linux_dsm_epyc7002/fs/xfs/xfs_aops.h

56 lines
1.8 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2005-2006 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#ifndef __XFS_AOPS_H__
#define __XFS_AOPS_H__
extern struct bio_set xfs_ioend_bioset;
/*
* Types of I/O for bmap clustering and I/O completion tracking.
*/
enum {
xfs: Introduce writeback context for writepages xfs_vm_writepages() calls generic_writepages to writeback a range of a file, but then xfs_vm_writepage() clusters pages itself as it does not have any context it can pass between->writepage calls from __write_cache_pages(). Introduce a writeback context for xfs_vm_writepages() and call __write_cache_pages directly with our own writepage callback so that we can pass that context to each writepage invocation. This encapsulates the current mapping, whether it is valid or not, the current ioend and it's IO type and the ioend chain being built. This requires us to move the ioend submission up to the level where the writepage context is declared. This does mean we do not submit IO until we packaged the entire writeback range, but with the block plugging in the writepages call this is the way IO is submitted, anyway. It also means that we need to handle discontiguous page ranges. If the pages sent down by write_cache_pages to the writepage callback are discontiguous, we need to detect this and put each discontiguous page range into individual ioends. This is needed to ensure that the ioend accurately represents the range of the file that it covers so that file size updates during IO completion set the size correctly. Failure to take into account the discontiguous ranges results in files being too small when writeback patterns are non-sequential. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-02-15 13:21:19 +07:00
XFS_IO_INVALID, /* initial state */
XFS_IO_DELALLOC, /* covers delalloc region */
XFS_IO_UNWRITTEN, /* covers allocated but uninitialized data */
XFS_IO_OVERWRITE, /* covers already allocated extent */
XFS_IO_COW, /* covers copy-on-write extent */
XFS_IO_HOLE, /* covers region without any block allocation */
};
#define XFS_IO_TYPES \
xfs: Introduce writeback context for writepages xfs_vm_writepages() calls generic_writepages to writeback a range of a file, but then xfs_vm_writepage() clusters pages itself as it does not have any context it can pass between->writepage calls from __write_cache_pages(). Introduce a writeback context for xfs_vm_writepages() and call __write_cache_pages directly with our own writepage callback so that we can pass that context to each writepage invocation. This encapsulates the current mapping, whether it is valid or not, the current ioend and it's IO type and the ioend chain being built. This requires us to move the ioend submission up to the level where the writepage context is declared. This does mean we do not submit IO until we packaged the entire writeback range, but with the block plugging in the writepages call this is the way IO is submitted, anyway. It also means that we need to handle discontiguous page ranges. If the pages sent down by write_cache_pages to the writepage callback are discontiguous, we need to detect this and put each discontiguous page range into individual ioends. This is needed to ensure that the ioend accurately represents the range of the file that it covers so that file size updates during IO completion set the size correctly. Failure to take into account the discontiguous ranges results in files being too small when writeback patterns are non-sequential. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-02-15 13:21:19 +07:00
{ XFS_IO_INVALID, "invalid" }, \
{ XFS_IO_DELALLOC, "delalloc" }, \
{ XFS_IO_UNWRITTEN, "unwritten" }, \
{ XFS_IO_OVERWRITE, "overwrite" }, \
{ XFS_IO_COW, "CoW" }, \
{ XFS_IO_HOLE, "hole" }
/*
* Structure for buffered I/O completions.
*/
struct xfs_ioend {
xfs: don't chain ioends during writepage submission Currently we can build a long ioend chain during ->writepages that gets attached to the writepage context. IO submission only then occurs when we finish all the writepage processing. This means we can have many ioends allocated and pending, and this violates the mempool guarantees that we need to give about forwards progress. i.e. we really should only have one ioend being built at a time, otherwise we may drain the mempool trying to allocate a new ioend and that blocks submission, completion and freeing of ioends that are already in progress. To prevent this situation from happening, we need to submit ioends for IO as soon as they are ready for dispatch rather than queuing them for later submission. This means the ioends have bios built immediately and they get queued on any plug that is current active. Hence if we schedule away from writeback, the ioends that have been built will make forwards progress due to the plug flushing on context switch. This will also prevent context switches from creating unnecessary IO submission latency. We can't completely avoid having nested IO allocation - when we have a block size smaller than a page size, we still need to hold the ioend submission until after we have marked the current page dirty. Hence we may need multiple ioends to be held while the current page is completely mapped and made ready for IO dispatch. We cannot avoid this problem - the current code already has this ioend chaining within a page so we can mostly ignore that it occurs. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dave Chinner <david@fromorbit.com>
2016-02-15 13:23:12 +07:00
struct list_head io_list; /* next ioend in chain */
unsigned int io_type; /* delalloc / unwritten */
struct inode *io_inode; /* file being written to */
size_t io_size; /* size of the extent */
xfs_off_t io_offset; /* offset in the file */
struct work_struct io_work; /* xfsdatad work queue */
struct xfs_trans *io_append_trans;/* xact. for size update */
struct bio *io_bio; /* bio being built */
struct bio io_inline_bio; /* MUST BE LAST! */
};
extern const struct address_space_operations xfs_address_space_operations;
extern const struct address_space_operations xfs_dax_aops;
int xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size);
extern void xfs_count_page_state(struct page *, int *, int *);
extern struct block_device *xfs_find_bdev_for_inode(struct inode *);
extern struct dax_device *xfs_find_daxdev_for_inode(struct inode *);
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-15 06:14:59 +07:00
#endif /* __XFS_AOPS_H__ */