Race:
drbd_adm_attach() | async drbd_md_endio()
|
device->ldev is still NULL. |
|
drbd_md_read( |
.endio = drbd_md_endio; |
submit; |
.... |
wait for done == 1; | done = 1;
); | wake_up();
.. lot of other stuff, |
.. includeing taking and |
...giving up locks, |
.. doing further IO, |
.. stuff that takes "some time" |
| while in this context,
| this is the next statement.
| which means this context was scheduled
.. only then, finally, | away for "some time".
device->ldev = nbc; |
| if (device->ldev)
| put_ldev()
Unlikely, but possible. I was able to provoke it "reliably"
by adding an mdelay(500); after the wake_up().
Fixed by moving the if (!NULL) put_ldev() before done = 1;
Impact of the bug was that the resulting refcount imbalance
could lead to premature destruction of the object, potentially
causing a NULL pointer dereference during a subsequent detach.
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 get a few warnings when building kernel with W=1:
drbd/drbd_receiver.c:1224:6: warning: no previous prototype for 'one_flush_endio' [-Wmissing-prototypes]
drbd/drbd_req.c:1450:6: warning: no previous prototype for 'send_and_submit_pending' [-Wmissing-prototypes]
drbd/drbd_main.c:924:6: warning: no previous prototype for 'assign_p_sizes_qlim' [-Wmissing-prototypes]
....
In fact, these functions are only used in the file in which they are
declared and don't need a declaration, but can be made static.
So this patch marks these functions with 'static'.
Signed-off-by: Baoyou Xie <baoyou.xie@linaro.org>
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>
In protocol != C, we forgot to send the P_NEG_ACK for failing writes.
Once we no longer submit to local disk, because we already "detached",
due to the typical "on-io-error detach;" config setting,
we already send the neg acks right away.
Only those requests that have been submitted,
and have been error-completed by the local disk,
would forget to send the neg-ack,
and only in asynchronous replication (protocol != C).
Unless this happened during resync,
where we already always send acks, regardless of protocol.
The primary side needs the P_NEG_ACK in order to mark
the affected block(s) for resync in its out-of-sync bitmap.
If the blocks in question are not re-written again,
we may miss to resync them later, causing data inconsistencies.
This patch will always send the neg-acks, and also at least try to
persist the out-of-sync status on the local node already.
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>
Recently, drbd_recv_header() was changed to potentially
implicitly "unplug" the backend device(s), in case there
is currently nothing to receive.
Be more explicit about it: re-introduce the original drbd_recv_header(),
and introduce a new drbd_recv_header_maybe_unplug() for use by the
receiver "main loop".
Using explicit plugging via blk_start_plug(); blk_finish_plug();
really helps the io-scheduler of the backend with merging requests.
Wrap the receiver "main loop" with such a plug.
Also catch unplug events on the Primary,
and try to propagate.
This is performance relevant. Without this, if the receiving side does
not merge requests, number of IOPS on the peer can me significantly
higher than IOPS on the Primary, and can easily become the bottleneck.
Together, both changes should help to reduce the number of IOPS
as seen on the backend of the receiving side, by increasing
the chance of merging mergable requests, without trading latency
for more throughput.
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>
This way we don't need a block_device structure to submit I/O. The
block_device has different life time rules from the gendisk and
request_queue and is usually only available when the block device node
is open. Other callers need to explicitly create one (e.g. the lightnvm
passthrough code, or the new nvme multipathing code).
For the actual I/O path all that we need is the gendisk, which exists
once per block device. But given that the block layer also does
partition remapping we additionally need a partition index, which is
used for said remapping in generic_make_request.
Note that all the block drivers generally want request_queue or
sometimes the gendisk, so this removes a layer of indirection all
over the stack.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Replace bi_error with a new bi_status to allow for a clear conversion.
Note that device mapper overloaded bi_error with a private value, which
we'll have to keep arround at least for now and thus propagate to a
proper blk_status_t value.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
It seems like DRBD assumes its on the wire TRIM request always zeroes data.
Use that fact to implement REQ_OP_WRITE_ZEROES.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Since commit 63a4cc2486, bio->bi_rw contains flags in the lower
portion and the op code in the higher portions. This means that
old code that relies on manually setting bi_rw is most likely
going to be broken. Instead of letting that brokeness linger,
rename the member, to force old and out-of-tree code to break
at compile time instead of at runtime.
No intended functional changes in this commit.
Signed-off-by: Jens Axboe <axboe@fb.com>
These two are confusing leftover of the old world order, combining
values of the REQ_OP_ and REQ_ namespaces. For callers that don't
special case we mostly just replace bi_rw with bio_data_dir or
op_is_write, except for the few cases where a switch over the REQ_OP_
values makes more sense. Any check for READA is replaced with an
explicit check for REQ_RAHEAD. Also remove the READA alias for
REQ_RAHEAD.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This contains various cosmetic fixes ranging from simple typos to
const-ifying, and using booleans properly.
