During handshake communication, we also reconsider our device size,
using drbd_determine_dev_size(). Just in case we need to change the
offsets or layout of our on-disk metadata, we lock out application
and other meta data IO, and wait for the activity log to be "idle"
(no more referenced extents).
If this handshake happens just after a connection loss, with a fencing
policy of "resource-and-stonith", we have frozen IO.
If, additionally, the activity log was "starving" (too many incoming
random writes at that point in time), it won't become idle, ever,
because of the frozen IO, and this would be a lockup of the receiver
thread, and consquentially of DRBD.
Previous logic (re-)initialized with a special "empty" transaction
block, which required the activity log to fully drain first.
Instead, write out some standard activity log transactions.
Using lc_try_lock_for_transaction() instead of lc_try_lock() does not
care about pending activity log references, avoiding the 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@fb.com>
To be able to "force out" an activity log transaction,
even if there are no pending updates.
This will be used to relocate the on-disk activity log,
if the on-disk offsets have to be changed,
without the need to empty the activity log first.
While at it, move the definition,
so we can drop the forward declaration of a static helper.
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>
Now they follow the _endio naming sheme.
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>
size is always 4096,
page is always device->md_io.page.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
During resync, if we need to block some specific incoming write because
of active resync requests to that same range, we potentially caused
*all* new application writes (to "cold" activity log extents) to block
until this one request has been processed.
Improve the do_submit() logic to
* grab all incoming requests to some "incoming" list
* process this list
- move aside requests that are blocked by resync
- prepare activity log transactions,
- commit transactions and submit corresponding requests
- if there are remaining requests that only wait for
activity log extents to become free, stop the fast path
(mark activity log as "starving")
- iterate until no more requests are waiting for the activity log,
but all potentially remaining requests are only blocked by resync
* only then grab new incoming requests
That way, very busy IO on currently "hot" activity log extents cannot
starve scattered IO to "cold" extents. And blocked-by-resync requests
are processed once resync traffic on the affected region has ceased,
without blocking anything else.
The only blocking mode left is when we cannot start requests to "cold"
extents because all currently "hot" extents are actually used.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Background resynchronisation does some "side-stepping", or throttles
itself, if it detects application IO activity, and the current resync
rate estimate is above the configured "cmin-rate".
What was not detected: if there is no application IO,
because it blocks on activity log transactions.
Introduce a new atomic_t ap_actlog_cnt, tracking such blocked requests,
and count non-zero as application IO activity.
This counter is exposed at proc_details level 2 and above.
Also make sure to release the currently locked resync extent
if we side-step due to such voluntary throttling.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
For diagnostic purposes, track intent, start time
and latest submit time of meta data IO.
Move separate members from struct drbd_device
into the embeded struct drbd_md_io.
s/md_io_(page|in_use)/md_io.\1/
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
The last user was al_write_transaction, if called with "delegate",
and the last user to call it with "delegate = true" was the receiver
thread, which has no need to delegate, but can call it himself.
Finally drop the delegate parameter, drop the extra
w_al_write_transaction callback, and drop drbd_queue_work_front.
Do not (yet) change dequeue_work_item to dequeue_work_batch, though.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
The recent fix to put_ldev() (correct ordering of access to local_cnt
and state.disk; memory barrier in __drbd_set_state) guarantees
that the cleanup happens exactly once.
However it does not yet guarantee that the cleanup happens from worker
context, the last put_ldev() may still happen from atomic context,
which must not happen: blkdev_put() may sleep.
Fix this by scheduling the cleanup to the worker instead,
using a couple more bits in device->flags and a new helper,
drbd_device_post_work().
Generalized the "resync progress" work to cover these new work bits.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
For some reason we have assumed NOIDLE was implied
by one of the other flags we set. It is not (anymore?).
Explicitly set REQ_NOIDLE for synchronous meta data updates,
or we can seriously starve random writes when using CFQ.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
This fixes one recent regresion,
and one long existing bug.
The bug:
drbd_try_clear_on_disk_bm() assumed that all "count" bits have to be
accounted in the resync extent corresponding to the start sector.
