Pull block driver updates from Jens Axboe:
"This branch also contains core changes. I've come to the conclusion
that from 4.9 and forward, I'll be doing just a single branch. We
often have dependencies between core and drivers, and it's hard to
always split them up appropriately without pulling core into drivers
when that happens.
That said, this contains:
- separate secure erase type for the core block layer, from
Christoph.
- set of discard fixes, from Christoph.
- bio shrinking fixes from Christoph, as a followup up to the
op/flags change in the core branch.
- map and append request fixes from Christoph.
- NVMeF (NVMe over Fabrics) code from Christoph. This is pretty
exciting!
- nvme-loop fixes from Arnd.
- removal of ->driverfs_dev from Dan, after providing a
device_add_disk() helper.
- bcache fixes from Bhaktipriya and Yijing.
- cdrom subchannel read fix from Vchannaiah.
- set of lightnvm updates from Wenwei, Matias, Johannes, and Javier.
- set of drbd updates and fixes from Fabian, Lars, and Philipp.
- mg_disk error path fix from Bart.
- user notification for failed device add for loop, from Minfei.
- NVMe in general:
+ NVMe delay quirk from Guilherme.
+ SR-IOV support and command retry limits from Keith.
+ fix for memory-less NUMA node from Masayoshi.
+ use UINT_MAX for discard sectors, from Minfei.
+ cancel IO fixes from Ming.
+ don't allocate unused major, from Neil.
+ error code fixup from Dan.
+ use constants for PSDT/FUSE from James.
+ variable init fix from Jay.
+ fabrics fixes from Ming, Sagi, and Wei.
+ various fixes"
* 'for-4.8/drivers' of git://git.kernel.dk/linux-block: (115 commits)
nvme/pci: Provide SR-IOV support
nvme: initialize variable before logical OR'ing it
block: unexport various bio mapping helpers
scsi/osd: open code blk_make_request
target: stop using blk_make_request
block: simplify and export blk_rq_append_bio
block: ensure bios return from blk_get_request are properly initialized
virtio_blk: use blk_rq_map_kern
memstick: don't allow REQ_TYPE_BLOCK_PC requests
block: shrink bio size again
block: simplify and cleanup bvec pool handling
block: get rid of bio_rw and READA
block: don't ignore -EOPNOTSUPP blkdev_issue_write_same
block: introduce BLKDEV_DISCARD_ZERO to fix zeroout
NVMe: don't allocate unused nvme_major
nvme: avoid crashes when node 0 is memoryless node.
nvme: Limit command retries
loop: Make user notify for adding loop device failed
nvme-loop: fix nvme-loop Kconfig dependencies
nvmet: fix return value check in nvmet_subsys_alloc()
...
Pull core block updates from Jens Axboe:
- the big change is the cleanup from Mike Christie, cleaning up our
uses of command types and modified flags. This is what will throw
some merge conflicts
- regression fix for the above for btrfs, from Vincent
- following up to the above, better packing of struct request from
Christoph
- a 2038 fix for blktrace from Arnd
- a few trivial/spelling fixes from Bart Van Assche
- a front merge check fix from Damien, which could cause issues on
SMR drives
- Atari partition fix from Gabriel
- convert cfq to highres timers, since jiffies isn't granular enough
for some devices these days. From Jan and Jeff
- CFQ priority boost fix idle classes, from me
- cleanup series from Ming, improving our bio/bvec iteration
- a direct issue fix for blk-mq from Omar
- fix for plug merging not involving the IO scheduler, like we do for
other types of merges. From Tahsin
- expose DAX type internally and through sysfs. From Toshi and Yigal
* 'for-4.8/core' of git://git.kernel.dk/linux-block: (76 commits)
block: Fix front merge check
block: do not merge requests without consulting with io scheduler
block: Fix spelling in a source code comment
block: expose QUEUE_FLAG_DAX in sysfs
block: add QUEUE_FLAG_DAX for devices to advertise their DAX support
Btrfs: fix comparison in __btrfs_map_block()
block: atari: Return early for unsupported sector size
Doc: block: Fix a typo in queue-sysfs.txt
cfq-iosched: Charge at least 1 jiffie instead of 1 ns
cfq-iosched: Fix regression in bonnie++ rewrite performance
cfq-iosched: Convert slice_resid from u64 to s64
block: Convert fifo_time from ulong to u64
blktrace: avoid using timespec
block/blk-cgroup.c: Declare local symbols static
block/bio-integrity.c: Add #include "blk.h"
block/partition-generic.c: Remove a set-but-not-used variable
block: bio: kill BIO_MAX_SIZE
cfq-iosched: temporarily boost queue priority for idle classes
block: drbd: avoid to use BIO_MAX_SIZE
block: bio: remove BIO_MAX_SECTORS
...
