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: 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>

2 files changed, 25 insertions, 21 deletions

diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 82aa36c..50cfe8c 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -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*);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8252b04..580b513 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -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. */