Revert commit 1307bbd2, which uses the s_umount semaphore to provide
exclusion between xfs_sync_worker and unmount, in favor of shutting down
the sync worker before freeing the log in xfs_log_unmount.  This is a
cleaner way of resolving the race between xfs_sync_worker and unmount
than using s_umount.
Signed-off-by: NBen Myers <bpm@sgi.com>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Reviewed-by: NDave Chinner <dchinner@redhat.com>

xfs_sync_worker checks the MS_ACTIVE flag in s_flags to avoid doing
work during mount and unmount.  This flag can be cleared by unmount
after the xfs_sync_worker checks it but before the work is completed.
The has caused crashes in the completion handler for the dummy
transaction commited by xfs_sync_worker:

PID: 27544  TASK: ffff88013544e040  CPU: 3   COMMAND: "kworker/3:0"
 #0 [ffff88016fdff930] machine_kexec at ffffffff810244e9
 #1 [ffff88016fdff9a0] crash_kexec at ffffffff8108d053
 #2 [ffff88016fdffa70] oops_end at ffffffff813ad1b8
 #3 [ffff88016fdffaa0] no_context at ffffffff8102bd48
 #4 [ffff88016fdffaf0] __bad_area_nosemaphore at ffffffff8102c04d
 #5 [ffff88016fdffb40] bad_area_nosemaphore at ffffffff8102c12e
 #6 [ffff88016fdffb50] do_page_fault at ffffffff813afaee
 #7 [ffff88016fdffc60] page_fault at ffffffff813ac635
    [exception RIP: xlog_get_lowest_lsn+0x30]
    RIP: ffffffffa04a9910  RSP: ffff88016fdffd10  RFLAGS: 00010246
    RAX: ffffc90014e48000  RBX: ffff88014d879980  RCX: ffff88014d879980
    RDX: ffff8802214ee4c0  RSI: 0000000000000000  RDI: 0000000000000000
    RBP: ffff88016fdffd10   R8: ffff88014d879a80   R9: 0000000000000000
    R10: 0000000000000001  R11: 0000000000000000  R12: ffff8802214ee400
    R13: ffff88014d879980  R14: 0000000000000000  R15: ffff88022fd96605
    ORIG_RAX: ffffffffffffffff  CS: 0010  SS: 0018
 #8 [ffff88016fdffd18] xlog_state_do_callback at ffffffffa04aa186 [xfs]
 #9 [ffff88016fdffd98] xlog_state_done_syncing at ffffffffa04aa568 [xfs]

Protect xfs_sync_worker by using the s_umount semaphore at the read
level to provide exclusion with unmount while work is progressing.
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

With the removal of xfs_rw.h and other changes over time, xfs_bit.h
is being included in many files that don't actually need it. Clean
up the includes as necessary.

Also move the only-used-once xfs_ialloc_find_free() static inline
function out of a header file that is widely included to reduce
the number of needless dependencies on xfs_bit.h.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

xfs_trans_ail_delete_bulk() can be called from different contexts so
if the item is not in the AIL we need different shutdown for each
context.  Pass in the shutdown method needed so the correct action
can be taken.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

Queue delwri buffers on a local on-stack list instead of a per-buftarg one,
and write back the buffers per-process instead of by waking up xfsbufd.

This is now easily doable given that we have very few places left that write
delwri buffers:

 - log recovery:
	Only done at mount time, and already forcing out the buffers
	synchronously using xfs_flush_buftarg

 - quotacheck:
	Same story.

 - dquot reclaim:
	Writes out dirty dquots on the LRU under memory pressure.  We might
	want to look into doing more of this via xfsaild, but it's already
	more optimal than the synchronous inode reclaim that writes each
	buffer synchronously.

 - xfsaild:
	This is the main beneficiary of the change.  By keeping a local list
	of buffers to write we reduce latency of writing out buffers, and
	more importably we can remove all the delwri list promotions which
	were hitting the buffer cache hard under sustained metadata loads.

The implementation is very straight forward - xfs_buf_delwri_queue now gets
a new list_head pointer that it adds the delwri buffers to, and all callers
need to eventually submit the list using xfs_buf_delwi_submit or
xfs_buf_delwi_submit_nowait.  Buffers that already are on a delwri list are
skipped in xfs_buf_delwri_queue, assuming they already are on another delwri
list.  The biggest change to pass down the buffer list was done to the AIL
pushing. Now that we operate on buffers the trylock, push and pushbuf log
item methods are merged into a single push routine, which tries to lock the
item, and if possible add the buffer that needs writeback to the buffer list.
This leads to much simpler code than the previous split but requires the
individual IOP_PUSH instances to unlock and reacquire the AIL around calls
to blocking routines.