Currently, presence of direct_access() in block_device_operations
indicates support of DAX on its block device. Because
block_device_operations is instantiated with 'const', this DAX
capablity may not be enabled conditinally.
In preparation for supporting DAX to device-mapper devices, add
QUEUE_FLAG_DAX to request_queue flags to advertise their DAX
support. This will allow to set the DAX capability based on how
mapped device is composed.
Signed-off-by: Toshi Kani <toshi.kani@hpe.com>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: <linux-s390@vger.kernel.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
blk_get_request is used for BLOCK_PC and similar passthrough requests.
Currently we always need to call blk_rq_set_block_pc or an open coded
version of it to allow appending bios using the request mapping helpers
later on, which is a somewhat awkward API. Instead move the
initialization part of blk_rq_set_block_pc into blk_get_request, so that
we always have a safe to use request.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
Similar to how SCSI and NVMe prepare passthrough requests. This avoids
poking into request internals too much.
Signed-off-by: Christoph Hellwig <hch@lst.de>
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>
There is no error number returned if loop driver fails in function
alloc_disk to add new loop device. Add a correct error number to make
user notify in this case.
Signed-off-by: Minfei Huang <mnghuan@gmail.com>
Reviewed-by: Ming Lei <tom.leiming@gmail.com>
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Dan writes:
"The removal of ->driverfs_dev in favor of just passing the parent
device in as a parameter to add_disk(). See below, it has received a
"Reviewed-by" from Christoph, Bart, and Johannes.
It is also a pre-requisite for Fam Zheng's work to cleanup gendisk
uevents vs attribute visibility [1]. We would extend device_add_disk()
to take an attribute_group list.
This is based off a branch of block.git/for-4.8/drivers and has
received a positive build success notification from the kbuild robot
across several configs.
[1]: "gendisk: Generate uevent after attribute available"
http://marc.info/?l=linux-virtualization&m=146725201522201&w=2"
Pull block IO fixes from Jens Axboe:
"Three small fixes that have been queued up and tested for this series:
- A bug fix for xen-blkfront from Bob Liu, fixing an issue with
incomplete requests during migration.
- A fix for an ancient issue in retrieving the IO priority of a
different PID than self, preventing that task from going away while
we access it. From Omar.
- A writeback fix from Tahsin, fixing a case where we'd call ihold()
with a zero ref count inode"
* 'for-linus' of git://git.kernel.dk/linux-block:
block: fix use-after-free in sys_ioprio_get()
writeback: inode cgroup wb switch should not call ihold()
xen-blkfront: save uncompleted reqs in blkfront_resume()
Uncompleted reqs used to be 'saved and resubmitted' in blkfront_recover() during
migration, but that's too late after multi-queue was introduced.
After a migrate to another host (which may not have multiqueue support), the
number of rings (block hardware queues) may be changed and the ring and shadow
structure will also be reallocated.
The blkfront_recover() then can't 'save and resubmit' the real
uncompleted reqs because shadow structure have been reallocated.
