We need to write the whole bitmap after we moved the meta data
due to an online resize operation.
With the support for one peta byte devices bitmap IO was optimized
to only write out touched pages. This optimization must be turned
off when writing the bitmap after an online resize.
This issue was introduced with drbd-8.3.10.
The impact of this bug is that after an online resize, the next
resync could become larger than expected.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Aborting local requests (not waiting for completion from the lower level
disk) is dangerous: if the master bio has been completed to upper
layers, data pages may be re-used for other things already.
If local IO is still pending and later completes,
this may cause crashes or corrupt unrelated data.
Only abort local IO if explicitly requested.
Intended use case is a lower level device that turned into a tarpit,
not completing io requests, not even doing error completion.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
BUG: unable to handle kernel NULL pointer dereference at (null)
...
[<d1e17561>] ? _drbd_bm_set_bits+0x151/0x240 [drbd]
[<d1e236f8>] ? receive_bitmap+0x4f8/0xbc0 [drbd]
This fixes an off-by-one error in the receive_bitmap() path,
if run-length encoded bitmap transfer is enabled.
If the bitmap is an exact multiple of PAGE_SIZE, which means the visible
capacity of the drbd device is an exact multiple of 128 MiB (for 4k page
size), and bitmap compression (use-rle) is enabled (which became default
with 8.4), and the very last bit is dirty and reported in an rle
comressed bitmap packet, we ended up trying to kmap_atomic a page pointer
that does not exist (bitmap->bm_pages[last index + 1]).
bug introduced by:
Date: Fri Jul 24 15:33:24 2009 +0200
set bits: optimize for complete last word, fix off-by-one-word corner case
made effective by:
Date: Thu Dec 16 00:32:38 2010 +0100
drbd: get rid of unused debug code
Long time ago, we had paranoia code in the bitmap that allocated one
extra word, assigned a magic value, and checked on every occasion that
the magic value was still unchanged.
That debug code is unused, the extra long word complicates code a bit.
Get rid of it.
No-one triggered this bug in the last few years, because a large subset
of our userbase is unaffected:
* typically the last few blocks of a device are not modified
frequently, and remain unset
* use-rle was disabled by default in drbd < 8.4
* those with slightly "odd" device sizes, or
* drbd internal meta data (which will skew the device size slightly,
thus makes it harder to have a bug relevant device size)
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Don't rely on availability of bios from the global fs_bio_set,
we should use our own bio_set for meta data IO.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
If bm_page_async_io is advised to use a new page for I/O
(BM_AIO_COPY_PAGES is set), it will get it from a mempool.
Once the mempool has to dip into its reserves the page is
not reinitialized, i.e. page->private contains garbage, which
will lead to various problems once the I/O completes (dereferences
of NULL pointers, the submitting thread getting stuck in D-state,
...).
Signed-off-by: Arne Redlich <arne.redlich@googlemail.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Symptom: messages similar to
"FIXME asender in bm_change_bits_to,
bitmap locked for 'write from resync_finished' by worker"
If a resync or verify is finished (or aborted), a full bitmap writeout
is triggered. If we have ongoing local IO, the bitmap may still change
during that writeout, pending and not yet processed acks may cause bits
to be cleared, while new writes may cause bits to be to be set.
To fix this, introduce the drbd_bm_write_copy_pages() variant.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
If the backing device is already frozen during attach, we failed
to recognize that. The current disk-timeout code works on top
of the drbd_request objects. During attach we do not allow IO
and therefore never generate a drbd_request object but block
before that in drbd_make_request().
This patch adds the timeout to all drbd_md_sync_page_io().
