First remove items from work_list as soon as we start working on them. This
means we don't have to track any pending or visited state and can get
rid of all the RCU magic freeing the work items - we can simply free
them once the operation has finished. Second use a real completion for
tracking synchronous requests - if the caller sets the completion pointer
we complete it, otherwise use it as a boolean indicator that we can free
the work item directly. Third unify struct wb_writeback_args and struct
bdi_work into a single data structure, wb_writeback_work. Previous we
set all parameters into a struct wb_writeback_args, copied it into
struct bdi_work, copied it again on the stack to use it there. Instead
of just allocate one structure dynamically or on the stack and use it
all the way through the stack.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
The case where we have a superblock doesn't require a loop here as we scan
over all inodes in writeback_sb_inodes. Split it out into a separate helper
to make the code simpler. This also allows to get rid of the sb member in
struct writeback_control, which was rather out of place there.
Also update the comments in writeback_sb_inodes that explain the handling
of inodes from wrong superblocks.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
This was just an odd wrapper around writeback_inodes_wb. Removing this
also allows to get rid of the bdi member of struct writeback_control
which was rather out of place there.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Fix kernel-doc to match the function's changed args.
Warning(fs/fs-writeback.c:190): No description found for parameter 'args'
Warning(fs/fs-writeback.c:190): Excess function parameter 'sb' description in 'bdi_queue_work_onstack'
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
We need to check for s_instances to make sure we don't bother working
against a filesystem that is beeing unmounted, and we need to call
put_super to make sure a superblock is freed when we race against
umount. Also no need to keep sb_lock after we got a reference on it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
In "writeback: fix writeback_inodes_wb from writeback_inodes_sb" I
accidentally removed the requeue_io if we need to skip a superblock
because we can't pin it. Add it back, otherwise we're getting spurious
lockups after multiple xfstests runs.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
bdi_start_writeback now never gets a superblock passed, so we can just remove
that case. And to further untangle the code and flatten the call stack
split it into two trivial helpers for it's two callers.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
bdi_writeback_all only has one caller, so fold it to simplify the code and
flatten the call stack.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
When we call writeback_inodes_wb from writeback_inodes_sb we always have
s_umount held, which currently makes the whole operation a no-op.
But if we are called to write out inodes for a specific superblock we always
have s_umount held, so replace the incorrect logic checking for WB_SYNC_ALL
which only worked by coincidence with the proper check for an explicit
superblock argument.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Make sure that not only sync_filesystem but all callers of writeback_inodes_sb
have the superblock protected against remount. As-is this disables all
functionality for these callers, but the next patch relies on this locking to
fix writeback_inodes_sb for sync_filesystem.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
If we want to rely on s_umount in the caller we need to wait for completion
of the I/O submission before returning to the caller. Refactor
bdi_sync_writeback into a bdi_queue_work_onstack helper and use it for this
case.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
The code dealing with bdi_work->state and completion of a bdi_work is a
major mess currently. This patch makes sure we directly use one set of
flags to deal with it, and use it consistently, which means:
- always notify about completion from the rcu callback. We only ever
wait for it from on-stack callers, so this simplification does not
even cause a theoretical slowdown currently. It also makes sure we
don't miss out on the notification if we ever add other callers to
wait for it.
- make earlier completion notification depending on the on-stack
allocation, not the sync mode. If we introduce new callers that
want to do WB_SYNC_NONE writeback from on-stack callers this will
be nessecary.
Also rename bdi_wait_on_work_clear to bdi_wait_on_work_done and inline
a few small functions into their only caller to make the code
understandable.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
This reverts commit e913fc825d.
We are investigating a hang associated with the WB_SYNC_NONE changes,
so revert them for now.
Conflicts:
fs/fs-writeback.c
mm/page-writeback.c
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
This reverts commit 7c8a3554c6.
We are investigating a hang associated with the WB_SYNC_NONE changes,
so revert them for now.
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
When wb_writeback() hasn't written anything it will re-acquire the inode
lock before calling inode_wait_for_writeback.
This change tests the sync bit first so that is doesn't need to drop &
re-acquire the lock if the inode became available while wb_writeback() was
waiting to get the lock.
Signed-off-by: Richard Kennedy <richard@rsk.demon.co.uk>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (69 commits)
fix handling of offsets in cris eeprom.c, get rid of fake on-stack files
get rid of home-grown mutex in cris eeprom.c
switch ecryptfs_write() to struct inode *, kill on-stack fake files
switch ecryptfs_get_locked_page() to struct inode *
simplify access to ecryptfs inodes in ->readpage() and friends
AFS: Don't put struct file on the stack
Ban ecryptfs over ecryptfs
logfs: replace inode uid,gid,mode initialization with helper function
ufs: replace inode uid,gid,mode initialization with helper function
udf: replace inode uid,gid,mode init with helper
ubifs: replace inode uid,gid,mode initialization with helper function
sysv: replace inode uid,gid,mode initialization with helper function
reiserfs: replace inode uid,gid,mode initialization with helper function
ramfs: replace inode uid,gid,mode initialization with helper function
omfs: replace inode uid,gid,mode initialization with helper function
bfs: replace inode uid,gid,mode initialization with helper function
ocfs2: replace inode uid,gid,mode initialization with helper function
nilfs2: replace inode uid,gid,mode initialization with helper function
minix: replace inode uid,gid,mode init with helper
ext4: replace inode uid,gid,mode init with helper
...
Trivial conflict in fs/fs-writeback.c (mark bitfields unsigned)
This fixes sparse noise:
error: dubious one-bit signed bitfield
Signed-off-by: H Hartley Sweeten <hsweeten@visionengravers.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Calling schedule without setting the task state to non-running will
return immediately, so ensure that we set it properly and check our
sleep conditions after doing so.
This is a fixup for commit 69b62d01.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Even if the writeout itself isn't a data integrity operation, we need
to ensure that the caller doesn't drop the sb umount sem before we
have actually done the writeback.
This is a fixup for commit e913fc82.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Filesystems with delalloc support may dirty inode during writepages.
As result inode will have dirty metadata flags even after write_inode.
In fact we have two dedicated functions for proper data and metadata
writeback. It is reasonable to separate flags updates in two stages.
https://bugzilla.kernel.org/show_bug.cgi?id=15906
Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
When umount calls sync_filesystem(), we first do a WB_SYNC_NONE
writeback to kick off writeback of pending dirty inodes, then follow
that up with a WB_SYNC_ALL to wait for it. Since umount already holds
the sb s_umount mutex, WB_SYNC_NONE ends up doing nothing and all
writeback happens as WB_SYNC_ALL. This can greatly slow down umount,
since WB_SYNC_ALL writeback is a data integrity operation and thus
a bigger hammer than simple WB_SYNC_NONE. For barrier aware file systems
it's a lot slower.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Prior to 2.6.32, setting /proc/sys/vm/dirty_writeback_centisecs disabled
periodic dirty writeback from kupdate. This got broken and now causes
excessive sys CPU usage if set to zero, as we'll keep beating on
schedule().
