Writing to known bad blocks on drives that have seen a write error
is asking for trouble. So try to avoid these blocks.
Signed-off-by: NeilBrown <neilb@suse.de>
When recovering one or more devices, if all the good devices have
bad blocks we should record a bad block on the device being rebuilt.
If this fails, we need to abort the recovery.
To ensure we don't think that we aborted later than we actually did,
we need to move the check for MD_RECOVERY_INTR earlier in md_do_sync,
in particular before mddev->curr_resync is updated.
Signed-off-by: NeilBrown <neilb@suse.de>
During resync/recovery limit the size of the request to avoid
reading into a bad block that does not start at-or-before the current
read address.
Similarly if there is a bad block at this address, don't allow the
current request to extend beyond the end of that bad block.
Now that we don't ever read from known bad blocks, it is safe to allow
devices with those blocks into the array.
Signed-off-by: NeilBrown <neilb@suse.de>
When attempting to repair a read error, don't read from
devices with a known bad block.
As we are only reading PAGE_SIZE blocks, we don't try to
narrow down to smaller regions in the hope that only part of this
page is bad - it isn't worth the effort.
Signed-off-by: NeilBrown <neilb@suse.de>
When redirecting a read error to a different device, we must
again avoid bad blocks and possibly split the request.
Spin_lock typo fixed thanks to Dan Carpenter <error27@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
This patch just covers the basic read path:
1/ read_balance needs to check for badblocks, and return not only
the chosen slot, but also how many good blocks are available
there.
2/ read submission must be ready to issue multiple reads to
different devices as different bad blocks on different devices
could mean that a single large read cannot be served by any one
device, but can still be served by the array.
This requires keeping count of the number of outstanding requests
per bio. This count is stored in 'bi_phys_segments'
On read error we currently just fail the request if another target
cannot handle the whole request. Next patch refines that a bit.
Signed-off-by: NeilBrown <neilb@suse.de>
When a loop ends with a large if, it can be neater to change the
if to invert the condition and just 'continue'.
Then the body of the if can be indented to a lower level.
Signed-off-by: NeilBrown <neilb@suse.de>
On a successful write to a known bad block, flag the sh
so that raid5d can remove the known bad block from the list.
Signed-off-by: NeilBrown <neilb@suse.de>
When a write error is detected, don't mark the device as failed
immediately but rather record the fact for handle_stripe to deal with.
Handle_stripe then attempts to record a bad block. Only if that fails
does the device get marked as faulty.
Signed-off-by: NeilBrown <neilb@suse.de>
If we get an uncorrectable read error - record a bad block rather than
failing the device.
And if these errors (which may be due to known bad blocks) cause
recovery to be impossible, record a bad block on the recovering
devices, or abort the recovery.
As we might abort a recovery without failing a device we need to teach
RAID5 about recovery_disabled handling.
Signed-off-by: NeilBrown <neilb@suse.de>
There are two times that we might read in raid5:
1/ when a read request fits within a chunk on a single
working device.
In this case, if there is any bad block in the range of
the read, we simply fail the cache-bypass read and
perform the read though the stripe cache.
2/ when reading into the stripe cache. In this case we
mark as failed any device which has a bad block in that
strip (1 page wide).
Note that we will both avoid reading and avoid writing.
This is correct (as we will never read from the block, there
is no point writing), but not optimal (as writing could 'fix'
the error) - that will be addressed later.
If we have not seen any write errors on the device yet, we treat a bad
block like a recent read error. This will encourage an attempt to fix
the read error which will either generate a write error, or will
ensure good data is stored there. We don't yet forget the bad block
in that case. That comes later.
Now that we honour bad blocks when reading we can allow devices with
bad blocks into the array.
Signed-off-by: NeilBrown <neilb@suse.de>
raid1d is too big with several deep branches.
So separate them out into their own functions.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Namhyung Kim <namhyung@gmail.com>
If we cannot read a block from anywhere during recovery, there is
now a better approach than just giving up.
We can record a bad block on each device and keep going - being
careful not to clear the bad block when a write succeeds as it might -
it will be a write of incorrect data.
We have now reached the state where - for raid1 - we only call
md_error if md_set_badblocks has failed.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Namhyung Kim <namhyung@gmail.com>
If we find a bad block while writing as part of resync/recovery we
need to report that back to raid1d which must record the bad block,
or fail the device.
