[XFS updates] XFS development tree branch, for-linus, updated. v3.1-rc3-1242-g9e4c109
xfs at oss.sgi.com
xfs at oss.sgi.com
Thu Oct 27 11:58:07 CDT 2011
This is an automated email from the git hooks/post-receive script. It was
generated because a ref change was pushed to the repository containing
the project "XFS development tree".
The branch, for-linus has been updated
discards 8e749e30958c1e592b4001a4a186d2b133df0aa0 (commit)
9e4c109 xfs: add AIL pushing tracepoints
2900b33 xfs: put in missed fix for merge problem
9508534 Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux
5a93a06 xfs: do not flush data workqueues in xfs_flush_buftarg
a9add83 xfs: remove XFS_bflush
02b102d xfs: remove xfs_buf_target_name
b38505b xfs: use xfs_ioerror_alert in xfs_buf_iodone_callbacks
901796a xfs: clean up xfs_ioerror_alert
4347b9d xfs: clean up buffer allocation
af5c4be xfs: remove buffers from the delwri list in xfs_buf_stale
c867cb6 xfs: remove XFS_BUF_STALE and XFS_BUF_SUPER_STALE
38f2323 xfs: remove XFS_BUF_SET_VTYPE and XFS_BUF_SET_VTYPE_REF
5fde032 xfs: remove XFS_BUF_FINISH_IOWAIT
b17b833 xfs: remove xfs_get_buftarg_list
87c7bec xfs: fix buffer flushing during unmount
1da2f2d xfs: optimize fsync on directories
670ce93 xfs: reduce the number of log forces from tail pushing
3815832 xfs: Don't allocate new buffers on every call to _xfs_buf_find
ddc3415 xfs: simplify xfs_trans_ijoin* again
23bb0be xfs: unlock the inode before log force in xfs_change_file_space
8292d88 xfs: unlock the inode before log force in xfs_fs_nfs_commit_metadata
b103705 xfs: unlock the inode before log force in xfs_fsync
815cb21 xfs: XFS_TRANS_SWAPEXT is not a valid flag for xfs_trans_commit
c029a50 xfs: fix possible overflow in xfs_ioc_trim()
d952e2f xfs: cleanup xfs_bmap.h
b0eab14 xfs: dont ignore error code from xfs_bmbt_update
c653424 xfs: pass bmalloca to xfs_bmap_add_extent_hole_real
572a4cf xfs: pass bmalloca to xfs_bmap_add_extent_delay_real
c315c90 xfs: move logflags into bmalloca
e0c3da5 xfs: move lastx and nallocs into bmalloca
29c8d17 xfs: move btree cursor into bmalloca
963c30c xfs: do not keep local copies of allocation ranges in xfs_bmapi_allocate
3a75667 xfs: rename allocation range fields in struct xfs_bmalloca
0937e0f xfs: move firstblock and bmap freelist cursor into bmalloca structure
baf41a5 xfs: move extent records into bmalloca structure
1b16447 xfs: pass bmalloca structure to xfs_bmap_isaeof
a5bd606 xfs: remove xfs_bmap_add_extent
27a3f8f xfs: introduce xfs_bmap_last_extent
c0dc782 xfs: rename xfs_bmapi to xfs_bmapi_write
b447fe5 xfs: factor unwritten extent map manipulations out of xfs_bmapi
7e47a4e xfs: factor extent allocation out of xfs_bmapi
1fd044d xfs: do not use xfs_bmap_add_extent for adding delalloc extents
4403280 xfs: introduce xfs_bmapi_delay()
b64dfe4 xfs: factor delalloc reservations out of xfs_bmapi
5b777ad xfs: remove xfs_bmapi_single()
5c8ed20 xfs: introduce xfs_bmapi_read()
aef9a89 xfs: factor extent map manipulations out of xfs_bmapi
ecee76b xfs: remove the nextents variable in xfs_bmapi
b9b984d xfs: remove impossible to read code in xfs_bmap_add_extent_delay_real
e7455e0 xfs: remove the first extent special case in xfs_bmap_add_extent
ed32201 xfs: Return -EIO when xfs_vn_getattr() failed
eabbaf1 xfs: Fix the incorrect comment in the header of _xfs_buf_find
2a30f36d xfs: Check the return value of xfs_trans_get_buf()
b522950 xfs: Check the return value of xfs_buf_get()
04f658e xfs: improve ioend error handling
c58cb16 xfs: avoid direct I/O write vs buffered I/O race
859f57c xfs: avoid synchronous transactions when deleting attr blocks
4a06fd2 xfs: remove i_iocount
2b3ffd7 xfs: wait for I/O completion when writing out pages in xfs_setattr_size
fc0063c xfs: reduce ioend latency
c859cdd xfs: defer AIO/DIO completions
398d25e xfs: remove dead ENODEV handling in xfs_destroy_ioend
c4e1c09 xfs: use the "delwri" terminology consistently
c2b006c xfs: let xfs_bwrite callers handle the xfs_buf_relse
61551f1 xfs: call xfs_buf_delwri_queue directly
5a8ee6b xfs: move more delwri setup into xfs_buf_delwri_queue
527cfdf xfs: remove the unlock argument to xfs_buf_delwri_queue
375ec69 xfs: remove delwri buffer handling from xfs_buf_iorequest
7271d24 xfs: don't serialise adjacent concurrent direct IO appending writes
0c38a25 xfs: don't serialise direct IO reads on page cache checks
from 8e749e30958c1e592b4001a4a186d2b133df0aa0 (commit)
Those revisions listed above that are new to this repository have
not appeared on any other notification email; so we list those
revisions in full, below.