Cc: stable@kernel.org
Reported-by: Justin Maggard <jmaggard10@gmail.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
* 'for-linus' of git://git.kernel.dk/linux-2.6-block: (34 commits)
cfq-iosched: Fix the incorrect timeslice accounting with forced_dispatch
loop: Update mtime when writing using aops
block: expose the statistics in blkio.time and blkio.sectors for the root cgroup
backing-dev: Handle class_create() failure
Block: Fix block/elevator.c elevator_get() off-by-one error
drbd: lc_element_by_index() never returns NULL
cciss: unlock on error path
cfq-iosched: Do not merge queues of BE and IDLE classes
cfq-iosched: Add additional blktrace log messages in CFQ for easier debugging
i2o: Remove the dangerous kobj_to_i2o_device macro
block: remove 16 bytes of padding from struct request on 64bits
cfq-iosched: fix a kbuild regression
block: make CONFIG_BLK_CGROUP visible
Remove GENHD_FL_DRIVERFS
block: Export max number of segments and max segment size in sysfs
block: Finalize conversion of block limits functions
block: Fix overrun in lcm() and move it to lib
vfs: improve writeback_inodes_wb()
paride: fix off-by-one test
drbd: fix al-to-on-disk-bitmap for 4k logical_block_size
...
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Do not pin/unpin superblock for every inode in writeback_inodes_wb(), pin
it for the whole group of inodes which belong to the same superblock and
call writeback_sb_inodes() handler for them.
Signed-off-by: Edward Shishkin <edward.shishkin@gmail.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
This gives the filesystem more information about the writeback that
is happening. Trond requested this for the NFS unstable write handling,
and other filesystems might benefit from this too by beeing able to
distinguish between the different callers in more detail.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Similar to the fsync issue fixed a while ago in commit
2daea67e96 we need to write for data to
actually hit the disk before writing out the metadata to guarantee
data integrity for filesystems that modify the inode in the data I/O
completion path. Currently XFS and NFS handle this manually, and AFS
has a write_inode method that does nothing but waiting for data, while
others are possibly missing out on this.
Fortunately this change has a lot less impact than the fsync change
as none of the write_inode methods starts data writeout of any form
by itself.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Fix the following htmldocs warning:
Warning(fs/fs-writeback.c:255): No description found for parameter 'sb'
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Acked-by: Wu Fengguang <fengguang.wu@intel.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
ext4, at least, would like to start pushing on writeback if it starts
to get close to ENOSPC when reserving worst-case blocks for delalloc
writes. Writing out delalloc data will convert those worst-case
predictions into usually smaller actual usage, freeing up space
before we hit ENOSPC based on this speculation.
Thanks to Jens for the suggestion for the helper function,
& the naming help.
I've made the helper return status on whether writeback was
started even though I don't plan to use it in the ext4 patch;
it seems like it would be potentially useful to test this
in some cases.
Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Acked-by: Jan Kara <jack@suse.cz>
- no one is calling wb_writeback and write_cache_pages with
wbc.nonblocking=1 any more
- lumpy pageout will want to do nonblocking writeback without the
congestion wait
So remove the congestion checks as suggested by Chris.
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Evgeniy Polyakov <zbr@ioremap.net>
Cc: Alex Elder <aelder@sgi.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
It will lower the flush priority for NFS, and maybe more in future.
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
This is dead code because no bdi flush thread will be started for
!bdi_cap_writeback_dirty bdi.
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Sometimes we only want to write pages from a specific super_block,
so allow that to be passed in.
This fixes a problem with commit 56a131dcf7
causing writeback on all super_blocks on a bdi, where we only really
want to sync a specific sb from writeback_inodes_sb().
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Debug traces show that in per-bdi writeback, the inode under writeback
almost always get redirtied by a busy dirtier. We used to call
redirty_tail() in this case, which could delay inode for up to 30s.
This is unacceptable because it now happens so frequently for plain cp/dd,
that the accumulated delays could make writeback of big files very slow.
So let's distinguish between data redirty and metadata only redirty.
The first one is caused by a busy dirtier, while the latter one could
happen in XFS, NFS, etc. when they are doing delalloc or updating isize.
The inode being busy dirtied will now be requeued for next io, while
the inode being redirtied by fs will continue to be delayed to avoid
repeated IO.
CC: Jan Kara <jack@suse.cz>
CC: Theodore Ts'o <tytso@mit.edu>
CC: Dave Chinner <david@fromorbit.com>
CC: Chris Mason <chris.mason@oracle.com>
CC: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Currently we pin the inode->i_sb for every single inode. This
increases cache traffic on sb->s_umount sem. Lets instead
cache the inode sb pin state and keep the super_block pinned
for as long as keep writing out inodes from the same
super_block.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
If we only moved inodes from a single super_block to the temporary
list, there's no point in doing a resort for multiple super_blocks.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
__mark_inode_dirty adds inode to wb dirty list in random order. If a disk has
several partitions, writeback might keep spindle moving between partitions.
To reduce the move, better write big chunk of one partition and then move to
another. Inodes from one fs usually are in one partion, so idealy move indoes
from one fs together should reduce spindle move. This patch tries to address
this. Before per-bdi writeback is added, the behavior is write indoes
from one fs first and then another, so the patch restores previous behavior.
The loop in the patch is a bit ugly, should we add a dirty list for each
superblock in bdi_writeback?
Test in a two partition disk with attached fio script shows about 3% ~ 6%
improvement.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Reviewed-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Make the if-else straight in writeback_single_inode().
No behavior change.
Cc: Jan Kara <jack@suse.cz>
Cc: Michael Rubin <mrubin@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Fix the kupdate case, which disregards wbc.more_io and stop writeback
prematurely even when there are more inodes to be synced.
wbc.more_io should always be respected.
Also remove the pages_skipped check. It will set when some page(s) of some
inode(s) cannot be written for now. Such inodes will be delayed for a while.
This variable has nothing to do with whether there are other writeable inodes.
CC: Jan Kara <jack@suse.cz>
CC: Dave Chinner <david@fromorbit.com>
CC: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Treat bdi_start_writeback(0) as a special request to do background write,
and stop such work when we are below the background dirty threshold.
Also simplify the (nr_pages <= 0) checks. Since we already pass in
nr_pages=LONG_MAX for WB_SYNC_ALL and background writes, we don't
need to worry about it being decreased to zero.
