[PATCH 3/7] readahead: combine file_ra_state.prev_index/prev_offset into prev_pos
Combine the file_ra_state members
unsigned long prev_index
unsigned int prev_offset
into
loff_t prev_pos
It is more consistent and better supports huge files.
Thanks to Peter for the nice proposal!
Cc: Peter Zijlstra <[EMAIL PROTECTED]>
Signed-off-by: Fengguang Wu <[EMAIL PROTECTED]>
---
fs/ext3/dir.c |2 +-
fs/ext4/dir.c |2 +-
fs/splice.c|2 +-
include/linux/fs.h |3 +--
mm/filemap.c | 11 ++-
mm/readahead.c | 15 ---
6 files changed, 18 insertions(+), 17 deletions(-)
--- linux-2.6.22-rc6-mm1.orig/include/linux/fs.h
+++ linux-2.6.22-rc6-mm1/include/linux/fs.h
@@ -778,8 +778,7 @@ struct file_ra_state {
unsigned int ra_pages; /* Maximum readahead window */
int mmap_miss; /* Cache miss stat for mmap accesses */
- unsigned long prev_index; /* Cache last read() position */
- unsigned int prev_offset; /* Offset where last read() ended in a
page */
+ loff_t prev_pos;/* Cache last read() position */
};
/*
--- linux-2.6.22-rc6-mm1.orig/mm/filemap.c
+++ linux-2.6.22-rc6-mm1/mm/filemap.c
@@ -881,8 +881,8 @@ void do_generic_mapping_read(struct addr
index = *ppos >> PAGE_CACHE_SHIFT;
next_index = index;
- prev_index = ra.prev_index;
- prev_offset = ra.prev_offset;
+ prev_index = ra.prev_pos >> PAGE_CACHE_SHIFT;
+ prev_offset = ra.prev_pos & (PAGE_CACHE_SIZE-1);
last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >>
PAGE_CACHE_SHIFT;
offset = *ppos & ~PAGE_CACHE_MASK;
@@ -968,7 +968,6 @@ page_ok:
index += offset >> PAGE_CACHE_SHIFT;
offset &= ~PAGE_CACHE_MASK;
prev_offset = offset;
- ra.prev_offset = offset;
page_cache_release(page);
if (ret == nr && desc->count)
@@ -1055,7 +1054,9 @@ no_cached_page:
out:
*_ra = ra;
- _ra->prev_index = prev_index;
+ _ra->prev_pos = prev_index;
+ _ra->prev_pos <<= PAGE_CACHE_SHIFT;
+ _ra->prev_pos |= prev_offset;
*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
if (filp)
@@ -1435,7 +1436,7 @@ retry_find:
* Found the page and have a reference on it.
*/
mark_page_accessed(page);
- ra->prev_index = page->index;
+ ra->prev_pos = page->index << PAGE_CACHE_SHIFT;
return page;
outside_data_content:
--- linux-2.6.22-rc6-mm1.orig/mm/readahead.c
+++ linux-2.6.22-rc6-mm1/mm/readahead.c
@@ -45,7 +45,7 @@ void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping)
{
ra->ra_pages = mapping->backing_dev_info->ra_pages;
- ra->prev_index = -1;
+ ra->prev_pos = -1;
}
EXPORT_SYMBOL_GPL(file_ra_state_init);
@@ -318,7 +318,7 @@ static unsigned long get_next_ra_size(st
* indicator. The flag won't be set on already cached pages, to avoid the
* readahead-for-nothing fuss, saving pointless page cache lookups.
*
- * prev_index tracks the last visited page in the _previous_ read request.
+ * prev_pos tracks the last visited byte in the _previous_ read request.
* It should be maintained by the caller, and will be used for detecting
* small random reads. Note that the readahead algorithm checks loosely
* for sequential patterns. Hence interleaved reads might be served as
@@ -342,11 +342,9 @@ ondemand_readahead(struct address_space
bool hit_readahead_marker, pgoff_t offset,
unsigned long req_size)
{
- int max;/* max readahead pages */
- int sequential;
-
- max = ra->ra_pages;
- sequential = (offset - ra->prev_index <= 1UL) || (req_size > max);
+ int max = ra->ra_pages; /* max readahead pages */
+ pgoff_t prev_offset;
+ int sequential;
/*
* It's the expected callback offset, assume sequential access.
@@ -360,6 +358,9 @@ ondemand_readahead(struct address_space
goto readit;
}
+ prev_offset = ra->prev_pos >> PAGE_CACHE_SHIFT;
+ sequential = offset - prev_offset <= 1UL || req_size > max;
+
/*
* Standalone, small read.
* Read as is, and do not pollute the readahead state.
--- linux-2.6.22-rc6-mm1.orig/fs/ext3/dir.c
+++ linux-2.6.22-rc6-mm1/fs/ext3/dir.c
@@ -143,7 +143,7 @@ static int ext3_readdir(struct file * fi
sb->s_bdev->bd_inode->i_mapping,
>f_ra, filp,
index, 1);
- filp->f_ra.prev_index = index;
+ filp->f_ra.prev_pos = index << PAGE_CACHE_SHIFT;
bh = ext3_bread(NULL, inode, blk, 0, );
}
--- linux-2.6.22-rc6-mm1.orig/fs/ext4/dir.c
+++
[PATCH 3/7] readahead: combine file_ra_state.prev_index/prev_offset into prev_pos
Combine the file_ra_state members
unsigned long prev_index
unsigned int prev_offset
into
loff_t prev_pos
It is more consistent and better supports huge files.
