Make dm_flush return void.
The first error during flush is stored in md->barrier_error instead.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Fix a potential deadlock when creating multiple snapshots by holding a
reference to struct block_device for the whole lifecycle of every dm
device instead of obtaining it independently at each point it is needed.
bdget_disk() was called while the device was being suspended, in
dm_suspend(). However there could be other devices already suspended,
for example when creating additional snapshots of a device. bdget_disk()
can wait for IO and allocate memory resulting in waiting for the
already-suspended device - deadlock.
This patch changes the code so that it gets the reference to struct
block_device when struct mapped_device is allocated and initialized in
alloc_dev() where it is always OK to allocate memory or wait for I/O.
It drops the reference when it is destroyed in free_dev(). Thus there
is no call to bdget_disk() while any device is suspended.
Previously unlock_fs() was called only if bdev was held. Now it is
called unconditionally, but the superfluous calls are harmless because
it returns immediately if the filesystem was not previously frozen.
This patch also now allows the device size to be changed in a
noflush suspend because the bdev is held. This has no adverse effect.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Rename suspended_bdev to bdev.
This patch doesn't change any functionality, just renames the variable.
In the next patch, the variable will be used even for non-suspended device.
(Pre-requisite for the per-target barrier support patches.)
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
When snapshots are created using 'p' instead of 'P' as the
exception store type, the device-mapper table loading fails.
This patch makes the code case insensitive as intended and fixes some
regressions reported with device-mapper snapshots.
Signed-off-by: Jonathan Brassow <jbrassow@redhat.com>
Cc: stable@kernel.org
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Use i_size_read() instead of reading i_size.
If someone changes the size of the device simultaneously, i_size_read
is guaranteed to return a valid value (either the old one or the new one).
i_size can return some intermediate invalid value (on 32-bit computers
with 64-bit i_size, the reads to both halves of i_size can be interleaved
with updates to i_size, resulting in garbage being returned).
Cc: stable@kernel.org
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
A bio that has two or more vector entries, size less than or equal to
page size, that crosses a stripe boundary of an underlying md device is
accepted by device mapper (it conforms to all its limits) but not by the
underlying device.
The fix is: If device mapper selects the one-page maximum request size,
it also needs to set its own q->merge_bvec_fn to reject any bios with
multiple vector entries that span more pages.
The problem was discovered in the following scenario:
* MD - RAID-0
* LV on the top of it (raid1, snapshot or striped with chunk
size/stripe larger than RAID-0 stripe)
* one of the logical volumes is exported to xen domU
* inside xen domU it is partitioned, the key point is that the partition
must be unaligned on page boundary (fdisk normally aligns the partition to
63 sectors which will trigger it)
* install the system on the partitioned disk in domU
This causes I/O failures in dom0.
Reference: https://bugzilla.redhat.com/show_bug.cgi?id=223947
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
The commit fe9cf30eb8 moves dm table event
submission from kmultipath queue to kernel kevent queue to avoid a
deadlock.
There is a possibility of race condition because kevent queue is not flushed
in the multipath destructor. The scenario is:
- some event happens and is queued to keventd
- keventd thread is delayed due to scheuling latency or some other work
- multipath device is destroyed
- keventd now attempts to process work_struct that is residing in already
released memory.
The patch flushes the keventd queue in multipath constructor.
I've already fixed similar bug in dm-raid1.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Cc: stable@kernel.org
If the code can't handle allocation failures, use __GFP_NOFAIL so that
in case of memory pressure the allocator will retry indefinitely and
won't return NULL which would cause a crash in the function.
This is still not a correct fix, it may cause a classic deadlock when
memory manager waits for I/O being done and I/O waits for some free memory.
I/O code shouldn't allocate any memory. But in this case it probably
doesn't matter much in practice, people usually do not swap on RAID.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Fixed a problem affecting reinstatement of passive paths.
Before we moved the hardware handler from dm to SCSI, it performed a pg_init
for a path group and didn't maintain any state about each path in hardware
handler code.
But in SCSI dh, such state is now maintained, as we want to fail I/O early on a
path if it is not the active path.
All the hardware handlers have a state now and set to active or some form of
inactive. They have prep_fn() which uses this state to fail the I/O without
it ever being sent to the device.
So in effect when dm-multipath calls scsi_dh_activate(), activate is
sent to only one path and the "state" of that path is changed appropriately
to "active" while other paths in the same path group are never changed
as they never got an "activate".
In order make sure all the paths in a path group gets their state set
properly when a pg_init happens, we need to call scsi_dh_activate() on
all paths in a path group.
Doing this at the hardware handler layer is not a good option as we
want the multipath layer to define the relationship between path and path
groups and not the hardware handler.
Attached patch sends an "activate" on each path in a path group when a
path group is switched. It also sends an activate when a path is reinstated.
Signed-off-by: Chandra Seetharaman <sekharan@us.ibm.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
When specifying a different hardware handler via multipath
features we should be able to override the built-in defaults.
The problem here is the hardware table from scsi_dh is compiled
in and cannot be changed from userland. The multipath.conf OTOH
is purely user-defined and, what's more, the user might have a valid
reason for modifying it.