Reported-by: Richard Kennedy <richard@rsk.demon.co.uk>
CC: Jan Kara <jack@suse.cz>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
If all inodes are under writeback (e.g. in case when there's only one inode
with dirty pages), wb_writeback() with WB_SYNC_NONE work basically degrades
to busylooping until I_SYNC flags of the inode is cleared. Fix the problem by
waiting on I_SYNC flags of an inode on b_more_io list in case we failed to
write anything.
Tested-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
wb_clear_pending AFAIKS should not be called after the item has been
put on the list, except by the worker threads. It could lead to the
situation where the refcount is decremented below 0 and cause lots of
problems.
Presumably the !wb_has_dirty_io case is not a common one, so it can
be discovered when the thread wakes up to check?
Also add a comment in bdi_work_clear.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
By the time bdi_work_on_stack gets evaluated again in bdi_work_free, it
can already have been deallocated and used for something else in the
!on stack case, giving a false positive in this test and causing
corruption.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
If you're going to do an atomic RMW on each list entry, there's not much
point in all the RCU complexities of the list walking. This is only going
to help the multi-thread case I guess, but it doesn't hurt to do now.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
bdi_start_writeback() is currently split into two paths, one for
WB_SYNC_NONE and one for WB_SYNC_ALL. Add bdi_sync_writeback()
for WB_SYNC_ALL writeback and let bdi_start_writeback() handle
only WB_SYNC_NONE.
Push down the writeback_control allocation and only accept the
parameters that make sense for each function. This cleans up
the API considerably.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
This gets rid of work == NULL in bdi_queue_work() and puts the
OOM handling where it belongs.
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Now that bdi_writeback_all() no longer handles integrity writeback,
it doesn't have to block anymore. This means that we can switch
bdi_list reader side protection to RCU.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Data integrity writeback must use bdi_start_writeback() and ensure
that wbc->sb and wbc->bdi are set.
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
We need to be able to pass in range_cyclic as well, so instead
of growing yet another argument, split the arguments into a
struct wb_writeback_args structure that we can use internally.
Also makes it easier to just copy all members to an on-stack
struct, since we can't access work after clearing the pending
bit.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Since it's an opportunistic writeback and not a data integrity action,
don't punt to blocking writeback. Just wakeup the thread and it will
flush old data.
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Also a debugging aid. We want to catch dirty inodes being added to
backing devices that don't do writeback.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
This gets rid of pdflush for bdi writeout and kupdated style cleaning.
pdflush writeout suffers from lack of locality and also requires more
threads to handle the same workload, since it has to work in a
non-blocking fashion against each queue. This also introduces lumpy
behaviour and potential request starvation, since pdflush can be starved
for queue access if others are accessing it. A sample ffsb workload that
does random writes to files is about 8% faster here on a simple SATA drive
during the benchmark phase. File layout also seems a LOT more smooth in
vmstat:
r b swpd free buff cache si so bi bo in cs us sy id wa
0 1 0 608848 2652 375372 0 0 0 71024 604 24 1 10 48 42
0 1 0 549644 2712 433736 0 0 0 60692 505 27 1 8 48 44
1 0 0 476928 2784 505192 0 0 4 29540 553 24 0 9 53 37
0 1 0 457972 2808 524008 0 0 0 54876 331 16 0 4 38 58
0 1 0 366128 2928 614284 0 0 4 92168 710 58 0 13 53 34
0 1 0 295092 3000 684140 0 0 0 62924 572 23 0 9 53 37
0 1 0 236592 3064 741704 0 0 4 58256 523 17 0 8 48 44
0 1 0 165608 3132 811464 0 0 0 57460 560 21 0 8 54 38
0 1 0 102952 3200 873164 0 0 4 74748 540 29 1 10 48 41
0 1 0 48604 3252 926472 0 0 0 53248 469 29 0 7 47 45
where vanilla tends to fluctuate a lot in the creation phase:
r b swpd free buff cache si so bi bo in cs us sy id wa
1 1 0 678716 5792 303380 0 0 0 74064 565 50 1 11 52 36
1 0 0 662488 5864 319396 0 0 4 352 302 329 0 2 47 51
0 1 0 599312 5924 381468 0 0 0 78164 516 55 0 9 51 40
0 1 0 519952 6008 459516 0 0 4 78156 622 56 1 11 52 37
1 1 0 436640 6092 541632 0 0 0 82244 622 54 0 11 48 41
0 1 0 436640 6092 541660 0 0 0 8 152 39 0 0 51 49
0 1 0 332224 6200 644252 0 0 4 102800 728 46 1 13 49 36
1 0 0 274492 6260 701056 0 0 4 12328 459 49 0 7 50 43
0 1 0 211220 6324 763356 0 0 0 106940 515 37 1 10 51 39
1 0 0 160412 6376 813468 0 0 0 8224 415 43 0 6 49 45
1 1 0 85980 6452 886556 0 0 4 113516 575 39 1 11 54 34
0 2 0 85968 6452 886620 0 0 0 1640 158 211 0 0 46 54
A 10 disk test with btrfs performs 26% faster with per-bdi flushing. A
SSD based writeback test on XFS performs over 20% better as well, with
the throughput being very stable around 1GB/sec, where pdflush only
manages 750MB/sec and fluctuates wildly while doing so. Random buffered
writes to many files behave a lot better as well, as does random mmap'ed
writes.
A separate thread is added to sync the super blocks. In the long term,
adding sync_supers_bdi() functionality could get rid of this thread again.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
This is a first step at introducing per-bdi flusher threads. We should
have no change in behaviour, although sb_has_dirty_inodes() is now
ridiculously expensive, as there's no easy way to answer that question.
Not a huge problem, since it'll be deleted in subsequent patches.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
This adds two new exported functions:
- writeback_inodes_sb(), which only attempts to writeback dirty inodes on
this super_block, for WB_SYNC_NONE writeout.
- sync_inodes_sb(), which writes out all dirty inodes on this super_block
and also waits for the IO to complete.
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
There is no reason to for the split between __writeback_single_inode and
__sync_single_inode, the former just does a couple of checks before
tail-calling the latter. So merge the two, and while we're at it split
out the I_SYNC waiting case for data integrity writers, as it's
logically separate function. Finally rename __writeback_single_inode to
writeback_single_inode.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
1) I_FREEING tests should be coupled with I_CLEAR
The two I_FREEING tests are racy because clear_inode() can set i_state to
I_CLEAR between the clear of I_SYNC and the test of I_FREEING.
