The list of active AIL cursors uses a roll-your-own linked list with
special casing for the AIL push cursor. Simplify this code by
replacing the list with standard struct list_head lists, and use a
separate list_head to track the active cursors. This allows us to
treat the AIL push cursor as a generic cursor rather than as a
special case, further simplifying the code.
Further, fix the duplicate push cursor initialisation that the
special case handling was hiding, and clean up all the comments
around the active cursor list handling.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>
Delayed logging can insert tens of thousands of log items into the
AIL at the same LSN. When the committing of log commit records
occur, we can get insertions occurring at an LSN that is not at the
end of the AIL. If there are thousands of items in the AIL on the
tail LSN, each insertion has to walk the AIL to find the correct
place to insert the new item into the AIL. This can consume large
amounts of CPU time and block other operations from occurring while
the traversals are in progress.
To avoid this repeated walk, use a AIL cursor to record
where we should be inserting the new items into the AIL without
having to repeat the walk. The cursor infrastructure already
provides this functionality for push walks, so is a simple extension
of existing code. While this will not avoid the initial walk, it
will avoid repeating it tens of thousands of times during a single
checkpoint commit.
This version includes logic improvements from Christoph Hellwig.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex 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: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Alex Elder <aelder@sgi.com>
Similar to the xfssyncd, the per-filesystem xfsaild threads can be
converted to a global workqueue and run periodically by delayed
works. This makes sense for the AIL pushing because it uses
variable timeouts depending on the work that needs to be done.
By removing the xfsaild, we simplify the AIL pushing code and
remove the need to spread the code to implement the threading
and pushing across multiple files.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Alex Elder <aelder@sgi.com>
We now have two copies of AIL delete operations that are mostly
duplicate functionality. The single log item deletes can be
implemented via the bulk updates by turning xfs_trans_ail_delete()
into a simple wrapper. This removes all the duplicate delete
functionality and associated helpers.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
We now have two copies of AIL insert operations that are mostly
duplicate functionality. The single log item updates can be
implemented via the bulk updates by turning xfs_trans_ail_update()
into a simple wrapper. This removes all the duplicate insert
functionality and associated helpers.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
When inode buffer IO completes, usually all of the inodes are removed from the
AIL. This involves processing them one at a time and taking the AIL lock once
for every inode. When all CPUs are processing inode IO completions, this causes
excessive amount sof contention on the AIL lock.
Instead, change the way we process inode IO completion in the buffer
IO done callback. Allow the inode IO done callback to walk the list
of IO done callbacks and pull all the inodes off the buffer in one
go and then process them as a batch.
Once all the inodes for removal are collected, take the AIL lock
once and do a bulk removal operation to minimise traffic on the AIL
lock.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
When inserting items into the AIL from the transaction committed
callbacks, we take the AIL lock for every single item that is to be
inserted. For a CIL checkpoint commit, this can be tens of thousands
of individual inserts, yet almost all of the items will be inserted
at the same point in the AIL because they have the same index.
To reduce the overhead and contention on the AIL lock for such
operations, introduce a "bulk insert" operation which allows a list
of log items with the same LSN to be inserted in a single operation
via a list splice. To do this, we need to pre-sort the log items
being committed into a temporary list for insertion.
The complexity is that not every log item will end up with the same
LSN, and not every item is actually inserted into the AIL. Items
that don't match the commit LSN will be inserted and unpinned as per
the current one-at-a-time method (relatively rare), while items that
are not to be inserted will be unpinned and freed immediately. Items
that are to be inserted at the given commit lsn are placed in a
temporary array and inserted into the AIL in bulk each time the
array fills up.
As a result of this, we trade off AIL hold time for a significant
reduction in traffic. lock_stat output shows that the worst case
hold time is unchanged, but contention from AIL inserts drops by an
order of magnitude and the number of lock traversal decreases
significantly.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
When we commit a transaction using delayed logging, we need to
unlock the items in the transaciton before we unlock the CIL context
and allow it to be checkpointed. If we unlock them after we release
the CIl context lock, the CIL can checkpoint and complete before
we free the log items. This breaks stale buffer item unlock and
unpin processing as there is an implicit assumption that the unlock
will occur before the unpin.
Also, some log items need to store the LSN of the transaction commit
in the item (inodes and EFIs) and so can race with other transaction
completions if we don't prevent the CIL from checkpointing before
the unlock occurs.