(EG EMC Clariion can well be run in PNR mode even though ALUA is
active, or the user might want to try ALUA on any as-of-yet unknown
devices)
So _not_ allowing multipath to override the device handler setting
will just add to the confusion and makes error tracking even more
difficult.
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Do not process sysfs attributes when device is being destroyed.
Otherwise code can cause
BUG_ON(test_bit(DMF_FREEING, &md->flags));
in dm_put() call.
Cc: stable@kernel.org
Signed-off-by: Milan Broz <mbroz@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Follow-up to "block: enable by default support for large devices
and files on 32-bit archs".
Rename CONFIG_LBD to CONFIG_LBDAF to:
- allow update of existing [def]configs for "default y" change
- reflect that it is used also for large files support nowadays
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* 'for-linus' of git://neil.brown.name/md: (39 commits)
md/raid5: correctly update sync_completed when we reach max_resync
md/raid5: add missing call to schedule() after prepare_to_wait()
md/linear: use call_rcu to free obsolete 'conf' structures.
md linear: Protecting mddev with rcu locks to avoid races
md: Move check for bitmap presence to personality code.
md: remove chunksize rounding from common code.
md: raid0/linear: ensure device sizes are rounded to chunk size.
md: move assignment of ->utime so that it never gets skipped.
md: Push down reconstruction log message to personality code.
md: merge reconfig and check_reshape methods.
md: remove unnecessary arguments from ->reconfig method.
md: raid5: check stripe cache is large enough in start_reshape
md: raid0: chunk_sectors cleanups.
md: fix some comments.
md/raid5: Use is_power_of_2() in raid5_reconfig()/raid6_reconfig().
md: convert conf->chunk_size and conf->prev_chunk to sectors.
md: Convert mddev->new_chunk to sectors.
md: Make mddev->chunk_size sector-based.
md: raid0 :Enables chunk size other than powers of 2.
md: prepare for non-power-of-two chunk sizes
...
At the end of reshape_request we update cyrr_resync_completed
if we are about to pause due to reaching resync_max.
However we update it to the wrong value. We need to add the
"reshape_sectors" that have just been reshaped.
Signed-off-by: NeilBrown <neilb@suse.de>
In the unlikely event that reshape progresses past the current request
while it is waiting for a stripe we need to schedule() before retrying
for 2 reasons:
1/ Prevent list corruption from duplicated list_add() calls without
intervening list_del().
2/ Give the reshape code a chance to make some progress to resolve the
conflict.
Cc: <stable@kernel.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Current, when we update the 'conf' structure, when adding a
drive to a linear array, we keep the old version around until
the array is finally stopped, as it is not safe to free it
immediately.
Now that we have rcu protection on all accesses to 'conf',
we can use call_rcu to free it more promptly.
Signed-off-by: NeilBrown <neilb@suse.de>
Due to the lack of memory ordering guarantees, we may have races around
mddev->conf.
In particular, the correct contents of the structure we get from
dereferencing ->private might not be visible to this CPU yet, and
they might not be correct w.r.t mddev->raid_disks.
This patch addresses the problem using rcu protection to avoid
such race conditions.
Signed-off-by: SandeepKsinha <sandeepksinha@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
If the superblock of a component device indicates the presence of a
bitmap but the corresponding raid personality does not support bitmaps
(raid0, linear, multipath, faulty), then something is seriously wrong
and we'd better refuse to run such an array.
Currently, this check is performed while the superblocks are examined,
i.e. before entering personality code. Therefore the generic md layer
must know which raid levels support bitmaps and which do not.
This patch avoids this layer violation without adding identical code
to various personalities. This is accomplished by introducing a new
public function to md.c, md_check_no_bitmap(), which replaces the
hard-coded checks in the superblock loading functions.
A call to md_check_no_bitmap() is added to the ->run method of each
personality which does not support bitmaps and assembly is aborted
if at least one component device contains a bitmap.
Signed-off-by: Andre Noll <maan@systemlinux.org>
Signed-off-by: NeilBrown <neilb@suse.de>
It is easiest to round sizes to multiples of chunk size in
the personality code for those personalities which care.
Those personalities now do the rounding, so we can
remove that function from common code.
Also remove the upper bound on the size of a chunk, and the lower
bound on the size of a device (1 chunk), neither of which really buy
us anything.
Signed-off-by: NeilBrown <neilb@suse.de>
This is currently ensured by common code, but it is more reliable to
ensure it where it is needed in personality code.
All the other personalities that care already round the size to
the chunk_size. raid0 and linear are the only hold-outs.
Signed-off-by: NeilBrown <neilb@suse.de>
Currently the assignment to utime gets skipped for 'external'
metadata. So move it to the top of the function so that it
always gets effected.
This is of largely cosmetic interest. Nothing actually depends
on ->utime being right for external arrays.
"mdadm --monitor" does use it for 0.90 and 1.x arrays, but with
mdadm-3.0, this is not important for external metadata.
Signed-off-by: NeilBrown <neilb@suse.de>
Currently, the md layer checks in analyze_sbs() if the raid level
supports reconstruction (mddev->level >= 1) and if reconstruction is
in progress (mddev->recovery_cp != MaxSector).
Move that printk into the personality code of those raid levels that
care (levels 1, 4, 5, 6, 10).