2) skip I_WILL_FREE inodes in generic_sync_sb_inodes() to avoid possible
races with generic_forget_inode()
generic_forget_inode() sets I_WILL_FREE call writeback on its own, so
generic_sync_sb_inodes() shall not try to step in and create possible races:
generic_forget_inode
inode->i_state |= I_WILL_FREE;
spin_unlock(&inode_lock);
generic_sync_sb_inodes()
spin_lock(&inode_lock);
__iget(inode);
__writeback_single_inode
// see non zero i_count
may WARN here ==> WARN_ON(inode->i_state & I_WILL_FREE);
spin_unlock(&inode_lock);
may call generic_forget_inode again ==> iput(inode);
The above race and warning didn't turn up because writeback_inodes() holds
the s_umount lock, so generic_forget_inode() finds MS_ACTIVE and returns
early. But we are not sure the UBIFS calls and future callers will
guarantee that. So skip I_WILL_FREE inodes for the sake of safety.
Cc: Eric Sandeen <sandeen@sandeen.net>
Acked-by: Jeff Layton <jlayton@redhat.com>
Cc: Masayoshi MIZUMA <m.mizuma@jp.fujitsu.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Cc: Artem Bityutskiy <dedekind1@gmail.com>
Cc: Christoph Hellwig <hch@infradead.org>
Acked-by: Jan Kara <jack@suse.cz>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I think the block_dump output in __mark_inode_dirty is missing dentry locking.
Surely the i_dentry list can change any time, so we may not even *get* a
dentry there. If we do get one by chance, then it would appear to be able to
go away or get renamed at any time...
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Some filesystems can call in to sync an inode that is still in the
I_NEW state (eg. ext family, when mounted with -osync). This is OK
because the filesystem has sole access to the new inode, so it can
modify i_state without races (because no other thread should be
modifying it, by definition of I_NEW). Ie. a false positive, so
remove the warnings.
The races are described here 7ef0d7377c,
which is also where the warnings were introduced.
Reported-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
It is unnecessarily fragile to have two places (fsync_super() and do_sync())
doing data integrity sync of the filesystem. Alter __fsync_super() to
accommodate needs of both callers and use it. So after this patch
__fsync_super() is the only place where we gather all the calls needed to
properly send all data on a filesystem to disk.
Nice bonus is that we get a complete livelock avoidance and write_supers()
is now only used for periodic writeback of superblocks.
sync_blockdevs() introduced a couple of patches ago is gone now.
[build fixes folded]
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial: (28 commits)
trivial: Update my email address
trivial: NULL noise: drivers/mtd/tests/mtd_*test.c
trivial: NULL noise: drivers/media/dvb/frontends/drx397xD_fw.h
trivial: Fix misspelling of "Celsius".
trivial: remove unused variable 'path' in alloc_file()
trivial: fix a pdlfush -> pdflush typo in comment
trivial: jbd header comment typo fix for JBD_PARANOID_IOFAIL
trivial: wusb: Storage class should be before const qualifier
trivial: drivers/char/bsr.c: Storage class should be before const qualifier
trivial: h8300: Storage class should be before const qualifier
trivial: fix where cgroup documentation is not correctly referred to
trivial: Give the right path in Documentation example
trivial: MTD: remove EOL from MODULE_DESCRIPTION
trivial: Fix typo in bio_split()'s documentation
trivial: PWM: fix of #endif comment
trivial: fix typos/grammar errors in Kconfig texts
trivial: Fix misspelling of firmware
trivial: cgroups: documentation typo and spelling corrections
trivial: Update contact info for Jochen Hein
trivial: fix typo "resgister" -> "register"
...
The dirtied_when value on an inode is supposed to represent the first time
that an inode has one of its pages dirtied. This value is in units of
jiffies. It's used in several places in the writeback code to determine
when to write out an inode.
The problem is that these checks assume that dirtied_when is updated
periodically. If an inode is continuously being used for I/O it can be
persistently marked as dirty and will continue to age. Once the time
compared to is greater than or equal to half the maximum of the jiffies
type, the logic of the time_*() macros inverts and the opposite of what is
needed is returned. On 32-bit architectures that's just under 25 days
(assuming HZ == 1000).
As the least-recently dirtied inode, it'll end up being the first one that
pdflush will try to write out. sync_sb_inodes does this check:
/* Was this inode dirtied after sync_sb_inodes was called? */
if (time_after(inode->dirtied_when, start))
break;
...but now dirtied_when appears to be in the future. sync_sb_inodes bails
out without attempting to write any dirty inodes. When this occurs,
pdflush will stop writing out inodes for this superblock. Nothing can
unwedge it until jiffies moves out of the problematic window.
This patch fixes this problem by changing the checks against dirtied_when
to also check whether it appears to be in the future. If it does, then we
consider the value to be far in the past.
This should shrink the problematic window of time to such a small period
(30s) as not to matter.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Acked-by: Ian Kent <raven@themaw.net>
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
clear_inode() will switch inode state from I_FREEING to I_CLEAR, and do so
_outside_ of inode_lock. So any I_FREEING testing is incomplete without a
coupled testing of I_CLEAR.
So add I_CLEAR tests to drop_pagecache_sb(), generic_sync_sb_inodes() and
add_dquot_ref().
Masayoshi MIZUMA discovered the bug in drop_pagecache_sb() and Jan Kara
reminds fixing the other two cases.
Masayoshi MIZUMA has a nice panic flow:
=====================================================================
[process A] | [process B]
| |
| prune_icache() | drop_pagecache()
| spin_lock(&inode_lock) | drop_pagecache_sb()
| inode->i_state |= I_FREEING; | |
| spin_unlock(&inode_lock) | V
| | | spin_lock(&inode_lock)
| V | |
| dispose_list() | |
| list_del() | |
| clear_inode() | |
| inode->i_state = I_CLEAR | |
| | | V
| | | if (inode->i_state & (I_FREEING|I_WILL_FREE))
| | | continue; <==== NOT MATCH
| | |
| | | (DANGER from here on! Accessing disposing inode!)
| | |
| | | __iget()
| | | list_move() <===== PANIC on poisoned list !!
V V |
(time)
=====================================================================
Reported-by: Masayoshi MIZUMA <m.mizuma@jp.fujitsu.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
There was a report of a data corruption
http://lkml.org/lkml/2008/11/14/121. There is a script included to
reproduce the problem.
During testing, I encountered a number of strange things with ext3, so I
tried ext2 to attempt to reduce complexity of the problem. I found that
fsstress would quickly hang in wait_on_inode, waiting for I_LOCK to be
cleared, even though instrumentation showed that unlock_new_inode had
already been called for that inode. This points to memory scribble, or
synchronisation problme.
i_state of I_NEW inodes is not protected by inode_lock because other
processes are not supposed to touch them until I_LOCK (and I_NEW) is
cleared. Adding WARN_ON(inode->i_state & I_NEW) to sites where we modify
i_state revealed that generic_sync_sb_inodes is picking up new inodes from
the inode lists and passing them to __writeback_single_inode without
waiting for I_NEW. Subsequently modifying i_state causes corruption. In
my case it would look like this:
CPU0 CPU1
unlock_new_inode() __sync_single_inode()
reg <- inode->i_state
reg -> reg & ~(I_LOCK|I_NEW) reg <- inode->i_state
reg -> inode->i_state reg -> reg | I_SYNC
reg -> inode->i_state
Non-atomic RMW on CPU1 overwrites CPU0 store and sets I_LOCK|I_NEW again.