- Log -----------------------------------------------------------------
commit 9e4c109ac822395e0aae650e4e3c9e4903f6602f
Author: Christoph Hellwig <hch at infradead.org>
Date: Tue Oct 11 15:14:11 2011 +0000
xfs: add AIL pushing tracepoints
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 2900b33999e2fc8a8edf0dddaafffec4da25ee10
Author: Alex Elder <aelder at sgi.com>
Date: Tue Oct 18 20:00:14 2011 +0000
xfs: put in missed fix for merge problem
I intended to do this as part of fixing part of the conflict with
the merge with Linus' tree, but evidently it didn't get included in
the commit.
Signed-off-by: Alex Elder <aelder at sgi.com>
Reviewed-by: Christoph Hellwig <hch at lst.de>
commit 9508534c5f170ada5a745cde0df49732718440e9
Merge: 5a93a064d27b42e4af1772b0599b53e3241191ac a84a79e4d369a73c0130b5858199e949432da4c6
Author: Alex Elder <aelder at sgi.com>
Date: Mon Oct 17 15:42:02 2011 -0500
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux
Resolved conflicts:
fs/xfs/xfs_trans_priv.h:
- deleted struct xfs_ail field xa_flags
- kept field xa_log_flush in struct xfs_ail
fs/xfs/xfs_trans_ail.c:
- in xfsaild_push(), in XFS_ITEM_PUSHBUF case, replaced
"flush_log = 1" with "ailp->xa_log_flush++"
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 5a93a064d27b42e4af1772b0599b53e3241191ac
Author: Christoph Hellwig <hch at infradead.org>
Date: Mon Oct 10 16:52:53 2011 +0000
xfs: do not flush data workqueues in xfs_flush_buftarg
When we call xfs_flush_buftarg (generally from sync or umount) it already
is too late to flush the data workqueues, as I/O completion is signalled
for them and we are thus already done with the data we would flush here.
There are places where flushing them might be useful, but the current
sync interface doesn't give us that opportunity.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit a9add83e5abd29bf2b7b3658311199eeabbdefc6
Author: Christoph Hellwig <hch at infradead.org>
Date: Mon Oct 10 16:52:52 2011 +0000
xfs: remove XFS_bflush
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 02b102df1502a7ea4167d115510e1e8fe6467f12
Author: Christoph Hellwig <hch at infradead.org>
Date: Mon Oct 10 16:52:51 2011 +0000
xfs: remove xfs_buf_target_name
The calling convention that returns a pointer to a static buffer is
fairly nasty, so just opencode it in the only caller that is left.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit b38505b09b7854d446b2f60b4414e3231277aa1a
Author: Christoph Hellwig <hch at infradead.org>
Date: Mon Oct 10 16:52:50 2011 +0000
xfs: use xfs_ioerror_alert in xfs_buf_iodone_callbacks
Use xfs_ioerror_alert instead of opencoding a very similar error
message.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 901796afca0d31d97bf6d1bf2ab251a93a4b8c83
Author: Christoph Hellwig <hch at infradead.org>
Date: Mon Oct 10 16:52:49 2011 +0000
xfs: clean up xfs_ioerror_alert
Instead of passing the block number and mount structure explicitly
get them off the bp and fix make the argument order more natural.
Also move it to xfs_buf.c and stop printing the device name given
that we already get the fs name as part of xfs_alert, and we know
what device is operates on because of the caller that gets printed,
finally rename it to xfs_buf_ioerror_alert and pass __func__ as
argument where it makes sense.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 4347b9d7ad4223474d315c3ab6bc1ce7cce7fa2d
Author: Christoph Hellwig <hch at infradead.org>
Date: Mon Oct 10 16:52:48 2011 +0000
xfs: clean up buffer allocation
Change _xfs_buf_initialize to allocate the buffer directly and rename it to
xfs_buf_alloc now that is the only buffer allocation routine. Also remove
the xfs_buf_deallocate wrapper around the kmem_zone_free calls for buffers.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit af5c4bee499eb68bc36ca046030394d82d0e3669
Author: Christoph Hellwig <hch at infradead.org>
Date: Mon Oct 10 16:52:47 2011 +0000
xfs: remove buffers from the delwri list in xfs_buf_stale
For each call to xfs_buf_stale we call xfs_buf_delwri_dequeue either
directly before or after it, or are guaranteed by the surrounding
conditionals that we are never called on delwri buffers. Simply
this situation by moving the call to xfs_buf_delwri_dequeue into
xfs_buf_stale.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit c867cb61641751fd3d86350232d64ae2a10137d4
Author: Christoph Hellwig <hch at infradead.org>
Date: Mon Oct 10 16:52:46 2011 +0000
xfs: remove XFS_BUF_STALE and XFS_BUF_SUPER_STALE
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 38f23232449c9d2c0bc8e9541cb8ab08b7c2b9ce
Author: Christoph Hellwig <hch at infradead.org>
Date: Mon Oct 10 16:52:45 2011 +0000
xfs: remove XFS_BUF_SET_VTYPE and XFS_BUF_SET_VTYPE_REF
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 5fde0326ddb1472ef31034c8ed952a19d4679191
Author: Christoph Hellwig <hch at infradead.org>
Date: Mon Oct 10 16:52:44 2011 +0000
xfs: remove XFS_BUF_FINISH_IOWAIT
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit b17b833443a3b65907f5ecb36f8af33996f6ec78
Author: Christoph Hellwig <hch at infradead.org>
Date: Mon Oct 10 16:52:43 2011 +0000
xfs: remove xfs_get_buftarg_list
The code is unused and under a config option that doesn't exist, remove it.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 87c7bec7fc3377b3873eb3a0f4b603981ea16ebb
Author: Christoph Hellwig <hch at infradead.org>
Date: Wed Sep 14 14:08:26 2011 +0000
xfs: fix buffer flushing during unmount
The code to flush buffers in the umount code is a bit iffy: we first
flush all delwri buffers out, but then might be able to queue up a
new one when logging the sb counts. On a normal shutdown that one
would get flushed out when doing the synchronous superblock write in
xfs_unmountfs_writesb, but we skip that one if the filesystem has
been shut down.
