src/module, branch zfs-0.6.4 FreeBSD source tree Use vmem_alloc() in spa_config_write() 2015-04-07T22:10:19+00:00 Brian Behlendorf behlendorf1@llnl.gov 2015-04-03T16:12:02+00:00 f42d7f4111f754b0f77e5982278fc79d31408d8c The packed nvlist allocated in spa_config_write() may exceed the warning threshold for large configurations. Use the vmem interfaces for this short lived allocation. Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #3251 
The packed nvlist allocated in spa_config_write() may exceed the
warning threshold for large configurations.  Use the vmem interfaces
for this short lived allocation.

Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #3251
Mark all ZPL and ioctl functions as PF_FSTRANS 2015-04-03T18:38:59+00:00 Tim Chase tim@chase2k.com 2015-03-31T03:43:29+00:00 40d06e3c78c23b199dfd9284809e710fab549391 Prevent deadlocks by disabling direct reclaim during all ZPL and ioctl calls as well as the l2arc and adapt ARC threads. This obviates the need for MUTEX_FSTRANS so its previous uses and definition have been eliminated. Signed-off-by: Tim Chase <tim@chase2k.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #3225 
Prevent deadlocks by disabling direct reclaim during all ZPL and ioctl
calls as well as the l2arc and adapt ARC threads.

This obviates the need for MUTEX_FSTRANS so its previous uses and
definition have been eliminated.

Signed-off-by: Tim Chase <tim@chase2k.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #3225
Illumus 5693 - ztest fails in dbuf_verify: buf[i] == 0, due to dedup and bp_override 2015-03-27T22:02:56+00:00 Matthew Ahrens mahrens@delphix.com 2015-03-27T06:11:50+00:00 0f7d2a4b3d2d7fc0975a7ef53bd3c4700d47c51b 5693 ztest fails in dbuf_verify: buf[i] == 0, due to dedup and bp_override Reviewed by: George Wilson <george@delphix.com> Reviewed by: Christopher Siden <christopher.siden@delphix.com> Reviewed by: Bayard Bell <buffer.g.overflow@gmail.com> Approved by: Dan McDonald <danmcd@omniti.com> References: https://www.illumos.org/issues/5693 https://github.com/illumos/illumos-gate/commit/7f7ace3 Ported-by: Chris Dunlop <chris@onthe.net.au> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #3231 
5693 ztest fails in dbuf_verify: buf[i] == 0, due to dedup and bp_override
Reviewed by: George Wilson <george@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Reviewed by: Bayard Bell <buffer.g.overflow@gmail.com>
Approved by: Dan McDonald <danmcd@omniti.com>

References:
  https://www.illumos.org/issues/5693
  https://github.com/illumos/illumos-gate/commit/7f7ace3

Ported-by: Chris Dunlop <chris@onthe.net.au>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #3231
Illumos 5694 - traverse_prefetcher does not prefetch enough 2015-03-27T22:02:50+00:00 George Wilson george.wilson@delphix.com 2015-03-27T04:31:52+00:00 b738bc5a0f8ccd0281ed06831c34fbe31d2b2138 5694 traverse_prefetcher does not prefetch enough Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Alex Reece <alex@delphix.com> Reviewed by: Christopher Siden <christopher.siden@delphix.com> Reviewed by: Josef 'Jeff' Sipek <josef.sipek@nexenta.com> Reviewed by: Bayard Bell <buffer.g.overflow@gmail.com> Approved by: Garrett D'Amore <garrett@damore.org> References: https://www.illumos.org/issues/5694 https://github.com/illumos/illumos-gate/commit/34d7ce05 Ported-by: Chris Dunlop <chris@onthe.net.au> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #3230 
5694 traverse_prefetcher does not prefetch enough
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Alex Reece <alex@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Reviewed by: Josef 'Jeff' Sipek <josef.sipek@nexenta.com>
Reviewed by: Bayard Bell <buffer.g.overflow@gmail.com>
Approved by: Garrett D'Amore <garrett@damore.org>

References:
  https://www.illumos.org/issues/5694
  https://github.com/illumos/illumos-gate/commit/34d7ce05

Ported-by: Chris Dunlop <chris@onthe.net.au>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #3230
Align code with Illumos 2015-03-27T21:52:45+00:00 Chris Dunlop chris@onthe.net.au 2015-03-27T04:04:12+00:00 ee2f17aa2af3d8620470c3bbbe6f9dac9449d546 Align code in traverse_visitbp() with that in Illumos in preparation for applying Illumos-5694. No functional change: use a temporary variable pd to replace multiple occurrences of td->td_pfd. This increases our stack use slightly more then normal because the function is called recursively. Signed-off-by: Chris Dunlop <chris@onthe.net.au> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Issue #3230 
Align code in traverse_visitbp() with that in Illumos in preparation for
applying Illumos-5694.

No functional change: use a temporary variable pd to replace multiple
occurrences of td->td_pfd.  This increases our stack use slightly more
then normal because the function is called recursively.

Signed-off-by: Chris Dunlop <chris@onthe.net.au>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #3230
Illumos 5695 - dmu_sync'ed holes do not retain birth time 2015-03-27T21:51:34+00:00 Prakash Surya prakash.surya@delphix.com 2015-03-27T02:03:22+00:00 a4069eef2e403a3b2a307b23b7500e2adc6ecae5 5695 dmu_sync'ed holes do not retain birth time Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: George Wilson <george@delphix.com> Reviewed by: Christopher Siden <christopher.siden@delphix.com> Reviewed by: Bayard Bell <buffer.g.overflow@gmail.com> Approved by: Dan McDonald <danmcd@omniti.com> References: https://www.illumos.org/issues/5695 https://github.com/illumos/illumos-gate/commit/70163ac Ported-by: Chris Dunlop <chris@onthe.net.au> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #3229 
5695 dmu_sync'ed holes do not retain birth time
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: George Wilson <george@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>
Reviewed by: Bayard Bell <buffer.g.overflow@gmail.com>
Approved by: Dan McDonald <danmcd@omniti.com>

References:
  https://www.illumos.org/issues/5695
  https://github.com/illumos/illumos-gate/commit/70163ac

Ported-by: Chris Dunlop <chris@onthe.net.au>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #3229
dbuf_free_range() overzealously frees dbufs 2015-03-25T21:48:22+00:00 Ned Bass bass6@llnl.gov 2015-03-25T00:00:08+00:00 58806b4cdc32e6f4e4a214cfba3b62a24efb34b7 When called to free a spill block from a dnode, dbuf_free_range() has a bug that results in all dbufs for the dnode getting freed. A variety of problems may result from this bug, but a common one was a zap lookup tripping an ASSERT because the zap buffers had been zeroed out. This could happen on a dataset with xattr=sa set when extended attributes are written and removed on a directory concurrently with I/O to files in that directory. Signed-off-by: Ned Bass <bass6@llnl.gov> Signed-off-by: Tim Chase <tim@chase2k.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Fixes #3195 Fixes #3204 Fixes #3222 
When called to free a spill block from a dnode, dbuf_free_range() has a
bug that results in all dbufs for the dnode getting freed.  A variety of
problems may result from this bug, but a common one was a zap lookup
tripping an ASSERT because the zap buffers had been zeroed out.  This
could happen on a dataset with xattr=sa set when extended attributes are
written and removed on a directory concurrently with I/O to files in
that directory.

Signed-off-by: Ned Bass <bass6@llnl.gov>
Signed-off-by: Tim Chase <tim@chase2k.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Fixes #3195
Fixes #3204
Fixes #3222
Set the maximum ZVOL transfer size correctly 2015-03-25T18:58:42+00:00 Tim Chase tim@chase2k.com 2015-03-23T17:10:19+00:00 ded576e28fe70a40e78a90e4668de8130d599380 ZoL had been setting max_sectors to UINT_MAX, but until Linux 3.19, it the kernel artifically capped it at 1024 (BLK_DEF_MAX_SECTORS). This cap was removed in torvalds/linux@34b48db. This patch changes it to DMU_MAX_ACCESS (in sectors) and also changes the ASSERT in dmu_tx_hold_write() to allow the maximum transfer size. Signed-off-by: Tim Chase <tim@chase2k.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #3212 
ZoL had been setting max_sectors to UINT_MAX, but until Linux 3.19, it
the kernel artifically capped it at 1024 (BLK_DEF_MAX_SECTORS).
This cap was removed in torvalds/linux@34b48db.  This patch changes
it to DMU_MAX_ACCESS (in sectors) and also changes the ASSERT in
dmu_tx_hold_write() to allow the maximum transfer size.

Signed-off-by: Tim Chase <tim@chase2k.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #3212
zio_injection_enabled should not be a module option 2015-03-24T20:22:03+00:00 Isaac Huang he.huang@intel.com 2015-03-22T05:32:54+00:00 e89bd69775d5379f6835dade1e14005aa17f4903 The zio_inject.c keeps zio_injection_enabled as a counter of fault handlers, so it should not be exported to user space as a module option. Several EXPORT_SYMBOLs are moved from zio.c to zio_inject.c, where the symbols are defined. Signed-off-by: Isaac Huang <he.huang@intel.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #3199 
The zio_inject.c keeps zio_injection_enabled as a counter of
fault handlers, so it should not be exported to user space as
a module option.

Several EXPORT_SYMBOLs are moved from zio.c to zio_inject.c,
where the symbols are defined.

Signed-off-by: Isaac Huang <he.huang@intel.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #3199
Reduce size of zfs_sb_t: allocate z_hold_mtx separately 2015-03-24T20:17:44+00:00 Chris Dunlop chris@onthe.net.au 2015-03-16T01:21:21+00:00 d07b7c7f210e3f92775ad93a7306812edf524bfc zfs_sb_t has grown to the point where using kmem_zalloc() for allocations is triggering the 32k warning threshold. We can't safely convert this entire allocation to use vmem_alloc() instead of kmem_alloc() because the backing_dev_info structure is embedded here. It depends on the bit_waitqueue() function which won't behave properly when given a virtual address. Instead, use vmem_alloc() to allocate the z_hold_mtx array separately. Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Chris Dunlop <chris@onthe.net.au> Closes #3178 
zfs_sb_t has grown to the point where using kmem_zalloc() for allocations
is triggering the 32k warning threshold.

We can't safely convert this entire allocation to use vmem_alloc() instead
of kmem_alloc() because the backing_dev_info structure is embedded here.
It depends on the bit_waitqueue() function which won't behave properly
when given a virtual address.

Instead, use vmem_alloc() to allocate the z_hold_mtx array separately.

Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Chris Dunlop <chris@onthe.net.au>
Closes #3178