Commit Graph

578 Commits

Author SHA1 Message Date
Martin Matuska
e70664bafc MFV v242732:
Merge the ZFS I/O deadman thread from vendor (illumos).
This feature panics the system on hanging ZFS I/O, helps debugging
and resumes failed service.

The panic behavior can be controlled with the loader-only tunables:
vfs.zfs.deadman_enabled (enable or disable panic on stalled ZFS I/O)
vfs.zfs.deadman_synctime (expiration time for stalled ZFS I/O)

By default, ZFS I/O deadman is enabled by default on amd64 and i386
excluding virtual guest machines.

Illumos ZFS issues:
  3246 ZFS I/O deadman thread

References:
  https://www.illumos.org/issues/3246

MFC after:	2 weeks
2013-02-25 12:33:31 +00:00
Martin Matuska
781c0f87d3 MFV r246653:
Import vendor change to avoid "unitialized variable" warnings.

Illumos ZFS issues:
  3522 zfs module should not allow uninitialized variables

References:
  https://www.illumos.org/issues/3522
2013-02-23 11:21:05 +00:00
Justin T. Gibbs
6a8f90edf5 Avoid panic when tearing down the DTrace pid provider for a
process that has crashed.

sys/cddl/contrib/opensolaris/uts/common/dtrace/fasttrap.c:
	In fasttrap_pid_disable(), we cannot PHOLD the proc
	structure for a process that no longer exists, but
	we still have other, fasttrap specific, state that
	must be cleaned up for probes that existed in the
	dead process.  Instead of returning early if the
	process related to our probes isn't found,
	conditionalize the locking and carry on with a NULL
	proc pointer.  The rest of the fasttrap code already
	understands that a NULL proc is possible and does
	the right things in this case.

Sponsored by:	Spectra Logic Corporation
Reviewed by:	rpaulo, gnn
MFC after:	1 week
2013-02-20 17:55:17 +00:00
Xin LI
e469d5a70f Eliminate real_LZ4_uncompress. It's unused and does not perform sufficient
check against input stream (i.e. it could read beyond specified input
buffer).
2013-02-14 21:02:18 +00:00
Martin Matuska
7c695febc9 Change vfs.zfs.write_to_degraded from CTLFLAG_RW to CTLFLAG_RWTUN
Suggested by:	pjd
2013-02-13 23:11:25 +00:00
Xin LI
314caba11c Restore De Bruijn algorithm for sparc64 where the compiler rely on a
library function for __builtin_c?z.

Tested by:	Michael Moll <kvedulv kvedulv de>
2013-02-13 17:30:54 +00:00
Martin Matuska
6a33bbc041 Merge zfs_ioctl.c code that should have been merged together with ZFS v28.
Fixes several problems if working with read-only pools.

Changed code originaly introduced in onnv-gate 13061:bda0decf867b
Contains changes up to illumos-gate 13700:4bc0783f6064

PR:		kern/175897
Suggested by:	avg

MFC after:	2 weeks
2013-02-11 21:10:55 +00:00
Martin Matuska
9689178c3f MFV r246633:
Import vendor bugfixes regarding SA rounding, header size and layout.
This was already partially fixed by avg.

Illumos ZFS issues:
  3512 rounding discrepancy in sa_find_sizes()
  3513 mismatch between SA header size and layout

References:
  https://www.illumos.org/issues/3512
  https://www.illumos.org/issues/3513

MFC after:	2 weeks
2013-02-11 14:29:38 +00:00
Martin Matuska
bb03847418 MFV r246394:
Add tunable to allow block allocation on degraded vdevs.

Illumos ZFS issues:
  3507 Tunable to allow block allocation even on degraded vdevs

References:
  https://www.illumos.org/issues/3507

MFC after:	2 weeks
2013-02-11 13:59:57 +00:00
Martin Matuska
ff20578569 MFV r246392:
Import vendor ZFS bugfix fixing a possible deadlock in arc_read().