Before this patch we used to go from D_ATTACHING directly
to D_DISKLESS if IO failed during attach. We can no longer
do this since we have to stay in D_FAILED until all IO
ops issued to the backing device returned.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Bitmap IO may happend in the context of an application write,
in the generic block IO path. We need to use GFP_NOIO.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
If we have a good resync rate, we will frequently update the on-disk
bitmap, which, if not accounted for as resync io, may let an otherwise
idle device appear to be "busy", and cause us to throttle resync.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
The last commit, drbd: add missing spinlock to bitmap receive,
introduced a cond_resched_lock(), where the lock in question is taken
with irqs disabled.
As we must not schedule with IRQs disabled,
and cond_resched_lock_irq() does not exist, yet,
we re-aquire the spin_lock_irq() for each bitmap page processed in turn.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
During bitmap exchange, when using the RLE bitmap compression scheme,
we have a code path that can set the whole bitmap at once.
To avoid holding spin_lock_irq() for too long, we used to lock out other
bitmap modifications during bitmap exchange by other means, and then,
knowing we have exclusive access to the bitmap, modify it without
the spinlock, and with IRQs enabled.
Since we now allow local IO to continue, potentially setting additional
bits during the bitmap receive phase, this is no longer true, and we get
uncoordinated updates of bitmap members, causing bm_set to no longer
accurately reflect the total number of set bits.
To actually see this, you'd need to have a large bitmap, use RLE bitmap
compression, and have busy IO during sync handshake and bitmap exchange.
Fix this by taking the spin_lock_irq() in this code path as well, but
calling cond_resched_lock() after each page worth of bits processed.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Found these with the help of ispell -l.
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
In commit 95a0f10cdd ("drbd: store in-core bitmap little endian,
regardless of architecture") drbd had made the sane choice to use
little-endian bitmap functions everywhere. However, it used the
horrible old functions names from <asm-generic/bitops/le.h>, that were
never really meant to be exported.
In the meantime, things got cleaned up, and in commit c4945b9ed4
("asm-generic: rename generic little-endian bitops functions") we
renamed the LE bitops to something sane, exactly so that they could be
used in random code without people gouging their eyes out when seeing
the crazy jumble of letters that were the old internal names.
As a result the drbd thing merged cleanly (commit 8d49a77568: "Merge
branch 'for-2.6.39/drivers' of git://git.kernel.dk/linux-2.6-block"),
since there was no data conflict - but the end result obviously doesn't
actually compile.
Reported-and-tested-by: Ingo Molnar <mingo@elte.hu>
Cc: Jens Axboe <jaxboe@fusionio.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Now that we do no longer in-place endian-swap the bitmap, we allow
selected bitmap operations (testing bits, sometimes even settting bits)
during some bulk operations.
This caused us to hit a lot of FIXME asserts similar to
FIXME asender in drbd_bm_count_bits,
bitmap locked for 'write from resync_finished' by worker
Which now is nonsense: looking at the bitmap is perfectly legal
as long as it is not being resized.
This cosmetic patch defines some flags to describe expectations in finer
detail, so the asserts in e.g. bm_change_bits_to() can be skipped if
appropriate.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
I run into something declaring itself as "spinlock deadlock",
BUG: spinlock lockup on CPU#1, kjournald/27816, ffff88000ad6bca0
Pid: 27816, comm: kjournald Tainted: G W 2.6.34.6 #2
Call Trace:
<IRQ> [<ffffffff811ba0aa>] do_raw_spin_lock+0x11e/0x14d
[<ffffffff81340fde>] _raw_spin_lock_irqsave+0x6a/0x81
[<ffffffff8103b694>] ? __wake_up+0x22/0x50
[<ffffffff8103b694>] __wake_up+0x22/0x50
[<ffffffffa07ff661>] bm_async_io_complete+0x258/0x299 [drbd]
but the call traces do not fit at all,
all other cpus are cpu_idle.
I think it may be this race:
drbd_bm_write_page
wait_queue_head_t io_wait;
atomic_t in_flight;
bm_async_io
submit_bio
bm_async_io_complete
if (atomic_dec_and_test(in_flight))
wait_event(io_wait,
atomic_read(in_flight) == 0)
return
wake_up(io_wait)
The wake_up now accesses the wait_queue_head_t spinlock, which is no
longer valid, since the stack frame of drbd_bm_write_page has been
clobbered now.