Given that xfsailds now also handle writing out buffers, the conditions for
log forcing and the sleep times needed some small changes.  The most
important one is that we consider an AIL busy as long we still have buffers
to push, and the other one is that we do increment the pushed LSN for
buffers that are under flushing at this moment, but still count them towards
the stuck items for restart purposes.  Without this we could hammer on stuck
items without ever forcing the log and not make progress under heavy random
delete workloads on fast flash storage devices.

[ Dave Chinner:
	- rebase on previous patches.
	- improved comments for XBF_DELWRI_Q handling
	- fix XBF_ASYNC handling in queue submission (test 106 failure)
	- rename delwri submit function buffer list parameters for clarity
	- xfs_efd_item_push() should return XFS_ITEM_PINNED ]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

Instead of writing the buffer directly from inside xfs_iflush return it to
the caller and let the caller decide what to do with the buffer.  Also
remove the pincount check in xfs_iflush that all non-blocking callers already
implement and the now unused flags parameter.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

We already flush dirty inodes throug the AIL regularly, there is no reason
to have second thread compete with it and disturb the I/O pattern.  We still
do write inodes when doing a synchronous reclaim from the shrinker or during
unmount for now.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

Now that we write back all metadata either synchronously or through
the AIL we can simply implement metadata freezing in terms of
emptying the AIL.

The implementation for this is fairly simply and straight-forward:
A new routine is added that asks the xfsaild to push the AIL to the
end and waits for it to complete and send a wakeup. The routine will
then loop if the AIL is not actually empty, and continue to do so
until the AIL is compeltely empty.

We keep an inode reclaim pass in the freeze process to avoid having
memory pressure have to reclaim inodes that require dirtying the
filesystem to be reclaimed after the freeze has completed. This
means we can also treat unmount in the exact same way as freeze.

As an upside we can now remove the radix tree based inode writeback
and xfs_unmountfs_writesb.

[ Dave Chinner:
	- Cleaned up commit message.
	- Added inode reclaim passes back into freeze.
	- Cleaned up wakeup mechanism to avoid the use of a new
	  sleep counter variable. ]
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

If a filesystem has been forced shutdown we are never going to write inodes
to disk, which means the inode items will stay in the AIL until we free
the inode. Currently that is not a problem, but a pending change requires us
to empty the AIL before shutting down the filesystem. In that case leaving
the inode in the AIL is lethal. Make sure to remove the log item from the AIL
to allow emptying the AIL on shutdown filesystems.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

Because the mount process can run a quotacheck and consume lots of
inodes, we need to be able to run periodic inode reclaim during the
mount process. This will prevent running the system out of memory
during quota checks.

This essentially reverts 2bcf6e97, but that is safe to do now that
the quota sync code that was causing problems during long quotacheck
executions is now gone.

The reclaim work is currently protected from running during the
unmount process by a check against MS_ACTIVE. Unfortunately, this
also means that the reclaim work cannot run during mount.  The
unmount process should stop the reclaim cleanly before freeing
anything that the reclaim work depends on, so there is no need to
have this guard in place.

Also, the inode reclaim work is demand driven, so there is no need
to start it immediately during mount. It will be started the moment
an inode is queued for reclaim, so qutoacheck will trigger it just
fine.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

Timestamps on regular files are the last metadata that XFS does not update
transactionally.  Now that we use the delaylog mode exclusively and made
the log scode scale extremly well there is no need to bypass that code for
timestamp updates.  Logging all updates allows to drop a lot of code, and
will allow for further performance improvements later on.

Note that this patch drops optimized handling of fdatasync - it will be
added back in a separate commit.
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

At the end of xfs_reclaim_inode(), the inode is locked in order to
we wait for a possible concurrent lookup to complete before the
inode is freed.  This synchronization step was taking both the ILOCK
and the IOLOCK, but the latter was causing lockdep to produce
reports of the possibility of deadlock.

It turns out that there's no need to acquire the IOLOCK at this
point anyway.  It may have been required in some earlier version of
the code, but there should be no need to take the IOLOCK in
xfs_iget(), so there's no (longer) any need to get it here for
synchronization.  Add an assertion in xfs_iget() as a reminder
of this assumption.