Cc: <stable@kernel.org>
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Currently we track log item descriptor belonging to a transaction using a
complex opencoded chunk allocator. This code has been there since day one
and seems to work around the lack of an efficient slab allocator.
This patch replaces it with dynamically allocated log item descriptors
from a dedicated slab pool, linked to the transaction by a linked list.
This allows to greatly simplify the log item descriptor tracking to the
point where it's just a couple hundred lines in xfs_trans.c instead of
a separate file. The external API has also been simplified while we're
at it - the xfs_trans_add_item and xfs_trans_del_item functions to add/
delete items from a transaction have been simplified to the bare minium,
and the xfs_trans_find_item function is replaced with a direct dereference
of the li_desc field. All debug code walking the list of log items in
a transaction is down to a simple list_for_each_entry.
Note that we could easily use a singly linked list here instead of the
double linked list from list.h as the fastpath only does deletion from
sequential traversal. But given that we don't have one available as
a library function yet I use the list.h functions for simplicity.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
The delayed logging code only changes in-memory structures and as
such can be enabled and disabled with a mount option. Add the mount
option and emit a warning that this is an experimental feature that
should not be used in production yet.
We also need infrastructure to track committed items that have not
yet been written to the log. This is what the Committed Item List
(CIL) is for.
The log item also needs to be extended to track the current log
vector, the associated memory buffer and it's location in the Commit
Item List. Extend the log item and log vector structures to enable
this tracking.
To maintain the current log format for transactions with delayed
logging, we need to introduce a checkpoint transaction and a context
for tracking each checkpoint from initiation to transaction
completion. This includes adding a log ticket for tracking space
log required/used by the context checkpoint.
To track all the changes we need an io vector array per log item,
rather than a single array for the entire transaction. Using the new
log vector structure for this requires two passes - the first to
allocate the log vector structures and chain them together, and the
second to fill them out. This log vector chain can then be passed
to the CIL for formatting, pinning and insertion into the CIL.
Formatting of the log vector chain is relatively simple - it's just
a loop over the iovecs on each log vector, but it is made slightly
more complex because we re-write the iovec after the copy to point
back at the memory buffer we just copied into.
This code also needs to pin log items. If the log item is not
already tracked in this checkpoint context, then it needs to be
pinned. Otherwise it is already pinned and we don't need to pin it
again.
The only other complexity is calculating the amount of new log space
the formatting has consumed. This needs to be accounted to the
transaction in progress, and the accounting is made more complex
becase we need also to steal space from it for log metadata in the
checkpoint transaction. Calculate all this at insert time and update
all the tickets, counters, etc correctly.
Once we've formatted all the log items in the transaction, attach
the busy extents to the checkpoint context so the busy extents live
until checkpoint completion and can be processed at that point in
time. Transactions can then be freed at this point in time.
Now we need to issue checkpoints - we are tracking the amount of log space
used by the items in the CIL, so we can trigger background checkpoints when the
space usage gets to a certain threshold. Otherwise, checkpoints need ot be
triggered when a log synchronisation point is reached - a log force event.
Because the log write code already handles chained log vectors, writing the
transaction is trivial, too. Construct a transaction header, add it
to the head of the chain and write it into the log, then issue a
commit record write. Then we can release the checkpoint log ticket
and attach the context to the log buffer so it can be called during
Io completion to complete the checkpoint.
We also need to allow for synchronising multiple in-flight
checkpoints. This is needed for two things - the first is to ensure
that checkpoint commit records appear in the log in the correct
sequence order (so they are replayed in the correct order). The
second is so that xfs_log_force_lsn() operates correctly and only
flushes and/or waits for the specific sequence it was provided with.
To do this we need a wait variable and a list tracking the
checkpoint commits in progress. We can walk this list and wait for
the checkpoints to change state or complete easily, an this provides
the necessary synchronisation for correct operation in both cases.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>
When we free a metadata extent, we record it in the per-AG busy
extent array so that it is not re-used before the freeing
transaction hits the disk. This array is fixed size, so when it
overflows we make further allocation transactions synchronous
because we cannot track more freed extents until those transactions
hit the disk and are completed. Under heavy mixed allocation and
freeing workloads with large log buffers, we can overflow this array
quite easily.