Fix this by moving the delwri list flushing until just before unmounting
the log, and while we're at it also remove the superflous delwri list
and buffer lru flusing for the rt and log device that can never have
cached or delwri buffers.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reported-by: Amit Sahrawat <amit.sahrawat83 at gmail.com>
Tested-by: Amit Sahrawat <amit.sahrawat83 at gmail.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 1da2f2dbf2d2aaa1b0f6ca2f61fcf07e24eb659b
Author: Christoph Hellwig <hch at infradead.org>
Date: Sun Oct 2 14:25:16 2011 +0000
xfs: optimize fsync on directories
Directories are only updated transactionally, which means fsync only
needs to flush the log the inode is currently dirty, but not bother
with checking for dirty data, non-transactional updates, and most
importanly doesn't have to flush disk caches except as part of a
transaction commit.
While the first two optimizations can't easily be measured, the
latter actually makes a difference when doing lots of fsync that do
not actually have to commit the inode, e.g. because an earlier fsync
already pushed the log far enough.
The new xfs_dir_fsync is identical to xfs_nfs_commit_metadata except
for the prototype, but I'm not sure creating a common helper for the
two is worth it given how simple the functions are.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 670ce93fef93bba8c8a422a79747385bec8e846a
Author: Dave Chinner <dchinner at redhat.com>
Date: Fri Sep 30 04:45:03 2011 +0000
xfs: reduce the number of log forces from tail pushing
The AIL push code will issue a log force on ever single push loop
that it exits and has encountered pinned items. It doesn't rescan
these pinned items until it revisits the AIL from the start. Hence
we only need to force the log once per walk from the start of the
AIL to the target LSN.
This results in numbers like this:
xs_push_ail_flush..... 1456
xs_log_force......... 1485
For an 8-way 50M inode create workload - almost all the log forces
are coming from the AIL pushing code.
Reduce the number of log forces by only forcing the log if the
previous walk found pinned buffers. This reduces the numbers to:
xs_push_ail_flush..... 665
xs_log_force......... 682
For the same test.
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Reviewed-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 3815832a2aa4df9815d15dac05227e0c8551833f
Author: Dave Chinner <dchinner at redhat.com>
Date: Fri Sep 30 04:45:02 2011 +0000
xfs: Don't allocate new buffers on every call to _xfs_buf_find
Stats show that for an 8-way unlink @ ~80,000 unlinks/s we are doing
~1 million cache hit lookups to ~3000 buffer creates. That's almost
3 orders of magnitude more cahce hits than misses, so optimising for
cache hits is quite important. In the cache hit case, we do not need
to allocate a new buffer in case of a cache miss, so we are
effectively hitting the allocator for no good reason for vast the
majority of calls to _xfs_buf_find. 8-way create workloads are
showing similar cache hit/miss ratios.
The result is profiles that look like this:
samples pcnt function DSO
_______ _____ _______________________________ _________________
1036.00 10.0% _xfs_buf_find [kernel.kallsyms]
582.00 5.6% kmem_cache_alloc [kernel.kallsyms]
519.00 5.0% __memcpy [kernel.kallsyms]
468.00 4.5% __ticket_spin_lock [kernel.kallsyms]
388.00 3.7% kmem_cache_free [kernel.kallsyms]
331.00 3.2% xfs_log_commit_cil [kernel.kallsyms]
Further, there is a fair bit of work involved in initialising a new
buffer once a cache miss has occurred and we currently do that under
the rbtree spinlock. That increases spinlock hold time on what are
heavily used trees.
To fix this, remove the initialisation of the buffer from
_xfs_buf_find() and only allocate the new buffer once we've had a
cache miss. Initialise the buffer immediately after allocating it in
xfs_buf_get, too, so that is it ready for insert if we get another
cache miss after allocation. This minimises lock hold time and
avoids unnecessary allocator churn. The resulting profiles look
like:
samples pcnt function DSO
_______ _____ ___________________________ _________________
8111.00 9.1% _xfs_buf_find [kernel.kallsyms]
4380.00 4.9% __memcpy [kernel.kallsyms]
4341.00 4.8% __ticket_spin_lock [kernel.kallsyms]
3401.00 3.8% kmem_cache_alloc [kernel.kallsyms]
2856.00 3.2% xfs_log_commit_cil [kernel.kallsyms]
2625.00 2.9% __kmalloc [kernel.kallsyms]
2380.00 2.7% kfree [kernel.kallsyms]
2016.00 2.3% kmem_cache_free [kernel.kallsyms]
Showing a significant reduction in time spent doing allocation and
freeing from slabs (kmem_cache_alloc and kmem_cache_free).
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Reviewed-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit ddc3415aba1cb2f86d1fcad720cea834ee178f54
Author: Christoph Hellwig <hch at infradead.org>
Date: Mon Sep 19 15:00:54 2011 +0000
xfs: simplify xfs_trans_ijoin* again
There is no reason to keep a reference to the inode even if we unlock
it during transaction commit because we never drop a reference between
the ijoin and commit. Also use this fact to merge xfs_trans_ijoin_ref
back into xfs_trans_ijoin - the third argument decides if an unlock
is needed now.
