linux/fs/xfs
Christoph Hellwig 43ff2122e6 xfs: on-stack delayed write buffer lists
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: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
2012-05-14 16:20:31 -05:00
..
Kconfig quota: Make QUOTACTL config be selected by its users 2010-10-05 12:16:37 +02:00
kmem.c xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
kmem.h xfs: use a normal shrinker for the dquot freelist 2012-02-10 12:38:09 -06:00
Makefile xfs: use common code for quota statistics 2012-03-14 11:09:06 -05:00
mrlock.h xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
time.h xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
uuid.c xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
uuid.h xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
xfs_acl.c xfs: fix acl count validation in xfs_acl_from_disk() 2011-12-16 15:17:42 -06:00
xfs_acl.h xfs: Fix build breakage in xfs_iops.c when CONFIG_FS_POSIX_ACL is not set 2011-08-01 02:35:04 -04:00
xfs_ag.h xfs: Remove the macro XFS_BUF_PTR 2011-07-25 15:03:13 -05:00
xfs_alloc_btree.c xfs: remove leftovers of the old btree tracing code 2011-07-13 13:43:50 +02:00
xfs_alloc_btree.h
xfs_alloc.c xfs: fix fstrim offset calculations 2012-03-27 16:07:03 -05:00
xfs_alloc.h xfs: fix fstrim offset calculations 2012-03-27 16:07:03 -05:00
xfs_aops.c xfs: punch all delalloc blocks beyond EOF on write failure. 2012-05-14 16:20:22 -05:00
xfs_aops.h xfs: log file size updates at I/O completion time 2012-03-13 16:30:49 -05:00
xfs_attr_leaf.c xfs: add lots of attribute trace points 2012-03-27 17:18:21 -05:00
xfs_attr_leaf.h
xfs_attr_sf.h xfs: convert attr to use unsigned names 2010-01-20 10:47:48 +11:00
xfs_attr.c xfs: add lots of attribute trace points 2012-03-27 17:18:21 -05:00
xfs_attr.h xfs: convert attr to use unsigned names 2010-01-20 10:47:48 +11:00
xfs_bit.c
xfs_bit.h
xfs_bmap_btree.c xfs: remove leftovers of the old btree tracing code 2011-07-13 13:43:50 +02:00
xfs_bmap_btree.h xfs: make several more functions static 2010-01-15 15:31:38 -06:00
xfs_bmap.c xfs: fix deadlock in xfs_rtfree_extent 2012-03-22 15:31:06 -05:00
xfs_bmap.h xfs: cleanup xfs_bmap.h 2011-10-11 21:15:07 -05:00
xfs_btree.c xfs: remove XFS_BUF_SET_VTYPE and XFS_BUF_SET_VTYPE_REF 2011-10-11 21:15:09 -05:00
xfs_btree.h xfs: Remove the macro XFS_BUF_PTR 2011-07-25 15:03:13 -05:00
xfs_buf_item.c xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_buf_item.h xfs: use struct list_head for the buf cancel table 2010-12-16 16:05:22 -06:00
xfs_buf.c xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_buf.h xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_da_btree.c xfs: add lots of attribute trace points 2012-03-27 17:18:21 -05:00
xfs_da_btree.h xfs: remove the dead XFS_DABUF_DEBUG code 2011-07-13 13:43:50 +02:00
xfs_dfrag.c xfs: split in-core and on-disk inode log item fields 2012-03-13 17:08:17 -05:00
xfs_dfrag.h xfs: clean up inconsistent variable naming in xfs_swap_extent 2010-01-15 15:31:23 -06:00
xfs_dinode.h xfs: Remove the macro XFS_BUF_PTR 2011-07-25 15:03:13 -05:00
xfs_dir2_block.c xfs: clean up minor sparse warnings 2012-03-14 13:21:17 -05:00
xfs_dir2_data.c xfs: reshuffle dir2 headers 2011-07-13 13:43:48 +02:00
xfs_dir2_format.h xfs: cleanup struct xfs_dir2_free 2011-07-13 13:43:48 +02:00
xfs_dir2_leaf.c xfs: introduce xfs_bmapi_read() 2011-10-11 21:15:03 -05:00
xfs_dir2_node.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial 2011-07-25 13:56:39 -07:00
xfs_dir2_priv.h xfs: reshuffle dir2 headers 2011-07-13 13:43:48 +02:00
xfs_dir2_sf.c xfs: reshuffle dir2 headers 2011-07-13 13:43:48 +02:00
xfs_dir2.c xfs: get rid of open-coded S_ISREG(), etc. 2011-07-26 15:05:16 -04:00