Dave Chinner diagnosed this on IRC, and Christoph Hellwig suggested
no longer including the IOLOCK.  I just put together the patch.
Signed-off-by: NAlex Elder <elder@dreamhost.com>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NBen Myers <bpm@sgi.com>

We almost never block on i_flock, the exception is synchronous inode
flushing.  Instead of bloating the inode with a 16/24-byte completion
that we abuse as a semaphore just implement it as a bitlock that uses
a bit waitqueue for the rare sleeping path.  This primarily is a
tradeoff between a much smaller inode and a faster non-blocking
path vs faster wakeups, and we are much better off with the former.

A small downside is that we will lose lockdep checking for i_flock, but
given that it's always taken inside the ilock that should be acceptable.

Note that for example the inode writeback locking is implemented in a
very similar way.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

Since Linux 2.6.36 the writeback code has introduces various measures for
live lock prevention during sync().  Unfortunately some of these are
actively harmful for the XFS model, where the inode gets marked dirty for
metadata from the data I/O handler.

The older_than_this checks that are now more strictly enforced since

    writeback: avoid livelocking WB_SYNC_ALL writeback

by only calling into __writeback_inodes_sb and thus only sampling the
current cut off time once.  But on a slow enough devices the previous
asynchronous sync pass might not have fully completed yet, and thus XFS
might mark metadata dirty only after that sampling of the cut off time for
the blocking pass already happened.  I have not myself reproduced this
myself on a real system, but by introducing artificial delay into the
XFS I/O completion workqueues it can be reproduced easily.

Fix this by iterating over all XFS inodes in ->sync_fs and log all that
are dirty.  This might log inode that only got redirtied after the
previous pass, but given how cheap delayed logging of inodes is it
isn't a major concern for performance.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Tested-by: NMark Tinguely <tinguely@sgi.com>
Reviewed-by: NMark Tinguely <tinguely@sgi.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

Now that we can't have any dirty dquots around that aren't in the AIL we
can get rid of the explicit dquot syncing from xfssyncd and xfs_fs_sync_fs
and instead rely on AIL pushing to write out any quota updates.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NBen Myers <bpm@sgi.com>

If we are doing synchronous inode reclaim we block the VM from making
progress in memory reclaim.  So if we encouter a flush locked inode
promote it in the delwri list and wake up xfsbufd to write it out now.
Without this we can get hangs of up to 30 seconds during workloads hitting
synchronous inode reclaim.

The scheme is copied from what we do for dquot reclaims.
Reported-by: NSimon Kirby <sim@hostway.ca>
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Tested-by: NSimon Kirby <sim@hostway.ca>
Signed-off-by: NBen Myers <bpm@sgi.com>

Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

We now have an i_dio_count filed and surrounding infrastructure to wait
for direct I/O completion instead of i_icount, and we have never needed
to iocount waits for buffered I/O given that we only set the page uptodate
after finishing all required work.  Thus remove i_iocount, and replace
the actually needed waits with calls to inode_dio_wait.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Remove the xfs_buf_relse from xfs_bwrite and let the caller handle it to
mirror the delwri and read paths.

Also remove the mount pointer passed to xfs_bwrite, which is superflous now
that we have a mount pointer in the buftarg.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Use the move from Linux 2.6 to Linux 3.x as an excuse to kill the
annoying subdirectories in the XFS source code.  Besides the large
amount of file rename the only changes are to the Makefile, a few
files including headers with the subdirectory prefix, and the binary
sysctl compat code that includes a header under fs/xfs/ from
kernel/.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Replace the macro XFS_BUF_ISPINNED with an inline helper function
xfs_buf_ispinned, and change all its usages.
Signed-off-by: NChandra Seetharaman <sekharan@us.ibm.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Convert the inode reclaim shrinker to use the new per-sb shrinker
operations. This allows much bigger reclaim batches to be used, and
allows the XFS inode cache to be shrunk in proportion with the VFS
dentry and inode caches. This avoids the problem of the VFS caches
being shrunk significantly before the XFS inode cache is shrunk
resulting in imbalances in the caches during reclaim.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>

Remove the second parameter to xfs_sb_count() since all callers of
the function set them.