Signed-off-by: Andre Noll <maan@systemlinux.org>
Signed-off-by: NeilBrown <neilb@suse.de>
The difference between these two methods is artificial.
Both check that a pending reshape is valid, and perform any
aspect of it that can be done immediately.
'reconfig' handles chunk size and layout.
'check_reshape' handles raid_disks.
So make them just one method.
Signed-off-by: NeilBrown <neilb@suse.de>
Passing the new layout and chunksize as args is not necessary as
the mddev has fields for new_check and new_layout.
This is preparation for combining the check_reshape and reconfig
methods
Signed-off-by: NeilBrown <neilb@suse.de>
In reshape cases that do not change the number of devices,
start_reshape is called without first calling check_reshape.
Currently, the check that the stripe_cache is large enough is
only done in check_reshape. It should be in start_reshape too.
Signed-off-by: NeilBrown <neilb@suse.de>
1/ Raid5 has learned to take over also raid4 and raid6 arrays.
2/ new_chunk in mdp_superblock_1 is in sectors, not bytes.
Signed-off-by: NeilBrown <neilb@suse.de>
A straight-forward conversion which gets rid of some
multiplications/divisions/shifts. The patch also introduces a couple
of new ones, most of which are due to conf->chunk_size still being
represented in bytes. This will be cleaned up in subsequent patches.
Signed-off-by: Andre Noll <maan@systemlinux.org>
Signed-off-by: NeilBrown <neilb@suse.de>
This patch renames the chunk_size field to chunk_sectors with the
implied change of semantics. Since
is_power_of_2(chunk_size) = is_power_of_2(chunk_sectors << 9)
= is_power_of_2(chunk_sectors)
these bits don't need an adjustment for the shift.
Signed-off-by: Andre Noll <maan@systemlinux.org>
Signed-off-by: NeilBrown <neilb@suse.de>
* git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core-2.6: (64 commits)
debugfs: use specified mode to possibly mark files read/write only
debugfs: Fix terminology inconsistency of dir name to mount debugfs filesystem.
xen: remove driver_data direct access of struct device from more drivers
usb: gadget: at91_udc: remove driver_data direct access of struct device
uml: remove driver_data direct access of struct device
block/ps3: remove driver_data direct access of struct device
s390: remove driver_data direct access of struct device
parport: remove driver_data direct access of struct device
parisc: remove driver_data direct access of struct device
of_serial: remove driver_data direct access of struct device
mips: remove driver_data direct access of struct device
ipmi: remove driver_data direct access of struct device
infiniband: ehca: remove driver_data direct access of struct device
ibmvscsi: gadget: at91_udc: remove driver_data direct access of struct device
hvcs: remove driver_data direct access of struct device
xen block: remove driver_data direct access of struct device
thermal: remove driver_data direct access of struct device
scsi: remove driver_data direct access of struct device
pcmcia: remove driver_data direct access of struct device
PCIE: remove driver_data direct access of struct device
...
Manually fix up trivial conflicts due to different direct driver_data
direct access fixups in drivers/block/{ps3disk.c,ps3vram.c}
When porting blktrace to tracepoints, we changed to trace/block.h
for trace prober declarations.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Maintain two flows, one for pow2 chunk sizes (which uses masks and
shift), and a flow for the general case (which uses sector_div).
This is for the sake of performance.
- introduce map_sector and is_io_in_chunk_boundary to encapsulate
those two flows better for raid0_make_request
- fix blk_mergeable to support the two flows.
Signed-off-by: raziebe@gmail.com
Signed-off-by: NeilBrown <neilb@suse.de>
Remove chunk size check from md as this is now performed in the run
function in each personality.
Replace chunk size power 2 code calculations by a regular division.
Signed-off-by: raziebe@gmail.com
Signed-off-by: NeilBrown <neilb@suse.de>
have raid0 check chunk size in run method instead of in md.
This is part of a series moving the checks from common code to
the personalities where they belong.
hardsect is short and chunksize is an int, so it is safe to use %.
Signed-off-by: raziebe@gmail.com
Signed-off-by: NeilBrown <neilb@suse.de>
Replace the linear search with binary search in which_dev.
Signed-off-by: Sandeep K Sinha <sandeepksinha@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Remove num_sectors from dev_info and replace start_sector with
end_sector. This makes a lot of comparisons much simpler.
Signed-off-by: Sandeep K Sinha <sandeepksinha@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Get rid of sector_div and hash table for linear raid and replace
with a linear search in which_dev.
The hash table adds a lot of complexity for little if any gain.
Ultimately a binary search will be used which will have smaller
cache foot print, a similar number of memory access, and no
divisions.
Signed-off-by: Sandeep K Sinha <sandeepksinha@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Having a macro just to cast a void* isn't really helpful.
I would must rather see that we are simply de-referencing ->private,
than have to know what the macro does.
So open code the macro everywhere and remove the pointless cast.
Signed-off-by: NeilBrown <neilb@suse.de>
This setting doesn't seem to make sense (half the chunk size??) and
shouldn't be needed.
The segment boundary exported by raid0 should simply be the minimum
of the segment boundary of all component devices. And we already
get that right.
