Scenario:
Something (say, flush-147:0) is in drbd_al_begin_io,
holding a local_cnt, waiting for the resync to make progress.
Disk fails, worker in after_state_ch does drbd_rs_cancel_all,
then waits for local_cnt to drop to zero.
flush-147:0 is woken by drbd_rs_cancel_all, needs to write an AL
transaction, and queues that on the worker.
Deadlock.
Fix: do not wait in the worker, have put_ldev() trigger the
state change D_FAILED -> D_DISKLESS when necessary.
put_ldev() cannot do the state change directly, as it may or may not
already hold various spinlocks. We queue a short work instead.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
If it was an "empty" resync, the SyncSource may have already "finished"
the resync and rotated the UUIDs, before noticing the connection loss
(and generating a new uuid, if Primary, rotating again), while the
SyncTarget did not change its uuids at all, or only got to the previous
sync-uuid.
This would then again lead to a full sync on next handshake
(see also Bug #251).
Fix:
Use explicit resync finished notification even for empty resyncs,
do not finish an empty resync implicitly on the SyncSource.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
drbd commit 17c854fea474a5eb3cfa12e4fb019e46debbc4ec
drbd: receiving of big packets, for payloads between 64kByte and 4GByte
introduced a new on-the-wire packet header format. We must no longer
assume either format, but use the result of whatever drbd_recv_header
has decoded.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
If we release the page pointed to by md_io_tmpp, we need to zero out the
pointer, too, as that may be used later to decide whether we need to
allocate a new page again.
Impact: a previously freed page may be used and clobbered. Depending on
what that particular page is being used for meanwhile, this may result
in silent data corruption of completely unrelated things.
Only of concern on devices with logical_block_size != 512 byte,
if you re-attach after becoming diskless once.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
There are three ways to get IO suspended:
* Loss of any access to data
* Fence-peer-handler running
* User requested to suspend IO
Track those in different bits, so that one condition clearing its
state bit does not interfere with the other two conditions.
Only when the user resumes IO he overrules all three bits.
The fact is hidden from the user, he sees only a single suspend
bit.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
If a synctarget lost connection while being WFSyncUUID,
due to "state sanitizing", the attempted state change to SyncTarget
looked like an "invalidate" to after_state_ch() later,
thus caused a full sync on next handshake (Bug #318).
drbd0: PingAck did not arrive in time.
drbd0: peer( Primary -> Unknown ) conn( WFSyncUUID -> NetworkFailure ) pdsk( UpToDate -> DUnknown )
from : { cs:NetworkFailure ro:Secondary/Unknown ds:UpToDate/DUnknown r--- }
to : { cs:SyncTarget ro:Secondary/Unknown ds:Inconsistent/DUnknown r--- }
after sanizising, resulted in
state: { cs:NetworkFailure ro:Secondary/Unknown ds:Inconsistent/DUnknown r--- }
drbd0: disk( UpToDate -> Inconsistent )
Fix:
don't mask state transition errors in "sanitizing",
so the requested state change to SyncTarget fails,
instead of being implicitly "remaped" to invalidate.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
addendum to baa33ae4eaa4477b60af7c434c0ddd1d182c1ae7
The race:
drbd_md_sync()
if (!test_and_clear_bit(MD_DIRTY, &mdev->flags))
return;
==> RACE with drbd_md_mark_dirty() rearming the timer.
del_timer(&mdev->md_sync_timer);
Fixed by moving the del_timer before the test_and_clear_bit.
Additionally only rearm the timer in drbd_md_mark_dirty, if MD_DIRTY was
not already set, reduce the grace period from five to one second, and
add an ifdef'ed debuging aid to find code paths missing an explicit
drbd_md_sync, if any, as those are the only relevant ones for this race.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
The actual race happened int the drbd_start_resync() function. Where
drbd_resync_finished() -> __drbd_set_state() set STOP_SYNC_TIMER and
armed the timer.
If the timer fired before execution reaches the mod_timer statement
at the end of drbd_start_resync() the latter would cause an
unexpected call to w_make_resync_request().
Removed the STOP_SYNC_TIMER bit, and base it on the connection state.
The STOP_SYNC_TIMER bit probably originates probably the time before
the state engine.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.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>
Now we have multiple BIOs per ee, packets with a 32 bit length field,
it gets time to use these goodies.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
We now track the data rate of locally submitted resync related requests,
and can thus detect non-resync activity on the lower level device.
If the current sync rate is above c-min-rate, and the lower level device
appears to be busy, we throttle the resyncer.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
The current resync speed as displayed in /proc/drbd fluctuates a lot.