Fix for this is rather than wait for I_NEW inodes, just skip over them:
inodes concurrently being created are not subject to data integrity
operations, and should not significantly contribute to dirty memory
either.
After this change, I'm unable to reproduce any of the added warnings or
hangs after ~1hour of running. Previously, the new warnings would start
immediately and hang would happen in under 5 minutes.
I'm also testing on ext3 now, and so far no problems there either. I
don't know whether this fixes the problem reported above, but it fixes a
real problem for me.
Cc: "Jorge Boncompte [DTI2]" <jorge@dti2.net>
Reported-by: Adrian Hunter <ext-adrian.hunter@nokia.com>
Cc: Jan Kara <jack@suse.cz>
Cc: <stable@kernel.org>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
s_syncing livelock avoidance was breaking data integrity guarantee of
sys_sync, by allowing sys_sync to skip writing or waiting for superblocks
if there is a concurrent sys_sync happening.
This livelock avoidance is much less important now that we don't have the
get_super_to_sync() call after every sb that we sync. This was replaced
by __put_super_and_need_restart.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix data integrity semantics required by sys_sync, by iterating over all
inodes and waiting for any writeback pages after the initial writeout.
Comments explain the exact problem.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Remove WB_SYNC_HOLD. The primary motiviation is the design of my
anti-starvation code for fsync. It requires taking an inode lock over the
sync operation, so we could run into lock ordering problems with multiple
inodes. It is possible to take a single global lock to solve the ordering
problem, but then that would prevent a future nice implementation of "sync
multiple inodes" based on lock order via inode address.
Seems like a backward step to remove this, but actually it is busted
anyway: we can't use the inode lists for data integrity wait: an inode can
be taken off the dirty lists but still be under writeback. In order to
satisfy data integrity semantics, we should wait for it to finish
writeback, but if we only search the dirty lists, we'll miss it.
It would be possible to have a "writeback" list, for sys_sync, I suppose.
But why complicate things by prematurely optimise? For unmounting, we
could avoid the "livelock avoidance" code, which would be easier, but
again premature IMO.
Fixing the existing data integrity problem will come next.
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
People can use the real name an an index into MAINTAINERS to find the
current email address.
Signed-off-by: Francois Cami <francois.cami@free.fr>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch exports the 'sync_sb_inodes()' which is needed for
UBIFS because it has to force write-back from time to time.
Namely, the UBIFS budgeting subsystem forces write-back when
its pessimistic callculations show that there is no free
space on the media.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
This patch makes 'sync_sb_inodes()' lock 'inode_lock', rather
than expect that the caller will do this.
This change was previously done by Hans Reiser <reiser@namesys.com>
and sat in the -mm tree.
Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>
Make the following needlessly global functions static:
- writeback_acquire()
- writeback_release()
Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix kernel-doc notation warnings in fs/.
Warning(mmotm-2008-0314-1449//fs/super.c:560): missing initial short description on line:
* mark_files_ro
Warning(mmotm-2008-0314-1449//fs/locks.c:1277): missing initial short description on line:
* lease_get_mtime
Warning(mmotm-2008-0314-1449//fs/locks.c:1277): missing initial short description on line:
* lease_get_mtime
Warning(mmotm-2008-0314-1449//fs/namei.c:1368): missing initial short description on line:
* lookup_one_len: filesystem helper to lookup single pathname component
Warning(mmotm-2008-0314-1449//fs/buffer.c:3221): missing initial short description on line:
* bh_uptodate_or_lock: Test whether the buffer is uptodate
Warning(mmotm-2008-0314-1449//fs/buffer.c:3240): missing initial short description on line:
* bh_submit_read: Submit a locked buffer for reading
Warning(mmotm-2008-0314-1449//fs/fs-writeback.c:30): missing initial short description on line:
* writeback_acquire: attempt to get exclusive writeback access to a device
Warning(mmotm-2008-0314-1449//fs/fs-writeback.c:47): missing initial short description on line:
* writeback_in_progress: determine whether there is writeback in progress
Warning(mmotm-2008-0314-1449//fs/fs-writeback.c:58): missing initial short description on line:
* writeback_release: relinquish exclusive writeback access against a device.
Warning(mmotm-2008-0314-1449//include/linux/jbd.h:351): contents before sections
Warning(mmotm-2008-0314-1449//include/linux/jbd.h:561): contents before sections
Warning(mmotm-2008-0314-1449//fs/jbd/transaction.c:1935): missing initial short description on line:
* void journal_invalidatepage()
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We shouldn't use WB_SYNC_ALL if the caller is asking for asynchronous
treatment.
Signed-off-by: Mike Galbraith <efault@gmx.de>
Acked-by: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Use list_for_each_entry_reverse for super_blocks list and remove
unused sb_entry macro.
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
After making dirty a 100M file, the normal behavior is to start the
writeback for all data after 30s delays. But sometimes the following
happens instead:
- after 30s: ~4M
- after 5s: ~4M
- after 5s: all remaining 92M
Some analyze shows that the internal io dispatch queues goes like this:
s_io s_more_io
-------------------------
1) 100M,1K 0
2) 1K 96M
3) 0 96M
1) initial state with a 100M file and a 1K file
2) 4M written, nr_to_write <= 0, so write more
3) 1K written, nr_to_write > 0, no more writes(BUG)
nr_to_write > 0 in (3) fools the upper layer to think that data have all
been written out. The big dirty file is actually still sitting in
s_more_io. We cannot simply splice s_more_io back to s_io as soon as s_io
becomes empty, and let the loop in generic_sync_sb_inodes() continue: this
may starve newly expired inodes in s_dirty. It is also not an option to
draw inodes from both s_more_io and s_dirty, an let the loop go on: this
might lead to live locks, and might also starve other superblocks in sync
time(well kupdate may still starve some superblocks, that's another bug).
We have to return when a full scan of s_io completes. So nr_to_write > 0
does not necessarily mean that "all data are written". This patch
introduces a flag writeback_control.more_io to indicate that more io should
be done. With it the big dirty file no longer has to wait for the next
kupdate invokation 5s later.
In sync_sb_inodes() we only set more_io on super_blocks we actually
visited. This avoids the interaction between two pdflush deamons.
