBUSY)) {
~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~
This is because nBUSY is 0x80, so the plain char argument is wrapped to
a negative value. Fix this in a minimal fashion, by using uint8_t in a
few places.
Reviewed by: emaste
MFC after: 3 days
Differential Revision: https://reviews.freebsd.org/D7771
Ed Maste [Sat, 3 Sep 2016 13:01:37 +0000 (13:01 +0000)]
remove CONSTRUCTORS from MIPS uboot linker script
The linker script CONSTRUCTORS keyword is only meaningful "when linking
object file formats which do not support arbitrary sections, such as
ECOFF and XCOFF"[1] and is ignored for other object file formats.
LLVM's lld does not yet accept (and ignore) CONSTRUCTORS, so just remove
CONSTRUCTORS from the linker script as it has no effect.
Alexander Motin [Sat, 3 Sep 2016 11:00:29 +0000 (11:00 +0000)]
MFC r305337: 7004 dmu_tx_hold_zap() does dnode_hold() 7x on same object
Using a benchmark which has 32 threads creating 2 million files in the
same directory, on a machine with 16 CPU cores, I observed poor
performance. I noticed that dmu_tx_hold_zap() was using about 30% of
all CPU, and doing dnode_hold() 7 times on the same object (the ZAP
object that is being held).
dmu_tx_hold_zap() keeps a hold on the dnode_t the entire time it is
running, in dmu_tx_hold_t:txh_dnode, so it would be nice to use the
dnode_t that we already have in hand, rather than repeatedly calling
dnode_hold(). To do this, we need to pass the dnode_t down through
all the intermediate calls that dmu_tx_hold_zap() makes, making these
routines take the dnode_t* rather than an objset_t* and a uint64_t
object number. In particular, the following routines will need to have
analogous *_by_dnode() variants created:
This can improve performance on the benchmark described above by 100%,
from 30,000 file creations per second to 60,000. (This improvement is on
top of that provided by working around the object allocation issue. Peak
performance of ~90,000 creations per second was observed with 8 CPUs;
adding CPUs past that decreased performance due to lock contention.) The
CPU used by dmu_tx_hold_zap() was reduced by 88%, from 340 CPU-seconds
to 40 CPU-seconds.
Sponsored by: Intel Corp.
Closes #109
Reviewed by: Steve Gonczi <steve.gonczi@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed by: Ned Bass <bass6@llnl.gov>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Author: Matthew Ahrens <mahrens@delphix.com>
Alexander Motin [Sat, 3 Sep 2016 10:59:05 +0000 (10:59 +0000)]
MFV r305336: 7247 zfs receive of deduplicated stream fails
This resolves two 'zfs recv' issues. First, when receiving into an
existing filesystem, a snapshot created during the receive process is
not added to the guid->dataset map for the stream, resulting in failed
lookups for deduped streams when a WRITE_BYREF record refers to a
snapshot received earlier in the stream. Second, the newly created
snapshot was also not set properly, referencing the snapshot before the
new receiving dataset rather than the existing filesystem.
Closes #159
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Dan Kimmel <dan.kimmel@delphix.com>
Author: Chris Williamson <chris.williamson@delphix.com>
Alexander Motin [Sat, 3 Sep 2016 10:58:14 +0000 (10:58 +0000)]
MFV r305335: 7003 zap_lockdir() should tag hold
zap_lockdir() / zap_unlockdir() should take a "void *tag" argument which
tags the hold on the zap. This will help diagnose programming errors
which misuse the hold on the ZAP.
Sponsored by: Intel Corp.
Closes #108
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed by: Steve Gonczi <steve.gonczi@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Author: Matthew Ahrens <mahrens@delphix.com>
Alexander Motin [Sat, 3 Sep 2016 10:54:56 +0000 (10:54 +0000)]
7004 dmu_tx_hold_zap() does dnode_hold() 7x on same object
Using a benchmark which has 32 threads creating 2 million files in the
same directory, on a machine with 16 CPU cores, I observed poor
performance. I noticed that dmu_tx_hold_zap() was using about 30% of
all CPU, and doing dnode_hold() 7 times on the same object (the ZAP
object that is being held).
dmu_tx_hold_zap() keeps a hold on the dnode_t the entire time it is
running, in dmu_tx_hold_t:txh_dnode, so it would be nice to use the
dnode_t that we already have in hand, rather than repeatedly calling
dnode_hold(). To do this, we need to pass the dnode_t down through
all the intermediate calls that dmu_tx_hold_zap() makes, making these
routines take the dnode_t* rather than an objset_t* and a uint64_t
object number. In particular, the following routines will need to have
analogous *_by_dnode() variants created:
This can improve performance on the benchmark described above by 100%,
from 30,000 file creations per second to 60,000. (This improvement is on
top of that provided by working around the object allocation issue. Peak
performance of ~90,000 creations per second was observed with 8 CPUs;
adding CPUs past that decreased performance due to lock contention.) The
CPU used by dmu_tx_hold_zap() was reduced by 88%, from 340 CPU-seconds
to 40 CPU-seconds.