Using an array of rolling marks makes this calculation much more stable.
We used to have this (a long time ago with 0.7), but it got lost somehow.
If "stalled", do not discard the rest of the information, just add a
" (stalled)" tag to the progress line.
This patch also shortens a spinlock critical section somewhat, and
reduces the number of atomic operations in put_ldev.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
We may not free tl_hash when IO is suspended, since we can not wait
until ap_bio_cnt reaches zero.
We can do this after susp reched 0, since then tl_clear was called
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
After disconnect (most likely mdev->net_cnt == 0) and we are
still in an unstable state (!drbd_state_is_stable()). When we
get an IO request in drbd_get_max_buffers() (called from
__inc_ap_bio_cond(), called from inc_ap_bio()) we wake up
misc_wait. Misc_wait is also used in inc_ap_bio() to sleep
until the outcome of __inc_ap_bio_cond() changes. => Busy loop!
Solution: Have a dedicated wait queue for get_net_conf() and
put_net_conf().
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
When a fencing policy of "resource-and-stonith" is configured,
and DRBD looses connection to it's peer, we can delay the
creation of a new current-UUID until IO gets thawed.
That allows one to deploy fence-peer handlers that actually
commit suicide on the machine they get started.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
State transitions in the space of non-allowed states used
to be very noisy. Reduce that, since that has little value
for the majority of the user base.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
When no data is accessible (no connection to the peer, nor a local disk)
allow the user to select to freeze all IO operations instead of getting
IO errors.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
If IO was frozen for a temporal network outage, resend the
content of the transfer-log into the newly established connection.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
With that the drbd_fail_pending_reads() function becomes obsolete.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
The block device drivers have all gained new lock_kernel
calls from a recent pushdown, and some of the drivers
were already using the BKL before.
This turns the BKL into a set of per-driver mutexes.
Still need to check whether this is safe to do.
file=$1
name=$2
if grep -q lock_kernel ${file} ; then
if grep -q 'include.*linux.mutex.h' ${file} ; then
sed -i '/include.*<linux\/smp_lock.h>/d' ${file}
else
sed -i 's/include.*<linux\/smp_lock.h>.*$/include <linux\/mutex.h>/g' ${file}
fi
sed -i ${file} \
-e "/^#include.*linux.mutex.h/,$ {
1,/^\(static\|int\|long\)/ {
/^\(static\|int\|long\)/istatic DEFINE_MUTEX(${name}_mutex);
} }" \
-e "s/\(un\)*lock_kernel\>[ ]*()/mutex_\1lock(\&${name}_mutex)/g" \
-e '/[ ]*cycle_kernel_lock();/d'
else
sed -i -e '/include.*\<smp_lock.h\>/d' ${file} \
-e '/cycle_kernel_lock()/d'
fi
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
It was a now abandoned attempt to throttle resync bandwidth
based on the delay it causes on the bulk data socket.
It has no userbase yet, and has been disabled by
9173465ccb51c09cc3102a10af93e9f469a0af6f already.
This removes the now unused code.
The basic feature, namely using up "idle" bandwith
of network and disk IO subsystem, with minimal impact
to application IO, is being reimplemented differently.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
The open and release block_device_operations are currently
called with the BKL held. In order to change that, we must
first make sure that all drivers that currently rely
on this have no regressions.
This blindly pushes the BKL into all .open and .release
operations for all block drivers to prepare for the
next step. The drivers can subsequently replace the BKL
with their own locks or remove it completely when it can
be shown that it is not needed.
The functions blkdev_get and blkdev_put are the only
remaining users of the big kernel lock in the block
layer, besides a few uses in the ioctl code, none
of which need to serialize with blkdev_{get,put}.
Most of these two functions is also under the protection
of bdev->bd_mutex, including the actual calls to
->open and ->release, and the common code does not
access any global data structures that need the BKL.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Remove the current bio flags and reuse the request flags for the bio, too.
This allows to more easily trace the type of I/O from the filesystem
down to the block driver. There were two flags in the bio that were
missing in the requests: BIO_RW_UNPLUG and BIO_RW_AHEAD. Also I've
renamed two request flags that had a superflous RW in them.
Note that the flags are in bio.h despite having the REQ_ name - as
blkdev.h includes bio.h that is the only way to go for now.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
This was a very hard to trigger race condition.