Also in __sync_single_inode() we don't blindly keep requeuing the io if the
filesystem cannot progress. Failing to do so may lead to 100% iowait.
Tested-by: Mike Snitzer <snitzer@gmail.com>
Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
Cc: Michael Rubin <mrubin@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Since I_SYNC was split out from I_LOCK, the concern in commit
4b89eed93e ("Write back inode data pages
even when the inode itself is locked") is not longer valid.
We should revert to the original behavior: in __writeback_single_inode(),
when we find an I_SYNC-ed inode and we're not doing a data-integrity sync,
skip writing entirely. Otherwise, we are double calling do_writepages()
Signed-off-by: Qi Yong <qiyong@fc-cn.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Joern Engel <joern@wohnheim.fh-wedel.de>
Cc: WU Fengguang <wfg@mail.ustc.edu.cn>
Cc: Michael Rubin <mrubin@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This reverts commit 2e6883bdf4, as
requested by Fengguang Wu. It's not quite fully baked yet, and while
there are patches around to fix the problems it caused, they should get
more testing. Says Fengguang: "I'll resend them both for -mm later on,
in a more complete patchset".
See
http://bugzilla.kernel.org/show_bug.cgi?id=9738
for some of this discussion.
Requested-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The task_struct->pid member is going to be deprecated, so start
using the helpers (task_pid_nr/task_pid_vnr/task_pid_nr_ns) in
the kernel.
The first thing to start with is the pid, printed to dmesg - in
this case we may safely use task_pid_nr(). Besides, printks produce
more (much more) than a half of all the explicit pid usage.
[akpm@linux-foundation.org: git-drm went and changed lots of stuff]
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Cc: Dave Airlie <airlied@linux.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I_LOCK was used for several unrelated purposes, which caused deadlock
situations in certain filesystems as a side effect. One of the purposes
now uses the new I_SYNC bit.
Also document the various bits and change their order from historical to
logical.
[bunk@stusta.de: make fs/inode.c:wake_up_inode() static]
Signed-off-by: Joern Engel <joern@wohnheim.fh-wedel.de>
Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
Cc: David Chinner <dgc@sgi.com>
Cc: Anton Altaparmakov <aia21@cam.ac.uk>
Cc: Al Viro <viro@ftp.linux.org.uk>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
After making dirty a 100M file, the normal behavior is to start the writeback
for all data after 30s delays. But sometimes the following happens instead:
- after 30s: ~4M
- after 5s: ~4M
- after 5s: all remaining 92M
Some analyze shows that the internal io dispatch queues goes like this:
s_io s_more_io
-------------------------
1) 100M,1K 0
2) 1K 96M
3) 0 96M
1) initial state with a 100M file and a 1K file
2) 4M written, nr_to_write <= 0, so write more
3) 1K written, nr_to_write > 0, no more writes(BUG)
nr_to_write > 0 in (3) fools the upper layer to think that data have all been
written out. The big dirty file is actually still sitting in s_more_io. We
cannot simply splice s_more_io back to s_io as soon as s_io becomes empty, and
let the loop in generic_sync_sb_inodes() continue: this may starve newly
expired inodes in s_dirty. It is also not an option to draw inodes from both
s_more_io and s_dirty, an let the loop go on: this might lead to live locks,
and might also starve other superblocks in sync time(well kupdate may still
starve some superblocks, that's another bug).
We have to return when a full scan of s_io completes. So nr_to_write > 0 does
not necessarily mean that "all data are written". This patch introduces a
flag writeback_control.more_io to indicate this situation. With it the big
dirty file no longer has to wait for the next kupdate invocation 5s later.
Cc: David Chinner <dgc@sgi.com>
Cc: Ken Chen <kenchen@google.com>
Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
NTFS's if-condition on dirty inodes is not complete. Fix it with
sb_has_dirty_inodes().
Cc: Anton Altaparmakov <aia21@cantab.net>
Cc: Ken Chen <kenchen@google.com>
Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Streamline the management of dirty inode lists and fix time ordering bugs.
The writeback logic used to move not-yet-expired dirty inodes from s_dirty to
s_io, *only to* move them back. The move-inodes-back-and-forth thing is a
mess, which is eliminated by this patch.
The new scheme is:
- s_dirty acts as a time ordered io delaying queue;
- s_io/s_more_io together acts as an io dispatching queue.
On kupdate writeback, we pull some inodes from s_dirty to s_io at the start of
every full scan of s_io. Otherwise (i.e. for sync/throttle/background
writeback), we always pull from s_dirty on each run (a partial scan).
Note that the line
list_splice_init(&sb->s_more_io, &sb->s_io);
is moved to queue_io() to leave s_io empty. Otherwise a big dirtied file will
sit in s_io for a long time, preventing new expired inodes to get in.
Cc: Ken Chen <kenchen@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Current -mm tree has bucketful of bug fixes in periodic writeback path.
However, we still hit a glitch where dirty pages on a given inode aren't
completely flushed to the disk, and system will accumulate large amount of
dirty pages beyond what dirty_expire_interval is designed for.
The problem is __sync_single_inode() will move an inode to sb->s_dirty list
even when there are more pending dirty pages on that inode. If there is
another inode with a small number of dirty pages, we hit a case where the loop
iteration in wb_kupdate() terminates prematurely because wbc.nr_to_write > 0.
Thus leaving the inode that has large amount of dirty pages behind and it has
to wait for another dirty_writeback_interval before we flush it again. We
effectively only write out MAX_WRITEBACK_PAGES every dirty_writeback_interval.
If the rate of dirtying is sufficiently high, the system will start
accumulate a large number of dirty pages.
So fix it by having another sb->s_more_io list on which to park the inode
while we iterate through sb->s_io and to allow each dirty inode which resides
on that sb to have an equal chance of flushing some amount of dirty pages.
Signed-off-by: Ken Chen <kenchen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This one fixes four bugs.
There are a few situation in there where writeback decides it is going to skip
over a blockdev inode on the kernel-internal blockdev superblock. It
presently does this by moving the blockdev inode onto the tail of the blockdev
superblock's s_dirty. But
a) this screws up s_dirty's reverse-time-orderedness and
b) refiling the blockdev for writeback in another 30 second is rude. We
should try again sooner than that.
Fix all this up by using redirty_head(): move the blockdev inode onto the head
of the blockdev superblock's s_dirty list for prompt writeback.
Cc: Mike Waychison <mikew@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Recycling the previous changelog:
When the writeback function is operating in writeback-for-flushing mode
(as opposed to writeback-for-integrity) and it encounters an I_LOCKed inode,
it will skip writing that inode. This is done for throughput and latency:
move on to another inode rather than blocking for this one.
Writeback skips this inode by moving it off s_io and onto s_dirty, so that
writeback can proceed with the other inodes on s_io.