This patch fixes this issue by moving the 'save' logic out of
blkfront_recover() to earlier place in blkfront_resume().
The 'resubmit' is not changed and still in blkfront_recover().
Signed-off-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: stable@vger.kernel.org
MG_DISK_MAJ is defined as 0 so dynamic block major number
allocation is used by the driver and the assigned major
number is stored in host->major. This patch fixes error
path in mg_probe() to use host->major instead of using
MG_DISK_MAJ.
Cc: unsik Kim <donari75@gmail.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
For block drivers that specify a parent device, convert them to use
device_add_disk().
This conversion was done with the following semantic patch:
@@
struct gendisk *disk;
expression E;
@@
- disk->driverfs_dev = E;
...
- add_disk(disk);
+ device_add_disk(E, disk);
@@
struct gendisk *disk;
expression E1, E2;
@@
- disk->driverfs_dev = E1;
...
E2 = disk;
...
- add_disk(E2);
+ device_add_disk(E1, E2);
...plus some manual fixups for a few missed conversions.
Cc: Jens Axboe <axboe@fb.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: James Bottomley <James.Bottomley@hansenpartnership.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
This is the third version of the patchset previously sent [1]. I have
basically only rebased it on top of 4.7-rc1 tree and dropped "dm: get
rid of superfluous gfp flags" which went through dm tree. I am sending
it now because it is tree wide and chances for conflicts are reduced
considerably when we want to target rc2. I plan to send the next step
and rename the flag and move to a better semantic later during this
release cycle so we will have a new semantic ready for 4.8 merge window
hopefully.
Motivation:
While working on something unrelated I've checked the current usage of
__GFP_REPEAT in the tree. It seems that a majority of the usage is and
always has been bogus because __GFP_REPEAT has always been about costly
high order allocations while we are using it for order-0 or very small
orders very often. It seems that a big pile of them is just a
copy&paste when a code has been adopted from one arch to another.
I think it makes some sense to get rid of them because they are just
making the semantic more unclear. Please note that GFP_REPEAT is
documented as
* __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt
* _might_ fail. This depends upon the particular VM implementation.
while !costly requests have basically nofail semantic. So one could
reasonably expect that order-0 request with __GFP_REPEAT will not loop
for ever. This is not implemented right now though.
I would like to move on with __GFP_REPEAT and define a better semantic
for it.
$ git grep __GFP_REPEAT origin/master | wc -l
111
$ git grep __GFP_REPEAT | wc -l
36
So we are down to the third after this patch series. The remaining
places really seem to be relying on __GFP_REPEAT due to large allocation
requests. This still needs some double checking which I will do later
after all the simple ones are sorted out.
I am touching a lot of arch specific code here and I hope I got it right
but as a matter of fact I even didn't compile test for some archs as I
do not have cross compiler for them. Patches should be quite trivial to
review for stupid compile mistakes though. The tricky parts are usually
hidden by macro definitions and thats where I would appreciate help from
arch maintainers.
[1] http://lkml.kernel.org/r/1461849846-27209-1-git-send-email-mhocko@kernel.org
This patch (of 19):
__GFP_REPEAT has a rather weak semantic but since it has been introduced
around 2.6.12 it has been ignored for low order allocations. Yet we
have the full kernel tree with its usage for apparently order-0
allocations. This is really confusing because __GFP_REPEAT is
explicitly documented to allow allocation failures which is a weaker
semantic than the current order-0 has (basically nofail).
Let's simply drop __GFP_REPEAT from those places. This would allow to
identify place which really need allocator to retry harder and formulate
a more specific semantic for what the flag is supposed to do actually.
Link: http://lkml.kernel.org/r/1464599699-30131-2-git-send-email-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "James E.J. Bottomley" <jejb@parisc-linux.org>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chen Liqin <liqin.linux@gmail.com>
Cc: Chris Metcalf <cmetcalf@mellanox.com> [for tile]
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jan Kara <jack@suse.cz>
Cc: John Crispin <blogic@openwrt.org>
Cc: Lennox Wu <lennox.wu@gmail.com>
Cc: Ley Foon Tan <lftan@altera.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
crypto_alloc_hash returns an ERR_PTR(), not NULL.
