Commit 8ab22b9a authored by Hisashi Hifumi's avatar Hisashi Hifumi Committed by Linus Torvalds

vfs: pagecache usage optimization for pagesize!=blocksize

When we read some part of a file through pagecache, if there is a
pagecache of corresponding index but this page is not uptodate, read IO
is issued and this page will be uptodate.

I think this is good for pagesize == blocksize environment but there is
room for improvement on pagesize != blocksize environment.  Because in
this case a page can have multiple buffers and even if a page is not
uptodate, some buffers can be uptodate.

So I suggest that when all buffers which correspond to a part of a file
that we want to read are uptodate, use this pagecache and copy data from
this pagecache to user buffer even if a page is not uptodate.  This can
reduce read IO and improve system throughput.

I wrote a benchmark program and got result number with this program.

This benchmark do:

  1: mount and open a test file.

  2: create a 512MB file.

  3: close a file and umount.

  4: mount and again open a test file.

  5: pwrite randomly 300000 times on a test file.  offset is aligned
     by IO size(1024bytes).

  6: measure time of preading randomly 100000 times on a test file.

The result was:
	2.6.26
        330 sec

	2.6.26-patched
        226 sec

Arch:i386
Filesystem:ext3
Blocksize:1024 bytes
Memory: 1GB

On ext3/4, a file is written through buffer/block.  So random read/write
mixed workloads or random read after random write workloads are optimized
with this patch under pagesize != blocksize environment.  This test result
showed this.

The benchmark program is as follows:

#include <stdio.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <unistd.h>
#include <time.h>
#include <stdlib.h>
#include <string.h>
#include <sys/mount.h>

#define LEN 1024
#define LOOP 1024*512 /* 512MB */

main(void)
{
	unsigned long i, offset, filesize;
	int fd;
	char buf[LEN];
	time_t t1, t2;

	if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) {
		perror("cannot mount\n");
		exit(1);
	}
	memset(buf, 0, LEN);
	fd = open("/root/test1/testfile", O_CREAT|O_RDWR|O_TRUNC);
	if (fd < 0) {
		perror("cannot open file\n");
		exit(1);
	}
	for (i = 0; i < LOOP; i++)
		write(fd, buf, LEN);
	close(fd);
	if (umount("/root/test1/") < 0) {
		perror("cannot umount\n");
		exit(1);
	}
	if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) {
		perror("cannot mount\n");
		exit(1);
	}
	fd = open("/root/test1/testfile", O_RDWR);
	if (fd < 0) {
		perror("cannot open file\n");
		exit(1);
	}

