Add a comment about our meta data layout variants,
and rename a few defines (e.g. MD_RESERVED_SECT -> MD_128MB_SECT)
to make it clear that they are short hand for fixed constants,
and not arbitrarily to be redefined as one may see fit.
Properly pad struct meta_data_on_disk to 4kB,
and initialize to zero not only the first 512 Byte,
but all of it in drbd_md_sync().
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Use copy_highpage() to copy from one page to another.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
The intention of force-detach is to be able to deal with a completely
unresponsive lower level IO stack, which does not even deliver error
completions anymore, but no completion at all.
In all other cases, we must still wait for the meta data IO completion.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
The former comment arguing that GFP_KERNEL was good enough was wrong: it
did not take resize into account at all, and assumed the only path
leading here was the normal attach on a still secondary device, so no
deadlock would be possible.
Both resize on a Primary, or attach on a diskless Primary,
could potentially deadlock.
drbd_bm_resize() is called while IO to the respective device is
suspended, so we must use GFP_NOIO to avoid potential deadlock.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
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>
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>
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>
* drbd-8.3:
documentation: Documented detach's --force and disk's --disk-timeout
drbd: Implemented the disk-timeout option
drbd: Force flag for the detach operation
drbd: Allow new IOs while the local disk in in FAILED state
drbd: Bitmap IO functions can not return prematurely if the disk breaks
drbd: Added a kref to bm_aio_ctx
drbd: Hold a reference to ldev while doing meta-data IO
drbd: Keep a reference to the bio until the completion handler finished
drbd: Implemented wait_until_done_or_disk_failure()
drbd: Replaced md_io_mutex by an atomic: md_io_in_use
drbd: moved md_io into mdev
drbd: Immediately allow completion of IOs, that wait for IO completions on a failed disk
drbd: Keep a reference to barrier acked requests
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
The intention of force-detach is to be able to deal with a completely
unresponsive lower level IO stack, which does not even deliver error
completions anymore, but no completion at all.
In all other cases, we must still wait for the meta data IO completion.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The former comment arguing that GFP_KERNEL was good enough was wrong: it
did not take resize into account at all, and assumed the only path
leading here was the normal attach on a still secondary device, so no
deadlock would be possible.
Both resize on a Primary, or attach on a diskless Primary,
could potentially deadlock.
drbd_bm_resize() is called while IO to the respective device is
suspended, so we must use GFP_NOIO to avoid potential deadlock.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
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>
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>
Summary log messages meant for global bitmap IO
should not be printed for bitmap IO caused by
activity log transactions.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
We are about to allow several changes to the active set in one activity
log transaction. We have to write out the corresponding bitmap pages as
well, if changed.
Introduce drbd_bm_mark_for_writeout(), then re-use the existing bitmap
writeout path to submit all marked pages in one go.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Some open-coded clear_bit(); smp_mb__after_clear_bit();
should in fact have been smp_mb__before_clear_bit(); clear_bit();
Instead, use clear_bit_unlock() to annotate the intention,
and have it do the right thing.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Remove the file name and line number from the syslog messages generated:
we have no duplicate function names, and no function contains the same
assertion more than once.
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>