Signed-off-by: NeilBrown <neilb@suse.de>
If we treat conf->devlist more like a 2 dimensional array,
we can get the devlist for a particular zone simply by indexing
that array, so we don't need to store the pointers to subarrays
in strip_zone. This makes strip_zone smaller and so (hopefully)
searches faster.
Signed-of-by: NeilBrown <neilb@suse.de>
storing ->sectors is redundant as is can be computed from the
difference z->zone_end - (z-1)->zone_end
The one place where it is used, it is just as efficient to use
a zone_end value instead.
And removing it makes strip_zone smaller, so they array of these that
is searched on every request has a better chance to say in cache.
So discard the field and get the value from elsewhere.
Signed-off-by: NeilBrown <neilb@suse.de>
raid0_stop() removes all references to the raid0 configuration but
misses to free the ->devlist buffer.
This patch closes this leak, removes a pointless initialization and
fixes a coding style issue in raid0_stop().
Signed-off-by: Andre Noll <maan@systemlinux.org>
Signed-off-by: NeilBrown <neilb@suse.de>
Currently the raid0 configuration is allocated in raid0_run() while
the buffers for the strip_zone and the dev_list arrays are allocated
in create_strip_zones(). On errors, all three buffers are freed
in raid0_run().
It's easier and more readable to do the allocation and cleanup within
a single function. So move that code into create_strip_zones().
Signed-off-by: Andre Noll <maan@systemlinux.org>
Signed-off-by: NeilBrown <neilb@suse.de>
Currently raid0_run() always returns -ENOMEM on errors. This is
incorrect as running the array might fail for other reasons, for
example because not all component devices were available.
This patch changes create_strip_zones() so that it returns a proper
error code (either -ENOMEM or -EINVAL) rather than 1 on errors and
makes raid0_run(), its single caller, return that value instead
of -ENOMEM.
Signed-off-by: Andre Noll <maan@systemlinux.org>
Signed-off-by: NeilBrown <neilb@suse.de>
The "sector_shift" and "spacing" fields of struct raid0_private_data
were only used for the hash table lookups. So the removal of the
hash table allows get rid of these fields as well which simplifies
create_strip_zones() and raid0_run() quite a bit.
Signed-off-by: Andre Noll <maan@systemlinux.org>
Signed-off-by: NeilBrown <neilb@suse.de>
The raid0 hash table has become unused due to the changes in the
previous patch. This patch removes the hash table allocation and
setup code and kills the hash_table field of struct raid0_private_data.
Signed-off-by: Andre Noll <maan@systemlinux.org>
Signed-off-by: NeilBrown <neilb@suse.de>
1/ remove current_start. The same value is available in
zone->dev_start and storing it separately doesn't gain anything.
2/ rename curr_zone_start to curr_zone_end as we are now more
focused on the 'end' of each zone. We end up storing the
same number though - the old name was a little confusing
(and what does 'current' mean in this context anyway).
Signed-off-by: NeilBrown <neilb@suse.de>
The number of strip_zones of a raid0 array is bounded by the number of
drives in the array and is in fact much smaller for typical setups. For
example, any raid0 array containing identical disks will have only
a single strip_zone.
Therefore, the hash tables which are used for quickly finding the
strip_zone that holds a particular sector are of questionable value
and add quite a bit of unnecessary complexity.
This patch replaces the hash table lookup by equivalent code which
simply loops over all strip zones to find the zone that holds the
given sector.
In order to make this loop as fast as possible, the zone->start field
of struct strip_zone has been renamed to zone_end, and it now stores
the beginning of the next zone in sectors. This allows to save one
addition in the loop.
Subsequent cleanup patches will remove the hash table structure.
Signed-off-by: Andre Noll <maan@systemlinux.org>
Signed-off-by: NeilBrown <neilb@suse.de>
This adds support for misc devices to report their requested nodename to
userspace. It also updates a number of misc drivers to provide the
needed subdirectory and device name to be used for them.
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Jan Blunck <jblunck@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
* 'for-2.6.31' of git://git.kernel.dk/linux-2.6-block: (153 commits)
block: add request clone interface (v2)
floppy: fix hibernation
ramdisk: remove long-deprecated "ramdisk=" boot-time parameter
fs/bio.c: add missing __user annotation
block: prevent possible io_context->refcount overflow
Add serial number support for virtio_blk, V4a
block: Add missing bounce_pfn stacking and fix comments
Revert "block: Fix bounce limit setting in DM"
cciss: decode unit attention in SCSI error handling code
cciss: Remove no longer needed sendcmd reject processing code
cciss: change SCSI error handling routines to work with interrupts enabled.
cciss: separate error processing and command retrying code in sendcmd_withirq_core()
cciss: factor out fix target status processing code from sendcmd functions
cciss: simplify interface of sendcmd() and sendcmd_withirq()
cciss: factor out core of sendcmd_withirq() for use by SCSI error handling code
cciss: Use schedule_timeout_uninterruptible in SCSI error handling code
block: needs to set the residual length of a bidi request
Revert "block: implement blkdev_readpages"
block: Fix bounce limit setting in DM
Removed reference to non-existing file Documentation/PCI/PCI-DMA-mapping.txt
...