Since we allow application requests to cross our "extent" boundaries,
this assumption is no longer true, resulting in possible misaccounting,
scary messages
("BAD! sector=12345s enr=6 rs_left=-7 rs_failed=0 count=58 cstate=..."),
and potentially, if the last bit to be cleared during resync would
reside in previously misaccounted resync extent, the resync would never
be recognized as finished, but would be "stalled" forever, even though
all blocks are in sync again and all bits have been cleared...
The regression was introduced by
drbd: get rid of atomic update on disk bitmap works
For an "empty" resync (rs_total == 0), we must not "finish" the
resync on the SyncSource before the SyncTarget knows all relevant
information (sync uuid). We need to wait for the full round-trip,
the SyncTarget will then explicitly notify us.
Also for normal, non-empty resyncs (rs_total > 0), the resync-finished
condition needs to be tested before the schedule() in wait_for_work, or
it is likely to be missed.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Just trigger the occasional lazy bitmap write-out during resync
from the central wait_for_work() helper.
Previously, during resync, bitmap pages would be written out separately,
synchronously, one at a time, at least 8 times each (every 512 bytes
worth of bitmap cleared).
Now we trigger "merge friendly" bulk write out of all cleared pages
every two seconds during resync, and once the resync is finished.
Most pages will be written out only once.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
When batching more updates to the activity log into single transactions,
we lost the ability for new requests to force themselves into the active
set: all preparation steps became non-blocking, and if all currently
hot extents keep busy, they could starve out new incoming requests
to cold extents for quite a while.
This can only happen if your IO backend accepts more IO operations per
average DRBD replication round trip time than you have al-extents
configured.
If we have incoming requests to cold extents,
at least do one blocking update per transaction.
In an artificial worst-case workload on SSD with an asynchronous 600 ms
replication link, with al-extents = 7 (the minimum we allow), and
concurrent full resynch, without this patch, some write requests have
been observed to be starved for 40 seconds.
With this patch, application observed a worst case latency of twice the
replication round trip time.
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 the receiver needs to serve a discard request on a queue that does
not announce to be discard cabable, it falls back to do synchronous
blkdev_issue_zeroout().
We expect only "reasonably" large (up to one activity log extent?)
discard requests.
We do this to not to not block the receiver for too long in this
fallback code path, and to not set/clear too many bits inside one
spinlock_irq_save() in drbd_set_in_sync/drbd_set_out_of_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@fb.com>
Before, application IO could pre-empt resync activity
for up to hardcoded 20 seconds per resync request.
A very busy server could throttle the effective resync bandwidth
down to one request per 20 seconds.
Now, we only let application IO pre-empt resync traffic
while the current resync rate estimate is above c-min-rate.
If you disable the c-min-rate throttle feature (set c-min-rate = 0),
application IO will no longer pre-empt resync traffic at all.
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>
drbd_device_work is a work item that has a reference to a device,
while drbd_work is a more generic work item that does not carry
a reference to a device.
All callbacks get a pointer to a drbd_work instance, those callbacks
that expect a drbd_device_work use the container_of macro to get it.
Signed-off-by: Andreas Gruenbacher <agruen@linbit.com>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
The implicit dependency on a variable inside the macro is problematic.
Signed-off-by: Andreas Gruenbacher <agruen@linbit.com>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
DRBD was using dev_err() and similar all over the code; instead of having to
write dev_err(disk_to_dev(device->vdisk), ...) to convert a drbd_device into a
kernel device, a DEV macro was used which implicitly references the device
variable. This is terrible; introduce separate drbd_err() and similar macros
with an explicit device parameter instead.
Signed-off-by: Andreas Gruenbacher <agruen@linbit.com>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
In a setup where a device (aka volume) can replicate to multiple peers and one
connection can be shared between multiple devices, we need separate objects to
represent devices on peer nodes and network connections.
As a first step to introduce multiple connections per device, give each
drbd_device object a single drbd_peer_device object which connects it to a
drbd_connection object.
Signed-off-by: Andreas Gruenbacher <agruen@linbit.com>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
sed -i -e 's:all_tconn:connections:g' -e 's:tconn:connection:g'
Signed-off-by: Andreas Gruenbacher <agruen@linbit.com>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
sed -i -e 's:\<drbd_conf\>:drbd_device:g'
Signed-off-by: Andreas Gruenbacher <agruen@linbit.com>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Mark the function drbd_al_begin_io_prepare() as static in
drbd/drbd_actlog.c because it is not used outside this file.