Illumos ZFS issues:
  3498 panic in arc_read(): !refcount_is_zero(&pbuf->b_hdr->b_refcnt)

References:
  https://www.illumos.org/issues/3498

MFC after:	2 weeks
2013-02-11 12:42:11 +00:00
Martin Matuska
8a2dc7faae MFV r246390:
Import minor type change in refcount.h header from vendor (illumos).

MFC after:	2 weeks
2013-02-11 07:48:57 +00:00
Martin Matuska
fd9778c236 MFV r246388:
Import vendor bugfixes

Illumos ZFS issues:
  3422 zpool create/syseventd race yield non-importable pool
  3425 first write to a new zvol can fail with EFBIG

References:
  https://www.illumos.org/issues/3422
  https://www.illumos.org/issues/3425

MFC after:	2 weeks
2013-02-10 19:32:55 +00:00
Xin LI
ef17620fc8 MFV r245512:
* Illumos zfs issue #3035 [1] LZ4 compression support in ZFS.

LZ4 is a new high-speed BSD-licensed compression algorithm created
by Yann Collet that delivers very high compression and decompression
performance compared to lzjb (>50% faster on compression, >80% faster
on decompression and around 3x faster on compression of incompressible
data), while giving better compression ratio [1].

This version of LZ4 corresponds to upstream's [2] revision 85.

Please note that for obvious reasons this is not backward read
compatible.  This means once a pool have LZ4 compressed data, these
data can no longer be read by older ZFS implementations.

Local changes:

 - On-stack hash table disabled and using kernel slab allocator
   instead, at this time.  This requires larger kernel thread stack
   for zio workers.  This may change in the future should we adjusted
   the zio workers' thread stack size.
 - likely and unlikely will be undefined if they are already defined,
   this is required for i386 XEN build.
 - Removed De Bruijn sequence based __builtin_ctz family of builtins
   in favor of the latter.  Both GCC and clang supports these builtins.
 - Changed the way the LZ4 code detects endianness.
 - Manual pages modifications to mention the feature based on Illumos
   counterpart.
 - Boot loader changes to make it support LZ4 decompression.

[1] https://www.illumos.org/issues/3035
[2] http://code.google.com/p/lz4/source/list

Obtained from:	Illumos (13921:9d721847e469)
Tested on:	FreeBSD/amd64
MFC after:	1 month
2013-02-09 06:39:28 +00:00
Andriy Gapon
0dcab786b8 zfs_vget, zfs_fhtovp: properly handle the z_shares_dir object
A special gfs vnode corresponds to that object.
A regular zfs vnode must not be returned.

This should be upstreamed.

Reported by:	pluknet
Submitted by:	rmacklem
Tested by:	pluknet
MFC after:	10 days
2013-02-08 07:49:54 +00:00
Andriy Gapon
e2bb19dce5 zfs: update comments about zfid_long_t to match the FreeBSD definitions
MFC after:	1 week
2013-02-08 07:44:15 +00:00
Andriy Gapon
c7d346f269 zfs: fix, improve and re-organize page_lookup and page_unlock
Now they are split into two pairs: page_hold/page_unhold for mappedread
and page_busy/page_unbusy for update_pages.

For mappedread we simply hold a page that is to be used as a source if it
is resident and valid (and not busy).  This is sufficient since we are
only doing page -> user buffer copying.  There is no page <-> backing
storage I/O involved.

update_pages is now better split to properly handle the putpages case
(page -> arc) and the regular write case (arc -> page).

For the latter we use complete protocol of marking an object with
paging-in-progress and marking a page with io_start (busy count).
Also, in this case we remove the write bit from all page mappings and
clear dirty bits of the pages, the former is needed to ensure that the
latter does the right thing.
Additionally we update a page if it is cached instead of just freeing it
as was done before.  This needs to be verified.

A minor detail: ZFS-backed pages should always be either fully valid
or fully invalid.  Assert this and use simpler API that does not deal
with sub-page blocks.

Reviewed by:	kib
MFC after:	26 days
2013-02-03 18:42:20 +00:00
Andriy Gapon
13235aaa89 zfs: add MODULE_VERSION for zfsctrl
This should allow the kernel linker to easily detect a situation
when the module is present both in a kernel and in a preloaded file
(zfs.ko).