However that inode movement can corrupt s_dirty's
reverse-time-orderedness. Fix that by using the new redirty_tail(), which
will update the refiled inode's dirtied_when field.
Note: the behaviour in here is a bit rude: if kupdate happens to come
across a locked inode then it will defer writeback of that inode for another
30 seconds. We'll address that in the next patch.
Address that here. What we do is to move the skipped inode to the _head_ of
s_dirty, immediately eligible for writeout again. Instead of deferring that
writeout for another 30 seconds.
One would think that this might cause a livelock: we keep on trying to write
the same locked inode. But it won't because:
a) if that was the case, it would _already_ be happening on the
balance_dirty_pages codepath. Because balance_dirty_pages() doesn't care
about inode timestamps.
b) if we skipped this inode then we won't have done any writeback. The
higher-level writeback paths will see that wbc.nr_to_write didn't change
and they'll then back off and take a nap.
Cc: Mike Waychison <mikew@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When the writeback function is operating in writeback-for-flushing mode (as
opposed to writeback-for-integrity) and it encounters an I_LOCKed inode, it
will skip writing that inode. This is done for throughput and latency: move
on to another inode rather than blocking for this one.
Writeback skips this inode by moving it off s_io and onto s_dirty, so that
writeback can proceed with the other inodes on s_io.
However that inode movement can corrupt s_dirty's reverse-time-orderedness.
Fix that by using the new redirty_tail(), which will update the refiled
inode's dirtied_when field.
Note: the behaviour in here is a bit rude: if kupdate happens to come across a
locked inode then it will defer writeback of that inode for another 30
seconds. We'll address that in the next patch.
Cc: Mike Waychison <mikew@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
There's a comment in there which claims that the inode is left on s_io
if nfs chickened out of writing some data.
But that's not been true for three years.
9290280ced13c85689adeffa587e9a53bd3a5873 fixed a livelock by moving these
inodes back onto s_dirty. Fix the comment.
In the second leg of the `if', use redirty_tail() rather than open-coding it.
Add weaselly comment indicating lack of confidence in the code and lack of the
fortitude which would be needed to fiddle with it.
Cc: Mike Waychison <mikew@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When the kupdate function has tried to write back an expired inode it will
then check to see whether some of the inode's pages are still dirty.
This can happen when the filesystem decided to not write a page for some
reason. But it does _not_ occur due to redirtyings: a redirtying will set
I_DIRTY_PAGES.
What we need to do here is to set I_DIRTY_PAGES to reflect reality and to then
put the inode onto the _head_ of s_dirty for consideration on the next kupdate
pass, in five seconds time.
Problem is, the code failed to modify the inode's timestamp when pushing the
inode onto thehead of s_dirty.
The patch:
If there are no other inodes on s_dirty then we leave the inode's timestamp
alone: it is already expired.
If there _are_ other inodes on s_dirty then we arrange for this inode to get
the same timestamp as the inode which is at the head of s_dirty, thus
preserving the s_dirty ordering. But we only need to do this if this inode
purports to have been dirtied before the one at head-of-list.
Cc: Mike Waychison <mikew@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
While writeback is working against a dirty inode it does a check after trying
to write some of the inode's pages:
"did the lower layers skip some of the inode's dirty pages because they were
locked (or under writeback, or whatever)"
If this turns out to be true, we must move the inode back onto s_dirty and
redirty it. The reason for doing this is that fsync() and friends only check
the s_dirty list, and those functions want to know about those pages which
were locked, so they can be waited upon and, if necessary, rewritten.
Problem is, that redirtying was putting the inode onto the tail of s_dirty
without updating its timestamp. This causes a violation of s_dirty ordering.
Fix this by updating inode->dirtied_when when moving the inode onto s_dirty.
But the code is still a bit buggy? If the inode was _already_ dirty then we
don't need to move it at all. Oh well, hopefully it doesn't matter too much,
as that was a redirtying, which was very recent anwyay.
Cc: Mike Waychison <mikew@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
For reasons which escape me, inodes which are dirty against a ram-backed
filesystem are managed in the same way as inodes which are backed by real
devices.
Probably we could optimise things here. But given that we skip the entire
supeblock as son as we hit the first dirty inode, there's not a lot to be
gained.
And the code does need to handle one particular non-backed superblock: the
kernel's fake internal superblock which holds all the blockdevs.
Still. At present when the code encounters an inode which is dirty against a
memory-backed filesystem it will skip that inode by refiling it back onto
s_dirty. But it fails to update the inode's timestamp when doing so which at
least makes the debugging code upset.
Fix.
Cc: Mike Waychison <mikew@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When writeback has finished writing back an inode it looks to see if that
inode is still dirty. If it is, that means that a process redirtied the inode
while its writeback was in progress.
What we need to do here is to refile the redirtied inode onto the s_dirty
list.
But we're doing that wrongly: it could be that this inode was redirtied
_before_ the last inode on s_dirty. We're blindly appending this inode to the
list, after an inode which might be less-recently-dirtied, thus violating the
list's ordering.
So we must either insertion-sort this inode into the correct place, or we must
update this inode's dirtied_when field when appending it to the reverse-sorted
s_dirty list, to preserve the reverse-time-ordering.
This patch does the latter: if this inode was dirtied less recently than the
tail inode then copy the tail inode's timestamp into this inode.
This means that in rare circumstances, some inodes will be writen back later
than they should have been. But the time slip will be small.
Cc: Mike Waychison <mikew@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Hide everything in blkdev.h with CONFIG_BLOCK isn't set, and fixup
the (few) files that fail to build because they were relying on blkdev.h
pulling in extra includes for them.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
In __writeback_single_inode(), when we find a locked inode and we're not
doing a data-integrity sync, we used to just skip writing entirely,
since we didn't want to wait for the inode to unlock.
However, there's really no reason to skip writing the data pages, which
are likely to be the the bulk of the dirty state anyway (and the main
reason why writeback was started for the non-data-integrity case, of
course!)
Acked-by: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Andrew Morton <akpm@osdl.org>,
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Move blockdev_superblock extern declaration from fs/fs-writeback.c to a
headerfile and remove the dependence on it by wrapping it in a macro.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Create a new header file, fs/internal.h, for common definitions local to the
sources in the fs/ directory.
Move extern definitions that should be in header files from fs/*.c to
fs/internal.h or other main header files where they span directories.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Conversion of nr_unstable to a per zone counter
We need to do some special modifications to the nfs code since there are
multiple cases of disposition and we need to have a page ref for proper
accounting.
This converts the last critical page state of the VM and therefore we need to
remove several functions that were depending on GET_PAGE_STATE_LAST in order
to make the kernel compile again. We are only left with event type counters
in page state.