xfs_dir2.h xfs: reshuffle dir2 headers 2011-07-13 13:43:48 +02:00
xfs_discard.c xfs: fix fstrim offset calculations 2012-03-27 16:07:03 -05:00
xfs_discard.h xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
xfs_dquot_item.c xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_dquot_item.h xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
xfs_dquot.c xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_dquot.h xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_error.c xfs: Convert remaining cmn_err() callers to new API 2011-03-07 10:08:35 +11:00
xfs_error.h xfs: kill support/debug.[ch] 2011-03-07 10:09:35 +11:00
xfs_export.c xfs: fix nfs export of 64-bit inodes numbers on 32-bit kernels 2011-12-06 10:46:23 -06:00
xfs_export.h xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
xfs_extfree_item.c xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_extfree_item.h xfs: Pull EFI/EFD handling out from under the AIL lock 2010-12-20 11:59:49 +11:00
xfs_file.c xfs: push the ilock into xfs_zero_eof 2012-05-14 16:20:20 -05:00
xfs_filestream.c xfs: rename allocation range fields in struct xfs_bmalloca 2011-10-11 21:15:06 -05:00
xfs_filestream.h xfs: clean up filestreams helpers 2010-07-26 13:16:51 -05:00
xfs_fs_subr.c xfs: remove the i_size field in struct xfs_inode 2012-01-17 15:08:53 -06:00
xfs_fs.h xfs: consolidate & clarify mount sanity checks 2011-07-08 11:32:51 -05:00
xfs_fsops.c xfs: Check the return value of xfs_buf_get() 2011-10-11 21:15:01 -05:00
xfs_fsops.h xfs: ensure log covering transactions are synchronous 2011-01-11 20:28:17 -06:00
xfs_globals.c xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
xfs_ialloc_btree.c xfs: remove leftovers of the old btree tracing code 2011-07-13 13:43:50 +02:00
xfs_ialloc_btree.h
xfs_ialloc.c xfs: propagate umode_t 2012-01-03 22:55:00 -05:00
xfs_ialloc.h xfs: propagate umode_t 2012-01-03 22:55:00 -05:00
xfs_iget.c xfs: remove log item from AIL in xfs_iflush after a shutdown 2012-05-14 16:20:25 -05:00
xfs_inode_item.c xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_inode_item.h xfs: reimplement fdatasync support 2012-03-13 17:18:14 -05:00
xfs_inode.c xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_inode.h xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_inum.h xfs: cleanup shortform directory inode number handling 2011-07-08 14:35:03 +02:00
xfs_ioctl32.c xfs: clean up minor sparse warnings 2012-03-14 13:21:17 -05:00
xfs_ioctl32.h xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
xfs_ioctl.c xfs: Fix open flag handling in open_by_handle code 2012-03-22 15:56:52 -05:00
xfs_ioctl.h xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
xfs_iomap.c xfs: use shared ilock mode for direct IO writes by default 2012-05-14 16:20:21 -05:00
xfs_iomap.h xfs: kill xfs_iomap 2010-12-16 16:05:51 -06:00
xfs_iops.c xfs: push the ilock into xfs_zero_eof 2012-05-14 16:20:20 -05:00
xfs_iops.h xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
xfs_itable.c xfs: don't cache inodes read through bulkstat 2012-03-26 17:19:08 -05:00
xfs_itable.h xfs: remove block number from inode lookup code 2010-06-24 11:35:17 +10:00
xfs_linux.h xfs: revert to using a kthread for AIL pushing 2011-10-11 11:02:49 -05:00
xfs_log_cil.c Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial 2012-01-08 13:21:22 -08:00
xfs_log_priv.h xfs: split and cleanup xfs_log_reserve 2012-02-22 22:37:04 -06:00
xfs_log_recover.c xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_log_recover.h xfs: Clean up XFS_BLI_* flag namespace 2010-05-24 10:33:39 -05:00
xfs_log.c xfs: allow assigning the tail lsn with the AIL lock held 2012-05-14 16:20:26 -05:00