Reviewed by:	jhb
MFC after:	5 days
2013-02-02 11:35:18 +00:00
Andriy Gapon
ea84c62f93 spa_generate_rootconf: add support for old vdev labels
It seems that old ZFS versions (v15) completely omit "vdev_children"
property when there is a single child.

Reported by:	jase
Tested by:	jase
MFC after:	1 week
2013-01-26 10:34:17 +00:00
Xin LI
5c74885e99 MFV r245510:
improve the comment in txg.c

Obtained from:	Illumos (13910:f3454e0a097c)
MFC after:	2 weeks
2013-01-16 22:59:50 +00:00
Konstantin Belousov
614b9f9130 For zfs vnodes, use the standard inode number based hash algorithm.
Reviewed and tested by:	peter
Sponsored by:	The FreeBSD Foundation
MFC after:	5 days
2013-01-14 05:45:33 +00:00
Xin LI
290a1ba9a4 The current ZFS code expects ddt_zap_count to always succeed by asserting
the underlying zap_count() to return no errors.  However, it is possible
that the pool reaches to such a state where zap_count would return error,
leading to panics when a pool is imported.

This commit changes the ddt_zap_count to return error returned from
zap_count and handle the error appropriately.  With this change, it's now
possible to let zpool rollback damaged transaction groups and import the
pool.

Obtained from:	ZFS on Linux github (e8fd45a0f975c6b8ae8cd644714fc21f14fac2bf)
MFC after:	1 month
2013-01-10 19:26:56 +00:00
Andriy Gapon
f71fbb1d12 zfs: solaris doesn't have KM_ZERO, kmem_zalloc should be used instead
To do:		remove KM_ZERO declaration
Pointyhat to:	avg (for mindlessly using the pseudo-flag)
MFC after:	instantly (to fix stable/8 build)
2012-12-23 19:58:41 +00:00
Steven Hartland
5780c4a723 Added vfs.zfs.vdev.trim_on_init sysctl which allows full vdev trim on
initialisation to be enabled (1) / disabled (0) defaults to enabled.

This is useful for devices which have a slow trim speed and are either
new or have otherwise already been wiped e.g. secure erase.

PR:     kern/173116
Submitted by:   Steven Hartland
Approved by:    pjd (mentor)
2012-12-13 17:39:07 +00:00
Steven Hartland
c440a359ca Upgrades trim free request sizes before inserting them into to free map,
making range consolidation much more effective particularly for small
deletes.

This reduces memory used by the free map as well as reducing the number
of bio requests down to geom required to process all deletes.

In tests this achieved a factor of 10 reduction of trim ranges / geom
call downs.

While I'm here correct the description of zio_vdev_io_start.

PR:		kern/173254
Submitted by:	Steven Hartland
Approved by:	pjd (mentor)
2012-12-13 17:06:38 +00:00
Steven Hartland
7150222c0a Renamed zfs trim stats removing duplicate zio_trim identifier from the name
Added description option to kstats.
Added descriptions for zio_trim kstats

PR:		kern/173113
Submitted by:	Steven Hartland
Reviewed by:	pjd
Approved by:	pjd
MFC after:	2 weeks
2012-12-12 16:14:14 +00:00
Xin LI
2740382ebd Use SA_ZPL_CRTIME instead of SA_ZPL_CTIME for creation time.
Submitted by:	phil.stone at gmx.com
MFC after:	2 weeks
2012-12-03 04:25:37 +00:00
Andriy Gapon
289b3b96ac zfs_getpages: make use of vm_page_readahead_finish
Suggested by:	kib
MFC after:	5 days
2012-12-01 18:13:53 +00:00
Andriy Gapon
992ffc58ae gfs_file_inactive: replace bad code with ugly code
Also, make it explicit that V_XATTRDIR is not properly supported in gfs
code yet.

The bad code was plain incorrect: (a) it spoiled handling of v_usecount
reaching zero and (b) it leaked v_holdcnt.