Also, fix the header comment regarding it being called periodically.
Signed-off-by: NChandra Seetharaman <sekharan@us.ibm.com>
Signed-off-by: NAlex Elder <aelder@sgi.com>

The following script from Wu Fengguang shows very bad behaviour in XFS
when aggressively dirtying data during a sync on XFS, with sync times
up to almost 10 times as long as ext4.

A large part of the issue is that XFS writes data out itself two times
in the ->sync_fs method, overriding the livelock protection in the core
writeback code, and another issue is the lock-less xfs_ioend_wait call,
which doesn't prevent new ioend from being queue up while waiting for
the count to reach zero.

This patch removes the XFS-internal sync calls and relies on the VFS
to do it's work just like all other filesystems do.  Note that the
i_iocount wait which is rather suboptimal is simply removed here.
We already do it in ->write_inode, which keeps the current supoptimal
behaviour.  We'll eventually need to remove that as well, but that's
material for a separate commit.

------------------------------ snip ------------------------------
#!/bin/sh

umount /dev/sda7
mkfs.xfs -f /dev/sda7
# mkfs.ext4 /dev/sda7
# mkfs.btrfs /dev/sda7
mount /dev/sda7 /fs

echo $((50<<20)) > /proc/sys/vm/dirty_bytes

pid=
for i in `seq 10`
do
	dd if=/dev/zero of=/fs/zero-$i bs=1M count=1000 &
	pid="$pid $!"
done

sleep 1

tic=$(date +'%s')
sync
tac=$(date +'%s')

echo
echo sync time: $((tac-tic))
egrep '(Dirty|Writeback|NFS_Unstable)' /proc/meminfo

pidof dd > /dev/null && { kill -9 $pid; echo sync NOT livelocked; }
------------------------------ snip ------------------------------
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reported-by: NWu Fengguang <fengguang.wu@intel.com>
Reviewed-by: NAlex Elder <aelder@sgi.com>
Reviewed-by: NDave Chinner <dchinner@redhat.com>

Change each shrinker's API by consolidating the existing parameters into
shrink_control struct.  This will simplify any further features added w/o
touching each file of shrinker.

[akpm@linux-foundation.org: fix build]
[akpm@linux-foundation.org: fix warning]
[kosaki.motohiro@jp.fujitsu.com: fix up new shrinker API]
[akpm@linux-foundation.org: fix xfs warning]
[akpm@linux-foundation.org: update gfs2]
Signed-off-by: NYing Han <yinghan@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Acked-by: NPavel Emelyanov <xemul@openvz.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Acked-by: NRik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When the underlying inode buffer is locked and xfs_sync_inode_attr()
is doing a non-blocking flush, xfs_iflush() can return EAGAIN.  When
this happens, clear the error rather than returning it to
xfs_inode_ag_walk(), as returning EAGAIN will result in the AG walk
delaying for a short while and trying again. This can result in
background walks getting stuck on the one AG until inode buffer is
unlocked by some other means.

This behaviour was noticed when analysing event traces followed by
code inspection and verification of the fix via further traces.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

On a 32 bit highmem PowerPC machine, the XFS inode cache was growing
without bound and exhausting low memory causing the OOM killer to be
triggered. After some effort, the problem was reproduced on a 32 bit
x86 highmem machine.

The problem is that the per-ag inode reclaim index cursor was not
getting reset to the start of the AG if the radix tree tag lookup
found no more reclaimable inodes. Hence every further reclaim
attempt started at the same index beyond where any reclaimable
inodes lay, and no further background reclaim ever occurred from the
AG.

Without background inode reclaim the VM driven cache shrinker
simply cannot keep up with cache growth, and OOM is the result.

While the change that exposed the problem was the conversion of the
inode reclaim to use work queues for background reclaim, it was not
the cause of the bug. The bug was introduced when the cursor code
was added, just waiting for some weird configuration to strike....
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Tested-By: NChristian Kujau <lists@nerdbynature.de>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

(cherry picked from commit b2232219)

On a 32 bit highmem PowerPC machine, the XFS inode cache was growing
without bound and exhausting low memory causing the OOM killer to be
triggered. After some effort, the problem was reproduced on a 32 bit
x86 highmem machine.

The problem is that the per-ag inode reclaim index cursor was not
getting reset to the start of the AG if the radix tree tag lookup
found no more reclaimable inodes. Hence every further reclaim
attempt started at the same index beyond where any reclaimable
inodes lay, and no further background reclaim ever occurred from the
AG.