xfs_log.h xfs: allow assigning the tail lsn with the AIL lock held 2012-05-14 16:20:26 -05:00
xfs_message.c xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
xfs_message.h treewide: use __printf not __attribute__((format(printf,...))) 2011-10-31 17:30:54 -07:00
xfs_mount.c xfs: implement freezing by emptying the AIL 2012-05-14 16:20:27 -05:00
xfs_mount.h xfs: implement freezing by emptying the AIL 2012-05-14 16:20:27 -05:00
xfs_mru_cache.c xfs: convert to alloc_workqueue() 2011-02-01 11:42:43 +01:00
xfs_mru_cache.h xfs: Kill filestreams cache flush 2010-01-15 15:34:22 -06:00
xfs_qm_bhv.c xfs: remove the global xfs_Gqm structure 2012-03-14 12:06:32 -05:00
xfs_qm_syscalls.c xfs: remove the per-filesystem list of dquots 2012-03-14 11:53:34 -05:00
xfs_qm.c xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_qm.h xfs: remove the global xfs_Gqm structure 2012-03-14 12:06:32 -05:00
xfs_quota_priv.h xfs: use per-filesystem radix trees for dquot lookup 2012-03-14 11:09:06 -05:00
xfs_quota.h Define new macro XFS_ALL_QUOTA_ACTIVE and simply some usage 2012-02-03 11:32:20 -06:00
xfs_quotaops.c xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
xfs_rename.c vfs: check i_nlink limits in vfs_{mkdir,rename_dir,link} 2012-03-20 21:29:32 -04:00
xfs_rtalloc.c xfs: fix deadlock in xfs_rtfree_extent 2012-03-22 15:31:06 -05:00
xfs_rtalloc.h xfs: Remove the macro XFS_BUF_PTR 2011-07-25 15:03:13 -05:00
xfs_rw.c xfs: clean up xfs_ioerror_alert 2011-10-11 21:15:10 -05:00
xfs_rw.h xfs: clean up xfs_ioerror_alert 2011-10-11 21:15:10 -05:00
xfs_sb.h xfs: kill the unused XFS_BB_FSB_OFFSET macro 2012-02-02 17:08:04 -06:00
xfs_stats.c xfs: use common code for quota statistics 2012-03-14 11:09:06 -05:00
xfs_stats.h xfs: use common code for quota statistics 2012-03-14 11:09:06 -05:00
xfs_super.c xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_super.h xfs: remove the global xfs_Gqm structure 2012-03-14 12:06:32 -05:00
xfs_sync.c xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_sync.h xfs: log timestamp updates 2012-03-13 17:01:15 -05:00
xfs_sysctl.c xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
xfs_sysctl.h xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
xfs_trace.c xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
xfs_trace.h xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_trans_ail.c xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_trans_buf.c xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_trans_dquot.c xfs: remove the global xfs_Gqm structure 2012-03-14 12:06:32 -05:00
xfs_trans_extfree.c xfs: Pull EFI/EFD handling out from under the AIL lock 2010-12-20 11:59:49 +11:00
xfs_trans_inode.c xfs: split in-core and on-disk inode log item fields 2012-03-13 17:08:17 -05:00
xfs_trans_priv.h xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_trans_space.h
xfs_trans.c xfs: split and cleanup xfs_log_reserve 2012-02-22 22:37:04 -06:00
xfs_trans.h xfs: on-stack delayed write buffer lists 2012-05-14 16:20:31 -05:00
xfs_types.h xfs: exact busy extent tracking 2011-04-28 13:18:04 -05:00
xfs_utils.c vfs: check i_nlink limits in vfs_{mkdir,rename_dir,link} 2012-03-20 21:29:32 -04:00
xfs_utils.h xfs: propagate umode_t 2012-01-03 22:55:00 -05:00
xfs_vnode.h xfs: remove remaining scraps of struct xfs_iomap 2012-03-15 13:40:16 -05:00
xfs_vnodeops.c vfs: check i_nlink limits in vfs_{mkdir,rename_dir,link} 2012-03-20 21:29:32 -04:00
xfs_vnodeops.h xfs: remove remaining scraps of struct xfs_iomap 2012-03-15 13:40:16 -05:00
xfs_xattr.c xfs: remove subdirectories 2011-08-12 16:21:35 -05:00
xfs.h xfs: don't expect xfs headers to be in subdirectories 2011-08-12 13:57:55 -05:00