I'm actually starting to wonder if allowing inodes to be unlocked
at transaction commit really is worth the effort. The only real
benefit is that they can be unlocked earlier when commiting a
synchronous transactions, but that could be solved by doing the
log force manually after the unlock, too.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 23bb0be1a237c8732ce1a43140e5cb103a676b92
Author: Christoph Hellwig <hch at infradead.org>
Date: Sun Sep 18 20:47:51 2011 +0000
xfs: unlock the inode before log force in xfs_change_file_space
Let the transaction commit unlock the inode before it potentially causes
a synchronous log force.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 8292d88c5c833fc8b837c3a018fd6d72c35a3231
Author: Christoph Hellwig <hch at infradead.org>
Date: Sun Sep 18 20:47:50 2011 +0000
xfs: unlock the inode before log force in xfs_fs_nfs_commit_metadata
Only read the LSN we need to push to with the ilock held, and then release
it before we do the log force to improve concurrency.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit b10370585349d364ff3c550afa7922e6e21f029d
Author: Christoph Hellwig <hch at infradead.org>
Date: Mon Sep 19 14:55:51 2011 +0000
xfs: unlock the inode before log force in xfs_fsync
Only read the LSN we need to push to with the ilock held, and then release
it before we do the log force to improve concurrency.
This also removes the only direct caller of _xfs_trans_commit, thus
allowing it to be merged into the plain xfs_trans_commit again.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 815cb21662b914e1e14c256a3d662b1352c8509e
Author: Christoph Hellwig <hch at infradead.org>
Date: Mon Sep 26 09:14:34 2011 +0000
xfs: XFS_TRANS_SWAPEXT is not a valid flag for xfs_trans_commit
XFS_TRANS_SWAPEXT is a transaction type, not a flag for xfs_trans_commit, so
don't pass it in xfs_swap_extents.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit c029a50d51b8a9520105ec903639de03389915d0
Author: Lukas Czerner <lczerner at redhat.com>
Date: Wed Sep 21 09:42:30 2011 +0000
xfs: fix possible overflow in xfs_ioc_trim()
In xfs_ioc_trim it is possible that computing the last allocation group
to discard might overflow for big start & len values, because the result
might be bigger then xfs_agnumber_t which is 32 bit long. Fix this by not
allowing the start and end block of the range to be beyond the end of the
file system.
Note that if the start is beyond the end of the file system we have to
return -EINVAL, but in the "end" case we have to truncate it to the fs
size.
Also introduce "end" variable, rather than using start+len which which
might be more confusing to get right as this bug shows.
Signed-off-by: Lukas Czerner <lczerner at redhat.com>
Reviewed-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit d952e2f81244d6502aff126df5011fab10f92187
Author: Christoph Hellwig <hch at infradead.org>
Date: Sun Sep 18 20:41:07 2011 +0000
xfs: cleanup xfs_bmap.h
Convert all function prototypes to the short form used elsewhere,
and remove duplicates of comments already placed at the function
body.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit b0eab14e74d2d7b22d065e18a1cdebcf7716debf
Author: Christoph Hellwig <hch at infradead.org>
Date: Sun Sep 18 20:41:06 2011 +0000
xfs: dont ignore error code from xfs_bmbt_update
Fix a case in xfs_bmap_add_extent_unwritten_real where we aren't
passing the returned error on.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit c6534249851d062113ab4d8d226be8dba8ecb92e
Author: Christoph Hellwig <hch at infradead.org>
Date: Sun Sep 18 20:41:05 2011 +0000
xfs: pass bmalloca to xfs_bmap_add_extent_hole_real
All the parameters passed to xfs_bmap_add_extent_hole_real() are in
the xfs_bmalloca structure now. Just pass the bmalloca parameter to
the function instead of 8 separate parameters.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 572a4cf04ac7f46e9206aabfef03dae602812341
Author: Christoph Hellwig <hch at infradead.org>
Date: Sun Sep 18 20:41:04 2011 +0000
xfs: pass bmalloca to xfs_bmap_add_extent_delay_real
All the parameters passed to xfs_bmap_add_extent_delay_real() are in
the xfs_bmalloca structure now. Just pass the bmalloca parameter to
the function instead of 8 separate parameters.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit c315c90b7d530d1ec3c226052e153b0cffa512c8
Author: Christoph Hellwig <hch at infradead.org>
Date: Sun Sep 18 20:41:02 2011 +0000
xfs: move logflags into bmalloca
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit e0c3da5d89dc1aeef2275a8b751231e147603f0f
Author: Dave Chinner <dchinner at redhat.com>
Date: Sun Sep 18 20:41:01 2011 +0000
xfs: move lastx and nallocs into bmalloca
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 29c8d17a8938be88e36b93522753f3519aefd05d
Author: Dave Chinner <dchinner at redhat.com>
Date: Sun Sep 18 20:41:00 2011 +0000
xfs: move btree cursor into bmalloca
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 963c30cf45e8c832ae11438ff9d99c954b9d0114
Author: Dave Chinner <dchinner at redhat.com>
Date: Sun Sep 18 20:40:59 2011 +0000
xfs: do not keep local copies of allocation ranges in xfs_bmapi_allocate
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 3a75667e902dbdb87718b1ee2b3b745b344a8163
Author: Dave Chinner <dchinner at redhat.com>
Date: Sun Sep 18 20:40:58 2011 +0000
xfs: rename allocation range fields in struct xfs_bmalloca
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 0937e0fd8be6f9c26844127d39d677bb752e8741
Author: Dave Chinner <dchinner at redhat.com>
Date: Sun Sep 18 20:40:57 2011 +0000
xfs: move firstblock and bmap freelist cursor into bmalloca structure
Rather than passing the firstblock and freelist structure around,
embed it into the bmalloca structure and remove it from the function
parameters.