Sponsored by: Intel Corp.
Closes #109
Reviewed by: Steve Gonczi <steve.gonczi@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed by: Ned Bass <bass6@llnl.gov>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Author: Matthew Ahrens <mahrens@delphix.com>
Alexander Motin [Sat, 3 Sep 2016 10:50:43 +0000 (10:50 +0000)]
7247 zfs receive of deduplicated stream fails
This resolves two 'zfs recv' issues. First, when receiving into an
existing filesystem, a snapshot created during the receive process is
not added to the guid->dataset map for the stream, resulting in failed
lookups for deduped streams when a WRITE_BYREF record refers to a
snapshot received earlier in the stream. Second, the newly created
snapshot was also not set properly, referencing the snapshot before the
new receiving dataset rather than the existing filesystem.
Closes #159
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Dan Kimmel <dan.kimmel@delphix.com>
Author: Chris Williamson <chris.williamson@delphix.com>
Alexander Motin [Sat, 3 Sep 2016 10:48:48 +0000 (10:48 +0000)]
7003 zap_lockdir() should tag hold
zap_lockdir() / zap_unlockdir() should take a "void *tag" argument which
tags the hold on the zap. This will help diagnose programming errors
which misuse the hold on the ZAP.
Sponsored by: Intel Corp.
Closes #108
Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed by: Steve Gonczi <steve.gonczi@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Author: Matthew Ahrens <mahrens@delphix.com>
https://www.illumos.org/issues/7230
A test failure occurred where a send stream had only a BEGIN record. This
should not be possible if the send returns without error. Prevented this from
happening in the future by adding an assertion to dmu_send_impl() to verify
that if the function returns 0 (success) both a BEGIN and END record are
present. Did this by adding flags to dmu_sendarg_t (indicating whether BEGIN o
r
END records sent), having dump_record() set flags appropriately, adding VERIFY
statement to dmu_send_impl().
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Paul Dagnelie <pcd@delphix.com>
Reviewed by: Igor Kozhukhov <ikozhukhov@gmail.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Author: Matt Krantz <matt.krantz@delphix.com>
https://www.illumos.org/issues/7235
The function dsl_dataset_set_blkptr() is unused. We should remove it.
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Alex Reece <alex@delphix.com>
Reviewed by: Prakash Surya <prakash.surya@delphix.com>
Reviewed by: Igor Kozhukhov <ikozhukhov@gmail.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Author: Matthew Ahrens <mahrens@delphix.com>
https://www.illumos.org/issues/7277
ztest always prints the debug messages (zfs_dbgmsg()) by calling
zfs_dbgmsg_print(). We should add a flag to zdb to make it do this as well
before exiting.
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Igor Kozhukhov <ikozhukhov@gmail.com>
Approved by: Dan McDonald <danmcd@omniti.com>
Author: Pavel Zakharov <pavel.zakharov@delphix.com>
https://www.illumos.org/issues/7090
When write I/Os are issued, they are issued in block order but the ZIO pipelin
e
will drive them asynchronously through the allocation stage which can result i
n
blocks being allocated out-of-order. It would be nice to preserve as much of
the logical order as possible.
In addition, the allocations are equally scattered across all top-level VDEVs
but not all top-level VDEVs are created equally. The pipeline should be able t
o
detect devices that are more capable of handling allocations and should
allocate more blocks to those devices. This allows for dynamic allocation
distribution when devices are imbalanced as fuller devices will tend to be
slower than empty devices.
The change includes a new pool-wide allocation queue which would throttle and
order allocations in the ZIO pipeline. The queue would be ordered by issued
time and offset and would provide an initial amount of allocation of work to
each top-level vdev. The allocation logic utilizes a reservation system to
reserve allocations that will be performed by the allocator. Once an allocatio
n
is successfully completed it's scheduled on a given top-level vdev. Each top-
level vdev maintains a maximum number of allocations that it can handle
(mg_alloc_queue_depth). The pool-wide reserved allocations (top-levels *
mg_alloc_queue_depth) are distributed across the top-level vdevs metaslab
groups and round robin across all eligible metaslab groups to distribute the
work. As top-levels complete their work, they receive additional work from the
pool-wide allocation queue until the allocation queue is emptied.
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Alex Reece <alex@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Reviewed by: Dan Kimmel <dan.kimmel@delphix.com>
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Paul Dagnelie <paul.dagnelie@delphix.com>
Reviewed by: Prakash Surya <prakash.surya@delphix.com>
Reviewed by: Sebastien Roy <sebastien.roy@delphix.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Author: George Wilson <george.wilson@delphix.com>
https://www.illumos.org/issues/7163
Running zloop from zfs-precommit hit this assertion:
*panicstr/s
0xfffffd7fd7419370: assertion failed for thread 0xfffffd7fe29ed240,
thread-id 577: parent != NULL, file ../../../uts/common/fs/zfs/dbuf.c, line
1827
$c
libc.so.1`_lwp_kill+0xa()
libc.so.1`_assfail+0x182(fffffd7ffb1c29fa, fffffd7ffb1cc028, 723)
libc.so.1`assfail+0x19(fffffd7ffb1c29fa, fffffd7ffb1cc028, 723)
libzpool.so.1`dbuf_dirty+0xc69(10e3bc10, 3601700)
libzpool.so.1`dbuf_dirty+0x61e(10c73640, 3601700)
libzpool.so.1`dbuf_dirty+0x61e(10e28280, 3601700)
libzpool.so.1`dmu_buf_will_fill+0x64(10e28280, 3601700)
libzpool.so.1`dmu_write+0x1b6(2c7e640, d, 400000002e000000, 200, 3717b40, 3601700)
ztest_replay_write+0x568(4950d0, 3717a80, 0)
ztest_write+0x125(4950d0, d, 400000002e000000, 200, 413f000)
ztest_io+0x1bb(4950d0, d, 400000002e000000)
ztest_dmu_write_parallel+0xaa(4950d0, 6)
ztest_execute+0x83(1, 420c98, 6)
ztest_thread+0xf4(6)
libc.so.1`_thrp_setup+0x8a(fffffd7fe29ed240)
libc.so.1`_lwp_start()
This is another manifestation of ECKSUM in ztest:
The lowest level ancestor that’s in memory is the L8 (topmost). The L7
ancestor is blkid 0x10:
::dbufs -O 0x2c7e640 -o d -l 7 |::dbuf
addr object lvl blkid holds os 600be50 d 7 4 1 ztest/ds_6 719d880 d 7 0 4 ztest/ds_6
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Paul Dagnelie <pcd@delphix.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Author: Matthew Ahrens <mahrens@delphix.com>
https://www.illumos.org/issues/6451
Sometimes ztest fails because zdb detects checksum errors. e.g.:
Traversing all blocks to verify checksums and verify nothing leaked ...
zdb_blkptr_cb: Got error 50 reading <71, 47, 0, 8000160> DVA0=<0:1cc2000:
180000> [L0 other uint64[]] sha256 uncompressed LE contiguou
s unique single size=100000L/100000P birth=271L/271P fill=1
cksum=c5a3e27d1ed0f894:843bca3a5473c4bf:f76a19b6830a2e4:91292591613a12bf --
skipping
zdb_blkptr_cb: Got error 50 reading <71, 47, 0, 800000180> DVA0=<0:ce16800:
180000> [L0 other uint64[]] sha256 uncompressed LE contigu
ous unique single size=100000L/100000P birth=840L/840P fill=1
cksum=5d018f3d061e17f3:6d1584784587bf63:2805a74a0ce37369:ba68a214806c7e75
-- skipping
zdb_blkptr_cb: Got error 50 reading <71, 47, 0, 1000000360> DVA0=<0:10d37400:
180000> [L0 other uint64[]] sha256 uncompressed LE conti
guous unique single size=100000L/100000P birth=904L/904P fill=1
cksum=fa1e11d4138bd14b:86c9488c444473e3:f31e43c72e72e46b:e3446472d1174d
ba -- skipping
zdb_blkptr_cb: Got error 50 reading <71, 47, 0, 400000002c0> DVA0=<0:127ef400:
180000> [L0 other uint64[]] sha256 uncompressed LE cont
iguous dedup single size=100000L/100000P birth=549L/549P fill=1
cksum=30e14955ebf13522:66dc2ff8067e6810:4607e750abb9d3b3:6582b8af909fcb
58 -- skipping
zdb_blkptr_cb: Got error 50 reading <657, 5, 0, 1c0> DVA0=<0:1a180400:180000>
[L0 other uint64[]] fletcher4 uncompressed LE contiguou
s unique single size=100000L/100000P birth=1091L/1091P fill=1 cksum=a6cf1e50: 29b3bd01c57e5:36779b914035db9a:db61cdcf6bec56f0 -- skippin
g
The problem is that ztest_fault_inject() can inject multiple faults into the
same block. It is designed such that it can inject errors on all leafs of a
RAID-Z or mirror, but for a given range of offsets, it will only inject errors
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Prakash Surya <prakash.surya@delphix.com>
Reviewed by: Jorgen Lundman <lundman@lundman.net>
Approved by: Dan McDonald <danmcd@omniti.com>
Author: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Prakash Surya <prakash.surya@delphix.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Author: George Wilson <george.wilson@delphix.com>
https://www.illumos.org/issues/7086
In dbuf_dirty(), we need to grab the dn_struct_rwlock before looking at the
db_blkptr, to prevent it from being changed by syncing context.
Otherwise we may see that ztest got a segfault from this stack:
libzpool.so.1`dva_get_dsize_sync+0x98(872f000, b32b240, fed7811b, 0, b4cda20,
0)
libzpool.so.1`bp_get_dsize+0x60(872f000, b32b240, 0, 97cb780, 9d4c1a8, 0)
libzpool.so.1`dbuf_dirty+0x9b3(ce0a100, 97cb780, 9, fecd2530)
libzpool.so.1`dmu_buf_will_dirty+0xc3(ce0a100, 97cb780, ea293d6c, 1)
libzpool.so.1`zap_lockdir+0x1a0(8aaa3c0, 1, 0, 97cb780, 1, 1)
libzpool.so.1`zap_remove_norm+0x30(8aaa3c0, 1, 0, 8728b10, 0, 97cb780)
libzpool.so.1`zap_remove+0x29(8aaa3c0, 1, 0, 8728b10, 97cb780, a)
ztest_replay_remove+0x225(ea294588, 8728ae8, 0, 38010000, 0, 0)
ztest_remove+0x9f(ea294588, ea293f50, 4, 3)
ztest_object_init+0x78(ea294588, ea293f50, 4e0, 1)
ztest_dmu_object_alloc_free+0x71(ea294588, 13)
ztest_dmu_objset_create_destroy+0x224(80cef08, 13, 0, 805d36c, 9017ad44, 0)
ztest_execute+0x89(a, 807c720, 13, 0)
ztest_thread+0xea(13, 0, 0, 0)
libc.so.1`_thrp_setup+0x88(f0983240)
libc.so.1`_lwp_start(f0983240, 0, 0, 0, 0, 0)
Looking into it a bit, we see that this is an embedded blockpointer, so
BP_GET_NDVAS should have returned 0: b32b240::blkptr
EMBEDDED [L0 ZAP_OTHER] et=0 LZ4 size=200L/4aP birth=80L
Instead, it looks like another thread is modifying this blockpointer: b32b240::ugrep | ::whatis f47a0e0c is in [ stack tid=0x19f ] ebd6ec40 is in [ stack tid=0x226 ] ea293bd0 is in [ stack tid=0x244 ] ea293be4 is in [ stack tid=0x244 ]
Reviewed by: Prakash Surya <prakash.surya@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Approved by: Robert Mustacchi <rm@joyent.com>
Author: Matthew Ahrens <mahrens@delphix.com>
https://www.illumos.org/issues/7072
upstream:
38733 zfs fails to expand if lun added when os is in shutdown state
DLPX-36910 spares and caches should not display expandable space
DLPX-39262 vdev_disk_open spam zfs_dbgmsg buffer
Reviewed by: Igor Kozhukhov <ikozhukhov@gmail.com>
Reviewed by: Dan Kimmel <dan.kimmel@delphix.com>
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Prakash Surya <prakash.surya@delphix.com>
Reviewed by: Alex Reece <alex@delphix.com>
Approved by: Dan McDonald <danmcd@omniti.com>
Author: George Wilson <george.wilson@delphix.com>
https://www.illumos.org/issues/6950
When reading compressed data from disk, the ARC should keep the compressed
block cached and only decompress it when consumers access the block. The
uncompressed data should be short-lived allowing the ARC to cache a much larger
amount of data. The DMU would also maintain a smaller cache of uncompressed
blocks to minimize the impact of decompressing frequently accessed blocks.
