aboutsummaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorHisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp>2008-07-28 18:46:36 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2008-07-28 19:30:21 -0400
commit8ab22b9abb5c55413802e4adc9aa6223324547c3 (patch)
treecff3319e1275e8a7c083d492889ec6bd0c7712d3 /mm
parentd84a52f62f6a396ed77aa0052da74ca9e760b28a (diff)
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>
Diffstat (limited to 'mm')
-rw-r--r--mm/filemap.c14
1 files changed, 12 insertions, 2 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index 5de7633e1dbe..42bbc6909ba4 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1023,8 +1023,17 @@ find_page:
1023 ra, filp, page, 1023 ra, filp, page,
1024 index, last_index - index); 1024 index, last_index - index);
1025 } 1025 }
1026 if (!PageUptodate(page)) 1026 if (!PageUptodate(page)) {
1027 goto page_not_up_to_date; 1027 if (inode->i_blkbits == PAGE_CACHE_SHIFT ||
1028 !mapping->a_ops->is_partially_uptodate)
1029 goto page_not_up_to_date;
1030 if (TestSetPageLocked(page))
1031 goto page_not_up_to_date;
1032 if (!mapping->a_ops->is_partially_uptodate(page,
1033 desc, offset))
1034 goto page_not_up_to_date_locked;
1035 unlock_page(page);
1036 }
1028page_ok: 1037page_ok:
1029 /* 1038 /*
1030 * i_size must be checked after we know the page is Uptodate. 1039 * i_size must be checked after we know the page is Uptodate.
@@ -1094,6 +1103,7 @@ page_not_up_to_date:
1094 if (lock_page_killable(page)) 1103 if (lock_page_killable(page))
1095 goto readpage_eio; 1104 goto readpage_eio;
1096 1105
1106page_not_up_to_date_locked:
1097 /* Did it get truncated before we got the lock? */ 1107 /* Did it get truncated before we got the lock? */
1098 if (!page->mapping) { 1108 if (!page->mapping) {
1099 unlock_page(page); 1109 unlock_page(page);