This also enables the minleft parameter to be set only once in
xfs_bmapi_write(), and the freelist cursor directly queried in
xfs_bmapi_allocate to clear it when the lowspace algorithm is
activated.
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit baf41a52b9c62f9a825371806129ed12e2c1e2d8
Author: Dave Chinner <david at fromorbit.com>
Date: Sun Sep 18 20:40:56 2011 +0000
xfs: move extent records into bmalloca structure
Rather that putting extent records on the stack and then pointing to
them in the bmalloca structure which is in the same stack frame, put
the extent records directly in the bmalloca structure. This reduces
the number of args that need to be passed around.
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 1b16447ba24ae39c7fe7133fcdcb4f174dec1901
Author: Dave Chinner <dchinner at redhat.com>
Date: Sun Sep 18 20:40:55 2011 +0000
xfs: pass bmalloca structure to xfs_bmap_isaeof
All the variables xfs_bmap_isaeof() is passed are contained within
the xfs_bmalloca structure. Pass that instead.
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit a5bd606ba65f24e5990edfc0e7b52702720ee6fa
Author: Christoph Hellwig <hch at infradead.org>
Date: Sun Sep 18 20:40:54 2011 +0000
xfs: remove xfs_bmap_add_extent
There is no real need to the xfs_bmap_add_extent, as the callers
know what kind of extents they need to it. Removing it means
duplicating the extents to btree conversion logic in three places,
but overall it's still much simpler code and quite a bit less code.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 27a3f8f2de758205765f277b3428bbf3d15da973
Author: Christoph Hellwig <hch at infradead.org>
Date: Sun Sep 18 20:40:53 2011 +0000
xfs: introduce xfs_bmap_last_extent
Add a common helper for finding the last extent in a file.
Largely based on a patch from Dave Chinner.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit c0dc7828af6952643219292be29e482ef74cb261
Author: Dave Chinner <dchinner at redhat.com>
Date: Sun Sep 18 20:40:52 2011 +0000
xfs: rename xfs_bmapi to xfs_bmapi_write
Now that all the read-only users of xfs_bmapi have been converted to
use xfs_bmapi_read(), we can remove all the read-only handling cases
from xfs_bmapi().
Once this is done, rename xfs_bmapi to xfs_bmapi_write to reflect
the fact it is for allocation only. This enables us to kill the
XFS_BMAPI_WRITE flag as well.
Also clean up xfs_bmapi_write to the style used in the newly added
xfs_bmapi_read/delay functions.
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit b447fe5a05cbd01c4bf7fe2fa41cb9e99ce7e58e
Author: Dave Chinner <dchinner at redhat.com>
Date: Sun Sep 18 20:40:51 2011 +0000
xfs: factor unwritten extent map manipulations out of xfs_bmapi
To further improve the readability of xfs_bmapi(), factor the
unwritten extent conversion out into a separate function. This
removes large block of logic from the xfs_bmapi() code loop and
makes it easier to see the operational logic flow for xfs_bmapi().
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 7e47a4efde33aa3f0cb901e086a75751c2269f04
Author: Dave Chinner <dchinner at redhat.com>
Date: Sun Sep 18 20:40:50 2011 +0000
xfs: factor extent allocation out of xfs_bmapi
To further improve the readability of xfs_bmapi(), factor the extent
allocation out into a separate function. This removes a large block
of logic from the xfs_bmapi() code loop and makes it easier to see
the operational logic flow for xfs_bmapi().
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 1fd044d9c6735e669f0db025f18023e56a608130
Author: Christoph Hellwig <hch at infradead.org>
Date: Sun Sep 18 20:40:49 2011 +0000
xfs: do not use xfs_bmap_add_extent for adding delalloc extents
We can just call xfs_bmap_add_extent_hole_delay directly to add a
delayed allocated regions to the extent tree, instead of going
through all the complexities of xfs_bmap_add_extent that aren't
needed for this simple case.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 4403280aa5c00c6074f2dc23e1cfc11f2bfb0032
Author: Christoph Hellwig <hch at infradead.org>
Date: Sun Sep 18 20:40:48 2011 +0000
xfs: introduce xfs_bmapi_delay()
Delalloc reservations are much simpler than allocations, so give
them a separate bmapi-level interface. Using the previously added
xfs_bmapi_reserve_delalloc we get a function that is only minimally
more complicated than xfs_bmapi_read, which is far from the complexity
in xfs_bmapi. Also remove the XFS_BMAPI_DELAY code after switching
over the only user to xfs_bmapi_delay.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit b64dfe4e180ab5047c59bcbe379538eb23be4d8e
Author: Christoph Hellwig <hch at infradead.org>
Date: Sun Sep 18 20:40:47 2011 +0000
xfs: factor delalloc reservations out of xfs_bmapi
Move the reservation of delayed allocations, and addition of delalloc
regions to the extent trees into a new helper function. For now
this adds some twisted goto logic to xfs_bmapi, but that will be
cleaned up in the following patches.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 5b777ad517ee75d3bb8d67c142d808822e46601b
Author: Dave Chinner <dchinner at redhat.com>
Date: Sun Sep 18 20:40:46 2011 +0000
xfs: remove xfs_bmapi_single()
Now we have xfs_bmapi_read, there is no need for xfs_bmapi_single().
Change the remaining caller over and kill the function.
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 5c8ed2021ff291f5e399a9b43c4f699b2fc58fbb
Author: Dave Chinner <dchinner at redhat.com>
Date: Sun Sep 18 20:40:45 2011 +0000
xfs: introduce xfs_bmapi_read()
xfs_bmapi() currently handles both extent map reading and
allocation. As a result, the code is littered with "if (wr)"
branches to conditionally do allocation operations if required.
