Revision b121186ab1b12e2a96a945d88eae0735b4542158 authored by Alex Shi on 21 August 2012, 23:16:08 UTC, committed by Linus Torvalds on 21 August 2012, 23:45:03 UTC
Commit cfd19c5a9ecf ("mm: only set page->pfmemalloc when
ALLOC_NO_WATERMARKS was used") tried to narrow down page->pfmemalloc
setting, but it missed some places the pfmemalloc should be set.

So, in __slab_alloc, the unalignment pfmemalloc and ALLOC_NO_WATERMARKS
cause incorrect deactivate_slab() on our core2 server:

    64.73%           fio  [kernel.kallsyms]     [k] _raw_spin_lock
                     |
                     --- _raw_spin_lock
                        |
                        |---0.34%-- deactivate_slab
                        |          __slab_alloc
                        |          kmem_cache_alloc
                        |          |

That causes our fio sync write performance to have a 40% regression.

Move the checking in get_page_from_freelist() which resolves this issue.

Signed-off-by: Alex Shi <alex.shi@intel.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: David Miller <davem@davemloft.net
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Eric Dumazet <eric.dumazet@gmail.com>
Tested-by: Sage Weil <sage@inktank.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 5ed12f1
Raw File
xfs_aops.h
/*
 * Copyright (c) 2005-2006 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#ifndef __XFS_AOPS_H__
#define __XFS_AOPS_H__

extern mempool_t *xfs_ioend_pool;

/*
 * Types of I/O for bmap clustering and I/O completion tracking.
 */
enum {
	XFS_IO_DIRECT = 0,	/* special case for direct I/O ioends */
	XFS_IO_DELALLOC,	/* covers delalloc region */
	XFS_IO_UNWRITTEN,	/* covers allocated but uninitialized data */
	XFS_IO_OVERWRITE,	/* covers already allocated extent */
};

#define XFS_IO_TYPES \
	{ 0,			"" }, \
	{ XFS_IO_DELALLOC,		"delalloc" }, \
	{ XFS_IO_UNWRITTEN,		"unwritten" }, \
	{ XFS_IO_OVERWRITE,		"overwrite" }

/*
 * xfs_ioend struct manages large extent writes for XFS.
 * It can manage several multi-page bio's at once.
 */
typedef struct xfs_ioend {
	struct xfs_ioend	*io_list;	/* next ioend in chain */
	unsigned int		io_type;	/* delalloc / unwritten */
	int			io_error;	/* I/O error code */
	atomic_t		io_remaining;	/* hold count */
	unsigned int		io_isasync : 1;	/* needs aio_complete */
	unsigned int		io_isdirect : 1;/* direct I/O */
	struct inode		*io_inode;	/* file being written to */
	struct buffer_head	*io_buffer_head;/* buffer linked list head */
	struct buffer_head	*io_buffer_tail;/* buffer linked list tail */
	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 kiocb		*io_iocb;
	int			io_result;
} xfs_ioend_t;

extern const struct address_space_operations xfs_address_space_operations;
extern int xfs_get_blocks(struct inode *, sector_t, struct buffer_head *, int);

extern void xfs_count_page_state(struct page *, int *, int *);

#endif /* __XFS_AOPS_H__ */
back to top