[akpm@osdl.org: bugfixes]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This makes nr_dirty a per zone counter. Looping over all processors is
avoided during writeback state determination.
The counter aggregation for nr_dirty had to be undone in the NFS layer since
we summed up the page counts from multiple zones. Someone more familiar with
NFS should probably review what I have done.
[akpm@osdl.org: bugfix]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
A process flag to indicate whether we are doing sync io is incredibly
ugly. It also causes performance problems when one does a lot of async
io and then proceeds to sync it. Part of the io will go out as async,
and the other part as sync. This causes a disconnect between the
previously submitted io and the synced io. For io schedulers such as CFQ,
this will cause us lost merges and suboptimal behaviour in scheduling.
Remove PF_SYNCWRITE completely from the fsync/msync paths, and let
the O_DIRECT path just directly indicate that the writes are sync
by using WRITE_SYNC instead.
Signed-off-by: Jens Axboe <axboe@suse.de>
When a writeback_control's `start' and `end' fields are used to
indicate a one-byte-range starting at file offset zero, the required
values of .start=0,.end=0 mean that the ->writepages() implementation
has no way of telling that it is being asked to perform a range
request. Because we're currently overloading (start == 0 && end == 0)
to mean "this is not a write-a-range request".
To make all this sane, the patch changes range of writeback_control.
So caller does: If it is calling ->writepages() to write pages, it
sets range (range_start/end or range_cyclic) always.
And if range_cyclic is true, ->writepages() thinks the range is
cyclic, otherwise it just uses range_start and range_end.
This patch does,
- Add LLONG_MAX, LLONG_MIN, ULLONG_MAX to include/linux/kernel.h
-1 is usually ok for range_end (type is long long). But, if someone did,
range_end += val; range_end is "val - 1"
u64val = range_end >> bits; u64val is "~(0ULL)"
or something, they are wrong. So, this adds LLONG_MAX to avoid nasty
things, and uses LLONG_MAX for range_end.
- All callers of ->writepages() sets range_start/end or range_cyclic.
- Fix updates of ->writeback_index. It seems already bit strange.
If it starts at 0 and ended by check of nr_to_write, this last
index may reduce chance to scan end of file. So, this updates
->writeback_index only if range_cyclic is true or whole-file is
scanned.
Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Cc: Nathan Scott <nathans@sgi.com>
Cc: Anton Altaparmakov <aia21@cantab.net>
Cc: Steven French <sfrench@us.ibm.com>
Cc: "Vladimir V. Saveliev" <vs@namesys.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
In here, I think the following order is more cache-friendly.
Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Convert to proper kernel-doc format.
Some have extra blank lines (not allowed immed. after the function name)
or need blank lines (after all parameters). Function summary must be only
one line.
Colon (":") in a function description does weird things (causes kernel-doc
to think that it's a new section head sadly).
Signed-off-by: Randy Dunlap <rdunlap@xenotime.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
If the backing_dev_info doesn't have BDI_CAP_NO_WRITEBACK we're not supposed
to write back an inode's pages. But in this situation write_inode_now()
refuses to write the inode itself as well. Fix.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
When the inode count is zero in inode writeback, the
WARN_ON(!(inode->i_state & I_WILL_FREE));
is broken, and needs to test for either I_WILL_FREE|I_FREEING.
When the inode is in I_FREEING state, it's already out of the visibility
of the vm so it can't be freed so it doesn't require the __iget and the
generic_delete_inode path can call the sync internally to the lowlevel
fs callback during the last iput. So the inode being in I_FREEING is
also a valid condition for calling the sync with i_count == 0.
The specific stack trace is this:
0xc00000007b8fb6e0 0xc00000000010118c .__writeback_single_inode +0x5c
0xc00000007b8fb6e0 0xc0000000001014dc (lr) .sync_inode +0x3c
0xc00000007b8fb790 0xc0000000001014dc .sync_inode +0x3c
0xc00000007b8fb820 0xc0000000001a5020 .ext2_sync_inode +0x64
0xc00000007b8fb8f0 0xc0000000001a65b4 .ext2_truncate +0x3f8
0xc00000007b8fba40 0xc0000000001a6940 .ext2_delete_inode +0xdc
0xc00000007b8fbac0 0xc0000000000f7a5c .generic_delete_inode +0x124
0xc00000007b8fbb50 0xc0000000000f5fe0 .iput +0xb8
0xc00000007b8fbbe0 0xc0000000000e9fd4 .sys_unlink +0x2a8
0xc00000007b8fbd10 0xc00000000001048c .ret_from_syscall_1 +0x0
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
list_move(&inode->i_list, &inode_in_use);
} else {
list_move(&inode->i_list, &inode_unused);
+ inodes_stat.nr_unused++;
}
}
wake_up_inode(inode);
Are you sure the above diff is correct? It was added somewhere between
2.6.5 and 2.6.8. I think it's wrong.
The only way I can imagine the i_count to be zero in the above path, is
that I_WILL_FREE is set. And if I_WILL_FREE is set, then we must not
increase nr_unused. So I believe the above change is buggy and it will
definitely overstate the number of unused inodes and it should be backed
out.
Note that __writeback_single_inode before calling __sync_single_inode, can
drop the spinlock and we can have both the dirty and locked bitflags clear
here:
spin_unlock(&inode_lock);
__wait_on_inode(inode);
iput(inode);
XXXXXXX
spin_lock(&inode_lock);
}
use inode again here
a construct like the above makes zero sense from a reference counting
standpoint.
Either we don't ever use the inode again after the iput, or the
inode_lock should be taken _before_ executing the iput (i.e. a __iput
would be required). Taking the inode_lock after iput means the iget was
useless if we keep using the inode after the iput.
So the only chance the 2.6 was safe to call __writeback_single_inode
with the i_count == 0, is that I_WILL_FREE is set (I_WILL_FREE will
prevent the VM to free the inode in XXXXX).
Potentially calling the above iput with I_WILL_FREE was also wrong
because it would recurse in iput_final (the second mainline bug).
The below (untested) patch fixes the nr_unused accounting, avoids recursing
in iput when I_WILL_FREE is set and makes sure (with the BUG_ON) that we
don't corrupt memory and that all holders that don't set I_WILL_FREE, keeps
a reference on the inode!
Signed-off-by: Andrea Arcangeli <andrea@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch removes O(n^2) super block loops in sync_inodes(),
sync_filesystems() etc. in favour of using __put_super_and_need_restart()
which I introduced earlier. We faced a noticably long freezes on sb
syncing when there are thousands of super blocks in the system.
Signed-Off-By: Kirill Korotaev <dev@sw.ru>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Some KernelDoc descriptions are updated to match the current code.
No code changes.
Signed-off-by: Martin Waitz <tali@admingilde.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!