This makes the code much harder to follow and causes significant
indent issues with the code.
Given that read mapping is much simpler than allocation, we can
split out read mapping from xfs_bmapi() and reuse the logic that
we have already factored out do do all the hard work of handling the
extent map manipulations. The results in a much simpler function for
the common extent read operations, and will allow the allocation
code to be simplified in another commit.
Once xfs_bmapi_read() is implemented, convert all the callers of
xfs_bmapi() that are only reading extents to use the new function.
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit aef9a89586fc8475bf0333b8736d5aa8aa6f4897
Author: Dave Chinner <dchinner at redhat.com>
Date: Sun Sep 18 20:40:44 2011 +0000
xfs: factor extent map manipulations out of xfs_bmapi
To further improve the readability of xfs_bmapi(), factor the pure
extent map manipulations out into separate functions. This removes
large blocks of logic from the xfs_bmapi() code loop and makes it
easier to see the operational logic flow for xfs_bmapi().
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit ecee76ba9d91fdcbdff933ca1bd41465ca4c4fdb
Author: Christoph Hellwig <hch at infradead.org>
Date: Sun Sep 18 20:40:43 2011 +0000
xfs: remove the nextents variable in xfs_bmapi
Instead of using a local variable that needs to updated when we modify
the extent map just check ifp->if_bytes directly where we use it.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit b9b984d7846e37c57e5b3f8cd883ad45e8ebc2cf
Author: Christoph Hellwig <hch at infradead.org>
Date: Sun Sep 18 20:40:42 2011 +0000
xfs: remove impossible to read code in xfs_bmap_add_extent_delay_real
We already have the worst case blocks reserved, so xfs_icsb_modify_counters
won't fail in xfs_bmap_add_extent_delay_real. In fact we've had an assert
to catch this case since day and it never triggered. So remove the code
to try smaller reservations, and just return the error for that case in
addition to keeping the assert.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit e7455e02e5effcdd49bb28e7dfface2d3473de52
Author: Christoph Hellwig <hch at infradead.org>
Date: Sun Sep 18 20:40:41 2011 +0000
xfs: remove the first extent special case in xfs_bmap_add_extent
Both xfs_bmap_add_extent_hole_delay and xfs_bmap_add_extent_hole_real
already contain code to handle the case where there is no extent to
merge with, which is effectively the same as the code duplicated here.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit ed32201e65e15f3e6955cb84cbb544b08f81e5a5
Author: Mitsuo Hayasaka <mitsuo.hayasaka.hu at hitachi.com>
Date: Sat Sep 17 13:38:38 2011 +0000
xfs: Return -EIO when xfs_vn_getattr() failed
An attribute of inode can be fetched via xfs_vn_getattr() in XFS.
Currently it returns EIO, not negative value, when it failed. As a
result, the system call returns not negative value even though an
error occured. The stat(2), ls and mv commands cannot handle this
error and do not work correctly.
This patch fixes this bug, and returns -EIO, not EIO when an error
is detected in xfs_vn_getattr().
Signed-off-by: Mitsuo Hayasaka <mitsuo.hayasaka.hu at hitachi.com>
Reviewed-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit eabbaf118239d0d4188298b52751040f3b4cc28f
Author: Chandra Seetharaman <sekharan at us.ibm.com>
Date: Thu Sep 8 20:18:50 2011 +0000
xfs: Fix the incorrect comment in the header of _xfs_buf_find
Fix the incorrect comment in the header of the function
_xfs_buf_find().
Signed-off-by: Chandra Seetharaman <sekharan at us.ibm.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 2a30f36d9069b0646dcdd73def5fd7ab674bffd6
Author: Chandra Seetharaman <sekharan at us.ibm.com>
Date: Tue Sep 20 13:56:55 2011 +0000
xfs: Check the return value of xfs_trans_get_buf()
Check the return value of xfs_trans_get_buf() and fail
appropriately.
Signed-off-by: Chandra Seetharaman <sekharan at us.ibm.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit b522950f0ab8551f2ef56c210ebd50e6c6396601
Author: Chandra Seetharaman <sekharan at us.ibm.com>
Date: Wed Sep 7 19:37:54 2011 +0000
xfs: Check the return value of xfs_buf_get()
Check the return value of xfs_buf_get() and fail appropriately.
Signed-off-by: Chandra Seetharaman <sekharan at us.ibm.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 04f658ee229f60dbb9a0dc2f3d6871b12b758051
Author: Christoph Hellwig <hch at infradead.org>
Date: Wed Aug 24 05:59:25 2011 +0000
xfs: improve ioend error handling
Return unwritten extent conversion errors to aio_complete.
Skip both unwritten extent conversion and size updates if we had an
I/O error or the filesystem has been shut down.