Thanks to Peter for the nice proposal!
Cc: Peter Zijlstra [EMAIL PROTECTED]
Signed-off-by: Fengguang Wu [EMAIL PROTECTED]
---
fs/ext3/dir.c |2 +-
fs/ext4/dir.c |2 +-
fs/splice.c|2 +-
include/linux/fs.h |3 +--
mm/filemap.c | 11 ++-
mm/readahead.c | 15 ---
6 files changed, 18 insertions(+), 17 deletions(-)
--- linux-2.6.22-rc6-mm1.orig/include/linux/fs.h
+++ linux-2.6.22-rc6-mm1/include/linux/fs.h
@@ -778,8 +778,7 @@ struct file_ra_state {
unsigned int ra_pages; /* Maximum readahead window */
int mmap_miss; /* Cache miss stat for mmap accesses */
- unsigned long prev_index; /* Cache last read() position */
- unsigned int prev_offset; /* Offset where last read() ended in a
page */
+ loff_t prev_pos;/* Cache last read() position */
};
/*
--- linux-2.6.22-rc6-mm1.orig/mm/filemap.c
+++ linux-2.6.22-rc6-mm1/mm/filemap.c
@@ -881,8 +881,8 @@ void do_generic_mapping_read(struct addr
index = *ppos PAGE_CACHE_SHIFT;
next_index = index;
- prev_index = ra.prev_index;
- prev_offset = ra.prev_offset;
+ prev_index = ra.prev_pos PAGE_CACHE_SHIFT;
+ prev_offset = ra.prev_pos (PAGE_CACHE_SIZE-1);
last_index = (*ppos + desc-count + PAGE_CACHE_SIZE-1)
PAGE_CACHE_SHIFT;
offset = *ppos ~PAGE_CACHE_MASK;
@@ -968,7 +968,6 @@ page_ok:
index += offset PAGE_CACHE_SHIFT;
offset = ~PAGE_CACHE_MASK;
prev_offset = offset;
- ra.prev_offset = offset;
page_cache_release(page);
if (ret == nr desc-count)
@@ -1055,7 +1054,9 @@ no_cached_page:
out:
*_ra = ra;
- _ra-prev_index = prev_index;
+ _ra-prev_pos = prev_index;
+ _ra-prev_pos = PAGE_CACHE_SHIFT;
+ _ra-prev_pos |= prev_offset;
*ppos = ((loff_t) index PAGE_CACHE_SHIFT) + offset;
if (filp)
@@ -1435,7 +1436,7 @@ retry_find:
* Found the page and have a reference on it.
*/
mark_page_accessed(page);
- ra-prev_index = page-index;
+ ra-prev_pos = page-index PAGE_CACHE_SHIFT;
return page;
outside_data_content:
--- linux-2.6.22-rc6-mm1.orig/mm/readahead.c
+++ linux-2.6.22-rc6-mm1/mm/readahead.c
@@ -45,7 +45,7 @@ void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping)
{
ra-ra_pages = mapping-backing_dev_info-ra_pages;
- ra-prev_index = -1;
+ ra-prev_pos = -1;
}
EXPORT_SYMBOL_GPL(file_ra_state_init);
@@ -318,7 +318,7 @@ static unsigned long get_next_ra_size(st
* indicator. The flag won't be set on already cached pages, to avoid the
* readahead-for-nothing fuss, saving pointless page cache lookups.
*
- * prev_index tracks the last visited page in the _previous_ read request.
+ * prev_pos tracks the last visited byte in the _previous_ read request.
* It should be maintained by the caller, and will be used for detecting
* small random reads. Note that the readahead algorithm checks loosely
* for sequential patterns. Hence interleaved reads might be served as
@@ -342,11 +342,9 @@ ondemand_readahead(struct address_space
bool hit_readahead_marker, pgoff_t offset,
unsigned long req_size)
{
- int max;/* max readahead pages */
- int sequential;
-
- max = ra-ra_pages;
- sequential = (offset - ra-prev_index = 1UL) || (req_size max);
+ int max = ra-ra_pages; /* max readahead pages */
+ pgoff_t prev_offset;
+ int sequential;
/*
* It's the expected callback offset, assume sequential access.
@@ -360,6 +358,9 @@ ondemand_readahead(struct address_space
goto readit;
}
+ prev_offset = ra-prev_pos PAGE_CACHE_SHIFT;
+ sequential = offset - prev_offset = 1UL || req_size max;
+
/*
* Standalone, small read.
* Read as is, and do not pollute the readahead state.
--- linux-2.6.22-rc6-mm1.orig/fs/ext3/dir.c
+++ linux-2.6.22-rc6-mm1/fs/ext3/dir.c
@@ -143,7 +143,7 @@ static int ext3_readdir(struct file * fi
sb-s_bdev-bd_inode-i_mapping,
filp-f_ra, filp,
index, 1);
- filp-f_ra.prev_index = index;
+ filp-f_ra.prev_pos = index PAGE_CACHE_SHIFT;
bh = ext3_bread(NULL, inode, blk, 0, err);
}
--- linux-2.6.22-rc6-mm1.orig/fs/ext4/dir.c
+++ linux-2.6.22-rc6-mm1/fs/ext4/dir.c
@@ -142,7 +142,7 @@ static