Also reset peer_integrity_tfm to NULL, to not call crypto_free_hash()
on an errno in the cleanup path.
Reported-by: Insu Yun <wuninsu@gmail.com>
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>
For larger devices, the array of bitmap page pointers can grow very
large (8000 pointers per TB of storage).
For each activity log transaction, we need to flush the associated
bitmap pages to stable storage. Currently, we just "mark" the respective
pages while setting up the transaction, then tell the bitmap code to
write out all marked pages, but skip unchanged pages.
But one such transaction can affect only a small number of bitmap pages,
there is no need to scan the full array of several (ten-)thousand
page pointers to find the few marked ones.
Instead, remember the index numbers of the few affected pages,
and later only re-check those to skip duplicates and unchanged ones.
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>
Also skip the message unless bitmap IO took longer than 5 ms.
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>
This should silence a warning about an empty statement. Thanks to Fabian
Frederick <fabf@skynet.be> who sent a patch I modified to be smaller and
avoids an additional indent level.
Signed-off-by: Roland Kammerer <roland.kammerer@linbit.com>
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.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>
Scenario, starting with normal operation
Connected Primary/Secondary UpToDate/UpToDate
NetworkFailure Primary/Unknown UpToDate/DUnknown (frozen)
... more failures happen, secondary loses it's disk,
but eventually is able to re-establish the replication link ...
Connected Primary/Secondary UpToDate/Diskless (resumed; needs to bump uuid!)
We used to just resume/resent suspended requests,
without bumping the UUID.
Which will lead to problems later, when we want to re-attach the disk on
the peer, without first disconnecting, or if we experience additional
failures, because we now have diverging data without being able to
recognize it.
Make sure we also bump the current data generation UUID,
if we notice "peer disk unknown" -> "peer disk known bad".
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>
We already serialize connection state changes,
and other, non-connection state changes (role changes)
while we are establishing a connection.
But if we have an established connection,
then trigger a resync handshake (by primary --force or similar),
until now we just had to be "lucky".
Consider this sequence (e.g. deployment scenario):
create-md; up;
-> Connected Secondary/Secondary Inconsistent/Inconsistent
then do a racy primary --force on both peers.
block drbd0: drbd_sync_handshake:
block drbd0: self 0000000000000004:0000000000000000:0000000000000000:0000000000000000 bits:25590 flags:0
block drbd0: peer 0000000000000004:0000000000000000:0000000000000000:0000000000000000 bits:25590 flags:0
block drbd0: peer( Unknown -> Secondary ) conn( WFReportParams -> Connected ) pdsk( DUnknown -> Inconsistent )
block drbd0: peer( Secondary -> Primary ) pdsk( Inconsistent -> UpToDate )
*** HERE things go wrong. ***
block drbd0: role( Secondary -> Primary )
block drbd0: drbd_sync_handshake:
block drbd0: self 0000000000000005:0000000000000000:0000000000000000:0000000000000000 bits:25590 flags:0
block drbd0: peer C90D2FC716D232AB:0000000000000004:0000000000000000:0000000000000000 bits:25590 flags:0
block drbd0: Becoming sync target due to disk states.
block drbd0: Writing the whole bitmap, full sync required after drbd_sync_handshake.
block drbd0: Remote failed to finish a request within 6007ms > ko-count (2) * timeout (30 * 0.1s)
drbd s0: peer( Primary -> Unknown ) conn( Connected -> Timeout ) pdsk( UpToDate -> DUnknown )
The problem here is that the local promotion happens before the sync handshake
triggered by the remote promotion was completed. Some assumptions elsewhere
become wrong, and when the expected resync handshake is then received and
processed, we get stuck in a deadlock, which can only be recovered by reboot :-(
Fix: if we know the peer has good data,
and our own disk is present, but NOT good,
and there is no resync going on yet,
we expect a sync handshake to happen "soon".