Return -EIO to the aio/buffer completion handlers in case of a
forced shutdown.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit c58cb165bd44de8aaee9755a144136ae743be116
Author: Christoph Hellwig <hch at infradead.org>
Date: Sat Aug 27 14:42:53 2011 +0000
xfs: avoid direct I/O write vs buffered I/O race
Currently a buffered reader or writer can add pages to the pagecache
while we are waiting for the iolock in xfs_file_dio_aio_write. Prevent
this by re-checking mapping->nrpages after we got the iolock, and if
nessecary upgrade the lock to exclusive mode. To simplify this a bit
only take the ilock inside of xfs_file_aio_write_checks.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 859f57ca00805e6c482eef1a7ab073097d02c8ca
Author: Christoph Hellwig <hch at infradead.org>
Date: Sat Aug 27 14:45:11 2011 +0000
xfs: avoid synchronous transactions when deleting attr blocks
Currently xfs_attr_inactive causes a synchronous transactions if we are
removing a file that has any extents allocated to the attribute fork, and
thus makes XFS extremely slow at removing files with out of line extended
attributes. The code looks a like a relict from the days before the busy
extent list, but with the busy extent list we avoid reusing data and attr
extents that have been freed but not commited yet, so this code is just
as superflous as the synchronous transactions for data blocks.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reported-by: Bernd Schubert <bernd.schubert at itwm.fraunhofer.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 4a06fd262dbeb70a2c315f7259e063efa493fe3d
Author: Christoph Hellwig <hch at infradead.org>
Date: Tue Aug 23 08:28:13 2011 +0000
xfs: remove i_iocount
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: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 2b3ffd7eb7b4392e3657c5046b055ca9f1f7cf5e
Author: Christoph Hellwig <hch at infradead.org>
Date: Tue Aug 23 08:28:12 2011 +0000
xfs: wait for I/O completion when writing out pages in xfs_setattr_size
The current code relies on the xfs_ioend_wait call later on to make sure
all I/O actually has completed. The xfs_ioend_wait call will go away soon,
so prepare for that by using the waiting filemap function.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit fc0063c4474599b7a066ba76b90902abe21bc675
Author: Christoph Hellwig <hch at infradead.org>
Date: Tue Aug 23 08:28:11 2011 +0000
xfs: reduce ioend latency
There is no reason to queue up ioends for processing in user context
unless we actually need it. Just complete ioends that do not convert
unwritten extents or need a size update from the end_io context.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit c859cdd1da008b3825555be3242908088a3de366
Author: Christoph Hellwig <hch at infradead.org>
Date: Tue Aug 23 08:28:10 2011 +0000
xfs: defer AIO/DIO completions
We really shouldn't complete AIO or DIO requests until we have finished
the unwritten extent conversion and size update. This means fsync never
has to pick up any ioends as all work has been completed when signalling
I/O completion.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 398d25ef23b10ce75424e0336a8d059dda1dbc8d
Author: Christoph Hellwig <hch at infradead.org>
Date: Tue Aug 23 08:28:09 2011 +0000
xfs: remove dead ENODEV handling in xfs_destroy_ioend
No driver returns ENODEV from it bio completion handler, not has this
ever been documented. Remove the dead code dealing with it.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit c4e1c098ee8a72ea563a697a2b175868be86fdc9
Author: Christoph Hellwig <hch at infradead.org>
Date: Tue Aug 23 08:28:08 2011 +0000
xfs: use the "delwri" terminology consistently
And also remove the strange local lock and delwri list pointers in a few
functions.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit c2b006c1da1602551def200e4661535f02b82488
Author: Christoph Hellwig <hch at infradead.org>
Date: Tue Aug 23 08:28:07 2011 +0000
xfs: let xfs_bwrite callers handle the xfs_buf_relse
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: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 61551f1ee536289084a4a8f1c4f187e2f371c440
Author: Christoph Hellwig <hch at infradead.org>
Date: Tue Aug 23 08:28:06 2011 +0000
xfs: call xfs_buf_delwri_queue directly
Unify the ways we add buffers to the delwri queue by always calling
xfs_buf_delwri_queue directly. The xfs_bdwrite functions is removed and
opencoded in its callers, and the two places setting XBF_DELWRI while a
buffer is locked and expecting xfs_buf_unlock to pick it up are converted
to call xfs_buf_delwri_queue directly, too. Also replace the
XFS_BUF_UNDELAYWRITE macro with direct calls to xfs_buf_delwri_dequeue
to make the explicit queuing/dequeuing more obvious.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 5a8ee6bafdd0ab8555adceac8b2cec539a552a1f
Author: Christoph Hellwig <hch at infradead.org>
Date: Tue Aug 23 08:28:05 2011 +0000
xfs: move more delwri setup into xfs_buf_delwri_queue
Do not transfer a reference held by the caller to the buffer on the list,
or decrement it in xfs_buf_delwri_queue, but instead grab a new reference
if needed, and let the caller drop its own reference. Also move setting
of the XBF_DELWRI and XBF_ASYNC flags into xfs_buf_delwri_queue, and
only do it if needed. Note that for now xfs_buf_unlock already has
XBF_DELWRI, but that will change in the following patches.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 527cfdf19dd538a5a9e46b9bed0f30a38c28438d
Author: Christoph Hellwig <hch at infradead.org>
Date: Tue Aug 23 08:28:04 2011 +0000
xfs: remove the unlock argument to xfs_buf_delwri_queue
We can just unlock the buffer in the caller, and the decrement of b_hold
would also be needed in the !unlock, we just never hit that case currently
given that the caller handles that case.
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 375ec69d2ef6e0797f19f5823e36e249765c3d41
Author: Christoph Hellwig <hch at infradead.org>
Date: Tue Aug 23 08:28:03 2011 +0000
xfs: remove delwri buffer handling from xfs_buf_iorequest
We cannot ever reach xfs_buf_iorequest for a buffer with XBF_DELWRI set,
given that all write handlers make sure that the buffer is remove from
the delwri queue before, and we never do reads with the XBF_DELWRI flag
set (which the code would not handle correctly anyway).
Signed-off-by: Christoph Hellwig <hch at lst.de>
Reviewed-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 7271d243f9d1b4106289e4cf876c8b1203de59ab
Author: Dave Chinner <david at fromorbit.com>
Date: Thu Aug 25 07:17:02 2011 +0000
xfs: don't serialise adjacent concurrent direct IO appending writes
For append write workloads, extending the file requires a certain
amount of exclusive locking to be done up front to ensure sanity in
things like ensuring that we've zeroed any allocated regions
between the old EOF and the start of the new IO.