If we got a state packet from the peer, after drbd_nl_disk() has
already changed the disk state to D_NEGOTIATING but
after_state_ch() was not yet run by the worker, then receive_state()
might called drbd_sync_handshake(), which in turn crashed
when accessing p_uuid.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
using the global printk_ratelimit() may mask other messages.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
It seems to improve performance if we allow the "p_data" header in its
own frame (no MSG_MORE), but sendpage all but the last page with MSG_MORE.
This is also in preparation of a later zero copy receive implementation.
Suggested by Eduard.Guzovsky@stratus.com on drbd-dev.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
The late-UUID writing is delayed until the next release.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Got introduces with
commit 0c3f34516e
Author: Philipp Reisner <philipp.reisner@linbit.com>
Date: Mon May 17 16:10:43 2010 +0200
drbd: Create new current UUID as late as possible
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
The choice was to either delay creation of the new UUID until
IO got thawed or to delay it until the first IO request.
Both are correct, the later is more friendly to users of
dual-primary setups, that actually only write on one side.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
This should allow for better performance if the lower level IO stack
of the peers differs in limits exposed either via the queue,
or via some merge_bvec_fn.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
* Only send delay_probes with protocol 93 or newer
* drbd_send_delay_probes() is called only from worker context,
no atomic_t needed for delay_seq
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
* Mention P_DELAY_PROBE in the packet naming array
* Do not corrupt the mdev->data.work list in case the timer goes
off before delay_probe_work got handled by the worker
* Do not mod_timer() twice for a single delay_probe pair
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Delay_probes are new packets in the DRBD protocol, which allow
DRBD to know the current delay packets have on the data socket.
(relative to the meta data socket)
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
In case both nodes are "inconsistent", invalidate would
have started a resync anyways, without a chance to ever
succeed, just filling the logs with warning messages.
Simply disallow that state change,
re-using the SS_NO_UP_TO_DATE_DISK return value.
This also changes the corresponding error string to
"Need access to UpToDate Data" -- I found the
"Refusing to be Primary without at least one UpToDate disk"
answer misleading in some situations anyways.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
commit e4f925e12e
Author: Philipp Reisner <philipp.reisner@linbit.com>
Date: Wed Mar 17 14:18:41 2010 +0100
drbd: Do not upgrade state to Outdated if already Inconsistent
prevented the necessary state transition for attaching while connected
(Diskless -> Consistent respectively Outdated).
This is the fix for the fix.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
There was a race condition:
In a situation with a SyncSource+Primary and a SyncTarget+Secondary node,
and a resync dependency to some other device. After both nodes decided
to do the resync, the other device finishes its resync process.
At that time SyncSource already sent the P_SYNC_UUID packet, and
already updated its peer disk state to Inconsistent.
The SyncTarget node waits for the P_SYNC_UUID and sends a state packet
to report the resync dependency change. That packet still carries
a disk state of Outdated.
Impact:
If application writes come in, during that time on the Primary node,
those do not get replicated, and the out-of-sync counter gets increased.
=> The completion of resync is not detected on the primary node.
=> stalled.
Those blocks get resync'ed with the next resync, since the are get
marked as out-of-sync in the bitmap.
In order to fix this, we filter out that wrong state change in the
sanitize_state() function.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
To document that we know about deprecation of proc_create,
even though we are not affected, as we don't use the ->data member,
open code proc_create_data(..., NULL);
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
We leak memory if "--dry-run" is not supported by the peer.
Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Fixes a race and potential kernel panic if e.g. the worker was just
about to send a few P_RS_IS_IN_SYNC via the meta socket for checksum
based resync, while the receiver destroys the sockets in
drbd_disconnect.
To make sure no-one is using the meta socket,
it is not enough to stop the asender...
Grab the meta socket mutex before destroying it.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
blk_queue_make_request() internally calls blk_set_default_limits(),
so calling blk_queue_max_segment_size() before is useless.
Ergo: move the call to blk_queue_max_segment_size() down a few lines.
Impact:
If, after a fresh modprobe, you first connect a Diskless drbd,
then attach, this could result in a DRBD Protocol Error at first.
The next connection attempt would then succeeded.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
In D_DISKLESS we do not hand out any new references to ldev (local_cnt)
therefore waiting until all previously handed out refereces got returned
is sufficient before actually freeing mdev->ldev.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
rsp->count is unsigned so the test does not work.
Signed-off-by: Roel Kluin <roel.kluin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
When IO gets frozen due to a broken fence-peer script, the user
should be able to thaw IO by the resume-io command.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
It is force-included on the gcc command line since at least 2.6.15.
Explicit include lines seem to break compilation now in certain configurations.
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