So reject a racy promotion with SS_IN_TRANSIENT_STATE.
Result:
... as above ...
block drbd0: peer( Secondary -> Primary ) pdsk( Inconsistent -> UpToDate )
*** local promotion being postponed until ... ***
block drbd0: drbd_sync_handshake:
block drbd0: self 0000000000000004:0000000000000000:0000000000000000:0000000000000000 bits:25590 flags:0
block drbd0: peer 77868BDA836E12A5:0000000000000004:0000000000000000:0000000000000000 bits:25590 flags:0
...
block drbd0: conn( WFBitMapT -> WFSyncUUID )
block drbd0: updated sync uuid 85D06D0E8887AD44:0000000000000000:0000000000000000:0000000000000000
block drbd0: conn( WFSyncUUID -> SyncTarget )
*** ... after the resync handshake ***
block drbd0: role( Secondary -> Primary )
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 in a two-primary scenario, we lost our peer, freeze IO,
and are still frozen (no UUID rotation) when the peer comes back
as Secondary after a hard crash, we will see identical UUIDs.
The "rule_nr = 40" chose to use the "CRASHED_PRIMARY" bit as
arbitration, but that would cause the still running (but frozen) Primary
to become SyncTarget (which it typically refuses), and the handshake is
declined.
Fix: check current roles.
If we have *one* current primary, the Primary wins.
(rule_nr = 41)
Since that is a protocol change, use the newly introduced DRBD_FF_WSAME
to determine if rule_nr = 41 can be applied.
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>
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>
Even if discard_zeroes_data != 0,
if discard_zeroes_if_aligned is set, we assume we can reliably
zero-out/discard using the drbd_issue_peer_discard() 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>
When re-attaching the local backend device to a C_STANDALONE D_DISKLESS
R_PRIMARY with OND_SUSPEND_IO, we may only resume IO if we recognize the
backend that is being attached as D_UP_TO_DATE.
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 DRBD lost all path to good data,
and the on-no-data-accessible policy is OND_SUSPEND_IO,
all pending and new IO requests are suspended (will block).
If that setting is OND_IO_ERROR, IO will still be completed.
READ to "clean" areas (e.g. on an D_INCONSISTENT device,
and bitmap indicates a block is already in sync) will succeed.
READ to "unclean" areas (bitmap indicates block is out-of-sync),
will return EIO.
If we are already D_DISKLESS (or D_FAILED), we also return EIO.
Unfortunately, on a former R_PRIMARY C_SYNC_TARGET D_INCONSISTENT,
after replication link loss, new WRITE requests still went through OK.
The would also set the "out-of-sync" bit on their way, so READ after
WRITE would still return EIO. Also, the data generation UUIDs had not
been bumped, we would cause data divergence, without being able to
detect it on the next sync handshake, given the right sequence of events
in a multiple error scenario and "improper" order of recovery actions.
The right thing to do is to return EIO for all new writes,
unless we have access to good, current, D_UP_TO_DATE data.
The "established best practices" way to avoid these situations in the
first place is to set OND_SUSPEND_IO, or even do a hard-reset from
the pri-on-incon-degr policy helper hook.
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>
Possibly sequence of events:
SyncTarget is made Primary, then loses replication link
(only path to good data on SyncSource).
Behavior is then controlled by the on-no-data-accessible policy,
which defaults to OND_IO_ERROR (may be set to OND_SUSPEND_IO).
If OND_IO_ERROR is in fact the current policy, we clear the susp_fen
(IO suspended due to fencing policy) flag, do NOT set the susp_nod
(IO suspended due to no data) flag.
But we forgot to call the IO error completion for all pending,
suspended, requests.
While at it, also add a race check for a theoretically possible
race with a new handshake (network hickup), we may be able to
re-send requests, and can avoid passing IO errors up the stack.