For single threads, this typically isn't a problem, and for large
IOs we don't serialise enough for it to be a problem for two
threads on really fast block devices. However for smaller IO and
larger thread counts we have a problem.
Take 4 concurrent sequential, single block sized and aligned IOs.
After the first IO is submitted but before it completes, we end up
with this state:
IO 1 IO 2 IO 3 IO 4
+-------+-------+-------+-------+
^ ^
| |
| |
| |
| \- ip->i_new_size
\- ip->i_size
And the IO is done without exclusive locking because offset <=
ip->i_size. When we submit IO 2, we see offset > ip->i_size, and
grab the IO lock exclusive, because there is a chance we need to do
EOF zeroing. However, there is already an IO in progress that avoids
the need for IO zeroing because offset <= ip->i_new_size. hence we
could avoid holding the IO lock exlcusive for this. Hence after
submission of the second IO, we'd end up this state:
IO 1 IO 2 IO 3 IO 4
+-------+-------+-------+-------+
^ ^
| |
| |
| |
| \- ip->i_new_size
\- ip->i_size
There is no need to grab the i_mutex of the IO lock in exclusive
mode if we don't need to invalidate the page cache. Taking these
locks on every direct IO effective serialises them as taking the IO
lock in exclusive mode has to wait for all shared holders to drop
the lock. That only happens when IO is complete, so effective it
prevents dispatch of concurrent direct IO writes to the same inode.
And so you can see that for the third concurrent IO, we'd avoid
exclusive locking for the same reason we avoided the exclusive lock
for the second IO.
Fixing this is a bit more complex than that, because we need to hold
a write-submission local value of ip->i_new_size to that clearing
the value is only done if no other thread has updated it before our
IO completes.....
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Signed-off-by: Alex Elder <aelder at sgi.com>
commit 0c38a2512df272b14ef4238b476a2e4f70da1479
Author: Dave Chinner <dchinner at redhat.com>
Date: Thu Aug 25 07:17:01 2011 +0000
xfs: don't serialise direct IO reads on page cache checks
There is no need to grab the i_mutex of the IO lock in exclusive
mode if we don't need to invalidate the page cache. Taking these
locks on every direct IO effective serialises them as taking the IO
lock in exclusive mode has to wait for all shared holders to drop
the lock. That only happens when IO is complete, so effective it
prevents dispatch of concurrent direct IO reads to the same inode.
Fix this by taking the IO lock shared to check the page cache state,
and only then drop it and take the IO lock exclusively if there is
work to be done. Hence for the normal direct IO case, no exclusive
locking will occur.
Signed-off-by: Dave Chinner <dchinner at redhat.com>
Tested-by: Joern Engel <joern at logfs.org>
Reviewed-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Alex Elder <aelder at sgi.com>
-----------------------------------------------------------------------
Summary of changes:
fs/xfs/xfs_alloc.c | 4 +-
fs/xfs/xfs_aops.c | 119 +--
fs/xfs/xfs_aops.h | 4 +-
fs/xfs/xfs_attr.c | 89 +-
fs/xfs/xfs_attr_leaf.c | 7 +-
fs/xfs/xfs_bmap.c | 2531 +++++++++++++++++++++++-----------------------
fs/xfs/xfs_bmap.h | 318 ++-----
fs/xfs/xfs_btree.c | 11 +-
fs/xfs/xfs_buf.c | 244 ++---
fs/xfs/xfs_buf.h | 51 +-
fs/xfs/xfs_buf_item.c | 12 +-
fs/xfs/xfs_da_btree.c | 54 +-
fs/xfs/xfs_dfrag.c | 6 +-
fs/xfs/xfs_dir2_leaf.c | 6 +-
fs/xfs/xfs_discard.c | 20 +-
fs/xfs/xfs_dquot.c | 32 +-
fs/xfs/xfs_export.c | 12 +-
fs/xfs/xfs_file.c | 168 +++-
fs/xfs/xfs_filestream.c | 4 +-
fs/xfs/xfs_fsops.c | 60 +-
fs/xfs/xfs_ialloc.c | 15 +-
fs/xfs/xfs_iget.c | 2 -
fs/xfs/xfs_inode.c | 43 +-
fs/xfs/xfs_inode.h | 1 -
fs/xfs/xfs_inode_item.c | 4 +-
fs/xfs/xfs_ioctl.c | 2 +-
fs/xfs/xfs_iomap.c | 39 +-
fs/xfs/xfs_iops.c | 14 +-
fs/xfs/xfs_log.c | 20 +-
fs/xfs/xfs_log_recover.c | 43 +-
fs/xfs/xfs_mount.c | 36 +-
fs/xfs/xfs_qm.c | 12 +-
fs/xfs/xfs_qm_syscalls.c | 2 +-
fs/xfs/xfs_rename.c | 8 +-
fs/xfs/xfs_rtalloc.c | 48 +-
fs/xfs/xfs_rw.c | 23 +-
fs/xfs/xfs_rw.h | 2 -
fs/xfs/xfs_super.c | 13 +-
fs/xfs/xfs_sync.c | 16 +-
fs/xfs/xfs_trace.h | 2 +-
fs/xfs/xfs_trans.c | 13 +-
fs/xfs/xfs_trans.h | 8 +-
fs/xfs/xfs_trans_ail.c | 35 +-
fs/xfs/xfs_trans_buf.c | 24 +-
fs/xfs/xfs_trans_inode.c | 25 +-
fs/xfs/xfs_trans_priv.h | 1 +
fs/xfs/xfs_vnodeops.c | 109 +--
47 files changed, 1988 insertions(+), 2324 deletions(-)
hooks/post-receive
--
XFS development tree
More information about the xfs
mailing list