Further, the array is sparsely populated, which means that inserts
need to search for a free slot, and array searches often have to
search many more slots that are actually used to check all the
busy extents. Quite inefficient, really.
To enable this aspect of extent freeing to scale better, we need
a structure that can grow dynamically. While in other areas of
XFS we have used radix trees, the extents being freed are at random
locations on disk so are better suited to being indexed by an rbtree.
So, use a per-AG rbtree indexed by block number to track busy
extents. This incures a memory allocation when marking an extent
busy, but should not occur too often in low memory situations. This
should scale to an arbitrary number of extents so should not be a
limitation for features such as in-memory aggregation of
transactions.
However, there are still situations where we can't avoid allocating
busy extents (such as allocation from the AGFL). To minimise the
overhead of such occurences, we need to avoid doing a synchronous
log force while holding the AGF locked to ensure that the previous
transactions are safely on disk before we use the extent. We can do
this by marking the transaction doing the allocation as synchronous
rather issuing a log force.
Because of the locking involved and the ordering of transactions,
the synchronous transaction provides the same guarantees as a
synchronous log force because it ensures that all the prior
transactions are already on disk when the synchronous transaction
hits the disk. i.e. it preserves the free->allocate order of the
extent correctly in recovery.
By doing this, we avoid holding the AGF locked while log writes are
in progress, hence reducing the length of time the lock is held and
therefore we increase the rate at which we can allocate and free
from the allocation group, thereby increasing overall throughput.
The only problem with this approach is that when a metadata buffer is
marked stale (e.g. a directory block is removed), then buffer remains
pinned and locked until the log goes to disk. The issue here is that
if that stale buffer is reallocated in a subsequent transaction, the
attempt to lock that buffer in the transaction will hang waiting
the log to go to disk to unlock and unpin the buffer. Hence if
someone tries to lock a pinned, stale, locked buffer we need to
push on the log to get it unlocked ASAP. Effectively we are trading
off a guaranteed log force for a much less common trigger for log
force to occur.
Ideally we should not reallocate busy extents. That is a much more
complex fix to the problem as it involves direct intervention in the
allocation btree searches in many places. This is left to a future
set of modifications.
Finally, now that we track busy extents in allocated memory, we
don't need the descriptors in the transaction structure to point to
them. We can replace the complex busy chunk infrastructure with a
simple linked list of busy extents. This allows us to remove a large
chunk of code, making the overall change a net reduction in code
size.
Signed-off-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Alex Elder <aelder@sgi.com>
Change all the remaining AIL API functions that are passed struct
xfs_mount pointers to pass pointers directly to the struct xfs_ail being
used. With this conversion, all external access to the AIL is via the
struct xfs_ail. Hence the operation and referencing of the AIL is almost
entirely independent of the xfs_mount that is using it - it is now much
more tightly tied to the log and the items it is tracking in the log than
it is tied to the xfs_mount.
SGI-PV: 988143
SGI-Modid: xfs-linux-melb:xfs-kern:32353a
Signed-off-by: David Chinner <david@fromorbit.com>
Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>
Signed-off-by: Christoph Hellwig <hch@infradead.org>
Bring the ail lock inside the struct xfs_ail. This means the AIL can be
entirely manipulated via the struct xfs_ail rather than needing both the
struct xfs_mount and the struct xfs_ail.
SGI-PV: 988143
SGI-Modid: xfs-linux-melb:xfs-kern:32350a
Signed-off-by: David Chinner <david@fromorbit.com>
Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>
Signed-off-by: Christoph Hellwig <hch@infradead.org>
When copying lsn's from the log item to the inode or dquot flush lsn, we
currently grab the AIL lock. We do this because the LSN is a 64 bit
quantity and it needs to be read atomically. The lock is used to guarantee
atomicity for 32 bit platforms.
Make the LSN copying a small function, and make the function used
conditional on BITS_PER_LONG so that 64 bit machines don't need to take
the AIL lock in these places.
SGI-PV: 988143
SGI-Modid: xfs-linux-melb:xfs-kern:32349a
Signed-off-by: David Chinner <david@fromorbit.com>
Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>
Signed-off-by: Christoph Hellwig <hch@infradead.org>
With the new cursor interface, it makes sense to make all the traversing
code use the cursor interface and make the old one go away. This means
more of the AIL interfacing is done by passing struct xfs_ail pointers
around the place instead of struct xfs_mount pointers.