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 the replication link breaks exactly during "resync finished" detection,
finishing too early on the sync source could again lead to UUIDs rotated
too fast, and potentially a spurious full resync on next handshake.
Always wait for explicit resync finished state change notification from
the sync target.
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>
Make sure we have at least 67 (> AL_UPDATES_PER_TRANSACTION)
al-extents available, and allow up to half of that to be
discarded in one bio.
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>
For consistency, also zero-out partial unaligned chunks of discard
requests on the local backend.
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>
Now that we have the discard_zeroes_if_aligned setting, we should also
check it when setting up our queue parameters on the primary,
not only on the receiving side.
We announce discard support,
UNLESS
* we are connected to a peer that does not support TRIM
on the DRBD protocol level. Otherwise, it would either discard, or
do a fallback to zero-out, depending on its backend and configuration.
* our local backend does not support discards,
or (discard_zeroes_data=0 AND discard_zeroes_if_aligned=no).
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>
We can avoid spurious data divergence caused by partially-ignored
discards on certain backends with discard_zeroes_data=0, if we
translate partial unaligned discard requests into explicit zero-out.
The relevant use case is LVM/DM thin.
If on different nodes, DRBD is backed by devices with differing
discard characteristics, discards may lead to data divergence
(old data or garbage left over on one backend, zeroes due to
unmapped areas on the other backend). Online verify would now
potentially report tons of spurious differences.
While probably harmless for most use cases (fstrim on a file system),
DRBD cannot have that, it would violate our promise to upper layers
that our data instances on the nodes are identical.
To be correct and play safe (make sure data is identical on both copies),
we would have to disable discard support, if our local backend (on a
Primary) does not support "discard_zeroes_data=true".
We'd also have to translate discards to explicit zero-out on the
receiving (typically: Secondary) side, unless the receiving side
supports "discard_zeroes_data=true".
Which both would allocate those blocks, instead of unmapping them,
in contrast with expectations.
LVM/DM thin does set discard_zeroes_data=0,
because it silently ignores discards to partial chunks.
We can work around this by checking the alignment first.
For unaligned (wrt. alignment and granularity) or too small discards,
we zero-out the initial (and/or) trailing unaligned partial chunks,
but discard all the aligned full chunks.
At least for LVM/DM thin, the result is effectively "discard_zeroes_data=1".
Arguably it should behave this way internally, by default,
and we'll try to make that happen.
But our workaround is still valid for already deployed setups,
and for other devices that may behave this way.
Setting discard-zeroes-if-aligned=yes will allow DRBD to use
discards, and to announce discard_zeroes_data=true, even on
backends that announce discard_zeroes_data=false.
Setting discard-zeroes-if-aligned=no will cause DRBD to always
fall-back to zero-out on the receiving side, and to not even
announce discard capabilities on the Primary, if the respective
backend announces discard_zeroes_data=false.
We used to ignore the discard_zeroes_data setting completely.
To not break established and expected behaviour, and suddenly
cause fstrim on thin-provisioned LVs to run out-of-space,
instead of freeing up space, the default value is "yes".
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 maintain write-order fidelity accros all volumes in a DRBD resource,
the receiver of a P_BARRIER needs to issue flushes to all volumes.
We used to do this by calling blkdev_issue_flush(), synchronously,
one volume at a time.
We now submit all flushes to all volumes in parallel, then wait for all
completions, to reduce worst-case latencies on multi-volume resources.
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 command line parameter the kernel module uses to communicate the
device minor to userland helper is flawed in a way that the device
indentifier "minor-%d" is being truncated to minors with a maximum
of 5 digits.
But DRBD 8.4 allows 2^20 == 1048576 minors,
thus a minimum of 7 digits must be supported.
Reported by Veit Wahlich on drbd-dev.