	filesize = LEN * LOOP;
	for (i = 0; i < 300000; i++){
		offset = (random() % filesize) & (~(LEN - 1));
		pwrite(fd, buf, LEN, offset);
	}
	printf("start test\n");
	time(&t1);
	for (i = 0; i < 100000; i++){
		offset = (random() % filesize) & (~(LEN - 1));
		pread(fd, buf, LEN, offset);
	}
	time(&t2);
	printf("%ld sec\n", t2-t1);
	close(fd);
	if (umount("/root/test1/") < 0) {
		perror("cannot umount\n");
		exit(1);
	}
}
Signed-off-by: default avatarHisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Jan Kara <jack@ucw.cz>
Cc: <linux-ext4@vger.kernel.org>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent d84a52f6
......@@ -2095,6 +2095,52 @@ int generic_write_end(struct file *file, struct address_space *mapping,
}
EXPORT_SYMBOL(generic_write_end);
/*
* block_is_partially_uptodate checks whether buffers within a page are
* uptodate or not.
*
* Returns true if all buffers which correspond to a file portion
* we want to read are uptodate.
*/
int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
unsigned long from)
{
struct inode *inode = page->mapping->host;
unsigned block_start, block_end, blocksize;
unsigned to;
struct buffer_head *bh, *head;
int ret = 1;
if (!page_has_buffers(page))
return 0;
blocksize = 1 << inode->i_blkbits;
to = min_t(unsigned, PAGE_CACHE_SIZE - from, desc->count);
to = from + to;
if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize)
return 0;
head = page_buffers(page);
bh = head;
block_start = 0;
do {
block_end = block_start + blocksize;
if (block_end > from && block_start < to) {
if (!buffer_uptodate(bh)) {
ret = 0;
break;
}
if (block_end >= to)
break;
}
block_start = block_end;
bh = bh->b_this_page;
} while (bh != head);
return ret;
}
EXPORT_SYMBOL(block_is_partially_uptodate);
/*
* Generic "read page" function for block devices that have the normal
* get_block functionality. This is most of the block device filesystems.
......
......@@ -791,6 +791,7 @@ const struct address_space_operations ext2_aops = {
.direct_IO = ext2_direct_IO,
.writepages = ext2_writepages,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
};
const struct address_space_operations ext2_aops_xip = {
......
......@@ -1778,6 +1778,7 @@ static const struct address_space_operations ext3_ordered_aops = {
.releasepage = ext3_releasepage,
.direct_IO = ext3_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
};
static const struct address_space_operations ext3_writeback_aops = {
......@@ -1792,6 +1793,7 @@ static const struct address_space_operations ext3_writeback_aops = {
.releasepage = ext3_releasepage,
.direct_IO = ext3_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
};
static const struct address_space_operations ext3_journalled_aops = {
......@@ -1805,6 +1807,7 @@ static const struct address_space_operations ext3_journalled_aops = {
.bmap = ext3_bmap,
.invalidatepage = ext3_invalidatepage,
.releasepage = ext3_releasepage,
.is_partially_uptodate = block_is_partially_uptodate,
};
void ext3_set_aops(struct inode *inode)
......
......@@ -2817,6 +2817,7 @@ static const struct address_space_operations ext4_ordered_aops = {
.releasepage = ext4_releasepage,
.direct_IO = ext4_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
};
static const struct address_space_operations ext4_writeback_aops = {
......@@ -2831,6 +2832,7 @@ static const struct address_space_operations ext4_writeback_aops = {
.releasepage = ext4_releasepage,
.direct_IO = ext4_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
};
static const struct address_space_operations ext4_journalled_aops = {
......@@ -2844,6 +2846,7 @@ static const struct address_space_operations ext4_journalled_aops = {
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
.is_partially_uptodate = block_is_partially_uptodate,
};
static const struct address_space_operations ext4_da_aops = {
......@@ -2859,6 +2862,7 @@ static const struct address_space_operations ext4_da_aops = {
.releasepage = ext4_releasepage,
.direct_IO = ext4_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
};
void ext4_set_aops(struct inode *inode)
......
......@@ -205,6 +205,8 @@ void block_invalidatepage(struct page *page, unsigned long offset);
int block_write_full_page(struct page *page, get_block_t *get_block,
struct writeback_control *wbc);
int block_read_full_page(struct page*, get_block_t*);
int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
unsigned long from);
int block_write_begin(struct file *, struct address_space *,
loff_t, unsigned, unsigned,
struct page **, void **, get_block_t*);
......
......@@ -443,6 +443,27 @@ static inline size_t iov_iter_count(struct iov_iter *i)
return i->count;
}
/*
* "descriptor" for what we're up to with a read.
* This allows us to use the same read code yet
* have multiple different users of the data that
* we read from a file.
*
* The simplest case just copies the data to user
* mode.
*/
typedef struct {
size_t written;
size_t count;
union {
char __user *buf;
void *data;
} arg;
int error;
} read_descriptor_t;
typedef int (*read_actor_t)(read_descriptor_t *, struct page *,
unsigned long, unsigned long);
struct address_space_operations {
int (*writepage)(struct page *page, struct writeback_control *wbc);
......@@ -484,6 +505,8 @@ struct address_space_operations {
int (*migratepage) (struct address_space *,
struct page *, struct page *);
int (*launder_page) (struct page *);
int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
unsigned long);
};
/*
......@@ -1198,27 +1221,6 @@ struct block_device_operations {
struct module *owner;
};
/*
* "descriptor" for what we're up to with a read.
* This allows us to use the same read code yet
* have multiple different users of the data that
* we read from a file.
*
* The simplest case just copies the data to user
* mode.
*/
typedef struct {
size_t written;
size_t count;
union {
char __user * buf;
void *data;
} arg;
int error;
} read_descriptor_t;
typedef int (*read_actor_t)(read_descriptor_t *, struct page *, unsigned long, unsigned long);
/* These macros are for out of kernel modules to test that
* the kernel supports the unlocked_ioctl and compat_ioctl
* fields in struct file_operations. */
......
......@@ -1023,8 +1023,17 @@ static void do_generic_file_read(struct file *filp, loff_t *ppos,
ra, filp, page,
index, last_index - index);
}
if (!PageUptodate(page))
if (!PageUptodate(page)) {
if (inode->i_blkbits == PAGE_CACHE_SHIFT ||
!mapping->a_ops->is_partially_uptodate)
goto page_not_up_to_date;
if (TestSetPageLocked(page))
goto page_not_up_to_date;
if (!mapping->a_ops->is_partially_uptodate(page,
desc, offset))
goto page_not_up_to_date_locked;
unlock_page(page);
}
page_ok:
/*
* i_size must be checked after we know the page is Uptodate.
......@@ -1094,6 +1103,7 @@ static void do_generic_file_read(struct file *filp, loff_t *ppos,
if (lock_page_killable(page))
goto readpage_eio;
page_not_up_to_date_locked:
/* Did it get truncated before we got the lock? */
if (!page->mapping) {
unlock_page(page);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment