• W
    readahead: introduce FMODE_RANDOM for POSIX_FADV_RANDOM · 0141450f
    Wu Fengguang 提交于
    This fixes inefficient page-by-page reads on POSIX_FADV_RANDOM.
    
    POSIX_FADV_RANDOM used to set ra_pages=0, which leads to poor performance:
    a 16K read will be carried out in 4 _sync_ 1-page reads.
    
    In other places, ra_pages==0 means
    - it's ramfs/tmpfs/hugetlbfs/sysfs/configfs
    - some IO error happened
    where multi-page read IO won't help or should be avoided.
    
    POSIX_FADV_RANDOM actually want a different semantics: to disable the
    *heuristic* readahead algorithm, and to use a dumb one which faithfully
    submit read IO for whatever application requests.
    
    So introduce a flag FMODE_RANDOM for POSIX_FADV_RANDOM.
    
    Note that the random hint is not likely to help random reads performance
    noticeably.  And it may be too permissive on huge request size (its IO
    size is not limited by read_ahead_kb).
    
    In Quentin's report (http://lkml.org/lkml/2009/12/24/145), the overall
    (NFS read) performance of the application increased by 313%!
    Tested-by: NQuentin Barnes <qbarnes+nfs@yahoo-inc.com>
    Signed-off-by: NWu Fengguang <fengguang.wu@intel.com>
    Cc: Nick Piggin <npiggin@suse.de>
    Cc: Andi Kleen <andi@firstfloor.org>
    Cc: Steven Whitehouse <swhiteho@redhat.com>
    Cc: David Howells <dhowells@redhat.com>
    Cc: Jonathan Corbet <corbet@lwn.net>
    Cc: Al Viro <viro@zeniv.linux.org.uk>
    Cc: Christoph Hellwig <hch@infradead.org>
    Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
    Cc: Chuck Lever <chuck.lever@oracle.com>
    Cc: <stable@kernel.org>			[2.6.33.x]
    Cc: <qbarnes+nfs@yahoo-inc.com>
    Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
    Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
    0141450f
fadvise.c 3.5 KB
/*
 * mm/fadvise.c
 *
 * Copyright (C) 2002, Linus Torvalds
 *
 * 11Jan2003	Andrew Morton
 *		Initial version.
 */

#include <linux/kernel.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include <linux/fadvise.h>
#include <linux/writeback.h>
#include <linux/syscalls.h>

#include <asm/unistd.h>

/*
 * POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could
 * deactivate the pages and clear PG_Referenced.
 */
SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
{
	struct file *file = fget(fd);
	struct address_space *mapping;
	struct backing_dev_info *bdi;
	loff_t endbyte;			/* inclusive */
	pgoff_t start_index;
	pgoff_t end_index;
	unsigned long nrpages;
	int ret = 0;

	if (!file)
		return -EBADF;

	if (S_ISFIFO(file->f_path.dentry->d_inode->i_mode)) {
		ret = -ESPIPE;
		goto out;
	}

	mapping = file->f_mapping;
	if (!mapping || len < 0) {
		ret = -EINVAL;
		goto out;
	}

	if (mapping->a_ops->get_xip_mem) {
		switch (advice) {
		case POSIX_FADV_NORMAL:
		case POSIX_FADV_RANDOM:
		case POSIX_FADV_SEQUENTIAL:
		case POSIX_FADV_WILLNEED:
		case POSIX_FADV_NOREUSE:
		case POSIX_FADV_DONTNEED:
			/* no bad return value, but ignore advice */
			break;
		default:
			ret = -EINVAL;
		}
		goto out;
	}

	/* Careful about overflows. Len == 0 means "as much as possible" */
	endbyte = offset + len;
	if (!len || endbyte < len)
		endbyte = -1;
	else
		endbyte--;		/* inclusive */

	bdi = mapping->backing_dev_info;

	switch (advice) {
	case POSIX_FADV_NORMAL:
		file->f_ra.ra_pages = bdi->ra_pages;
		spin_lock(&file->f_lock);
		file->f_mode &= ~FMODE_RANDOM;
		spin_unlock(&file->f_lock);
		break;
	case POSIX_FADV_RANDOM:
		spin_lock(&file->f_lock);
		file->f_mode |= FMODE_RANDOM;
		spin_unlock(&file->f_lock);
		break;
	case POSIX_FADV_SEQUENTIAL:
		file->f_ra.ra_pages = bdi->ra_pages * 2;
		spin_lock(&file->f_lock);
		file->f_mode &= ~FMODE_RANDOM;
		spin_unlock(&file->f_lock);
		break;
	case POSIX_FADV_WILLNEED:
		if (!mapping->a_ops->readpage) {
			ret = -EINVAL;
			break;
		}

		/* First and last PARTIAL page! */
		start_index = offset >> PAGE_CACHE_SHIFT;
		end_index = endbyte >> PAGE_CACHE_SHIFT;

		/* Careful about overflow on the "+1" */
		nrpages = end_index - start_index + 1;
		if (!nrpages)
			nrpages = ~0UL;
		
		ret = force_page_cache_readahead(mapping, file,
				start_index,
				nrpages);
		if (ret > 0)
			ret = 0;
		break;
	case POSIX_FADV_NOREUSE:
		break;
	case POSIX_FADV_DONTNEED:
		if (!bdi_write_congested(mapping->backing_dev_info))
			filemap_flush(mapping);

		/* First and last FULL page! */
		start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
		end_index = (endbyte >> PAGE_CACHE_SHIFT);

		if (end_index >= start_index)
			invalidate_mapping_pages(mapping, start_index,
						end_index);
		break;
	default:
		ret = -EINVAL;
	}
out:
	fput(file);
	return ret;
}
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_fadvise64_64(long fd, loff_t offset, loff_t len, long advice)
{
	return SYSC_fadvise64_64((int) fd, offset, len, (int) advice);
}
SYSCALL_ALIAS(sys_fadvise64_64, SyS_fadvise64_64);
#endif

#ifdef __ARCH_WANT_SYS_FADVISE64

SYSCALL_DEFINE(fadvise64)(int fd, loff_t offset, size_t len, int advice)
{
	return sys_fadvise64_64(fd, offset, len, advice);
}
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_fadvise64(long fd, loff_t offset, long len, long advice)
{
	return SYSC_fadvise64((int) fd, offset, (size_t)len, (int)advice);
}
SYSCALL_ALIAS(sys_fadvise64, SyS_fadvise64);
#endif

#endif
反馈
建议
客服 返回
顶部