Manually fix conflicts with tracing updates in:
block/blk-sysfs.c
drivers/ide/ide-atapi.c
drivers/ide/ide-cd.c
drivers/ide/ide-floppy.c
drivers/ide/ide-tape.c
include/trace/events/block.h
kernel/trace/blktrace.c
* 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (244 commits)
Revert "x86, bts: reenable ptrace branch trace support"
tracing: do not translate event helper macros in print format
ftrace/documentation: fix typo in function grapher name
tracing/events: convert block trace points to TRACE_EVENT(), fix !CONFIG_BLOCK
tracing: add protection around module events unload
tracing: add trace_seq_vprint interface
tracing: fix the block trace points print size
tracing/events: convert block trace points to TRACE_EVENT()
ring-buffer: fix ret in rb_add_time_stamp
ring-buffer: pass in lockdep class key for reader_lock
tracing: add annotation to what type of stack trace is recorded
tracing: fix multiple use of __print_flags and __print_symbolic
tracing/events: fix output format of user stack
tracing/events: fix output format of kernel stack
tracing/trace_stack: fix the number of entries in the header
ring-buffer: discard timestamps that are at the start of the buffer
ring-buffer: try to discard unneeded timestamps
ring-buffer: fix bug in ring_buffer_discard_commit
ftrace: do not profile functions when disabled
tracing: make trace pipe recognize latency format flag
...
TRACE_EVENT is a more generic way to define tracepoints. Doing so adds
these new capabilities to this tracepoint:
- zero-copy and per-cpu splice() tracing
- binary tracing without printf overhead
- structured logging records exposed under /debug/tracing/events
- trace events embedded in function tracer output and other plugins
- user-defined, per tracepoint filter expressions
...
Cons:
- no dev_t info for the output of plug, unplug_timer and unplug_io events.
no dev_t info for getrq and sleeprq events if bio == NULL.
no dev_t info for rq_abort,...,rq_requeue events if rq->rq_disk == NULL.
This is mainly because we can't get the deivce from a request queue.
But this may change in the future.
- A packet command is converted to a string in TP_assign, not TP_print.
While blktrace do the convertion just before output.
Since pc requests should be rather rare, this is not a big issue.
- In blktrace, an event can have 2 different print formats, but a TRACE_EVENT
has a unique format, which means we have some unused data in a trace entry.
The overhead is minimized by using __dynamic_array() instead of __array().
I've benchmarked the ioctl blktrace vs the splice based TRACE_EVENT tracing:
dd dd + ioctl blktrace dd + TRACE_EVENT (splice)
1 7.36s, 42.7 MB/s 7.50s, 42.0 MB/s 7.41s, 42.5 MB/s
2 7.43s, 42.3 MB/s 7.48s, 42.1 MB/s 7.43s, 42.4 MB/s
3 7.38s, 42.6 MB/s 7.45s, 42.2 MB/s 7.41s, 42.5 MB/s
So the overhead of tracing is very small, and no regression when using
those trace events vs blktrace.
And the binary output of TRACE_EVENT is much smaller than blktrace:
# ls -l -h
-rw-r--r-- 1 root root 8.8M 06-09 13:24 sda.blktrace.0
-rw-r--r-- 1 root root 195K 06-09 13:24 sda.blktrace.1
-rw-r--r-- 1 root root 2.7M 06-09 13:25 trace_splice.out
Following are some comparisons between TRACE_EVENT and blktrace:
plug:
kjournald-480 [000] 303.084981: block_plug: [kjournald]
kjournald-480 [000] 303.084981: 8,0 P N [kjournald]
unplug_io:
kblockd/0-118 [000] 300.052973: block_unplug_io: [kblockd/0] 1
kblockd/0-118 [000] 300.052974: 8,0 U N [kblockd/0] 1
remap:
kjournald-480 [000] 303.085042: block_remap: 8,0 W 102736992 + 8 <- (8,8) 33384
kjournald-480 [000] 303.085043: 8,0 A W 102736992 + 8 <- (8,8) 33384
bio_backmerge:
kjournald-480 [000] 303.085086: block_bio_backmerge: 8,0 W 102737032 + 8 [kjournald]
kjournald-480 [000] 303.085086: 8,0 M W 102737032 + 8 [kjournald]
getrq:
kjournald-480 [000] 303.084974: block_getrq: 8,0 W 102736984 + 8 [kjournald]
kjournald-480 [000] 303.084975: 8,0 G W 102736984 + 8 [kjournald]
bash-2066 [001] 1072.953770: 8,0 G N [bash]
bash-2066 [001] 1072.953773: block_getrq: 0,0 N 0 + 0 [bash]
rq_complete:
konsole-2065 [001] 300.053184: block_rq_complete: 8,0 W () 103669040 + 16 [0]
konsole-2065 [001] 300.053191: 8,0 C W 103669040 + 16 [0]
ksoftirqd/1-7 [001] 1072.953811: 8,0 C N (5a 00 08 00 00 00 00 00 24 00) [0]
ksoftirqd/1-7 [001] 1072.953813: block_rq_complete: 0,0 N (5a 00 08 00 00 00 00 00 24 00) 0 + 0 [0]
rq_insert:
kjournald-480 [000] 303.084985: block_rq_insert: 8,0 W 0 () 102736984 + 8 [kjournald]
kjournald-480 [000] 303.084986: 8,0 I W 102736984 + 8 [kjournald]
Changelog from v2 -> v3:
- use the newly introduced __dynamic_array().