Similarly when fixing a read error, a further error should just
record a bad block if possible rather than failing the device.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Namhyung Kim <namhyung@gmail.com>
When we get a write error (in the data area, not in metadata),
update the badblock log rather than failing the whole device.
As the write may well be many blocks, we trying writing each
block individually and only log the ones which fail.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Namhyung Kim <namhyung@gmail.com>
When performing write-behind we allocate pages to store the data
during write.
Previously we just keep a list of pages. Now we keep a list of
bi_vec which includes offset and size.
This means that the r1bio has complete information to create a new
bio which will be needed for retrying after write errors.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Namhyung Kim <namhyung@gmail.com>
If we succeed in writing to a block that was recorded as
being bad, we clear the bad-block record.
This requires some delayed handling as the bad-block-list update has
to happen in process-context.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Namhyung Kim <namhyung@gmail.com>
If we have seen any write error on a drive, then don't write to
any known-bad blocks on that drive.
If necessary, we divide the write request up into pieces just
like we do for reads, so each piece is either all written or
all not written to any given drive.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Namhyung Kim <namhyung@gmail.com>
Previous patches in the bad block series extended behavior of
rdev's 'state' interface but lacked documentation update.
Fix it.
Signed-off-by: Namhyung Kim <namhyung@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
It is only safe to choose not to write to a bad block if that bad
block is safely recorded in metadata - i.e. if it has been
'acknowledged'.
If it hasn't we need to wait for the acknowledgement.
We support that using rdev->blocked wait and
md_wait_for_blocked_rdev by introducing a new device flag
'BlockedBadBlock'.
This flag is only advisory.
It is cleared whenever we acknowledge a bad block, so that a waiter
can re-check the particular bad blocks that it is interested it.
It should be set by a caller when they find they need to wait.
This (set after test) is inherently racy, but as
md_wait_for_blocked_rdev already has a timeout, losing the race will
have minimal impact.
When we clear "Blocked" was also clear "BlockedBadBlocks" incase it
was set incorrectly (see above race).
We also modify the way we manage 'Blocked' to fit better with the new
handling of 'BlockedBadBlocks' and to make it consistent between
externally managed and internally managed metadata. This requires
that each raidXd loop checks if the metadata needs to be written and
triggers a write (md_check_recovery) if needed. Otherwise a queued
write request might cause raidXd to wait for the metadata to write,
and only that thread can write it.
Before writing metadata, we set FaultRecorded for all devices that
are Faulty, then after writing the metadata we clear Blocked for any
device for which the Fault was certainly Recorded.
The 'faulty' device flag now appears in sysfs if the device is faulty
*or* it has unacknowledged bad blocks. So user-space which does not
understand bad blocks can continue to function correctly.
User space which does, should not assume a device is faulty until it
sees the 'faulty' flag, and then sees the list of unacknowledged bad
blocks is empty.
Signed-off-by: NeilBrown <neilb@suse.de>
If a device has ever seen a write error, we will want to handle
known-bad-blocks differently.
So create an appropriate state flag and export it via sysfs.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Namhyung Kim <namhyung@gmail.com>
When performing resync/etc, keep the size of the request
small enough that it doesn't overlap any known bad blocks.
Devices with badblocks at the start of the request are completely
excluded.
If there is nowhere to read from due to bad blocks, record
a bad block on each target device.
Now that we never read from known-bad-blocks we can allow devices with
known-bad-blocks into a RAID1.
Signed-off-by: NeilBrown <neilb@suse.de>
Now that we have a bad block list, we should not read from those
blocks.
There are several main parts to this:
1/ read_balance needs to check for bad blocks, and return not only
the chosen device, but also how many good blocks are available
there.
2/ fix_read_error needs to avoid trying to read from bad blocks.
3/ read submission must be ready to issue multiple reads to
different devices as different bad blocks on different devices
could mean that a single large read cannot be served by any one
device, but can still be served by the array.
This requires keeping count of the number of outstanding requests
per bio. This count is stored in 'bi_phys_segments'
4/ retrying a read needs to also be ready to submit a smaller read
and queue another request for the rest.
This does not yet handle bad blocks when reading to perform resync,
recovery, or check.
'md_trim_bio' will also be used for RAID10, so put it in md.c and
export it.
Signed-off-by: NeilBrown <neilb@suse.de>
Space must have been allocated when array was created.
A feature flag is set when the badblock list is non-empty, to
ensure old kernels don't load and trust the whole device.
We only update the on-disk badblocklist when it has changed.
If the badblocklist (or other metadata) is stored on a bad block, we
don't cope very well.