Without background inode reclaim the VM driven cache shrinker
simply cannot keep up with cache growth, and OOM is the result.

While the change that exposed the problem was the conversion of the
inode reclaim to use work queues for background reclaim, it was not
the cause of the bug. The bug was introduced when the cursor code
was added, just waiting for some weird configuration to strike....
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Tested-By: NChristian Kujau <lists@nerdbynature.de>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

When we are short on memory, we want to expedite the cleaning of
dirty objects.  Hence when we run short on memory, we need to kick
the AIL flushing into action to clean as many dirty objects as
quickly as possible.  To implement this, sample the lsn of the log
item at the head of the AIL and use that as the push target for the
AIL flush.

Further, we keep items in the AIL that are dirty that are not
tracked any other way, so we can get objects sitting in the AIL that
don't get written back until the AIL is pushed. Hence to get the
filesystem to the idle state, we might need to push the AIL to flush
out any remaining dirty objects sitting in the AIL. This requires
the same push mechanism as the reclaim push.

This patch also renames xfs_trans_ail_tail() to xfs_ail_min_lsn() to
match the new xfs_ail_max_lsn() function introduced in this patch.
Similarly for xfs_trans_ail_push -> xfs_ail_push.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NAlex Elder <aelder@sgi.com>

Background inode reclaim needs to run more frequently that the XFS
syncd work is run as 30s is too long between optimal reclaim runs.
Add a new periodic work item to the xfs syncd workqueue to run a
fast, non-blocking inode reclaim scan.

Background inode reclaim is kicked by the act of marking inodes for
reclaim.  When an AG is first marked as having reclaimable inodes,
the background reclaim work is kicked. It will continue to run
periodically untill it detects that there are no more reclaimable
inodes. It will be kicked again when the first inode is queued for
reclaim.

To ensure shrinker based inode reclaim throttles to the inode
cleaning and reclaim rate but still reclaim inodes efficiently, make it kick the
background inode reclaim so that when we are low on memory we are
trying to reclaim inodes as efficiently as possible. This kick shoul
d not be necessary, but it will protect against failures to kick the
background reclaim when inodes are first dirtied.

To provide the rate throttling, make the shrinker pass do
synchronous inode reclaim so that it blocks on inodes under IO. This
means that the shrinker will reclaim inodes rather than just
skipping over them, but it does not adversely affect the rate of
reclaim because most dirty inodes are already under IO due to the
background reclaim work the shrinker kicked.

These two modifications solve one of the two OOM killer invocations
Chris Mason reported recently when running a stress testing script.
The particular workload trigger for the OOM killer invocation is
where there are more threads than CPUs all unlinking files in an
extremely memory constrained environment. Unlike other solutions,
this one does not have a performance impact on performance when
memory is not constrained or the number of concurrent threads
operating is <= to the number of CPUs.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

On of the problems with the current inode flush at ENOSPC is that we
queue a flush per ENOSPC event, regardless of how many are already
queued. Thi can result in    hundreds of queued flushes, most of
which simply burn CPU scanned and do no real work. This simply slows
down allocation at ENOSPC.

We really only need one active flush at a time, and we can easily
implement that via the new xfs_syncd_wq. All we need to do is queue
a flush if one is not already active, then block waiting for the
currently active flush to complete. The result is that we only ever
have a single ENOSPC inode flush active at a time and this greatly
reduces the overhead of ENOSPC processing.

On my 2p test machine, this results in tests exercising ENOSPC
conditions running significantly faster - 042 halves execution time,
083 drops from 60s to 5s, etc - while not introducing test
regressions.

This allows us to remove the old xfssyncd threads and infrastructure
as they are no longer used.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

All of the work xfssyncd does is background functionality. There is
no need for a thread per filesystem to do this work - it can al be
managed by a global workqueue now they manage concurrency
effectively.

Introduce a new gglobal xfssyncd workqueue, and convert the periodic
work to use this new functionality. To do this, use a delayed work
construct to schedule the next running of the periodic sync work
for the filesystem. When the sync work is complete, queue a new
delayed work for the next running of the sync work.

For laptop mode, we wait on completion for the sync works, so ensure
that the sync work queuing interface can flush and wait for work to
complete to enable the work queue infrastructure to replace the
current sequence number and wakeup that is used.

