forked from Minki/linux
8ab22b9abb
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: Hisashi 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: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
||
|---|---|---|
| .. | ||
| acl.c | ||
| acl.h | ||
| balloc.c | ||
| dir.c | ||
| ext2.h | ||
| file.c | ||
| fsync.c | ||
| ialloc.c | ||
| inode.c | ||
| ioctl.c | ||
| Makefile | ||
| namei.c | ||
| super.c | ||
| symlink.c | ||
| xattr_security.c | ||
| xattr_trusted.c | ||
| xattr_user.c | ||
| xattr.c | ||
| xattr.h | ||
| xip.c | ||
| xip.h | ||