If metadata has no room for bad block, flag bad-blocks as disabled,
and do the same for 0.90 metadata.
Signed-off-by: NeilBrown <neilb@suse.de>
As no personality understand bad block lists yet, we must
reject any device that is known to contain bad blocks.
As the personalities get taught, these tests can be removed.
This only applies to raid1/raid5/raid10.
For linear/raid0/multipath/faulty the whole concept of bad blocks
doesn't mean anything so there is no point adding the checks.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Namhyung Kim <namhyung@gmail.com>
Previous patch in the bad block series added new sysfs interfaces
([unacknowledged_]bad_blocks) for each rdev without documentation.
Add it.
Signed-off-by: Namhyung Kim <namhyung@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
This can show the log (providing it fits in one page) and
allows bad blocks to be 'acknowledged' meaning that they
have safely been recorded in metadata.
Clearing bad blocks is not allowed via sysfs (except for
code testing). A bad block can only be cleared when
a write to the block succeeds.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Namhyung Kim <namhyung@gmail.com>
This the first step in allowing md to track bad-blocks per-device so
that we can fail individual blocks rather than the whole device.
This patch just adds a data structure for recording bad blocks, with
routines to add, remove, search the list.
Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Namhyung Kim <namhyung@gmail.com>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable:
Btrfs: make sure reserve_metadata_bytes doesn't leak out strange errors
Btrfs: use the commit_root for reading free_space_inode crcs
Btrfs: reduce extent_state lock contention for metadata
Btrfs: remove lockdep magic from btrfs_next_leaf
Btrfs: make a lockdep class for each root
Btrfs: switch the btrfs tree locks to reader/writer
Btrfs: fix deadlock when throttling transactions
Btrfs: stop using highmem for extent_buffers
Btrfs: fix BUG_ON() caused by ENOSPC when relocating space
Btrfs: tag pages for writeback in sync
Btrfs: fix enospc problems with delalloc
Btrfs: don't flush delalloc arbitrarily
Btrfs: use find_or_create_page instead of grab_cache_page
Btrfs: use a worker thread to do caching
Btrfs: fix how we merge extent states and deal with cached states
Btrfs: use the normal checksumming infrastructure for free space cache
Btrfs: serialize flushers in reserve_metadata_bytes
Btrfs: do transaction space reservation before joining the transaction
Btrfs: try to only do one btrfs_search_slot in do_setxattr
When calling bioset_create we pass the size of the front_pad as
sizeof(mddev)
which looks suspicious as mddev is a pointer and so it looks like a
common mistake where
sizeof(*mddev)
was intended.
The size is actually correct as we want to store a pointer in the
front padding of the bios created by the bioset, so make the intent
more explicit by using
sizeof(mddev_t *)
Reported-by: Zdenek Kabelac <zdenek.kabelac@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
* 'for-linus' of git://oss.sgi.com/xfs/xfs:
xfs: optimize the negative xattr caching
xfs: prevent against ioend livelocks in xfs_file_fsync
xfs: flag all buffers as metadata
xfs: encapsulate a block of debug code
* 'nfs-for-3.1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (44 commits)
NFSv4: Don't use the delegation->inode in nfs_mark_return_delegation()
nfs: don't use d_move in nfs_async_rename_done
RDMA: Increasing RPCRDMA_MAX_DATA_SEGS
SUNRPC: Replace xprt->resend and xprt->sending with a priority queue
SUNRPC: Allow caller of rpc_sleep_on() to select priority levels
SUNRPC: Support dynamic slot allocation for TCP connections
SUNRPC: Clean up the slot table allocation
SUNRPC: Initalise the struct xprt upon allocation
SUNRPC: Ensure that we grab the XPRT_LOCK before calling xprt_alloc_slot
pnfs: simplify pnfs files module autoloading
nfs: document nfsv4 sillyrename issues
NFS: Convert nfs4_set_ds_client to EXPORT_SYMBOL_GPL
SUNRPC: Convert the backchannel exports to EXPORT_SYMBOL_GPL
SUNRPC: sunrpc should not explicitly depend on NFS config options
NFS: Clean up - simplify the switch to read/write-through-MDS
NFS: Move the pnfs write code into pnfs.c
NFS: Move the pnfs read code into pnfs.c
NFS: Allow the nfs_pageio_descriptor to signal that a re-coalesce is needed
NFS: Use the nfs_pageio_descriptor->pg_bsize in the read/write request
NFS: Cache rpc_ops in struct nfs_pageio_descriptor
...
* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending:
target: Convert to DIV_ROUND_UP_SECTOR_T usage for sectors / dev_max_sectors
kernel.h: Add DIV_ROUND_UP_ULL and DIV_ROUND_UP_SECTOR_T macro usage
iscsi-target: Add iSCSI fabric support for target v4.1
iscsi: Add Serial Number Arithmetic LT and GT into iscsi_proto.h
iscsi: Use struct scsi_lun in iscsi structs instead of u8[8]
iscsi: Resolve iscsi_proto.h naming conflicts with drivers/target/iscsi
The btrfs transaction code will return any errors that come from
reserve_metadata_bytes. We need to make sure we don't return funny
things like 1 or EAGAIN.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
sys_ssetmask(), sys_rt_sigsuspend() and compat_sys_rt_sigsuspend()
change ->blocked directly. This is not correct, see the changelog in
e6fa16ab "signal: sigprocmask() should do retarget_shared_pending()"
Change them to use set_current_blocked().
Another change is that now we are doing ->saved_sigmask = ->blocked
lockless, it doesn't make any sense to do this under ->siglock.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Matt Fleming <matt.fleming@linux.intel.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Should have been done in commit 1af08a1407f4 ("This is in preparation
for more generic atomic").
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Arun Sharma <asharma@fb.com>
Cc: David Miller <davem@davemloft.net>
Cc: "Hans-Christian Egtvedt" <hans-christian.egtvedt@atmel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Since __proc_create() appends the name it is given to the end of the PDE
structure that it allocates, there isn't a need to store a name pointer.
Instead we can just replace the name pointer with a terminal char array of
_unspecified_ length. The compiler will simply append the string to statically
defined variables of PDE type overlapping any hole at the end of the structure
and, unlike specifying an explicitly _zero_ length array, won't give a warning
if you try to statically initialise it with a string of more than zero length.
Also, whilst we're at it:
(1) Move namelen to end just prior to name and reduce it to a single byte
(name shouldn't be longer than NAME_MAX).
(2) Move pde_unload_lock two places further on so that if it's four bytes in
size on a 64-bit machine, it won't cause an unused hole in the PDE struct.
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This collides with powerpc exported functions from bitops.h. Rename the
local copy in the oss soundblaster mixer and ad1848 driver.
Signed-off-by: Andy Whitcroft <apw@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Now that we are using regular file crcs for the free space cache,
we can deadlock if we try to read the free_space_inode while we are
updating the crc tree.
This commit fixes things by using the commit_root to read the crcs. This is
safe because we the free space cache file would already be loaded if
that block group had been changed in the current transaction.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
For metadata buffers that don't straddle pages (all of them), btrfs
can safely use the page uptodate bits and extent_buffer uptodate bit
instead of needing to use the extent_state tree.
This greatly reduces contention on the state tree lock.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Before the reader/writer locks, btrfs_next_leaf needed to keep
the path blocking to avoid making lockdep upset.
Now that btrfs_next_leaf only takes read locks, this isn't required.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
This patch was originally from Tejun Heo. lockdep complains about the btrfs
locking because we sometimes take btree locks from two different trees at the
same time. The current classes are based only on level in the btree, which
isn't enough information for lockdep to figure out if the lock is safe.
This patch makes a class for each type of tree, and lumps all the FS trees that
actually have files and directories into the same class.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The btrfs metadata btree is the source of significant
lock contention, especially in the root node. This
commit changes our locking to use a reader/writer
lock.
The lock is built on top of rw spinlocks, and it
extends the lock tracking to remember if we have a
read lock or a write lock when we go to blocking. Atomics
count the number of blocking readers or writers at any
given time.
It removes all of the adaptive spinning from the old code
and uses only the spinning/blocking hints inside of btrfs
to decide when it should continue spinning.
In read heavy workloads this is dramatically faster. In write
heavy workloads we're still faster because of less contention
on the root node lock.
We suffer slightly in dbench because we schedule more often
during write locks, but all other benchmarks so far are improved.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Hit this nice little deadlock. What happens is this
__btrfs_end_transaction with throttle set, --use_count so it equals 0
btrfs_commit_transaction
<somebody else actually manages to start the commit>
btrfs_end_transaction --use_count so now its -1 <== BAD
we just return and wait on the transaction
This is bad because we just return after our use_count is -1 and don't let go
of our num_writer count on the transaction, so the guy committing the
transaction just sits there forever. Fix this by inc'ing our use_count if we're
going to call commit_transaction so that if we call btrfs_end_transaction it's
valid. Thanks,
Signed-off-by: Josef Bacik <josef@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
The extent_buffers have a very complex interface where
we use HIGHMEM for metadata and try to cache a kmap mapping
to access the memory.
The next commit adds reader/writer locks, and concurrent use
of this kmap cache would make it even more complex.
This commit drops the ability to use HIGHMEM with extent buffers,
and rips out all of the related code.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
When we balanced the chunks across the devices, BUG_ON() in
__finish_chunk_alloc() was triggered.
------------[ cut here ]------------
kernel BUG at fs/btrfs/volumes.c:2568!
[SNIP]
Call Trace:
[<ffffffffa049525e>] btrfs_alloc_chunk+0x8e/0xa0 [btrfs]
[<ffffffffa04546b0>] do_chunk_alloc+0x330/0x3a0 [btrfs]
[<ffffffffa045c654>] btrfs_reserve_extent+0xb4/0x1f0 [btrfs]
[<ffffffffa045c86b>] btrfs_alloc_free_block+0xdb/0x350 [btrfs]
[<ffffffffa048a8d8>] ? read_extent_buffer+0xd8/0x1d0 [btrfs]
[<ffffffffa04476fd>] __btrfs_cow_block+0x14d/0x5e0 [btrfs]
[<ffffffffa044660d>] ? read_block_for_search+0x14d/0x4d0 [btrfs]
[<ffffffffa0447c9b>] btrfs_cow_block+0x10b/0x240 [btrfs]
[<ffffffffa044dd5e>] btrfs_search_slot+0x49e/0x7a0 [btrfs]
[<ffffffffa044f07d>] btrfs_insert_empty_items+0x8d/0xf0 [btrfs]
[<ffffffffa045e973>] insert_with_overflow+0x43/0x110 [btrfs]
[<ffffffffa045eb0d>] btrfs_insert_dir_item+0xcd/0x1f0 [btrfs]
[<ffffffffa0489bd0>] ? map_extent_buffer+0xb0/0xc0 [btrfs]
[<ffffffff812276ad>] ? rb_insert_color+0x9d/0x160
[<ffffffffa046cc40>] ? inode_tree_add+0xf0/0x150 [btrfs]
[<ffffffffa0474801>] btrfs_add_link+0xc1/0x1c0 [btrfs]
[<ffffffff811dacac>] ? security_inode_init_security+0x1c/0x30
[<ffffffffa04a28aa>] ? btrfs_init_acl+0x4a/0x180 [btrfs]
[<ffffffffa047492f>] btrfs_add_nondir+0x2f/0x70 [btrfs]
[<ffffffffa046af16>] ? btrfs_init_inode_security+0x46/0x60 [btrfs]
[<ffffffffa0474ac0>] btrfs_create+0x150/0x1d0 [btrfs]
[<ffffffff81159c63>] ? generic_permission+0x23/0xb0
[<ffffffff8115b415>] vfs_create+0xa5/0xc0
[<ffffffff8115ce6e>] do_last+0x5fe/0x880
[<ffffffff8115dc0d>] path_openat+0xcd/0x3d0
[<ffffffff8115e029>] do_filp_open+0x49/0xa0
[<ffffffff8116a965>] ? alloc_fd+0x95/0x160
[<ffffffff8114f0c7>] do_sys_open+0x107/0x1e0
[<ffffffff810bcc3f>] ? audit_syscall_entry+0x1bf/0x1f0
[<ffffffff8114f1e0>] sys_open+0x20/0x30
[<ffffffff81484ec2>] system_call_fastpath+0x16/0x1b
[SNIP]
RIP [<ffffffffa049444a>] __finish_chunk_alloc+0x20a/0x220 [btrfs]
The reason is:
Task1 Space balance task
do_chunk_alloc()
__finish_chunk_alloc()
update device info
in the chunk tree
alloc system metadata block
relocate system metadata block group
set system metadata block group
readonly, This block group is the
only one that can allocate space. So
there is no free space that can be
allocated now.
find no space and don't try
to alloc new chunk, and then
return ENOSPC
BUG_ON() in __finish_chunk_alloc()
was triggered.
Fix this bug by allocating a new system metadata chunk before relocating the
old one if we find there is no free space which can be allocated after setting
the old block group to be read-only.
Reported-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Tested-by: Tsutomu Itoh <t-itoh@jp.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