The ugly code employs potentially unsafe locking tricks.

Ideally we should separate vnode lifecycle and gfs node lifecycle.
A gfs node should have its own reference count where its child nodes
should be accounted.

PR:		kern/151111
Reviewed by:	kib
MFC after:	13 days
2012-12-01 18:12:55 +00:00
Martin Matuska
7faa32552f MFV r243395:
Introduce a new dataset aclmode setting "restricted" to protect ACL's
being destroyed or corrupted by a drive-by chmod.

illumos-gate 13889:a67716f16746
3254 add support in zfs for aclmode=restricted

References:
https://www.illumos.org/issues/3254

MFC after:	2 weeks
2012-11-26 12:24:39 +00:00
Martin Matuska
53e5858c68 Add loader(8) tunable to enable/disable nopwrite functionality:
vfs.zfs.nopwrite_enabled

MFC after:	2 weeks
2012-11-25 16:54:43 +00:00
Martin Matuska
dd801aa546 MFV r243013 and r243267:
Import the zio nop-write improvement from Illumos. To reduce I/O,
nop-write omits overwriting data if the checksum (cryptographically
secure) of new data matches the checksum of existing data.
It also saves space if snapshots are in use.

It currently works only on datasets with enabled compression, disabled
deduplication and sha256 checksums.

IllumOS 13887:196932ec9e6a and 13888:7204b3392a58
3236 zio nop-write

References:
https://www.illumos.org/issues/3236

MFC after:	2 weeks
2012-11-25 16:32:07 +00:00
Andriy Gapon
3a0e1b57bb zfs_freebsd_reclaim: remove a stray variable
... which leaked from a subsequent local change.
Unfortunately I noticed that only after commit.

MFC after:	5 weeks
X-MFC with:	r243520
2012-11-25 15:46:29 +00:00
Andriy Gapon
4ff1c77d22 zfs: overhaul zfs-vfs glue for vnode life-cycle management
* There is no need for the delayed destruction of znodes via taskqueue,
now that we do not need to fear recursion from getnewvnode into
zfs_inactive and zfs_freebsd_reclaim, thus making znode/vnode state
machine a bit simpler.

* More complete porting of zfs_inactive from Solaris VFS model to FreeBSD
vop_inactive and vop_reclaim model.  All destructive actions are done
in zfs_freebsd_reclaim.
This allows to simplify zfs_zget logic.

* Allow zfs_zget to return a doomed vnode if the current thread already
has an exclusive lock on the vnode.

* Clean up Solaris-isms like bailing out of reclaim/inactive on certain
values of v_usecount (aka v_count) or directly messing with this counter.

* Do not clear z_vnode while znode is still accessible.
z_vnode should be cleared only after zfs_znode_dmu_fini.
Otherwise zfs_zget may get an effectively half-deconstructed znode.
This allows to simplify zfs_zget logic further.

The above changes fix at least two known/reported problems:

o An indefinite wait in the following code path:
vgone -> VOP_RECLAIM -> zfs_freebsd_reclaim -> vnode_destroy_vobject ->
put_pages -> zfs_write -> zil_commit -> zfs_zget
This happened because vgone marks a vnode as VI_DOOMED before calling
VOP_RECLAIM, but zfs_zget would not return a doomed vnode under any
circumstances.
The fix in this change is not complete as it won't fix a deadlock between
two threads doing VOP_RECLAIM where one thread is in zil_commit trying to
zfs_zget a znode/vnode being reclaimed by the other thread, which would be
blocked trying to enter zil_commit.  This type of deadlock has not been
reported as of now.

o An indefinite wait in the unmount path caused by a znode "falling through
the cracks" in inactive+reclaim.  This would happen if the znode is unlinked
while its vnode is still active.

To Do: pass locking flags parameter to zfs_zget, so that the zfs-vfs
glue code doesn't have to re-lock a vnode but could ask for proper locking
from the very start.  This would also allow for the higher level code to
obtain a doomed vnode when it is expected/requested.  Or to avoid blocking
when it is not allowed (see zil_commit example above).

ffs_vgetf seems like a good source of inspiration.

Tested by:	Willem Jan Withagen <wjw@digiware.nl>
MFC after:	6 weeks
2012-11-25 15:33:26 +00:00
Andriy Gapon
7ca5310ea3 zfs_fhtovp: there is no reason to amend lock flags with LK_RETRY here
MFC after:	12 days
2012-11-25 15:07:27 +00:00
Andriy Gapon
7192f62bcc add zfs_bmap to aid vnode_pager_haspage
... otherwise zfs_getpages would mostly be called with one page at a time.

It is expected that ZFS VOP_BMAP is only called from vnode_pager_haspage.
Since ZFS files can have variable block sizes and also because we don't
really know if any given blocks are consecutive, we can not really report
any additional blocks behind or ahead of a given block.  Since physical
block numbers do not make sense for ZFS, we do not do any real translation
and thus pass back blk = lblk.  The net effect is that vnode_pager_haspage
knows that the block exists and that the pages backed by the block can be
accessed.  vnode_pager_haspage may be wrong about the exact count of the
pages backed by the block, because of a variable block size, which
vnode_pager_haspage doesn't really know - it only knows max block size in
a filesystem.  So pages from multiple blocks can be passed to zfs_getpages,
but that is expected and correctly handled.

vnode_pager should not call zfs_bmap for any other reason, because ZFS
implements VOP_PUTPAGES and thus vnode_pager_generic_getpages is not used.

vfs_cluster code vfs_bio code should not be called for ZFS, because ZFS does
not use buffer cache layer.

Also, ZFS does not use vn_bmap_seekhole, it has its prviate mechanism for
working with holes.

The above list should cover all the current calls to VOP_BMAP.

Reviewed by:	kib
MFC after:	6 weeks
2012-11-25 15:01:12 +00:00
Andriy Gapon
b609e5f891 zfs_getpages: optimize for large block sizes
MFC after:	6 weeks
2012-11-25 14:53:26 +00:00
Martin Matuska
2f06dfc9a3 MFV r243012:
Illumos 13886:e3261d03efbf

3349 zpool upgrade -V bumps the on disk version number, but leaves
     the in core version

References:
https://www.illumos.org/issues/3349

MFC after:	1 week
2012-11-25 10:53:42 +00:00
Martin Matuska
2b8d4033cc MFV r242735:
Illumos 13879:4eac7a87eff2:
3329 spa_sync() spends 10-20% of its time in spa_free_sync_cb()
3330 space_seg_t should have its own kmem_cache
3331 deferred frees should happen after sync_pass 1
3335 make SYNC_PASS_* constants tunable

New loader-only tunables:
vfs.zfs.sync_pass_deferred_free
vfs.zfs.sync_pass_dont_compress
vfs.zfs.sync_pass_rewrite

References:
https://www.illumos.org/issues/3329
https://www.illumos.org/issues/3330
https://www.illumos.org/issues/3331
https://www.illumos.org/issues/3335

MFC after:	2 weeks
2012-11-25 09:06:32 +00:00
Andriy Gapon
328998eac1 zfs roopool: add support for multi-vdev configurations
Tested by:	madpilot
MFC after:	10 days
2012-11-24 13:23:15 +00:00
Andriy Gapon
e1fccde2c9 spa_import_rootpool: initialize ub_version before calling spa_config_parse
... because the latter makes some decision based on the version.
This is especially important for raidz vdevs.
This is similar to what spa_load does.

This is not an issue for upstream because they do not seem to support
using raidz as a root pool.

Reported by:	Andrei Lavreniyuk <andy.lavr@gmail.com>
Tested by:	Andrei Lavreniyuk <andy.lavr@gmail.com>
MFC after:	6 days
2012-11-24 13:16:49 +00:00
Andriy Gapon
cfca00a2fb spa_import_rootpool: do not call spa_history_log_version
The call is a NOP, because pool version in spa_ubsync.ub_version is not
initialized and thus appears to be zero.
If the version is properly set then the call leads to a NULL pointer
dereference because the spa object is still under-constructed.

The same change was independently made in the upstream as a part of
a larger change (4445fffbbb1ea25fd0e9ea68b9380dd7a6709025).

MFC after:	6 days
2012-11-24 13:14:53 +00:00
Andriy Gapon
c4f59a3c09 zfs: create devices/geoms from zvols after receiveing them
PR:		kern/167066
Tested by:	Andreas Nilsson <andrnils@gmail.com>
MFC after:	13 days
2012-11-24 13:07:31 +00:00
Andriy Gapon
dbe922173c zfs_remove: assert that delete_now case is never true on FreeBSD
That case is specific to Solaris VFS and it would violate pretty
fundamental contracts of FreeBSD VFS.

Discussed with:	pjd
MFC after:	12 days
2012-11-19 11:30:08 +00:00
Andriy Gapon
7b069f7fee zfs_remove: set VV_NOSYNC flag if a node is unlinked
Suggested by:	kib
MFC after:	12 days
2012-11-19 11:25:20 +00:00
Andriy Gapon
62875a6b10 spa_import_rootpool: fall back to use configuration from zpool.cache...
if we fail to generate a proper root pool configuration based on disk
probing.  Currently we can not properly generate the configuration for
multi-vdev pools.  Make that explicit.

Reported by:	madpilot, Bartosz Stec <bartosz.stec@it4pro.pl>
Tested by:	madpilot, Bartosz Stec <bartosz.stec@it4pro.pl>
MFC after:	4 days
2012-11-18 11:47:25 +00:00
Konstantin Belousov
f13b5a0f01 Add the wait6(2) system call. It takes POSIX waitid()-like process
designator to select a process which is waited for. The system call
optionally returns siginfo_t which would be otherwise provided to
SIGCHLD handler, as well as extended structure accounting for child
and cumulative grandchild resource usage.

Allow to get the current rusage information for non-exited processes
as well, similar to Solaris.

The explicit WEXITED flag is required to wait for exited processes,
allowing for more fine-grained control of the events the waiter is
interested in.

Fix the handling of siginfo for WNOWAIT option for all wait*(2)
family, by not removing the queued signal state.

PR:	standards/170346
Submitted by:	"Jukka A. Ukkonen" <jau@iki.fi>
MFC after:	1 month
2012-11-13 12:52:31 +00:00
Andriy Gapon
7631b580ff zfs_ioc_destroy_snaps_nvl: remove disk device entries for zvol snapshots
... before trying to destroy the zvol snapshots themselves.

PR:		kern/173442
Reported by:	Petri Helenius <petri@helenius.fi>,
		mm
Obtained from:	Brian Behlendorf <behlendorf1@llnl.gov>,
		Illumos Bug #3170
Tested by:	Petri Helenius <petri@helenius.fi>
MFC after:	10 days
2012-11-10 12:22:26 +00:00
Xin LI
a9b09a3f3c MFV r242729 (mm):
Illumos r13840:97fd5cdf328a:

3145 single-copy arc
3212 ztest: race condition between vdev_online() and spa_vdev_remove()

Illumos r13849:3468a95b27cd:

3258 ztest's use of file descriptors is unstable
2012-11-10 01:52:52 +00:00
Attilio Rao
bc2258da88 Complete MPSAFE VFS interface and remove MNTK_MPSAFE flag.
Porters should refer to __FreeBSD_version 1000021 for this change as
it may have happened at the same timeframe.
2012-11-09 18:02:25 +00:00
Justin Hibbits
c757049235 Implement DTrace for PowerPC. This includes both 32-bit and 64-bit.
There is one known issue:  Some probes will display an error message along the
lines of:  "Invalid address (0)"

I tested this with both a simple dtrace probe and dtruss on a few different
binaries on 32-bit.  I only compiled 64-bit, did not run it, but I don't expect
problems without the modules loaded.  Volunteers are welcome.

MFC after:	1 month
2012-11-07 23:45:09 +00:00