Changelog from v1 -> v2:
- use __string() instead of __array() to minimize the memory required
to store hex dump of rq->cmd().
- support large pc requests.
- add missing blk_fill_rwbs_rq() in block_rq_requeue TRACE_EVENT.
- some cleanups.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4A2DF669.5070905@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Now that we support changing the chunksize, we calculate
"reshape_sectors" to be the max of number of sectors in old
and new chunk size.
However there is one please where we still use 'chunksize'
rather than 'reshape_sectors'.
This causes a reshape that reduces the size of chunks to freeze.
Signed-off-by: NeilBrown <neilb@suse.de>
md has functionality to 'quiesce' and array so that all pending
IO completed and no new IO starts. This is used to achieve a
stable state before making internal changes.
Currently this quiescing applies equally to normal IO, resync
IO, and reshape IO.
However there is a problem with applying it to reshape IO.
Reshape can have multiple 'stripe_heads' that must be active together.
If the quiesce come between allocating the first and the last of
such a collection, then we deadlock, as the last will not be allocated
until the quiesce is lifted, the quiesce will not be lifted until the
first (which has been allocated) gets used, and that first cannot be
used until the last is allocated.
It is not necessary to inhibit reshape IO when a quiesce is
requested. Those places in the code that require a full quiesce will
ensure the reshape thread is not running at all.
So allow reshape requests to get access to new stripe_heads without
being blocked by a 'quiesce'.
This only affects in-place reshapes (i.e. where the array does not
grow or shrink) and these are only newly supported. So this patch is
not needed in earlier kernels.
Signed-off-by: NeilBrown <neilb@suse.de>
mddev->raid_disks can be changed and any time by a request from
user-space. It is a suggestion as to what number of raid_disks is
desired.
conf->raid_disks can only be changed by the raid5 module with suitable
locks in place. It is a statement as to the current number of
raid_disks.
There are two places where the latter should be used, but the former
is used. This can lead to a crash when reshaping an array.
This patch changes to mddev-> to conf->
Signed-off-by: NeilBrown <neilb@suse.de>
blk_queue_bounce_limit() is more than a wrapper about the request queue
limits.bounce_pfn variable. Introduce blk_queue_bounce_pfn() which can
be called by stacking drivers that wish to set the bounce limit
explicitly.
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
A recent patch to raid5.c use min on an int and a sector_t.
This isn't allowed.
So change it to min_t(sector_t,x,y).
Signed-off-by: NeilBrown <neilb@suse.de>
In order for the metadata to always be consistent, we mustn't updated
curr_resync_completed without also updating reshape_position.
The reshape code updates both at the same time. However since
commit 97e4f42d62
the common md_do_sync will sometimes update curr_resync_completed
but is not in a position to update reshape_position.
So if MD_RECOVERY_RESHAPE is set (indicating that a reshape is
happening, so reshape_position might change), don't update
curr_resync_completed in md_do_sync, leave it to the per-personality
reshape code.
Signed-off-by: NeilBrown <neilb@suse.de>
As sector_t in unsigned, we cannot afford to let 'safepos' etc go
negative.
So replace
a -= b;
by
a -= min(b,a);
Signed-off-by: NeilBrown <neilb@suse.de>
The md resync engine has a 'frozen' state which ensures that
no resync/recovery. This is used to avoid races.
Export this state through the 'sync_action' sysfs attribute
so that user-space can benefit and also avoid some races.
Signed-off-by: NeilBrown <neilb@suse.de>
The code for checking which bits in the bitmap can be cleared
has 2 problems:
1/ it repeatedly takes and drops a spinlock, where it would make
more sense to just hold on to it most of the time.
2/ it doesn't make use of some opportunities to skip large sections
of the bitmap
This patch fixes those. It will only affect CPU consumption, not
correctness.
Signed-off-by: NeilBrown <neilb@suse.de>
Instead of always returns EINVAL if anything goes wrong
when setting the array size, add the option of
E2BIG
if the size requested is too large. This makes it easier
for user-space to be sure what went wrong.
Signed-off-by: NeilBrown <neilb@suse.de>
We previously didn't update these fields when writing the metadata
because they could never change. They can now, so we better write
them.
v0.90 metadata always updated these fields.
Signed-off-by: NeilBrown <neilb@suse.de>
Convert all external users of queue limits to using wrapper functions
instead of poking the request queue variables directly.
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Until now we have had a 1:1 mapping between storage device physical
block size and the logical block sized used when addressing the device.
With SATA 4KB drives coming out that will no longer be the case. The
sector size will be 4KB but the logical block size will remain
512-bytes. Hence we need to distinguish between the physical block size
and the logical ditto.
This patch renames hardsect_size to logical_block_size.
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Merge reason: tracing/core was on a .30-rc1 base and was missing out on
on a handful of tracing fixes present in .30-rc5-almost.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
md maintains link in sys/mdXX/md/ to identify which device has
which role in the array. e.g.
rd2 -> dev-sda
indicates that the device with role '2' in the array is sda.