Fix this by using struct completion, which does both the condition test
as well as the wake_up inside its spinlock, so this race cannot happen.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
We expect changes to a bitmap page in drbd_bm_write_page,
that's why we submit a copy page.
If a page changes during global writeout, that would be unexpected,
and reason to warn, though.
Also, often page writeout can be skipped (on activity log transactions
during normal operation, for example), no need to log that everytime.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Long time ago, we had paranoia code in the bitmap that allocated one
extra word, assigned a magic value, and checked on every occasion that
the magic value was still unchanged.
That debug code is unused, the extra long word complicates code a bit.
Get rid of it.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
When we set or clear bits in a bitmap page,
also set a flag in the page->private pointer.
This allows us to skip writes of unchanged pages.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Our on-disk bitmap is a little endian bitstream.
Up to now, we have stored the in-core copy of that in
native endian, applying byte order conversion when necessary.
Instead, keep the bitmap pages little endian, as they are read from disk,
and use the generic_*_le_bit family of functions.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
We trusted the on-disk bitmap to have unused bits cleared.
In case that is not true for whatever reason,
and we take a code path where the unused bits don't get cleared
elsewhere (bm_clear_surplus is not called), we may miscount the bits,
and get confused during resync, waiting for bits to get cleared that we
don't even use: the resync process would not terminate.
Fix this by masking out unused bits in __bm_count_bits.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
The FAULT_ACTIVE macro just wraps the drbd_insert_fault macro for no
apparent reason.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Code has been converted over to the new explicit on-stack plugging,
and delay users have been converted to use the new API for that.
So lets kill off the old plugging along with aops->sync_page().
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
When the complete device is marked as out of sync, we can disable
updates of the on disk AL. Currently AL updates are only disabled
if one uses the "invalidate-remote" command on an unconnected,
primary device, or when at attach time all bits in the bitmap are
set.
As of now, AL updated do not get disabled when a all bits becomes
set due to application writes to an unconnected DRBD device.
While this is a missing feature, it is not considered important,
and might get added later.
BTW, after initializing a "one legged" DRBD device
drbdadm create-md resX
drbdadm -- --force primary resX
AL updates also get disabled, until the first connect.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
The "surplus" bits of the old (smaller) bitmap must be clean
in case of online-grow without resync.
Note: Reverted 67ae8b80d4a116ab3b7094eb3723506b20c06dff as
well, since the lines added by this patch are redundant. The
bits get set by the bm_set_surplus(b) call before that.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
* 'for-linus' of git://git.kernel.dk/linux-2.6-block: (34 commits)
cfq-iosched: Fix the incorrect timeslice accounting with forced_dispatch
loop: Update mtime when writing using aops
block: expose the statistics in blkio.time and blkio.sectors for the root cgroup
backing-dev: Handle class_create() failure
Block: Fix block/elevator.c elevator_get() off-by-one error
drbd: lc_element_by_index() never returns NULL
cciss: unlock on error path
cfq-iosched: Do not merge queues of BE and IDLE classes
cfq-iosched: Add additional blktrace log messages in CFQ for easier debugging
i2o: Remove the dangerous kobj_to_i2o_device macro
block: remove 16 bytes of padding from struct request on 64bits
cfq-iosched: fix a kbuild regression
block: make CONFIG_BLK_CGROUP visible
Remove GENHD_FL_DRIVERFS
block: Export max number of segments and max segment size in sysfs
block: Finalize conversion of block limits functions
block: Fix overrun in lcm() and move it to lib
vfs: improve writeback_inodes_wb()
paride: fix off-by-one test
drbd: fix al-to-on-disk-bitmap for 4k logical_block_size
...
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
The bm_change semaphore is semantically a mutex. Convert it to a real
mutex.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