Because the sync work does non-trivial amounts of work, mark the
new work queue as CPU intensive.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

Fixes generated by 'codespell' and manually reviewed.
Signed-off-by: NLucas De Marchi <lucas.demarchi@profusion.mobi>

There is an ABBA deadlock between synchronous inode flushing in
xfs_reclaim_inode and xfs_icluster_free. xfs_icluster_free locks the
buffer, then takes inode ilocks, whilst synchronous reclaim takes
the ilock followed by the buffer lock in xfs_iflush().

To avoid this deadlock, separate the inode cluster buffer locking
semantics from the synchronous inode flush semantics, allowing
callers to attempt to lock the buffer but still issue synchronous IO
if it can get the buffer. This requires xfs_iflush() calls that
currently use non-blocking semantics to pass SYNC_TRYLOCK rather
than 0 as the flags parameter.

This allows xfs_reclaim_inode to avoid the deadlock on the buffer
lock and detect the failure so that it can drop the inode ilock and
restart the reclaim attempt on the inode. This allows
xfs_ifree_cluster to obtain the inode lock, mark the inode stale and
release it and hence defuse the deadlock situation. It also has the
pleasant side effect of avoiding IO in xfs_reclaim_inode when it
tries to next reclaim the inode as it is now marked stale.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NAlex Elder <aelder@sgi.com>

Convert the files in fs/xfs/linux-2.6/ to use the new xfs_<level>
logging format that replaces the old Irix inherited cmn_err()
interfaces. While there, also convert naked printk calls to use the
relevant xfs logging function to standardise output format.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NAlex Elder <aelder@sgi.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>

To ensure the log is covered and the filesystem idles correctly, we
need to ensure that dummy transactions hit the disk and do not stay
pinned in memory.  If the superblock is pinned in memory, it can't
be flushed so the log covering cannot make progress. The result is
dependent on timing - more oftent han not we continue to issues a
log covering transaction every 36s rather than idling after ~90s.

Fix this by making the log covering transaction synchronous. To
avoid additional log force from xfssyncd, make the log covering
transaction take the place of the existing log force in the xfssyncd
background sync process.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

now that we are using RCU protection for the inode cache lookups,
the lock is only needed on the modification side. Hence it is not
necessary for the lock to be a rwlock as there are no read side
holders anymore. Convert it to a spin lock to reflect it's exclusive
nature.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NAlex Elder <aelder@sgi.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>

With delayed logging greatly increasing the sustained parallelism of inode
operations, the inode cache locking is showing significant read vs write
contention when inode reclaim runs at the same time as lookups. There is
also a lot more write lock acquistions than there are read locks (4:1 ratio)
so the read locking is not really buying us much in the way of parallelism.

To avoid the read vs write contention, change the cache to use RCU locking on
the read side. To avoid needing to RCU free every single inode, use the built
in slab RCU freeing mechanism. This requires us to be able to detect lookups of
freed inodes, so enѕure that ever freed inode has an inode number of zero and
the XFS_IRECLAIM flag set. We already check the XFS_IRECLAIM flag in cache hit
lookup path, but also add a check for a zero inode number as well.

We canthen convert all the read locking lockups to use RCU read side locking
and hence remove all read side locking.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NAlex Elder <aelder@sgi.com>

The walk fails to decrement the per-ag reference count when the
non-blocking walk fails to obtain the per-ag reclaim lock, leading
to an assert failure on debug kernels when unmounting a filesystem.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NAlex Elder <aelder@sgi.com>

Memory reclaim via shrinkers has a terrible habit of having N+M
concurrent shrinker executions (N = num CPUs, M = num kswapds) all
trying to shrink the same cache. When the cache they are all working
on is protected by a single spinlock, massive contention an
slowdowns occur.

Wrap the per-ag inode caches with a reclaim mutex to serialise
reclaim access to the AG. This will block concurrent reclaim in each
AG but still allow reclaim to scan multiple AGs concurrently. Allow
shrinkers to move on to the next AG if it can't get the lock, and if
we can't get any AG, then start blocking on locks.

To prevent reclaimers from continually scanning the same inodes in
each AG, add a cursor that tracks where the last reclaim got up to
and start from that point on the next reclaim. This should avoid
only ever scanning a small number of inodes at the satart of each AG
and not making progress. If we have a non-shrinker based reclaim
pass, ignore the cursor and reset it to zero once we are done.
Signed-off-by: NDave Chinner <dchinner@redhat.com>
Reviewed-by: NAlex Elder <aelder@sgi.com>