These links are only present when the array is active. They are
created immediately after ->run is called, and so should be removed
immediately after ->stop is called.
However they are currently removed a little bit later, and it is
possible for ->run to be called again, thus adding these links, before
they are removed.
So move the removal earlier so they are consistently only present when
the array is active.
Signed-off-by: NeilBrown <neilb@suse.de>
Being able to write 'clean' to an 'array_state' of an inactive array
to activate it in 'clean' mode is both unnecessary and inconvenient.
It is unnecessary because the same can be achieved by writing
'active'. This activates and array, but it still remains 'clean'
until the first write.
It is inconvenient because writing 'clean' is more often used to
cause an 'active' array to revert to 'clean' mode (thus blocking
any writes until a 'write-pending' is promoted to 'active').
Allowing 'clean' to both activate an array and mark an active array as
clean can lead to races: One program writes 'clean' to mark the
active array as clean at the same time as another program writes
'inactive' to deactivate (stop) and active array. Depending on which
writes first, the array could be deactivated and immediately
reactivated which isn't what was desired.
So just disable the use of 'clean' to activate an array.
This avoids a race that can be triggered with mdadm-3.0 and external
metadata, so it suitable for -stable.
Reported-by: Rafal Marszewski <rafal.marszewski@intel.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Cc: <stable@kernel.org>
Signed-off-by: NeilBrown <neilb@suse.de>
Two problems in status_resync.
1/ It still used Kilobytes as the basic block unit, while most code
now uses sectors uniformly.
2/ It doesn't allow for the possibility that max_sectors exceeds
the range of "unsigned long".
So
- change "max_blocks" to "max_sectors", and store sector numbers
in there and in 'resync'
- Make 'rt' a 'sector_t' so it can temporarily hold the number of
remaining sectors.
- use sector_div rather than normal division.
- change the magic '100' used to preserve precision to '32'.
+ making it a power of 2 makes division easier
+ it doesn't need to be as large as it was chosen when we averaged
speed over the entire run. Now we average speed over the last 30
seconds or so.
Reported-by: "Mario 'BitKoenig' Holbe" <Mario.Holbe@TU-Ilmenau.DE>
Signed-off-by: NeilBrown <neilb@suse.de>
If a write intent bitmap covers more than 2TB, we sometimes work with
values beyond 32bit, so these need to be sector_t. This patches
add the required casts to some unsigned longs that are being shifted
up.
This will affect any raid10 larger than 2TB, or any raid1/4/5/6 with
member devices that are larger than 2TB.
Signed-off-by: NeilBrown <neilb@suse.de>
Reported-by: "Mario 'BitKoenig' Holbe" <Mario.Holbe@TU-Ilmenau.DE>
Cc: stable@kernel.org
If we have a raid10 with multiple missing devices, and we recover just
one of these to a spare, then we risk (depending on the bitmap and
array chunk size) clearing bits of the bitmap for which recovery isn't
complete (because a device is still missing).
This can lead to a subsequent "re-add" being recovered without
any IO happening, which would result in loss of data.
This patch takes the safe approach of not clearing bitmap bits
if the array will still be degraded.
This patch is suitable for all active -stable kernels.
Cc: stable@kernel.org
Signed-off-by: NeilBrown <neilb@suse.de>
When md is loading a bitmap which it knows is out of date, it fills
each page with 1s and writes it back out again. However the
write_page call makes used of bitmap->file_pages and
bitmap->last_page_size which haven't been set correctly yet. So this
can sometimes fail.
Move the setting of file_pages and last_page_size to before the call
to write_page.
This bug can cause the assembly on an array to fail, thus making the
data inaccessible. Hence I think it is a suitable candidate for
-stable.
Cc: stable@kernel.org
Reported-by: Vojtech Pavlik <vojtech@suse.cz>
Signed-off-by: NeilBrown <neilb@suse.de>
* 'for-linus' of git://neil.brown.name/md:
md: support bitmaps on RAID10 arrays larger then 2 terabytes
md: update sync_completed and reshape_position even more often.
md: improve usefulness and accuracy of sysfs file md/sync_completed.
md: allow setting newly added device to 'in_sync' via sysfs.
md: tiny md.h cleanups
.. and other arrays with components larger than 2 terabytes.
We use a "long" rather than a "sector_t" in part of the bitmap
size calculations, which is sad.
Reported-by: "Mario 'BitKoenig' Holbe" <Mario.Holbe@TU-Ilmenau.DE>
Signed-off-by: NeilBrown <neilb@suse.de>
There are circumstances when a user-space process might need to
"oversee" a resync/reshape process. For example when doing an
in-place reshape of a raid5, it is prudent to take a backup of each
section before reshaping it as this is the only way to provide
safety against an unplanned shutdown (i.e. crash/power failure).
The sync_max sysfs value can be used to stop the resync from
advancing beyond a particular point.
So user-space can:
suspend IO to the first section and back it up
set 'sync_max' to the end of the section
wait for 'sync_completed' to reach that point
resume IO on the first section and move on to the next section.
However this process requires the kernel and user-space to run in
lock-step which could introduce unnecessary delays.