Original commit messages from Fabian's patch set:
drbd: debugfs: constify drbd_version_fops
drbd: use seq_put instead of seq_print where possible
drbd: include linux/uaccess.h instead of asm/uaccess.h
drbd: use const char * const for drbd strings
drbd: kerneldoc warning fix in w_e_end_data_req()
drbd: use unsigned for one bit fields
drbd: use bool for peer is_ states
drbd: fix typo
drbd: use | for bitmask combination
drbd: use true/false for bool
drbd: fix drbd_bm_init() comments
drbd: introduce peer state union
drbd: fix maybe_pull_ahead() locking comments
drbd: use bool for growing
drbd: remove redundant declarations
drbd: replace if/BUG by BUG_ON
Signed-off-by: Fabian Frederick <fabf@skynet.be>
Signed-off-by: Roland Kammerer <roland.kammerer@linbit.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
We will support WRITE_SAME, if
* all peers support WRITE_SAME (both in kernel and DRBD version),
* all peer devices support WRITE_SAME
* logical_block_size is identical on all peers.
We may at some point introduce a fallback on the receiving side
for devices/kernels that do not support WRITE_SAME,
by open-coding a submit loop. But not yet.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
When resync is finished, we already call the "after-resync-target"
handler (on the former sync target, obviously), once per volume.
Paired with the before-resync-target handler, you can create snapshots,
before the resync causes the volumes to become inconsistent,
and discard those snapshots again, once they are no longer needed.
It was also overloaded to be paired with the "fence-peer" handler,
to "unfence" once the volumes are up-to-date and known good.
This has some disadvantages, though: we call "fence-peer" for the whole
connection (once for the group of volumes), but would call unfence as
side-effect of after-resync-target once for each volume.
Also, we fence on a (current, or about to become) Primary,
which will later become the sync-source.
Calling unfence only as a side effect of the after-resync-target
handler opens a race window, between a new fence on the Primary
(SyncTarget) and the unfence on the SyncTarget, which is difficult to
close without some kind of "cluster wide lock" in those handlers.
We would not need those handlers if we could still communicate.
Which makes trying to aquire a cluster wide lock from those handlers
seem like a very bad idea.
This introduces the "unfence-peer" handler, which will be called
per connection (once for the group of volumes), just like the fence
handler, only once all volumes are back in sync, and on the SyncSource.
Which is expected to be the node that previously called "fence", the
node that is currently allowed to be Primary, and thus the only node
that could trigger a new "fence" that could race with this unfence.
Which makes us not need any cluster wide synchronization here,
serializing two scripts running on the same node is trivial.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
If thinly provisioned volumes are used, during a resync the sync source
tries to find out if a block is deallocated. If it is deallocated, then
the resync target uses block_dev_issue_zeroout() on the range in
question.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
If during resync we read only zeroes for a range of sectors assume
that these secotors can be discarded on the sync target node.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Separate the op from the rq_flag_bits and have drbd
set/get the bio using bio_set_op_attrs/bio_op.
Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This patch replaces uses of the long obsolete hash interface with
either shash (for non-SG users) or ahash.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
lsblk should be able to pick up stacking device driver relations
involving DRBD conveniently.
Even though upstream kernel since 2011 says
"DON'T USE THIS UNLESS YOU'RE ALREADY USING IT."
a new user has been added since (bcache),
which sets the precedences for us to use it as well.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
The intention is to reduce CPU utilization. Recent measurements
unveiled that the current performance bottleneck is CPU utilization
on the receiving node. The asender thread became CPU limited.
One of the main points is to eliminate the idr_for_each_entry() loop
from the sending acks code path.
One exception in that is sending back ping_acks. These stay
in the ack-receiver thread. Otherwise the logic becomes too
complicated for no added value.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
The only way to make DRBD intentionally call panic is to
set a disk timeout, have that trigger, "abort" some request and complete
to upper layers, then have the backend IO subsystem later complete these
requests successfully regardless.
As the attached IO pages have been recycled for other purposes
meanwhile, this will cause unexpected random memory changes.
To prevent corruption, we rather panic in that case.
Make it obvious from stack traces that this was the case by introducing
drbd_panic_after_delayed_completion_of_aborted_request().
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Instead of using a rwlock for synchronizing state changes across
resources, take the request locks of all resources for global state
changes. Use resources_mutex to serialize global state changes.
This means that taking the request lock of a resource is now enough to
prevent changes of that resource. (Previously, a read lock on the
global state lock was needed as well.)
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Currently we have two different ways to signal an I/O error on a BIO:
(1) by clearing the BIO_UPTODATE flag
(2) by returning a Linux errno value to the bi_end_io callback
The first one has the drawback of only communicating a single possible
error (-EIO), and the second one has the drawback of not beeing persistent
when bios are queued up, and are not passed along from child to parent
bio in the ever more popular chaining scenario. Having both mechanisms
available has the additional drawback of utterly confusing driver authors
and introducing bugs where various I/O submitters only deal with one of
them, and the others have to add boilerplate code to deal with both kinds
of error returns.
So add a new bi_error field to store an errno value directly in struct
bio and remove the existing mechanisms to clean all this up.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Kees Cook
Roland Kammerer
Lars Ellenberg
Baoyou Xie
Christoph Hellwig
Ingo Molnar
Jens Axboe
Fabian Frederick
Lars Ellenberg
Philipp Reisner
Mike Christie
Herbert Xu
Andreas Gruenbacher