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Regression introduced with 8.4.5
drbd: application writes may set-in-sync in protocol != C
Overwriting the same block (LBA) while a former version is still
"in-flight" to the peer (to be exact: we did not receive the
P_BARRIER_ACK for its epoch yet) would wait for the full epoch of that
former version to be acknowledged by the peer.
In synchronous and quasi-synchronous protocols C and B,
this may double the latency on overwrites.
With protocol A, which is supposed to be asynchronous and only wait for
local completion, it is even worse: it would make overwrites
quasi-synchronous, they would be hit by the full RTT, which protocol A
was specifically meant to avoid, and possibly the additional time it
takes to drain the buffers first.
Particularly bad for databases, or anything else that
does frequent updates to the same blocks (various file system meta data).
No impact if >= rtt passes between updates to the same block.
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>
As long as the value is 0 the feature is disabled. With setting
it to a positive value, DRBD limits and aligns its resync requests
to the rs-discard-granularity setting. If the sync source detects
all zeros in such a block, the resync target discards the range
on disk.
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>
When leaving resync states because of disconnect,
do the bitmap write-out synchronously in the drbd_disconnected() path.
When leaving resync states because we go back to AHEAD/BEHIND, or
because resync actually finished, or some disk was lost during resync,
trigger the write-out from after_state_ch().
The bitmap write-out for resync -> ahead/behind was missing completely before.
Note that this is all only an optimization to avoid double-resyncs of
already completed blocks in case this node crashes.
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 was to only suspend IO if some normal bitmap operation is
supposed to be locked out, not always. If the bulk operation is flaged
as BM_LOCKED_CHANGE_ALLOWED, we do not need to suspend IO.
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>
Use BIO_MAX_PAGES instead and we will remove BIO_MAX_SIZE.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Tested-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Instead of overloading the discard support with the REQ_SECURE flag.
Use the opportunity to rename the queue flag as well, and remove the
dead checks for this flag in the RAID 1 and RAID 10 drivers that don't
claim support for secure erase.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>
Because we define WRITE/READ as REQ_OPs, we cannot do
switch (rq_data_dir(request))
case READ
....
case WRITE
...
without getting warnings about handling other REQ_OPs.
This just has mq_disk do a if/else like it does in other
places.
Signed-off-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
After a migrate to another host (which may not have multiqueue
support), the number of rings (block hardware queues)
may be changed and the ring info structure will also be reallocated.
This patch fixes two related bugs:
* call blk_mq_update_nr_hw_queues() to make blk-core know the number
of hardware queues have been changed.
* Don't store rinfo pointer to hctx->driver_data, because rinfo may be
reallocated so use hctx->queue_num to get the rinfo structure instead.
Signed-off-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Sometimes blkfront may twice receive blkback_changed() notification
(XenbusStateConnected) after migration, which will cause
talk_to_blkback() to be called twice too and confuse xen-blkback.
The flow is as follow:
blkfront blkback
blkfront_resume()
> talk_to_blkback()
> Set blkfront to XenbusStateInitialised
front changed()
> Connect()
> Set blkback to XenbusStateConnected
blkback_changed()
> Skip talk_to_blkback()
because frontstate == XenbusStateInitialised
> blkfront_connect()
> Set blkfront to XenbusStateConnected
-----
And here we get another XenbusStateConnected notification leading
to:
-----
blkback_changed()
> because now frontstate != XenbusStateInitialised
talk_to_blkback() is also called again
> blkfront state changed from
XenbusStateConnected to XenbusStateInitialised
(Which is not correct!)
front_changed():
> Do nothing because blkback
already in XenbusStateConnected
Now blkback is in XenbusStateConnected but blkfront is still
in XenbusStateInitialised - leading to no disks.
Poking of the XenbusStateConnected state is allowed (to deal with
block disk change) and has to be dealt with. The most likely
cause of this bug are custom udev scripts hooking up the disks
and then validating the size.
Signed-off-by: Bob Liu <bob.liu@oracle.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