Reviewed by: Prakash Surya <prakash.surya@delphix.com>
Reviewed by: Dan Kimmel <dan.kimmel@delphix.com>
Reviewed by: Matt Ahrens <mahrens@delphix.com>
Reviewed by: Paul Dagnelie <pcd@delphix.com>
Reviewed by: Don Brady <don.brady@intel.com>
Reviewed by: Richard Elling <Richard.Elling@RichardElling.com>
Approved by: Richard Lowe <richlowe@richlowe.net>
Author: George Wilson <george.wilson@delphix.com>
Alan Cox [Sat, 3 Sep 2016 03:14:24 +0000 (03:14 +0000)]
As an optimization to the machine-independent layer, change the machine-
dependent pmap_ts_referenced() so that it updates the page's dirty field
if a modified bit is found while counting reference bits. This
opportunistic update can be performed at low cost and can eliminate the
need for some future calls to pmap_is_modified() by the machine-
independent layer.
Enji Cooper [Sat, 3 Sep 2016 00:47:54 +0000 (00:47 +0000)]
Don't dedupe signals less than SIGRTMIN
FreeBSD always delivers all signals sent with sigqueue, except when
dealing with low memory conditions according to kib (see
bug # 212173 comment # 5).
Althought cryptotest itself has a -z mode to test all algorithms at a variety
of sizes, this script allows us to be more selective. Threads and buffer sizes
move in powers of two from 1, for threads, and 256 for buffer sizes.
e.g. cryptorun.sh aes 4 512
Test aes with 1, 2 and 4 processes, and at sizes of 256 and 512 bytes.
Renaming libifc to libifconfig in response to feedback on initial commit of
this library. Sticking to 'libifconfig' (and 'ifconfig_' as function prefix)
should reduce chances of namespace collisions, make it more clear what the
library does, and be more in line with existing libraries.
Submitted by: Marie Helene Kvello-Aune <marieheleneka@gmail.com>
Differential Revision: https://reviews.freebsd.org/D7742
Reviewed by: cem, kp
When -n is specified, don't make bogus DNS queries. Instead,
when -n is specified more than once, hostnames stored in utmp
are attempted to resolve to display them as network addresses.
Andrew Turner [Fri, 2 Sep 2016 10:13:51 +0000 (10:13 +0000)]
Add a pc_clock pcpu field and use it to implement cpu_est_clockrate. This
will allow drivers that manage the clock frequency to communicate this with
the reset of the kernel.
Fix array size issue when using the pre-scaling feature for
ISOCHRONOUS USB transfers. Make sure enough length and buffer pointers
are allocated when setting up the libusb transfer structure to support
the maximum number of frames the kernel can handle.
Ed Maste [Fri, 2 Sep 2016 03:15:54 +0000 (03:15 +0000)]
cron: use existing maximum username constant MAXLOGNAME
Previously cron had its own maximum username length limit, which was
smaller than the system's MAXLOGNAME. This could lead to crontab -u
updating the wrong user's crontab (if the name was truncated, and
matched another user).
PR: 212305
Reported by: Andrii Kuzik
Reviewed by: allanjude, jilles
MFC after: 3 days
Sponsored by: The FreeBSD Foundation
Differential Revision: https://reviews.freebsd.org/D7747
Kevin Lo [Fri, 2 Sep 2016 00:43:03 +0000 (00:43 +0000)]
Revert r304192 to fix short month names and replace %b with %_m in date_fmt
for Chinese locales.
As mentioned in the commit message of r289041, nl_langinfo(ABMON_*) only
returned numbers when using a Chinese locale, this causes problems in
applications that put the short month name and the day of the month together.
DIRDEPS_BUILD: Fix 'make bootstrap-tools' not using the proper tblgen binaries.
This was an incomplete item from r291561. The host {clang,llvm}-tblgen
binaries were used, rather than the ones built into the host stagedir by
normal Makefile.depend dependencies on tblgen.
META_MODE/DIRDEPS_BUILD: Fix various issues with crunch builds.
- DIRDEPS_BUILD: Fix crunchgen builds losing their library dependencies
on a nop-rebuild.
- META_MODE: Fix not rebuilding various crunch.mk targets if their .meta
files warrant a rebuild. They were lacking .meta files previously.
This adds .NOMETA to the crunch objects being used since they are
already built. Bmake was forcing a rebuild on them since their
.meta files were not in the expected place; there is no reason to
rebuild them.