This eliminates the following warnings in drbd/drbd_actlog.c:
drivers/block/drbd/drbd_actlog.c:277:6: warning: no previous prototype for ‘drbd_al_begin_io_prepare’ [-Wmissing-prototypes]
Signed-off-by: Rashika Kheria <rashika.kheria@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Allow to change the AL layout with an resize operation. For that
the reisze command gets two new fields: al_stripes and al_stripe_size.
In order to make the operation crash save:
1) Lock out all IO and MD-IO
2) Write the super block with MDF_PRIMARY_IND clear
3) write the bitmap to the new location (all zeros, since
we allow only while connected)
4) Initialize the new AL-area
5) Write the super block with the restored MDF_PRIMARY_IND.
6) Unfreeze all IO
Since the AL-layout has no influence on the protocol, this operation
needs to be beforemed on both sides of a resource (if intended).
Signed-off-by: Andreas Gruenbacher <agruen@linbit.com>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Recently introduced al_begin_io_nonblock() was returning -EBUSY,
even when it should return -EWOULDBLOCK.
Impact:
A few spurious wake_up() calls in prepare_al_transaction_nonblock().
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>
Depending on current IO depth, try to consolidate as many updates
as possible into one activity log transaction.
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>
To make the code easier to follow,
use an explicit find_active_resync_extent(),
and add a "nonblock" parameter to _al_get().
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>
A request hitting an already "hot" extent should proceed right away,
even if some other requests need to wait for pending transactions.
Without that short-circuit, several simultaneous make_request contexts
race for committing the transaction, possibly penalizing the innocent.
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 used to calculate all on-disk meta data offsets, and then compare
the stored offsets, basically treating them as magic numbers.
Now with the activity log striping, the activity log size is no longer
fixed. We need to first read the super block, then base the activity
log and bitmap offsets on the stored offsets/al stripe settings.
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>
Introduce two new on-disk meta data fields: al_stripes and al_stripe_size_4k
The intended use case is activity log on RAID 0 or similar.
Logically consecutive transactions will advance their on-disk position
by al_stripe_size_4k 4kB (transaction sized) blocks.
Right now, these are still asserted to be the backward compatible
values al_stripes = 1, al_stripe_size_4k = 8 (which amounts to 32kB).
Also introduce a caching member for meta_dev_idx in the in-core
structure: even though it is initially passed in in the rcu-protected
disk_conf structure, it cannot change without a detach/attach cycle.
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>
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>
If the disk has failed already, there is no point trying to change the
bitmap. drbd_set_out_of_sync() already had this safeguard,
time to add it to drbd_set_in_sync() as well.
This also prevents some warning messages, like
FIXME asender in bm_change_bits_to, bitmap locked for 'detach' by worker
if our disk fails during resync, while there are some resync acks queued up.
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>
In 8.4, we may have bios spanning two activity log extents.
Fixup drbd_al_begin_io() and drbd_al_complete_io() to deal with zero sized bios.
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>
cherry-picked and adapted from drbd 9 devel branch
In 8.4, we don't distinguish between "resource work" and "connection
work" yet, we have one worker for both, as we still have only one connection.
We only ever used the "data.work",
no need to keep the "meta.work" around.
Move tconn->data.work to tconn->sender_work.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
By disabling al-updates one might increase performace. The price for
that is that in case a crashed primary (that had al-updates disabled)
is reintegraded, it will receive a full-resync instead of a bitmap
based resync.
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_try_clear_on_disk_bm() has a sanity check for the number of blocks
left to be resynced (rs_left) in the current resync extent.
If it detects a mismatch, it complains, and forces a disconnect using
drbd_force_state(mdev, NS(conn, C_DISCONNECTING));
Unfortunately, this may be called while holding the req_lock,
and drbd_force_state() want's to aquire that lock itself. Deadlock.
Don't force a disconnect, but fix up rs_left by recounting and
reassigning the number of dirty blocks in that extent.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Since version 4.6.1 gcc warns about variables that get
a value assigned, but which are never read later on.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Since we now apply the AL in user space onto the bitmap, the AL
is not active for the requests we want to reply.
For that a al_write_transaction() that might be called from
worker context became necessary.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Lars Ellenberg