We can replace the use of xfs_trans_first_ail() in xfs_log_need_covered()
as it is only checking if the AIL is empty. We can do that with a call to
xfs_trans_ail_tail() instead, where a zero LSN returned indicates and
empty AIL...
SGI-PV: 988143
SGI-Modid: xfs-linux-melb:xfs-kern:32348a
Signed-off-by: David Chinner <david@fromorbit.com>
Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>
Signed-off-by: Christoph Hellwig <hch@infradead.org>
To replace the current generation number ensuring sanity of the AIL
traversal, replace it with an external cursor that is linked to the AIL.
Basically, we store the next item in the cursor whenever we want to drop
the AIL lock to do something to the current item. When we regain the lock.
the current item may already be free, so we can't reference it, but the
next item in the traversal is already held in the cursor.
When we move or delete an object, we search all the active cursors and if
there is an item match we clear the cursor(s) that point to the object.
This forces the traversal to restart transparently.
We don't invalidate the cursor on insert because the cursor still points
to a valid item. If the intem is inserted between the current item and the
cursor it does not matter; the traversal is considered to be past the
insertion point so it will be picked up in the next traversal.
Hence traversal restarts pretty much disappear altogether with this method
of traversal, which should substantially reduce the overhead of pushing on
a busy AIL.
Version 2 o add restart logic o comment cursor interface o minor cleanups
SGI-PV: 988143
SGI-Modid: xfs-linux-melb:xfs-kern:32347a
Signed-off-by: David Chinner <david@fromorbit.com>
Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>
Signed-off-by: Christoph Hellwig <hch@infradead.org>
Rather than embedding the struct xfs_ail in the struct xfs_mount, allocate
it during AIL initialisation. Add a back pointer to the struct xfs_ail so
that we can pass around the xfs_ail and still be able to access the
xfs_mount if need be. This is th first step involved in isolating the AIL
implementation from the surrounding filesystem code.
SGI-PV: 988143
SGI-Modid: xfs-linux-melb:xfs-kern:32346a
Signed-off-by: David Chinner <david@fromorbit.com>
Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>
Signed-off-by: Christoph Hellwig <hch@infradead.org>
When many hundreds to thousands of threads all try to do simultaneous
transactions and the log is in a tail-pushing situation (i.e. full), we
can get multiple threads walking the AIL list and contending on the AIL
lock.
The AIL push is, in effect, a simple I/O dispatch algorithm complicated by
the ordering constraints placed on it by the transaction subsystem. It
really does not need multiple threads to push on it - even when only a
single CPU is pushing the AIL, it can push the I/O out far faster that
pretty much any disk subsystem can handle.
So, to avoid contention problems stemming from multiple list walkers, move
the list walk off into another thread and simply provide a "target" to
push to. When a thread requires a push, it sets the target and wakes the
push thread, then goes to sleep waiting for the required amount of space
to become available in the log.
This mechanism should also be a lot fairer under heavy load as the waiters
will queue in arrival order, rather than queuing in "who completed a push
first" order.
Also, by moving the pushing to a separate thread we can do more
effectively overload detection and prevention as we can keep context from
loop iteration to loop iteration. That is, we can push only part of the
list each loop and not have to loop back to the start of the list every
time we run. This should also help by reducing the number of items we try
to lock and/or push items that we cannot move.
Note that this patch is not intended to solve the inefficiencies in the
AIL structure and the associated issues with extremely large list
contents. That needs to be addresses separately; parallel access would
cause problems to any new structure as well, so I'm only aiming to isolate
the structure from unbounded parallelism here.
SGI-PV: 972759
SGI-Modid: xfs-linux-melb:xfs-kern:30371a
Signed-off-by: David Chinner <dgc@sgi.com>
Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>
xfs_trans_delete_ail
xfs_trans_update_ail and xfs_trans_delete_ail get called with the AIL lock
held, and release it. Add lock annotations to these two functions so that
sparse can check callers for lock pairing, and so that sparse will not
complain about these functions since they intentionally use locks in this
manner.
SGI-PV: 954580
SGI-Modid: xfs-linux-melb:xfs-kern:26807a
Signed-off-by: Josh Triplett <josh@freedesktop.org>
Signed-off-by: Nathan Scott <nathans@sgi.com>
Signed-off-by: Tim Shimmin <tes@sgi.com>
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!
Dave Chinner