It would be better if a 'double buffered' approach could be used with
userspace and kernel space working on different sections with the
'next' section always ready when the 'current' section is finished.
One problem with implementing this is that sync_completed is only
guaranteed to be updated when the sync process reaches sync_max.
(it is updated on a time basis at other times, but it is hard to rely
on that). This defeats some of the double buffering.
With this patch, sync_completed (and reshape_position) get updated as
the current position approaches sync_max, so there is room for
userspace to advance sync_max early without losing updates.
To be precise, sync_completed is updated when the current sync
position reaches half way between the current value of sync_completed
and the value of sync_max. This will usually be a good time for user
space to update sync_max.
If sync_max does not get updated, the updates to sync_completed
(together with associated metadata updates) will occur at an
exponentially increasing frequency which will get unreasonably fast
(one update every page) immediately before the process hits sync_max
and stops. So the update rate will be unreasonably fast only for an
insignificant period of time.
Signed-off-by: NeilBrown <neilb@suse.de>
It's used by DM and MD and generally useful, so move the bio list
helpers into bio.h.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Alasdair G Kergon <agk@redhat.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
The sync_completed file reports how much of a resync (or recovery or
reshape) has been completed.
However due to the possibility of out-of-order completion of writes,
it is not certain to be accurate.
We have an internal value - mddev->curr_resync_completed - which is an
accurate value (though it might not always be quite so uptodate).
So:
- make curr_resync_completed be uptodate a little more often,
particularly when raid5 reshape updates status in the metadata
- report curr_resync_completed in the sysfs file
- allow poll/select to report all updates to md/sync_completed.
This makes sync_completed completed usable by any external metadata
handler that wants to record this status information in its metadata.
Signed-off-by: NeilBrown <neilb@suse.de>
When adding devices to an active array via sysfs, there is currently
no way to mark a device as 'in-sync' which is useful when
incrementally assembling an array.
So add that option.
Signed-off-by: NeilBrown <neilb@suse.de>
- update inclusion guard and make sure it covers the whole file
- remove superflous #ifdef CONFIG_BLOCK
- make sure all required headers are included so that new users aren't
required to include others before
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: NeilBrown <neilb@suse.de>
If the thread calling dm_kcopyd_copy is delayed due to scheduling inside
split_job/segment_complete and the subjobs complete before the loop in
split_job completes, the kcopyd callback could be invoked from the
thread that called dm_kcopyd_copy instead of the kcopyd workqueue.
dm_kcopyd_copy -> split_job -> segment_complete -> job->fn()
Snapshots depend on the fact that callbacks are called from the singlethreaded
kcopyd workqueue and expect that there is no racing between individual
callbacks. The racing between callbacks can lead to corruption of exception
store and it can also mean that exception store callbacks are called twice
for the same exception - a likely reason for crashes reported inside
pending_complete() / remove_exception().
This patch fixes two problems:
1. job->fn being called from the thread that submitted the job (see above).
- Fix: hand over the completion callback to the kcopyd thread.
2. job->fn(read_err, write_err, job->context); in segment_complete
reports the error of the last subjob, not the union of all errors.
- Fix: pass job->write_err to the callback to report all error bits
(it is done already in run_complete_job)
Cc: stable@kernel.org
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Use a variable in segment_complete() to point to the dm_kcopyd_client
struct and only release job->pages in run_complete_job() if any are
defined. These changes are needed by the next patch.
Cc: stable@kernel.org
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Barriers are submitted to a worker thread that issues them in-order.
The thread is modified so that when it sees a barrier request it waits
for all pending IO before the request then submits the barrier and
waits for it. (We must wait, otherwise it could be intermixed with
following requests.)
Errors from the barrier request are recorded in a per-device barrier_error
variable. There may be only one barrier request in progress at once.
For now, the barrier request is converted to a non-barrier request when
sending it to the underlying device.
This patch guarantees correct barrier behavior if the underlying device
doesn't perform write-back caching. The same requirement existed before
barriers were supported in dm.
Bottom layer barrier support (sending barriers by target drivers) and
handling devices with write-back caches will be done in further patches.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Remove queue_io return value and a loop in dm_request.
IO may be submitted to a worker thread with queue_io(). queue_io() sets
DMF_QUEUE_IO_TO_THREAD so that all further IO is queued for the thread. When
the thread finishes its work, it clears DMF_QUEUE_IO_TO_THREAD and from this
point on, requests are submitted from dm_request again. This will be used
for processing barriers.
Remove the loop in dm_request. queue_io() can submit I/Os to the worker thread
even if DMF_QUEUE_IO_TO_THREAD was not set.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Rework shutting down on suspend and document the associated rules.
Drop write lock in __split_and_process_bio to allow more processing
concurrency.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Refactor the code in dm_request().
Require the new DMF_BLOCK_FOR_SUSPEND flag on readahead bios we will
discard so we don't drop such bios while processing a barrier.
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
Split the DMF_BLOCK_IO flag into two.
DMF_BLOCK_IO_FOR_SUSPEND is set when I/O must be blocked while suspending a
device. DMF_QUEUE_IO_TO_THREAD is set when I/O must be queued to a
worker thread for later processing.
Signed-off-by: Alasdair G Kergon <agk@redhat.com>